From 44b3fbb06dd9436c5545c2a93432d65e400a360c Mon Sep 17 00:00:00 2001 From: Rahila Syed Date: Thu, 27 Mar 2025 12:59:02 +0530 Subject: [PATCH 1/2] Account for all the shared memory allocated by hash_create pg_shmem_allocations tracks the memory allocated by ShmemInitStruct, which, in case of shared hash tables, only covers memory allocated to the hash directory and header structure. The hash segments and buckets are allocated using ShmemAllocNoError which does not attribute the allocations to the hash table name. Thus, these allocations are not tracked in pg_shmem_allocations. Allocate memory for segments, buckets and elements together with the directory and header structures. This results in the existing ShmemIndex entries to reflect size of hash table more accurately, thus improving the pg_shmem_allocation monitoring. Also, make this change for non- shared hash table since they both share the hash_create code. --- src/backend/storage/ipc/shmem.c | 3 +- src/backend/utils/hash/dynahash.c | 265 +++++++++++++++++++++++------- src/include/utils/hsearch.h | 3 +- 3 files changed, 213 insertions(+), 58 deletions(-) diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39..d8aed0bfaa 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -73,6 +73,7 @@ #include "storage/shmem.h" #include "storage/spin.h" #include "utils/builtins.h" +#include "utils/dynahash.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); @@ -346,7 +347,7 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ /* look it up in the shmem index */ location = ShmemInitStruct(name, - hash_get_shared_size(infoP, hash_flags), + hash_get_init_size(infoP, hash_flags, init_size, 0), &found); /* diff --git a/src/backend/utils/hash/dynahash.c b/src/backend/utils/hash/dynahash.c index 3f25929f2d..1f215a16c5 100644 --- a/src/backend/utils/hash/dynahash.c +++ b/src/backend/utils/hash/dynahash.c @@ -260,12 +260,36 @@ static long hash_accesses, hash_expansions; #endif + +#define HASH_ELEMENTS_OFFSET(hctl, nsegs) \ + (MAXALIGN(sizeof(HASHHDR)) + \ + ((hctl)->dsize * MAXALIGN(sizeof(HASHSEGMENT))) + \ + ((hctl)->ssize * (nsegs) * MAXALIGN(sizeof(HASHBUCKET)))) + +#define HASH_ELEMENTS(hashp, nsegs) \ + ((char *) (hashp)->hctl + HASH_ELEMENTS_OFFSET((hashp)->hctl, nsegs)) + +#define HASH_SEGMENT_OFFSET(hctl, idx) \ + (MAXALIGN(sizeof(HASHHDR)) + \ + ((hctl)->dsize * MAXALIGN(sizeof(HASHSEGMENT))) + \ + ((hctl)->ssize * (idx) * MAXALIGN(sizeof(HASHBUCKET)))) + +#define HASH_SEGMENT_PTR(hashp, idx) \ + (HASHSEGMENT) ((char *) (hashp)->hctl + HASH_SEGMENT_OFFSET((hashp)->hctl, (idx))) + +#define HASH_SEGMENT_SIZE(hashp) ((hashp)->ssize * MAXALIGN(sizeof(HASHBUCKET))) + +#define HASH_DIRECTORY(hashp) (HASHSEGMENT *) (((char *) (hashp)->hctl) + MAXALIGN(sizeof(HASHHDR))) + +#define HASH_ELEMENT_NEXT(hctl, num, ptr) \ + ((char *) (ptr) + ((num) * (MAXALIGN(sizeof(HASHELEMENT)) + MAXALIGN((hctl)->entrysize)))) + /* * Private function prototypes */ static void *DynaHashAlloc(Size size); static HASHSEGMENT seg_alloc(HTAB *hashp); -static bool element_alloc(HTAB *hashp, int nelem, int freelist_idx); +static HASHELEMENT *element_alloc(HTAB *hashp, int nelem); static bool dir_realloc(HTAB *hashp); static bool expand_table(HTAB *hashp); static HASHBUCKET get_hash_entry(HTAB *hashp, int freelist_idx); @@ -281,6 +305,11 @@ static void register_seq_scan(HTAB *hashp); static void deregister_seq_scan(HTAB *hashp); static bool has_seq_scans(HTAB *hashp); +static void compute_buckets_and_segs(long nelem, long num_partitions, + long ssize, /* segment size */ + int *nbuckets, int *nsegments); +static void element_add(HTAB *hashp, HASHELEMENT *firstElement, + int nelem, int freelist_idx); /* * memory allocation support @@ -353,6 +382,7 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) { HTAB *hashp; HASHHDR *hctl; + int nelem_batch; /* * Hash tables now allocate space for key and data, but you have to say @@ -507,9 +537,19 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) hashp->isshared = false; } + /* Choose the number of entries to allocate at a time. */ + nelem_batch = choose_nelem_alloc(info->entrysize); + + /* + * Allocate the memory needed for hash header, directory, segments and + * elements together. Use pointer arithmetic to arrive at the start of + * each of these structures later. + */ if (!hashp->hctl) { - hashp->hctl = (HASHHDR *) hashp->alloc(sizeof(HASHHDR)); + Size size = hash_get_init_size(info, flags, nelem, nelem_batch); + + hashp->hctl = (HASHHDR *) hashp->alloc(size); if (!hashp->hctl) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -558,6 +598,9 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) hctl->keysize = info->keysize; hctl->entrysize = info->entrysize; + /* remember how many elements to allocate at once */ + hctl->nelem_alloc = nelem_batch; + /* make local copies of heavily-used constant fields */ hashp->keysize = hctl->keysize; hashp->ssize = hctl->ssize; @@ -582,6 +625,9 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) freelist_partitions, nelem_alloc, nelem_alloc_first; + void *ptr = NULL; + int nsegs; + int nbuckets; /* * If hash table is partitioned, give each freelist an equal share of @@ -592,6 +638,16 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) else freelist_partitions = 1; + compute_buckets_and_segs(nelem, hctl->num_partitions, hctl->ssize, + &nbuckets, &nsegs); + + /* + * Calculate the offset at which to find the first partition of + * elements. + * We have to skip space for the header, segments and buckets. + */ + ptr = HASH_ELEMENTS(hashp, nsegs); + nelem_alloc = nelem / freelist_partitions; if (nelem_alloc <= 0) nelem_alloc = 1; @@ -610,10 +666,17 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) { int temp = (i == 0) ? nelem_alloc_first : nelem_alloc; - if (!element_alloc(hashp, temp, i)) - ereport(ERROR, - (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("out of memory"))); + /* + * Assign the correct location of each parition within a + * pre-allocated buffer. + * + * Actual memory allocation happens in ShmemInitHash for + * shared hash tables or earlier in this function for non-shared + * hash tables. + * We just need to split that allocation per-batch freelists. + */ + element_add(hashp, (HASHELEMENT *) ptr, temp, i); + ptr = HASH_ELEMENT_NEXT(hctl, temp, ptr); } } @@ -701,30 +764,12 @@ init_htab(HTAB *hashp, long nelem) for (i = 0; i < NUM_FREELISTS; i++) SpinLockInit(&(hctl->freeList[i].mutex)); - /* - * Allocate space for the next greater power of two number of buckets, - * assuming a desired maximum load factor of 1. - */ - nbuckets = next_pow2_int(nelem); - - /* - * In a partitioned table, nbuckets must be at least equal to - * num_partitions; were it less, keys with apparently different partition - * numbers would map to the same bucket, breaking partition independence. - * (Normally nbuckets will be much bigger; this is just a safety check.) - */ - while (nbuckets < hctl->num_partitions) - nbuckets <<= 1; + compute_buckets_and_segs(nelem, hctl->num_partitions, hctl->ssize, + &nbuckets, &nsegs); hctl->max_bucket = hctl->low_mask = nbuckets - 1; hctl->high_mask = (nbuckets << 1) - 1; - /* - * Figure number of directory segments needed, round up to a power of 2 - */ - nsegs = (nbuckets - 1) / hctl->ssize + 1; - nsegs = next_pow2_int(nsegs); - /* * Make sure directory is big enough. If pre-allocated directory is too * small, choke (caller screwed up). @@ -737,26 +782,25 @@ init_htab(HTAB *hashp, long nelem) return false; } - /* Allocate a directory */ + /* + * Assign a directory by making it point to the correct location in the + * pre-allocated buffer. + */ if (!(hashp->dir)) { CurrentDynaHashCxt = hashp->hcxt; - hashp->dir = (HASHSEGMENT *) - hashp->alloc(hctl->dsize * sizeof(HASHSEGMENT)); - if (!hashp->dir) - return false; + hashp->dir = HASH_DIRECTORY(hashp); } - /* Allocate initial segments */ + /* Assign initial segments, which are also pre-allocated */ + i = 0; for (segp = hashp->dir; hctl->nsegs < nsegs; hctl->nsegs++, segp++) { - *segp = seg_alloc(hashp); - if (*segp == NULL) - return false; + *segp = HASH_SEGMENT_PTR(hashp, i++); + MemSet(*segp, 0, HASH_SEGMENT_SIZE(hashp)); } - /* Choose number of entries to allocate at a time */ - hctl->nelem_alloc = choose_nelem_alloc(hctl->entrysize); + Assert(i == nsegs); #ifdef HASH_DEBUG fprintf(stderr, "init_htab:\n%s%p\n%s%ld\n%s%ld\n%s%d\n%s%ld\n%s%u\n%s%x\n%s%x\n%s%ld\n", @@ -847,15 +891,79 @@ hash_select_dirsize(long num_entries) /* * Compute the required initial memory allocation for a shared-memory - * hashtable with the given parameters. We need space for the HASHHDR - * and for the (non expansible) directory. + * or non-shared memory hashtable with the given parameters. + * We need space for the HASHHDR, for the directory, segments and + * the init_size elements in buckets. + * + * For shared hash tables the directory size is non-expansive. + * + * init_size should match the total number of elements allocated + * during hash table creation, it could be zero for non-shared hash + * tables depending on the value of nelem_alloc. For more explanation + * see comments within this function. + * + * nelem_alloc parameter is not relevant for shared hash tables. */ Size -hash_get_shared_size(HASHCTL *info, int flags) +hash_get_init_size(const HASHCTL *info, int flags, long init_size, int nelem_alloc) { - Assert(flags & HASH_DIRSIZE); - Assert(info->dsize == info->max_dsize); - return sizeof(HASHHDR) + info->dsize * sizeof(HASHSEGMENT); + int nbuckets; + int nsegs; + int num_partitions; + long ssize; + long dsize; + bool element_alloc = true; /*Always true for shared hash tables */ + Size elementSize = MAXALIGN(sizeof(HASHELEMENT)) + MAXALIGN(info->entrysize); + + /* + * For non-shared hash tables, the requested number of elements are + * allocated only if they are less than nelem_alloc. In any case, the + * init_size should be equal to the number of elements added using + * element_add() in hash_create. + */ + if (!(flags & HASH_SHARED_MEM)) + { + if (init_size > nelem_alloc) + element_alloc = false; + } + else + { + Assert(flags & HASH_DIRSIZE); + Assert(info->dsize == info->max_dsize); + } + /* Non-shared hash tables may not specify dir size */ + if (!(flags & HASH_DIRSIZE)) + { + dsize = DEF_DIRSIZE; + } + else + dsize = info->dsize; + + if (flags & HASH_PARTITION) + { + num_partitions = info->num_partitions; + + /* Number of entries should be atleast equal to the freelists */ + if (init_size < NUM_FREELISTS) + init_size = NUM_FREELISTS; + } + else + num_partitions = 0; + + if (flags & HASH_SEGMENT) + ssize = info->ssize; + else + ssize = DEF_SEGSIZE; + + compute_buckets_and_segs(init_size, num_partitions, ssize, + &nbuckets, &nsegs); + + if (!element_alloc) + init_size = 0; + + return MAXALIGN(sizeof(HASHHDR)) + dsize * MAXALIGN(sizeof(HASHSEGMENT)) + + + MAXALIGN(sizeof(HASHBUCKET)) * ssize * nsegs + + init_size * elementSize; } @@ -1285,7 +1393,8 @@ get_hash_entry(HTAB *hashp, int freelist_idx) * Failing because the needed element is in a different freelist is * not acceptable. */ - if (!element_alloc(hashp, hctl->nelem_alloc, freelist_idx)) + newElement = element_alloc(hashp, hctl->nelem_alloc); + if (newElement == NULL) { int borrow_from_idx; @@ -1322,6 +1431,7 @@ get_hash_entry(HTAB *hashp, int freelist_idx) /* no elements available to borrow either, so out of memory */ return NULL; } + element_add(hashp, newElement, hctl->nelem_alloc, freelist_idx); } /* remove entry from freelist, bump nentries */ @@ -1700,30 +1810,43 @@ seg_alloc(HTAB *hashp) } /* - * allocate some new elements and link them into the indicated free list + * allocate some new elements */ -static bool -element_alloc(HTAB *hashp, int nelem, int freelist_idx) +static HASHELEMENT * +element_alloc(HTAB *hashp, int nelem) { HASHHDR *hctl = hashp->hctl; Size elementSize; - HASHELEMENT *firstElement; - HASHELEMENT *tmpElement; - HASHELEMENT *prevElement; - int i; + HASHELEMENT *firstElement = NULL; if (hashp->isfixed) - return false; + return NULL; /* Each element has a HASHELEMENT header plus user data. */ elementSize = MAXALIGN(sizeof(HASHELEMENT)) + MAXALIGN(hctl->entrysize); - CurrentDynaHashCxt = hashp->hcxt; firstElement = (HASHELEMENT *) hashp->alloc(nelem * elementSize); if (!firstElement) - return false; + return NULL; + + return firstElement; +} + +/* + * Link the elements allocated by element_alloc into the indicated free list + */ +static void +element_add(HTAB *hashp, HASHELEMENT *firstElement, int nelem, int freelist_idx) +{ + HASHHDR *hctl = hashp->hctl; + Size elementSize; + HASHELEMENT *tmpElement; + HASHELEMENT *prevElement; + int i; + /* Each element has a HASHELEMENT header plus user data. */ + elementSize = MAXALIGN(sizeof(HASHELEMENT)) + MAXALIGN(hctl->entrysize); /* prepare to link all the new entries into the freelist */ prevElement = NULL; tmpElement = firstElement; @@ -1744,8 +1867,6 @@ element_alloc(HTAB *hashp, int nelem, int freelist_idx) if (IS_PARTITIONED(hctl)) SpinLockRelease(&hctl->freeList[freelist_idx].mutex); - - return true; } /* @@ -1957,3 +2078,35 @@ AtEOSubXact_HashTables(bool isCommit, int nestDepth) } } } + +/* + * Calculate the number of buckets and segments to store the given + * number of elements in a hash table. Segments contain buckets which + * in turn contain elements. + */ +static void +compute_buckets_and_segs(long nelem, long num_partitions, long ssize, + int *nbuckets, int *nsegments) +{ + /* + * Allocate space for the next greater power of two number of buckets, + * assuming a desired maximum load factor of 1. + */ + *nbuckets = next_pow2_int(nelem); + + /* + * In a partitioned table, nbuckets must be at least equal to + * num_partitions; were it less, keys with apparently different partition + * numbers would map to the same bucket, breaking partition independence. + * (Normally nbuckets will be much bigger; this is just a safety check.) + */ + while ((*nbuckets) < num_partitions) + (*nbuckets) <<= 1; + + + /* + * Figure number of directory segments needed, round up to a power of 2 + */ + *nsegments = ((*nbuckets) - 1) / ssize + 1; + *nsegments = next_pow2_int(*nsegments); +} diff --git a/src/include/utils/hsearch.h b/src/include/utils/hsearch.h index 932cc4f34d..79b959ffc3 100644 --- a/src/include/utils/hsearch.h +++ b/src/include/utils/hsearch.h @@ -151,7 +151,8 @@ extern void hash_seq_term(HASH_SEQ_STATUS *status); extern void hash_freeze(HTAB *hashp); extern Size hash_estimate_size(long num_entries, Size entrysize); extern long hash_select_dirsize(long num_entries); -extern Size hash_get_shared_size(HASHCTL *info, int flags); +extern Size hash_get_init_size(const HASHCTL *info, int flags, + long init_size, int nelem_alloc); extern void AtEOXact_HashTables(bool isCommit); extern void AtEOSubXact_HashTables(bool isCommit, int nestDepth); -- 2.34.1