From 98ca9cc3f34b6dd0892281583b4eb5e38ce0a668 Mon Sep 17 00:00:00 2001 From: Rahila Syed Date: Thu, 6 Mar 2025 20:06:20 +0530 Subject: [PATCH 1/2] Account for initial 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 control 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. Include the allocation of segments, buckets and elements in the initial allocation of shared hash directory. This results in the existing ShmemIndex entries to reflect all these allocations. The resulting tuples in pg_shmem_allocations represent the total size of the initial hash table including all the buckets and the elements they contain, instead of just the directory size. --- src/backend/storage/ipc/shmem.c | 3 +- src/backend/utils/hash/dynahash.c | 209 ++++++++++++++++++++++-------- src/include/utils/hsearch.h | 3 +- 3 files changed, 161 insertions(+), 54 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 cd5a00132f..3bdf3d6fd5 100644 --- a/src/backend/utils/hash/dynahash.c +++ b/src/backend/utils/hash/dynahash.c @@ -265,7 +265,7 @@ static long hash_accesses, */ 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 +281,9 @@ static void register_seq_scan(HTAB *hashp); static void deregister_seq_scan(HTAB *hashp); static bool has_seq_scans(HTAB *hashp); +static int compute_buckets_and_segs(long nelem, int *nbuckets, + long num_partitions, long ssize); +static void element_add(HTAB *hashp, HASHELEMENT *firstElement, int freelist_idx, int nelem); /* * memory allocation support @@ -353,6 +356,7 @@ 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 +511,19 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) hashp->isshared = false; } + /* Choose 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 +572,8 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) hctl->keysize = info->keysize; hctl->entrysize = info->entrysize; + hctl->nelem_alloc = nelem_batch; + /* make local copies of heavily-used constant fields */ hashp->keysize = hctl->keysize; hashp->ssize = hctl->ssize; @@ -582,6 +598,9 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) freelist_partitions, nelem_alloc, nelem_alloc_first; + void *curr_offset = NULL; + int nsegs; + int nbuckets; /* * If hash table is partitioned, give each freelist an equal share of @@ -592,6 +611,15 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) else freelist_partitions = 1; + /* + * If table is shared, calculate the offset at which to find the the + * first partition of elements + */ + + nsegs = compute_buckets_and_segs(nelem, &nbuckets, hctl->num_partitions, hctl->ssize); + + curr_offset = (((char *) hashp->hctl) + sizeof(HASHHDR) + (hctl->dsize * sizeof(HASHSEGMENT)) + (sizeof(HASHBUCKET) * hctl->ssize * nsegs)); + nelem_alloc = nelem / freelist_partitions; if (nelem_alloc <= 0) nelem_alloc = 1; @@ -609,11 +637,16 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) for (i = 0; i < freelist_partitions; i++) { int temp = (i == 0) ? nelem_alloc_first : nelem_alloc; + HASHELEMENT *firstElement; + Size elementSize = MAXALIGN(sizeof(HASHELEMENT)) + MAXALIGN(hctl->entrysize); - if (!element_alloc(hashp, temp, i)) - ereport(ERROR, - (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("out of memory"))); + /* + * Memory is allocated as part of initial allocation in + * ShmemInitHash + */ + firstElement = (HASHELEMENT *) curr_offset; + curr_offset = (((char *) curr_offset) + (temp * elementSize)); + element_add(hashp, firstElement, i, temp); } } @@ -701,30 +734,11 @@ 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; + nsegs = compute_buckets_and_segs(nelem, &nbuckets, hctl->num_partitions, hctl->ssize); 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). @@ -741,22 +755,21 @@ init_htab(HTAB *hashp, long nelem) if (!(hashp->dir)) { CurrentDynaHashCxt = hashp->hcxt; - hashp->dir = (HASHSEGMENT *) - hashp->alloc(hctl->dsize * sizeof(HASHSEGMENT)); - if (!hashp->dir) - return false; + hashp->dir = (HASHSEGMENT *) (((char *) hashp->hctl) + sizeof(HASHHDR)); } /* Allocate initial segments */ + i = 0; for (segp = hashp->dir; hctl->nsegs < nsegs; hctl->nsegs++, segp++) { - *segp = seg_alloc(hashp); - if (*segp == NULL) - return false; - } + *segp = (HASHBUCKET *) (((char *) hashp->hctl) + + sizeof(HASHHDR) + + (hashp->hctl->dsize * sizeof(HASHSEGMENT)) + + (i * sizeof(HASHBUCKET) * hashp->ssize)); + MemSet(*segp, 0, sizeof(HASHBUCKET) * hashp->ssize); - /* Choose number of entries to allocate at a time */ - hctl->nelem_alloc = choose_nelem_alloc(hctl->entrysize); + i = i + 1; + } #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", @@ -851,11 +864,64 @@ hash_select_dirsize(long num_entries) * and for the (non expansible) directory. */ 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; + 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; + + nsegs = compute_buckets_and_segs(init_size, &nbuckets, num_partitions, ssize); + + if (!element_alloc) + init_size = 0; + + return sizeof(HASHHDR) + dsize * sizeof(HASHSEGMENT) + + +sizeof(HASHBUCKET) * ssize * nsegs + + init_size * elementSize; } @@ -1285,7 +1351,8 @@ 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 +1389,7 @@ get_hash_entry(HTAB *hashp, int freelist_idx) /* no elements available to borrow either, so out of memory */ return NULL; } + element_add(hashp, newElement, freelist_idx, hctl->nelem_alloc); } /* remove entry from freelist, bump nentries */ @@ -1702,28 +1770,38 @@ seg_alloc(HTAB *hashp) /* * allocate some new elements and link them into the indicated free list */ -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; +} +static void +element_add(HTAB *hashp, HASHELEMENT *firstElement, int freelist_idx, int nelem) +{ + 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 +1822,6 @@ element_alloc(HTAB *hashp, int nelem, int freelist_idx) if (IS_PARTITIONED(hctl)) SpinLockRelease(&hctl->freeList[freelist_idx].mutex); - - return true; } /* @@ -1957,3 +2033,32 @@ AtEOSubXact_HashTables(bool isCommit, int nestDepth) } } } + +static int +compute_buckets_and_segs(long nelem, int *nbuckets, long num_partitions, long ssize) +{ + int nsegs; + + /* + * 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 + */ + nsegs = ((*nbuckets) - 1) / ssize + 1; + nsegs = next_pow2_int(nsegs); + return nsegs; +} diff --git a/src/include/utils/hsearch.h b/src/include/utils/hsearch.h index 932cc4f34d..5e513c8116 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