agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH 1/8] sequential scan for dshash 54+ messages / 3 participants [nested] [flat]
* [PATCH 1/8] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index b2b8fe60e1..af904c034e 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index 8c733bfe25..8ab1a21f3e 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Thu_Nov_08_20_46_48_2018_519)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v7-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/8] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 138 +++++++++++++++++++++++++++++++++++++++++++++++ src/include/lib/dshash.h | 23 +++++++- 2 files changed, 160 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index b46f7c4cfd..5b133226ac 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -592,6 +592,144 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = ((size_t) 1) << hash_table->control->size_log2; + status->curitem = NULL; + status->curpartition = -1; + status->consistent = consistent; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), LW_SHARED); + } + } + ensure_valid_bucket_pointers(hash_table); +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + next_item_pointer = status->hash_table->buckets[status->curbucket]; + status->hash_table->find_locked = true; + } + else + next_item_pointer = status->curitem->next; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + Assert(status->hash_table->find_locked); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + + /* + * we need a lock on the scanning partition even if the caller don't + * requested a consistent snapshot. + */ + if (!status->consistent && DsaPointerIsValid(next_item_pointer)) + { + dshash_table_item *item = dsa_get_address(status->hash_table->area, + next_item_pointer); + int next_partition = PARTITION_FOR_HASH(item->hash); + if (status->curpartition != next_partition) + { + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + LW_SHARED); + status->curpartition = next_partition; + } + } + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->find_locked); + status->hash_table->find_locked = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +int +dshash_get_num_entries(dshash_table *hash_table) +{ + /* a shotcut implement. should be improved */ + dshash_seq_status s; + void *p; + int n = 0; + + dshash_seq_init(&s, hash_table, false); + while ((p = dshash_seq_next(&s)) != NULL) + n++; + + return n; +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index 8c733bfe25..8598d9ed84 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -15,6 +15,7 @@ #define DSHASH_H #include "utils/dsa.h" +#include "utils/hsearch.h" /* The opaque type representing a hash table. */ struct dshash_table; @@ -59,6 +60,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + int curpartition; + bool consistent; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +86,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern int dshash_get_num_entries(dshash_table *hash_table); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Thu_Sep_27_22_00_49_2018_853)---- ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/7] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index b2b8fe60e1..af904c034e 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index 8c733bfe25..8ab1a21f3e 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Tue_Nov_27_17_59_49_2018_846)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v10-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 185 +++++++++++++++++++++++++++++++++++++-- src/include/lib/dshash.h | 22 ++++- 2 files changed, 201 insertions(+), 6 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index fbdd941325..7675370058 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,164 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called for incomplete scans and otherwise + * shoudln't. Finished scans are cleaned up automatically. + * + * Returned elements are locked as is the case with dshash_find. However, the + * caller must not release the lock. + * + * Same as dynanash, the caller may delete returned elements midst of a scan. + * + * If consistent is set for dshash_seq_init, the all hash table partitions are + * locked in the requested mode (as determined by the exclusive flag) during + * the scan. Otherwise partitions are locked in one-at-a-time way during the + * scan. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Lock the next partition then release the current, not in the + * reverse order to to avoid concurrent resizing. Partitions + * are locked in the same order with resize() so dead locks + * won't happen. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. @@ -673,7 +849,6 @@ delete_item(dshash_table *hash_table, dshash_table_item *item) /* * Grow the hash table if necessary to the requested number of buckets. The * requested size must be double some previously observed size. - * * Must be called without any partition lock held. */ static void diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..ad88f32cdd 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,22 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +86,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +95,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.23.0 ----Next_Part(Wed_Jan_22_17_24_04_2020_620)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 350f8c0a66..4f0c7ec840 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index fa2e28ff3e..79698a6ad6 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Thu_Jul_11_16_40_59_2019_397)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v21-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index f095196fb6..d1908a6137 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index e5dfd57f0a..b80f3af995 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Mon_Feb_18_21_35_31_2019_949)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v14-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index f095196fb6..d1908a6137 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index e5dfd57f0a..b80f3af995 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Tue_Feb_19_21_40_07_2019_247)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v15-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v24 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 ++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 350f8c0a66..4f0c7ec840 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index fa2e28ff3e..79698a6ad6 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.23.0 ----Next_Part(Tue_Dec__3_17_27_59_2019_887)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v24-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/3] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 122 +++++++++++++++++++++++++++++++++++++++++++++++ src/include/lib/dshash.h | 20 +++++++- 2 files changed, 141 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index b46f7c4cfd..e6c1ef44f1 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -592,6 +592,128 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * Initialize a sequential scan on the hash_table. Allows no modifications + * during a scan if consistent = true. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = ((size_t) 1) << hash_table->control->size_log2; + status->curitem = NULL; + status->curpartition = -1; + status->consistent = consistent; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), LW_SHARED); + } + } + ensure_valid_bucket_pointers(hash_table); +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + next_item_pointer = status->hash_table->buckets[status->curbucket]; + status->hash_table->find_locked = true; + } + else + next_item_pointer = status->curitem->next; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_release(status); + return NULL; + } + Assert(status->hash_table->find_locked); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + + /* + * we need a lock on the scanning partition even if the caller don't + * requested a consistent snapshot. + */ + if (!status->consistent && DsaPointerIsValid(next_item_pointer)) + { + dshash_table_item *item = dsa_get_address(status->hash_table->area, + next_item_pointer); + int next_partition = PARTITION_FOR_HASH(item->hash); + if (status->curpartition != next_partition) + { + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + LW_SHARED); + status->curpartition = next_partition; + } + } + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_release(dshash_seq_status *status) +{ + Assert(status->hash_table->find_locked); + status->hash_table->find_locked = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +int +dshash_get_num_entries(dshash_table *hash_table) +{ + /* a shotcut implement. should be improved */ + dshash_seq_status s; + void *p; + int n = 0; + + dshash_seq_init(&s, hash_table, false); + while ((p = dshash_seq_next(&s)) != NULL) + n++; + + return n; +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index 8c733bfe25..a4565d3219 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -15,6 +15,7 @@ #define DSHASH_H #include "utils/dsa.h" +#include "utils/hsearch.h" /* The opaque type representing a hash table. */ struct dshash_table; @@ -59,6 +60,18 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + int curpartition; + bool consistent; +}; + +typedef struct dshash_seq_status dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +83,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +92,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_release(dshash_seq_status *status); +extern int dshash_get_num_entries(dshash_table *hash_table); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Tue_Jul_03_19_01_44_2018_430)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v2-0002-Change-stats-collector-to-an-axiliary-process.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/6] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 138 +++++++++++++++++++++++++++++++++++++++++++++++ src/include/lib/dshash.h | 23 +++++++- 2 files changed, 160 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index b46f7c4cfd..5b133226ac 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -592,6 +592,144 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = ((size_t) 1) << hash_table->control->size_log2; + status->curitem = NULL; + status->curpartition = -1; + status->consistent = consistent; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), LW_SHARED); + } + } + ensure_valid_bucket_pointers(hash_table); +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + next_item_pointer = status->hash_table->buckets[status->curbucket]; + status->hash_table->find_locked = true; + } + else + next_item_pointer = status->curitem->next; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + Assert(status->hash_table->find_locked); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + + /* + * we need a lock on the scanning partition even if the caller don't + * requested a consistent snapshot. + */ + if (!status->consistent && DsaPointerIsValid(next_item_pointer)) + { + dshash_table_item *item = dsa_get_address(status->hash_table->area, + next_item_pointer); + int next_partition = PARTITION_FOR_HASH(item->hash); + if (status->curpartition != next_partition) + { + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + LW_SHARED); + status->curpartition = next_partition; + } + } + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->find_locked); + status->hash_table->find_locked = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +int +dshash_get_num_entries(dshash_table *hash_table) +{ + /* a shotcut implement. should be improved */ + dshash_seq_status s; + void *p; + int n = 0; + + dshash_seq_init(&s, hash_table, false); + while ((p = dshash_seq_next(&s)) != NULL) + n++; + + return n; +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index 8c733bfe25..8598d9ed84 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -15,6 +15,7 @@ #define DSHASH_H #include "utils/dsa.h" +#include "utils/hsearch.h" /* The opaque type representing a hash table. */ struct dshash_table; @@ -59,6 +60,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + int curpartition; + bool consistent; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +86,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern int dshash_get_num_entries(dshash_table *hash_table); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Wed_Jul_04_17_29_11_2018_498)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v3-0002-Change-stats-collector-to-an-axiliary-process.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 24dd372252..a0ccd7ee7c 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index fa2e28ff3e..79698a6ad6 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Thu_Jul_04_19_27_54_2019_888)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/6] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index f095196fb6..1e8c22f94f 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index e5dfd57f0a..b80f3af995 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Thu_Feb_21_16_05_55_2019_560)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v16-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/6] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index f095196fb6..1e8c22f94f 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index e5dfd57f0a..b80f3af995 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Mon_Feb_25_13_52_14_2019_191)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v17-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/9] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index b2b8fe60e1..af904c034e 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index 8c733bfe25..8ab1a21f3e 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Fri_Nov_09_17_33_15_2018_162)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v8-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v22 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 350f8c0a66..4f0c7ec840 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index fa2e28ff3e..79698a6ad6 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Tue_Sep_10_17_58_58_2019_765)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v22-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v23 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 350f8c0a66..4f0c7ec840 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index fa2e28ff3e..79698a6ad6 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Fri_Sep_27_09_46_47_2019_292)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v23-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index f095196fb6..1e8c22f94f 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index e5dfd57f0a..b80f3af995 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Fri_May_17_14_27_22_2019_078)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v19-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index f095196fb6..1e8c22f94f 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index e5dfd57f0a..b80f3af995 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Fri_May_17_15_47_20_2019_554)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v20-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/7] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index f095196fb6..d1908a6137 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index e5dfd57f0a..b80f3af995 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Mon_Jan_21_21_19_07_2019_726)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v11-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index f095196fb6..d1908a6137 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index e5dfd57f0a..b80f3af995 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Tue_Jan_22_15_48_02_2019_276)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v12-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index f095196fb6..d1908a6137 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index e5dfd57f0a..b80f3af995 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Fri_Feb_15_17_29_00_2019_199)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v13-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/5] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index f095196fb6..1e8c22f94f 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index e5dfd57f0a..b80f3af995 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Wed_Mar_27_16_36_25_2019_836)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v18-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/6] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 138 +++++++++++++++++++++++++++++++++++++++++++++++ src/include/lib/dshash.h | 23 +++++++- 2 files changed, 160 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index b46f7c4cfd..5b133226ac 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -592,6 +592,144 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = ((size_t) 1) << hash_table->control->size_log2; + status->curitem = NULL; + status->curpartition = -1; + status->consistent = consistent; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), LW_SHARED); + } + } + ensure_valid_bucket_pointers(hash_table); +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + next_item_pointer = status->hash_table->buckets[status->curbucket]; + status->hash_table->find_locked = true; + } + else + next_item_pointer = status->curitem->next; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + Assert(status->hash_table->find_locked); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + + /* + * we need a lock on the scanning partition even if the caller don't + * requested a consistent snapshot. + */ + if (!status->consistent && DsaPointerIsValid(next_item_pointer)) + { + dshash_table_item *item = dsa_get_address(status->hash_table->area, + next_item_pointer); + int next_partition = PARTITION_FOR_HASH(item->hash); + if (status->curpartition != next_partition) + { + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + LW_SHARED); + status->curpartition = next_partition; + } + } + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->find_locked); + status->hash_table->find_locked = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +int +dshash_get_num_entries(dshash_table *hash_table) +{ + /* a shotcut implement. should be improved */ + dshash_seq_status s; + void *p; + int n = 0; + + dshash_seq_init(&s, hash_table, false); + while ((p = dshash_seq_next(&s)) != NULL) + n++; + + return n; +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index 8c733bfe25..8598d9ed84 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -15,6 +15,7 @@ #define DSHASH_H #include "utils/dsa.h" +#include "utils/hsearch.h" /* The opaque type representing a hash table. */ struct dshash_table; @@ -59,6 +60,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + int curpartition; + bool consistent; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +86,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern int dshash_get_num_entries(dshash_table *hash_table); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Tue_Jul_10_21_07_40_2018_417)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v4-0002-Change-stats-collector-to-an-axiliary-process.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH 1/7] sequential scan for dshash @ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw) Add sequential scan feature to dshash. --- src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 23 +++++- 2 files changed, 206 insertions(+), 5 deletions(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index b2b8fe60e1..af904c034e 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry) LW_EXCLUSIVE)); delete_item(hash_table, item); - hash_table->find_locked = false; - hash_table->find_exclusively_locked = false; - LWLockRelease(PARTITION_LOCK(hash_table, partition)); + + /* We need to keep partition lock while sequential scan */ + if (!hash_table->seqscan_running) + { + hash_table->find_locked = false; + hash_table->find_exclusively_locked = false; + LWLockRelease(PARTITION_LOCK(hash_table, partition)); + } } /* @@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan trhough dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should be called if and only if the scan is abandoned + * before completion; if dshash_seq_next returns NULL then it has already done + * the end-of-scan cleanup. + * + * On returning element, it is locked as is the case with dshash_find. + * However, the caller must not release the lock. The lock is released as + * necessary in continued scan. + * + * As opposed to the equivalent for dynanash, the caller is not supposed to + * delete the returned element before continuing the scan. + * + * If consistent is set for dshash_seq_init, the whole hash table is + * non-exclusively locked. Otherwise a part of the hash table is locked in the + * same mode (partition lock). + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->consistent = consistent; + status->exclusive = exclusive; + hash_table->seqscan_running = true; + + /* + * Protect all partitions from modification if the caller wants a + * consistent result. + */ + if (consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + { + Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i))); + + LWLockAcquire(PARTITION_LOCK(hash_table, i), + exclusive ? LW_EXCLUSIVE : LW_SHARED); + } + ensure_valid_bucket_pointers(hash_table); + } +} + +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + if (!status->consistent) + { + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finsih. */ + dshash_seq_term(status); + return NULL; + } + + /* Also move parititon lock if needed */ + if (!status->consistent) + { + int next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Take lock on the next partition then release the current, + * not in the reverse order. This is required to avoid + * resizing from happening during a sequential scan. Locks are + * taken in partition order so no dead lock happen with other + * seq scans or resizing. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * This item can be deleted by the caller. Store the next item for the + * next iteration for the occasion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->consistent) + { + int i; + + for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i) + LWLockRelease(PARTITION_LOCK(status->hash_table, i)); + } + else if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index 8c733bfe25..8ab1a21f3e 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,23 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state of dshash. The detail is exposed since the storage + * size should be known to users but it should be considered as an opaque + * type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool consistent; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area, extern void dshash_detach(dshash_table *hash_table); extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table); extern void dshash_destroy(dshash_table *hash_table); - /* Finding, creating, deleting entries. */ extern void *dshash_find(dshash_table *hash_table, const void *key, bool exclusive); @@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool consistent, bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.16.3 ----Next_Part(Mon_Nov_12_20_10_42_2018_878)---- ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v29 2/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 150 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 170 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..fb7e23c4cb 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,146 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Also move parititon lock if needed */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Lock the next partition then release the current, not in the + * reverse order to avoid concurrent resizing. Partitions are + * locked in the same order with resize() so dead locks won't + * happen. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..81a929b8d9 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Wed_Apr__1_15_15_11_2020_923)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v29-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v30 2/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 169 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..1ef093e2e9 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..0ca9514021 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Wed_Apr__1_17_37_23_2020_570)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v30-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v33 2/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 169 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..1ef093e2e9 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..0ca9514021 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Thu_Apr_30_13_22_05_2020_409)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v33-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v25 2/8] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 162 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 +++++ 2 files changed, 182 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..2086bdbea9 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -112,6 +112,7 @@ struct dshash_table size_t size_log2; /* log2(number of buckets) */ bool find_locked; /* Is any partition lock held by 'find'? */ bool find_exclusively_locked; /* ... exclusively? */ + bool seqscan_running;/* now under sequential scan */ }; /* Given a pointer to an item, find the entry (user data) it holds. */ @@ -127,6 +128,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +158,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg) hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; /* * Set up the initial array of buckets. Our initial size is the same as @@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params, hash_table->control = dsa_get_address(area, control); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; + hash_table->seqscan_running = false; Assert(hash_table->control->magic == DSHASH_MAGIC); /* @@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -568,6 +579,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry) Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index), hash_table->find_exclusively_locked ? LW_EXCLUSIVE : LW_SHARED)); + /* lock is under control of sequential scan */ + Assert(!hash_table->seqscan_running); hash_table->find_locked = false; hash_table->find_exclusively_locked = false; @@ -592,6 +605,153 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + /* allowed at most one scan at once */ + Assert(!hash_table->seqscan_running); + + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; + hash_table->seqscan_running = true; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + Assert(status->hash_table->seqscan_running); + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Also move parititon lock if needed */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Lock the next partition then release the current, not in the + * reverse order to avoid concurrent resizing. Partitions are + * locked in the same order with resize() so dead locks won't + * happen. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + Assert(status->hash_table->seqscan_running); + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + status->hash_table->seqscan_running = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..81a929b8d9 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Thu_Mar_19_20_30_04_2020_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v25-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v27 2/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 150 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 170 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..fb7e23c4cb 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,146 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Also move parititon lock if needed */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Lock the next partition then release the current, not in the + * reverse order to avoid concurrent resizing. Partitions are + * locked in the same order with resize() so dead locks won't + * happen. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..81a929b8d9 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Fri_Mar_27_16_31_15_2020_716)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v27-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v50 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 +++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 182 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index e0c763be32..520bfa0979 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index c069ec9de7..a6ea377173 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 8bd95aefa1..2b591e94e6 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2954,6 +2954,7 @@ dshash_hash dshash_hash_function dshash_parameters dshash_partition +dshash_seq_status dshash_table dshash_table_control dshash_table_handle -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v51 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 +++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 182 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index e0c763be32..520bfa0979 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index c069ec9de7..a6ea377173 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 8bd95aefa1..2b591e94e6 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2954,6 +2954,7 @@ dshash_hash dshash_hash_function dshash_parameters dshash_partition +dshash_seq_status dshash_table dshash_table_control dshash_table_handle -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v52 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 +++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 182 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index e0c763be32..520bfa0979 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index c069ec9de7..a6ea377173 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index e4d2debb3c..21fd98af66 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2954,6 +2954,7 @@ dshash_hash dshash_hash_function dshash_parameters dshash_partition +dshash_seq_status dshash_table dshash_table_control dshash_table_handle -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v57 1/6] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This commit adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan is in progress. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 161 ++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 +++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 183 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index e0c763be32..29ad767618 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition PG_USED_FOR_ASSERTS_ONLY + = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index c069ec9de7..a6ea377173 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 1d1d5d2f0e..58ad2991a7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2961,6 +2961,7 @@ dshash_hash dshash_hash_function dshash_parameters dshash_partition +dshash_seq_status dshash_table dshash_table_control dshash_table_handle -- 2.27.0 ----Next_Part(Thu_Mar_18_16_56_02_2021_947)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v57-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v44 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 ++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..b829167872 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..c337099061 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.27.0 ----Next_Part(Mon_Dec_21_17_16_20_2020_608)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v44-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v37 1/6] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 169 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..1ef093e2e9 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..0ca9514021 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.4 ----Next_Part(Fri_Sep_25_09_27_26_2020_419)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v37-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v33 2/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 169 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..1ef093e2e9 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..0ca9514021 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Fri_May_15_17_30_36_2020_111)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v33-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v32 2/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 169 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..1ef093e2e9 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..0ca9514021 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Tue_Apr__7_16_38_17_2020_299)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v32-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v28 2/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 150 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 170 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..fb7e23c4cb 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,146 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert (status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Also move parititon lock if needed */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + /* Move lock along with partition for the bucket */ + if (status->curpartition != next_partition) + { + /* + * Lock the next partition then release the current, not in the + * reverse order to avoid concurrent resizing. Partitions are + * locked in the same order with resize() so dead locks won't + * happen. + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..81a929b8d9 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; + int curbucket; + int nbuckets; + dshash_table_item *curitem; + dsa_pointer pnextitem; + int curpartition; + bool exclusive; +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Mon_Mar_30_09_29_45_2020_582)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v28-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v39 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 ++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..b829167872 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..c337099061 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.4 ----Next_Part(Tue_Oct__6_10_06_44_2020_382)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v39-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v31 2/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 169 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..1ef093e2e9 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..0ca9514021 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Fri_Apr__3_17_31_17_2020_104)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v31-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v56 1/6] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This commit adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan is in progress. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 161 ++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 +++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 183 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index e0c763be32..29ad767618 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition PG_USED_FOR_ASSERTS_ONLY + = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index c069ec9de7..a6ea377173 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 61cf4eae1f..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2958,6 +2958,7 @@ dshash_hash dshash_hash_function dshash_parameters dshash_partition +dshash_seq_status dshash_table dshash_table_control dshash_table_handle -- 2.27.0 ----Next_Part(Tue_Mar_16_10_27_55_2021_500)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v40 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 ++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..b829167872 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..c337099061 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.4 ----Next_Part(Wed_Nov__4_17_39_10_2020_208)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v40-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v35 2/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 169 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..1ef093e2e9 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..0ca9514021 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Mon_Jun__8_17_32_04_2020_489)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v35-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v41 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 ++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..b829167872 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..c337099061 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.4 ----Next_Part(Fri_Nov__6_09_27_56_2020_738)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v41-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v45 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 ++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index e0c763be32..520bfa0979 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index c069ec9de7..a6ea377173 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v46 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 ++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index e0c763be32..520bfa0979 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index c069ec9de7..a6ea377173 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v47 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 ++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index e0c763be32..520bfa0979 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index c069ec9de7..a6ea377173 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v49 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 +++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 182 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index e0c763be32..520bfa0979 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index c069ec9de7..a6ea377173 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 8bd95aefa1..2b591e94e6 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2954,6 +2954,7 @@ dshash_hash dshash_hash_function dshash_parameters dshash_partition +dshash_seq_status dshash_table dshash_table_control dshash_table_handle -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v48 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 +++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 182 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index e0c763be32..520bfa0979 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index c069ec9de7..a6ea377173 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 8bd95aefa1..2b591e94e6 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2954,6 +2954,7 @@ dshash_hash dshash_hash_function dshash_parameters dshash_partition +dshash_seq_status dshash_table dshash_table_control dshash_table_handle -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v43 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 ++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..b829167872 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..c337099061 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.27.0 ----Next_Part(Fri_Dec_11_16_50_03_2020_915)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v43-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v38 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 ++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..b829167872 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..c337099061 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.4 ----Next_Part(Thu_Oct__1_09_07_22_2020_252)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v38-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v42 1/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 22 ++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..b829167872 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table, + status->curpartition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED)); + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + +/* Get the current entry while a seq scan. */ +void * +dshash_get_current(dshash_seq_status *status) +{ + return ENTRY_FROM_ITEM(status->curitem); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..c337099061 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); +extern void *dshash_get_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.4 ----Next_Part(Wed_Nov_11_10_07_22_2020_796)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v42-0002-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v34 2/7] sequential scan for dshash @ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw) Dshash did not allow scan the all entries sequentially. This adds the functionality. The interface is similar but a bit different both from that of dynahash and simple dshash search functions. One of the most significant differences is the sequential scan interface of dshash always needs a call to dshash_seq_term when scan ends. Another is locking. Dshash holds partition lock when returning an entry, dshash_seq_next() also holds lock when returning an entry but callers shouldn't release it, since the lock is essential to continue a scan. The seqscan interface allows entry deletion while a scan. The in-scan deletion should be performed by dshash_delete_current(). --- src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++- src/include/lib/dshash.h | 21 ++++++ 2 files changed, 169 insertions(+), 1 deletion(-) diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c index 78ccf03217..1ef093e2e9 100644 --- a/src/backend/lib/dshash.c +++ b/src/backend/lib/dshash.c @@ -127,6 +127,10 @@ struct dshash_table #define NUM_SPLITS(size_log2) \ (size_log2 - DSHASH_NUM_PARTITIONS_LOG2) +/* How many buckets are there in a given size? */ +#define NUM_BUCKETS(size_log2) \ + (((size_t) 1) << (size_log2)) + /* How many buckets are there in each partition at a given size? */ #define BUCKETS_PER_PARTITION(size_log2) \ (((size_t) 1) << NUM_SPLITS(size_log2)) @@ -153,6 +157,10 @@ struct dshash_table #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2) \ ((partition) << NUM_SPLITS(size_log2)) +/* Choose partition based on bucket index. */ +#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2) \ + ((bucket_idx) >> NUM_SPLITS(size_log2)) + /* The head of the active bucket for a given hash value (lvalue). */ #define BUCKET_FOR_HASH(hash_table, hash) \ (hash_table->buckets[ \ @@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table) ensure_valid_bucket_pointers(hash_table); /* Free all the entries. */ - size = ((size_t) 1) << hash_table->size_log2; + size = NUM_BUCKETS(hash_table->size_log2); for (i = 0; i < size; ++i) { dsa_pointer item_pointer = hash_table->buckets[i]; @@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg) return tag_hash(v, size); } +/* + * dshash_seq_init/_next/_term + * Sequentially scan through dshash table and return all the + * elements one by one, return NULL when no more. + * + * dshash_seq_term should always be called when a scan finished. + * The caller may delete returned elements midst of a scan by using + * dshash_delete_current(). exclusive must be true to delete elements. + */ +void +dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive) +{ + status->hash_table = hash_table; + status->curbucket = 0; + status->nbuckets = 0; + status->curitem = NULL; + status->pnextitem = InvalidDsaPointer; + status->curpartition = -1; + status->exclusive = exclusive; +} + +/* + * Returns the next element. + * + * Returned elements are locked and the caller must not explicitly release + * it. It is released at the next call to dshash_next(). + */ +void * +dshash_seq_next(dshash_seq_status *status) +{ + dsa_pointer next_item_pointer; + + if (status->curitem == NULL) + { + int partition; + + Assert(status->curbucket == 0); + Assert(!status->hash_table->find_locked); + + /* first shot. grab the first item. */ + partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + LWLockAcquire(PARTITION_LOCK(status->hash_table, partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + status->curpartition = partition; + + /* resize doesn't happen from now until seq scan ends */ + status->nbuckets = + NUM_BUCKETS(status->hash_table->control->size_log2); + ensure_valid_bucket_pointers(status->hash_table); + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + else + next_item_pointer = status->pnextitem; + + /* Move to the next bucket if we finished the current bucket */ + while (!DsaPointerIsValid(next_item_pointer)) + { + int next_partition; + + if (++status->curbucket >= status->nbuckets) + { + /* all buckets have been scanned. finish. */ + return NULL; + } + + /* Check if move to the next partition */ + next_partition = + PARTITION_FOR_BUCKET_INDEX(status->curbucket, + status->hash_table->size_log2); + + if (status->curpartition != next_partition) + { + /* + * Move to the next partition. Lock the next partition then release + * the current, not in the reverse order to avoid concurrent + * resizing. Avoid dead lock by taking lock in the same order + * with resize(). + */ + LWLockAcquire(PARTITION_LOCK(status->hash_table, + next_partition), + status->exclusive ? LW_EXCLUSIVE : LW_SHARED); + LWLockRelease(PARTITION_LOCK(status->hash_table, + status->curpartition)); + status->curpartition = next_partition; + } + + next_item_pointer = status->hash_table->buckets[status->curbucket]; + } + + status->curitem = + dsa_get_address(status->hash_table->area, next_item_pointer); + status->hash_table->find_locked = true; + status->hash_table->find_exclusively_locked = status->exclusive; + + /* + * The caller may delete the item. Store the next item in case of deletion. + */ + status->pnextitem = status->curitem->next; + + return ENTRY_FROM_ITEM(status->curitem); +} + +/* + * Terminates the seqscan and release all locks. + * + * Should be always called when finishing or exiting a seqscan. + */ +void +dshash_seq_term(dshash_seq_status *status) +{ + status->hash_table->find_locked = false; + status->hash_table->find_exclusively_locked = false; + + if (status->curpartition >= 0) + LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition)); +} + +/* Remove the current entry while a seq scan. */ +void +dshash_delete_current(dshash_seq_status *status) +{ + dshash_table *hash_table = status->hash_table; + dshash_table_item *item = status->curitem; + size_t partition = PARTITION_FOR_HASH(item->hash); + + Assert(status->exclusive); + Assert(hash_table->control->magic == DSHASH_MAGIC); + Assert(hash_table->find_locked); + Assert(hash_table->find_exclusively_locked); + Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition), + LW_EXCLUSIVE)); + + delete_item(hash_table, item); +} + /* * Print debugging information about the internal state of the hash table to * stderr. The caller must hold no partition locks. diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h index b86df68e77..0ca9514021 100644 --- a/src/include/lib/dshash.h +++ b/src/include/lib/dshash.h @@ -59,6 +59,21 @@ typedef struct dshash_parameters struct dshash_table_item; typedef struct dshash_table_item dshash_table_item; +/* + * Sequential scan state. The detail is exposed to let users know the storage + * size but it should be considered as an opaque type by callers. + */ +typedef struct dshash_seq_status +{ + dshash_table *hash_table; /* dshash table working on */ + int curbucket; /* bucket number we are at */ + int nbuckets; /* total number of buckets in the dshash */ + dshash_table_item *curitem; /* item we are currently at */ + dsa_pointer pnextitem; /* dsa-pointer to the next item */ + int curpartition; /* partition number we are at */ + bool exclusive; /* locking mode */ +} dshash_seq_status; + /* Creating, sharing and destroying from hash tables. */ extern dshash_table *dshash_create(dsa_area *area, const dshash_parameters *params, @@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key); extern void dshash_delete_entry(dshash_table *hash_table, void *entry); extern void dshash_release_lock(dshash_table *hash_table, void *entry); +/* seq scan support */ +extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table, + bool exclusive); +extern void *dshash_seq_next(dshash_seq_status *status); +extern void dshash_seq_term(dshash_seq_status *status); +extern void dshash_delete_current(dshash_seq_status *status); /* Convenience hash and compare functions wrapping memcmp and tag_hash. */ extern int dshash_memcmp(const void *a, const void *b, size_t size, void *arg); extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg); -- 2.18.2 ----Next_Part(Mon_Jun__1_18_00_01_2020_089)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v34-0003-Add-conditional-lock-feature-to-dshash.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
* [PATCH v19 5/8] Row pattern recognition patch (executor). @ 2024-05-14 23:26 Tatsuo Ishii <[email protected]> 0 siblings, 0 replies; 54+ messages in thread From: Tatsuo Ishii @ 2024-05-14 23:26 UTC (permalink / raw) --- src/backend/executor/nodeWindowAgg.c | 1610 +++++++++++++++++++++++++- src/backend/utils/adt/windowfuncs.c | 37 +- src/include/catalog/pg_proc.dat | 6 + src/include/nodes/execnodes.h | 30 + 4 files changed, 1671 insertions(+), 12 deletions(-) diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c index 3221fa1522..140bb3941e 100644 --- a/src/backend/executor/nodeWindowAgg.c +++ b/src/backend/executor/nodeWindowAgg.c @@ -36,6 +36,7 @@ #include "access/htup_details.h" #include "catalog/objectaccess.h" #include "catalog/pg_aggregate.h" +#include "catalog/pg_collation_d.h" #include "catalog/pg_proc.h" #include "executor/executor.h" #include "executor/nodeWindowAgg.h" @@ -48,6 +49,7 @@ #include "utils/acl.h" #include "utils/builtins.h" #include "utils/datum.h" +#include "utils/fmgroids.h" #include "utils/expandeddatum.h" #include "utils/lsyscache.h" #include "utils/memutils.h" @@ -159,6 +161,43 @@ typedef struct WindowStatePerAggData bool restart; /* need to restart this agg in this cycle? */ } WindowStatePerAggData; +/* + * Set of StringInfo. Used in RPR. + */ +typedef struct StringSet +{ + StringInfo *str_set; + Size set_size; /* current array allocation size in number of + * items */ + int set_index; /* current used size */ +} StringSet; + +/* + * Allowed subsequent PATTERN variables positions. + * Used in RPR. + * + * pos represents the pattern variable defined order in DEFINE caluase. For + * example. "DEFINE START..., UP..., DOWN ..." and "PATTERN START UP DOWN UP" + * will create: + * VariablePos[0].pos[0] = 0; START + * VariablePos[1].pos[0] = 1; UP + * VariablePos[1].pos[1] = 3; UP + * VariablePos[2].pos[0] = 2; DOWN + * + * Note that UP has two pos because UP appears in PATTERN twice. + * + * By using this strucrture, we can know which pattern variable can be followed + * by which pattern variable(s). For example, START can be followed by UP and + * DOWN since START's pos is 0, and UP's pos is 1 or 3, DOWN's pos is 2. + * DOWN can be followed by UP since UP's pos is either 1 or 3. + * + */ +#define NUM_ALPHABETS 26 /* we allow [a-z] variable initials */ +typedef struct VariablePos +{ + int pos[NUM_ALPHABETS]; /* postion(s) in PATTERN */ +} VariablePos; + static void initialize_windowaggregate(WindowAggState *winstate, WindowStatePerFunc perfuncstate, WindowStatePerAgg peraggstate); @@ -184,6 +223,7 @@ static void release_partition(WindowAggState *winstate); static int row_is_in_frame(WindowAggState *winstate, int64 pos, TupleTableSlot *slot); + static void update_frameheadpos(WindowAggState *winstate); static void update_frametailpos(WindowAggState *winstate); static void update_grouptailpos(WindowAggState *winstate); @@ -195,9 +235,48 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype); static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1, TupleTableSlot *slot2); + +static int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot, + int relpos, int seektype, bool set_mark, + bool *isnull, bool *isout); static bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot); +static void attno_map(Node *node); +static bool attno_map_walker(Node *node, void *context); +static int row_is_in_reduced_frame(WindowObject winobj, int64 pos); +static bool rpr_is_defined(WindowAggState *winstate); + +static void create_reduced_frame_map(WindowAggState *winstate); +static int get_reduced_frame_map(WindowAggState *winstate, int64 pos); +static void register_reduced_frame_map(WindowAggState *winstate, int64 pos, + int val); +static void clear_reduced_frame_map(WindowAggState *winstate); +static void update_reduced_frame(WindowObject winobj, int64 pos); + +static int64 evaluate_pattern(WindowObject winobj, int64 current_pos, + char *vname, StringInfo encoded_str, bool *result); + +static bool get_slots(WindowObject winobj, int64 current_pos); + +static int search_str_set(char *pattern, StringSet * str_set, + VariablePos * variable_pos); +static char pattern_initial(WindowAggState *winstate, char *vname); +static int do_pattern_match(char *pattern, char *encoded_str); + +static StringSet * string_set_init(void); +static void string_set_add(StringSet * string_set, StringInfo str); +static StringInfo string_set_get(StringSet * string_set, int index); +static int string_set_get_size(StringSet * string_set); +static void string_set_discard(StringSet * string_set); +static VariablePos * variable_pos_init(void); +static void variable_pos_register(VariablePos * variable_pos, char initial, + int pos); +static bool variable_pos_compare(VariablePos * variable_pos, + char initial1, char initial2); +static int variable_pos_fetch(VariablePos * variable_pos, char initial, + int index); +static void variable_pos_discard(VariablePos * variable_pos); /* * initialize_windowaggregate @@ -774,10 +853,12 @@ eval_windowaggregates(WindowAggState *winstate) * transition function, or * - we have an EXCLUSION clause, or * - if the new frame doesn't overlap the old one + * - if RPR is enabled * * Note that we don't strictly need to restart in the last case, but if * we're going to remove all rows from the aggregation anyway, a restart * surely is faster. + * we restart aggregation too. *---------- */ numaggs_restart = 0; @@ -788,7 +869,8 @@ eval_windowaggregates(WindowAggState *winstate) (winstate->aggregatedbase != winstate->frameheadpos && !OidIsValid(peraggstate->invtransfn_oid)) || (winstate->frameOptions & FRAMEOPTION_EXCLUSION) || - winstate->aggregatedupto <= winstate->frameheadpos) + winstate->aggregatedupto <= winstate->frameheadpos || + rpr_is_defined(winstate)) { peraggstate->restart = true; numaggs_restart++; @@ -862,7 +944,22 @@ eval_windowaggregates(WindowAggState *winstate) * head, so that tuplestore can discard unnecessary rows. */ if (agg_winobj->markptr >= 0) - WinSetMarkPosition(agg_winobj, winstate->frameheadpos); + { + int64 markpos = winstate->frameheadpos; + + if (rpr_is_defined(winstate)) + { + /* + * If RPR is used, it is possible PREV wants to look at the + * previous row. So the mark pos should be frameheadpos - 1 + * unless it is below 0. + */ + markpos -= 1; + if (markpos < 0) + markpos = 0; + } + WinSetMarkPosition(agg_winobj, markpos); + } /* * Now restart the aggregates that require it. @@ -917,6 +1014,14 @@ eval_windowaggregates(WindowAggState *winstate) { winstate->aggregatedupto = winstate->frameheadpos; ExecClearTuple(agg_row_slot); + + /* + * If RPR is defined, we do not use aggregatedupto_nonrestarted. To + * avoid assertion failure below, we reset aggregatedupto_nonrestarted + * to frameheadpos. + */ + if (rpr_is_defined(winstate)) + aggregatedupto_nonrestarted = winstate->frameheadpos; } /* @@ -930,6 +1035,12 @@ eval_windowaggregates(WindowAggState *winstate) { int ret; +#ifdef RPR_DEBUG + elog(DEBUG1, "===== loop in frame starts: aggregatedupto: " INT64_FORMAT " aggregatedbase: " INT64_FORMAT, + winstate->aggregatedupto, + winstate->aggregatedbase); +#endif + /* Fetch next row if we didn't already */ if (TupIsNull(agg_row_slot)) { @@ -945,9 +1056,52 @@ eval_windowaggregates(WindowAggState *winstate) ret = row_is_in_frame(winstate, winstate->aggregatedupto, agg_row_slot); if (ret < 0) break; + if (ret == 0) goto next_tuple; + if (rpr_is_defined(winstate)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "reduced_frame_map: %d aggregatedupto: " INT64_FORMAT " aggregatedbase: " INT64_FORMAT, + get_reduced_frame_map(winstate, + winstate->aggregatedupto), + winstate->aggregatedupto, + winstate->aggregatedbase); +#endif + /* + * If the row status at currentpos is already decided and current + * row status is not decided yet, it means we passed the last + * reduced frame. Time to break the loop. + */ + if (get_reduced_frame_map(winstate, + winstate->currentpos) != RF_NOT_DETERMINED && + get_reduced_frame_map(winstate, + winstate->aggregatedupto) == RF_NOT_DETERMINED) + break; + + /* + * Otherwise we need to calculate the reduced frame. + */ + ret = row_is_in_reduced_frame(winstate->agg_winobj, + winstate->aggregatedupto); + if (ret == -1) /* unmatched row */ + break; + + /* + * Check if current row needs to be skipped due to no match. + */ + if (get_reduced_frame_map(winstate, + winstate->aggregatedupto) == RF_SKIPPED && + winstate->aggregatedupto == winstate->aggregatedbase) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "skip current row for aggregation"); +#endif + break; + } + } + /* Set tuple context for evaluation of aggregate arguments */ winstate->tmpcontext->ecxt_outertuple = agg_row_slot; @@ -976,6 +1130,7 @@ next_tuple: ExecClearTuple(agg_row_slot); } + /* The frame's end is not supposed to move backwards, ever */ Assert(aggregatedupto_nonrestarted <= winstate->aggregatedupto); @@ -995,7 +1150,6 @@ next_tuple: &winstate->perfunc[wfuncno], peraggstate, result, isnull); - /* * save the result in case next row shares the same frame. * @@ -1090,6 +1244,7 @@ begin_partition(WindowAggState *winstate) winstate->framehead_valid = false; winstate->frametail_valid = false; winstate->grouptail_valid = false; + create_reduced_frame_map(winstate); winstate->spooled_rows = 0; winstate->currentpos = 0; winstate->frameheadpos = 0; @@ -2053,6 +2208,11 @@ ExecWindowAgg(PlanState *pstate) CHECK_FOR_INTERRUPTS(); +#ifdef RPR_DEBUG + elog(DEBUG1, "ExecWindowAgg called. pos: " INT64_FORMAT, + winstate->currentpos); +#endif + if (winstate->status == WINDOWAGG_DONE) return NULL; @@ -2221,6 +2381,17 @@ ExecWindowAgg(PlanState *pstate) /* don't evaluate the window functions when we're in pass-through mode */ if (winstate->status == WINDOWAGG_RUN) { + /* + * If RPR is defined and skip mode is next row, we need to clear + * existing reduced frame info so that we newly calculate the info + * starting from current row. + */ + if (rpr_is_defined(winstate)) + { + if (winstate->rpSkipTo == ST_NEXT_ROW) + clear_reduced_frame_map(winstate); + } + /* * Evaluate true window functions */ @@ -2388,6 +2559,9 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) TupleDesc scanDesc; ListCell *l; + TargetEntry *te; + Expr *expr; + /* check for unsupported flags */ Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK))); @@ -2486,6 +2660,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc, &TTSOpsMinimalTuple); + winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc, + &TTSOpsMinimalTuple); + + winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc, + &TTSOpsMinimalTuple); + + winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc, + &TTSOpsMinimalTuple); + winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot); + /* * create frame head and tail slots only if needed (must create slots in * exactly the same cases that update_frameheadpos and update_frametailpos @@ -2667,6 +2851,43 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) winstate->inRangeAsc = node->inRangeAsc; winstate->inRangeNullsFirst = node->inRangeNullsFirst; + /* Set up SKIP TO type */ + winstate->rpSkipTo = node->rpSkipTo; + /* Set up row pattern recognition PATTERN clause */ + winstate->patternVariableList = node->patternVariable; + winstate->patternRegexpList = node->patternRegexp; + + /* Set up row pattern recognition DEFINE clause */ + winstate->defineInitial = node->defineInitial; + winstate->defineVariableList = NIL; + winstate->defineClauseList = NIL; + if (node->defineClause != NIL) + { + /* + * Tweak arg var of PREV/NEXT so that it refers to scan/inner slot. + */ + foreach(l, node->defineClause) + { + char *name; + ExprState *exps; + + te = lfirst(l); + name = te->resname; + expr = te->expr; + +#ifdef RPR_DEBUG + elog(DEBUG1, "defineVariable name: %s", name); +#endif + winstate->defineVariableList = + lappend(winstate->defineVariableList, + makeString(pstrdup(name))); + attno_map((Node *) expr); + exps = ExecInitExpr(expr, (PlanState *) winstate); + winstate->defineClauseList = + lappend(winstate->defineClauseList, exps); + } + } + winstate->all_first = true; winstate->partition_spooled = false; winstate->more_partitions = false; @@ -2674,6 +2895,64 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) return winstate; } +/* + * Rewrite varno of Var node that is the argument of PREV/NET so that it sees + * scan tuple (PREV) or inner tuple (NEXT). + */ +static void +attno_map(Node *node) +{ + (void) expression_tree_walker(node, attno_map_walker, NULL); +} + +static bool +attno_map_walker(Node *node, void *context) +{ + FuncExpr *func; + int nargs; + Expr *expr; + Var *var; + + if (node == NULL) + return false; + + if (IsA(node, FuncExpr)) + { + func = (FuncExpr *) node; + + if (func->funcid == F_PREV || func->funcid == F_NEXT) + { + /* sanity check */ + nargs = list_length(func->args); + if (list_length(func->args) != 1) + elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", + func->funcid, nargs); + + expr = (Expr *) lfirst(list_head(func->args)); + if (!IsA(expr, Var)) + elog(ERROR, "PREV/NEXT's arg is not Var"); /* XXX: is it possible + * that arg type is + * Const? */ + var = (Var *) expr; + + if (func->funcid == F_PREV) + + /* + * Rewrite varno from OUTER_VAR to regular var no so that the + * var references scan tuple. + */ + var->varno = var->varnosyn; + else + var->varno = INNER_VAR; + +#ifdef RPR_DEBUG + elog(DEBUG1, "PREV/NEXT's varno is rewritten to: %d", var->varno); +#endif + } + } + return expression_tree_walker(node, attno_map_walker, NULL); +} + /* ----------------- * ExecEndWindowAgg * ----------------- @@ -2723,6 +3002,8 @@ ExecReScanWindowAgg(WindowAggState *node) ExecClearTuple(node->agg_row_slot); ExecClearTuple(node->temp_slot_1); ExecClearTuple(node->temp_slot_2); + ExecClearTuple(node->prev_slot); + ExecClearTuple(node->next_slot); if (node->framehead_slot) ExecClearTuple(node->framehead_slot); if (node->frametail_slot) @@ -3083,7 +3364,8 @@ window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot) return false; if (pos < winobj->markpos) - elog(ERROR, "cannot fetch row before WindowObject's mark position"); + elog(ERROR, "cannot fetch row: " INT64_FORMAT " before WindowObject's mark position: " INT64_FORMAT, + pos, winobj->markpos); oldcontext = MemoryContextSwitchTo(winstate->ss.ps.ps_ExprContext->ecxt_per_query_memory); @@ -3403,14 +3685,54 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, WindowAggState *winstate; ExprContext *econtext; TupleTableSlot *slot; - int64 abs_pos; - int64 mark_pos; Assert(WindowObjectIsValid(winobj)); winstate = winobj->winstate; econtext = winstate->ss.ps.ps_ExprContext; slot = winstate->temp_slot_1; + if (WinGetSlotInFrame(winobj, slot, + relpos, seektype, set_mark, + isnull, isout) == 0) + { + econtext->ecxt_outertuple = slot; + return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno), + econtext, isnull); + } + + if (isout) + *isout = true; + *isnull = true; + return (Datum) 0; +} + +/* + * WinGetSlotInFrame + * slot: TupleTableSlot to store the result + * relpos: signed rowcount offset from the seek position + * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL + * set_mark: If the row is found/in frame and set_mark is true, the mark is + * moved to the row as a side-effect. + * isnull: output argument, receives isnull status of result + * isout: output argument, set to indicate whether target row position + * is out of frame (can pass NULL if caller doesn't care about this) + * + * Returns 0 if we successfullt got the slot. false if out of frame. + * (also isout is set) + */ +static int +WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot, + int relpos, int seektype, bool set_mark, + bool *isnull, bool *isout) +{ + WindowAggState *winstate; + int64 abs_pos; + int64 mark_pos; + int num_reduced_frame; + + Assert(WindowObjectIsValid(winobj)); + winstate = winobj->winstate; + switch (seektype) { case WINDOW_SEEK_CURRENT: @@ -3477,11 +3799,25 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, winstate->frameOptions); break; } + num_reduced_frame = row_is_in_reduced_frame(winobj, + winstate->frameheadpos); + if (num_reduced_frame < 0) + goto out_of_frame; + else if (num_reduced_frame > 0) + if (relpos >= num_reduced_frame) + goto out_of_frame; break; case WINDOW_SEEK_TAIL: /* rejecting relpos > 0 is easy and simplifies code below */ if (relpos > 0) goto out_of_frame; + + /* + * RPR cares about frame head pos. Need to call + * update_frameheadpos + */ + update_frameheadpos(winstate); + update_frametailpos(winstate); abs_pos = winstate->frametailpos - 1 + relpos; @@ -3548,6 +3884,14 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, mark_pos = 0; /* keep compiler quiet */ break; } + + num_reduced_frame = row_is_in_reduced_frame(winobj, + winstate->frameheadpos + relpos); + if (num_reduced_frame < 0) + goto out_of_frame; + else if (num_reduced_frame > 0) + abs_pos = winstate->frameheadpos + relpos + + num_reduced_frame - 1; break; default: elog(ERROR, "unrecognized window seek type: %d", seektype); @@ -3566,15 +3910,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, *isout = false; if (set_mark) WinSetMarkPosition(winobj, mark_pos); - econtext->ecxt_outertuple = slot; - return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno), - econtext, isnull); + return 0; out_of_frame: if (isout) *isout = true; *isnull = true; - return (Datum) 0; + return -1; } /* @@ -3605,3 +3947,1251 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull) return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno), econtext, isnull); } + +/* + * rpr_is_defined + * return true if Row pattern recognition is defined. + */ +static +bool +rpr_is_defined(WindowAggState *winstate) +{ + return winstate->patternVariableList != NIL; +} + +/* + * ----------------- + * row_is_in_reduced_frame + * Determine whether a row is in the current row's reduced window frame + * according to row pattern matching + * + * The row must has been already determined that it is in a full window frame + * and fetched it into slot. + * + * Returns: + * = 0, RPR is not defined. + * >0, if the row is the first in the reduced frame. Return the number of rows + * in the reduced frame. + * -1, if the row is unmatched row + * -2, if the row is in the reduced frame but needed to be skipped because of + * AFTER MATCH SKIP PAST LAST ROW + * ----------------- + */ +static +int +row_is_in_reduced_frame(WindowObject winobj, int64 pos) +{ + WindowAggState *winstate = winobj->winstate; + int state; + int rtn; + + if (!rpr_is_defined(winstate)) + { + /* + * RPR is not defined. Assume that we are always in the the reduced + * window frame. + */ + rtn = 0; +#ifdef RPR_DEBUG + elog(DEBUG1, "row_is_in_reduced_frame returns %d: pos: " INT64_FORMAT, + rtn, pos); +#endif + return rtn; + } + + state = get_reduced_frame_map(winstate, pos); + + if (state == RF_NOT_DETERMINED) + { + update_frameheadpos(winstate); + update_reduced_frame(winobj, pos); + } + + state = get_reduced_frame_map(winstate, pos); + + switch (state) + { + int64 i; + int num_reduced_rows; + + case RF_FRAME_HEAD: + num_reduced_rows = 1; + for (i = pos + 1; + get_reduced_frame_map(winstate, i) == RF_SKIPPED; i++) + num_reduced_rows++; + rtn = num_reduced_rows; + break; + + case RF_SKIPPED: + rtn = -2; + break; + + case RF_UNMATCHED: + rtn = -1; + break; + + default: + elog(ERROR, "Unrecognized state: %d at: " INT64_FORMAT, + state, pos); + break; + } + +#ifdef RPR_DEBUG + elog(DEBUG1, "row_is_in_reduced_frame returns %d: pos: " INT64_FORMAT, + rtn, pos); +#endif + return rtn; +} + +#define REDUCED_FRAME_MAP_INIT_SIZE 1024L + +/* + * create_reduced_frame_map + * Create reduced frame map + */ +static +void +create_reduced_frame_map(WindowAggState *winstate) +{ + winstate->reduced_frame_map = + MemoryContextAlloc(winstate->partcontext, + REDUCED_FRAME_MAP_INIT_SIZE); + winstate->alloc_sz = REDUCED_FRAME_MAP_INIT_SIZE; + clear_reduced_frame_map(winstate); +} + +/* + * clear_reduced_frame_map + * Clear reduced frame map + */ +static +void +clear_reduced_frame_map(WindowAggState *winstate) +{ + Assert(winstate->reduced_frame_map != NULL); + MemSet(winstate->reduced_frame_map, RF_NOT_DETERMINED, + winstate->alloc_sz); +} + +/* + * get_reduced_frame_map + * Get reduced frame map specified by pos + */ +static +int +get_reduced_frame_map(WindowAggState *winstate, int64 pos) +{ + Assert(winstate->reduced_frame_map != NULL); + + if (pos < 0 || pos >= winstate->alloc_sz) + elog(ERROR, "wrong pos: " INT64_FORMAT, pos); + + return winstate->reduced_frame_map[pos]; +} + +/* + * register_reduced_frame_map + * Add/replace reduced frame map member at pos. + * If there's no enough space, expand the map. + */ +static +void +register_reduced_frame_map(WindowAggState *winstate, int64 pos, int val) +{ + int64 realloc_sz; + + Assert(winstate->reduced_frame_map != NULL); + + if (pos < 0) + elog(ERROR, "wrong pos: " INT64_FORMAT, pos); + + if (pos > winstate->alloc_sz - 1) + { + realloc_sz = winstate->alloc_sz * 2; + + winstate->reduced_frame_map = + repalloc(winstate->reduced_frame_map, realloc_sz); + + MemSet(winstate->reduced_frame_map + winstate->alloc_sz, + RF_NOT_DETERMINED, realloc_sz - winstate->alloc_sz); + + winstate->alloc_sz = realloc_sz; + } + + winstate->reduced_frame_map[pos] = val; +} + +/* + * update_reduced_frame + * Update reduced frame info. + */ +static +void +update_reduced_frame(WindowObject winobj, int64 pos) +{ + WindowAggState *winstate = winobj->winstate; + ListCell *lc1, + *lc2; + bool expression_result; + int num_matched_rows; + int64 original_pos; + bool anymatch; + StringInfo encoded_str; + StringInfo pattern_str = makeStringInfo(); + StringSet *str_set; + int initial_index; + VariablePos *variable_pos; + bool greedy = false; + int64 result_pos, + i; + + /* + * Set of pattern variables evaluated to true. Each character corresponds + * to pattern variable. Example: str_set[0] = "AB"; str_set[1] = "AC"; In + * this case at row 0 A and B are true, and A and C are true in row 1. + */ + + /* initialize pattern variables set */ + str_set = string_set_init(); + + /* save original pos */ + original_pos = pos; + + /* + * Check if the pattern does not include any greedy quantifier. If it does + * not, we can just apply the pattern to each row. If it succeeds, we are + * done. + */ + foreach(lc1, winstate->patternRegexpList) + { + char *quantifier = strVal(lfirst(lc1)); + + if (*quantifier == '+' || *quantifier == '*') + { + greedy = true; + break; + } + } + + /* + * Non greedy case + */ + if (!greedy) + { + num_matched_rows = 0; + + foreach(lc1, winstate->patternVariableList) + { + char *vname = strVal(lfirst(lc1)); + + encoded_str = makeStringInfo(); + +#ifdef RPR_DEBUG + elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s", + pos, vname); +#endif + expression_result = false; + + /* evaluate row pattern against current row */ + result_pos = evaluate_pattern(winobj, pos, vname, + encoded_str, &expression_result); + if (!expression_result || result_pos < 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "expression result is false or out of frame"); +#endif + register_reduced_frame_map(winstate, original_pos, + RF_UNMATCHED); + return; + } + /* move to next row */ + pos++; + num_matched_rows++; + } +#ifdef RPR_DEBUG + elog(DEBUG1, "pattern matched"); +#endif + register_reduced_frame_map(winstate, original_pos, RF_FRAME_HEAD); + + for (i = original_pos + 1; i < original_pos + num_matched_rows; i++) + { + register_reduced_frame_map(winstate, i, RF_SKIPPED); + } + return; + } + + /* + * Greedy quantifiers included. Loop over until none of pattern matches or + * encounters end of frame. + */ + for (;;) + { + result_pos = -1; + + /* + * Loop over each PATTERN variable. + */ + anymatch = false; + encoded_str = makeStringInfo(); + + forboth(lc1, winstate->patternVariableList, lc2, + winstate->patternRegexpList) + { + char *vname = strVal(lfirst(lc1)); +#ifdef RPR_DEBUG + char *quantifier = strVal(lfirst(lc2)); + + elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s quantifier: %s", + pos, vname, quantifier); +#endif + expression_result = false; + + /* evaluate row pattern against current row */ + result_pos = evaluate_pattern(winobj, pos, vname, + encoded_str, &expression_result); + if (expression_result) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "expression result is true"); +#endif + anymatch = true; + } + + /* + * If out of frame, we are done. + */ + if (result_pos < 0) + break; + } + + if (!anymatch) + { + /* none of patterns matched. */ + break; + } + + string_set_add(str_set, encoded_str); + +#ifdef RPR_DEBUG + elog(DEBUG1, "pos: " INT64_FORMAT " encoded_str: %s", + encoded_str->data); +#endif + + /* move to next row */ + pos++; + + if (result_pos < 0) + { + /* out of frame */ + break; + } + } + + if (string_set_get_size(str_set) == 0) + { + /* no match found in the first row */ + register_reduced_frame_map(winstate, original_pos, RF_UNMATCHED); + return; + } + +#ifdef RPR_DEBUG + elog(DEBUG2, "pos: " INT64_FORMAT " encoded_str: %s", + pos, encoded_str->data); +#endif + + /* build regular expression */ + pattern_str = makeStringInfo(); + appendStringInfoChar(pattern_str, '^'); + initial_index = 0; + + variable_pos = variable_pos_init(); + + forboth(lc1, winstate->patternVariableList, + lc2, winstate->patternRegexpList) + { + char *vname = strVal(lfirst(lc1)); + char *quantifier = strVal(lfirst(lc2)); + char initial; + + initial = pattern_initial(winstate, vname); + Assert(initial != 0); + appendStringInfoChar(pattern_str, initial); + if (quantifier[0]) + appendStringInfoChar(pattern_str, quantifier[0]); + + /* + * Register the initial at initial_index. If the initial appears more + * than once, all of it's initial_index will be recorded. This could + * happen if a pattern variable appears in the PATTERN clause more + * than once like "UP DOWN UP" "UP UP UP". + */ + variable_pos_register(variable_pos, initial, initial_index); + + initial_index++; + } + +#ifdef RPR_DEBUG + elog(DEBUG2, "pos: " INT64_FORMAT " pattern: %s", + pos, pattern_str->data); +#endif + + /* look for matching pattern variable sequence */ +#ifdef RPR_DEBUG + elog(DEBUG1, "search_str_set started"); +#endif + num_matched_rows = search_str_set(pattern_str->data, + str_set, variable_pos); +#ifdef RPR_DEBUG + elog(DEBUG1, "search_str_set returns: %d", num_matched_rows); +#endif + variable_pos_discard(variable_pos); + string_set_discard(str_set); + + /* + * We are at the first row in the reduced frame. Save the number of + * matched rows as the number of rows in the reduced frame. + */ + if (num_matched_rows <= 0) + { + /* no match */ + register_reduced_frame_map(winstate, original_pos, RF_UNMATCHED); + } + else + { + register_reduced_frame_map(winstate, original_pos, RF_FRAME_HEAD); + + for (i = original_pos + 1; i < original_pos + num_matched_rows; i++) + { + register_reduced_frame_map(winstate, i, RF_SKIPPED); + } + } + + return; +} + +/* + * search_str_set + * Perform pattern matching using "pattern" against str_set. pattern is a + * regular expression derived from PATTERN clause. Note that the regular + * expression string is prefixed by '^' and followed by initials represented + * in a same way as str_set. str_set is a set of StringInfo. Each StringInfo + * has a string comprising initials of pattern variable strings being true in + * a row. The initials are one of [a-y], parallel to the order of variable + * names in DEFINE clause. Suppose DEFINE has variables START, UP and DOWN. If + * PATTERN has START, UP+ and DOWN, then the initials in PATTERN will be 'a', + * 'b' and 'c'. The "pattern" will be "^ab+c". + * + * variable_pos is an array representing the order of pattern variable string + * initials in PATTERN clause. For example initial 'a' potion is in + * variable_pos[0].pos[0] = 0. Note that if the pattern is "START UP DOWN UP" + * (UP appears twice), then "UP" (initial is 'b') has two position 1 and + * 3. Thus variable_pos for b is variable_pos[1].pos[0] = 1 and + * variable_pos[1].pos[1] = 3. + * + * Returns the longest number of the matching rows (greedy matching) if + * quatifier '+' or '*' is included in "pattern". + */ +static +int +search_str_set(char *pattern, StringSet * str_set, VariablePos * variable_pos) +{ +#define MAX_CANDIDATE_NUM 10000 /* max pattern match candidate size */ +#define FREEZED_CHAR 'Z' /* a pattern is freezed if it ends with the + * char */ +#define DISCARD_CHAR 'z' /* a pattern is not need to keep */ + + int set_size; /* number of rows in the set */ + int resultlen; + int index; + StringSet *old_str_set, + *new_str_set; + int new_str_size; + int len; + + set_size = string_set_get_size(str_set); + new_str_set = string_set_init(); + len = 0; + resultlen = 0; + + /* + * Generate all possible pattern variable name initials as a set of + * StringInfo named "new_str_set". For example, if we have two rows + * having "ab" (row 0) and "ac" (row 1) in the input str_set, new_str_set + * will have set of StringInfo "aa", "ac", "ba" and "bc" in the end. + */ +#ifdef RPR_DEBUG + elog(DEBUG1, "pattern: %s set_size: %d", pattern, set_size); +#endif + for (index = 0; index < set_size; index++) + { + StringInfo str; /* search target row */ + char *p; + int old_set_size; + int i; + +#ifdef RPR_DEBUG + elog(DEBUG1, "index: %d", index); +#endif + if (index == 0) + { + /* copy variables in row 0 */ + str = string_set_get(str_set, index); + p = str->data; + + /* + * Loop over each new pattern variable char. + */ + while (*p) + { + StringInfo new = makeStringInfo(); + + /* add pattern variable char */ + appendStringInfoChar(new, *p); + /* add new one to string set */ + string_set_add(new_str_set, new); +#ifdef RPR_DEBUG + elog(DEBUG1, "old_str: NULL new_str: %s", new->data); +#endif + p++; /* next pattern variable */ + } + } + else /* index != 0 */ + { + old_str_set = new_str_set; + new_str_set = string_set_init(); + str = string_set_get(str_set, index); + old_set_size = string_set_get_size(old_str_set); + + /* + * Loop over each rows in the previous result set. + */ + for (i = 0; i < old_set_size; i++) + { + StringInfo new; + char last_old_char; + int old_str_len; + StringInfo old = string_set_get(old_str_set, i); + + p = old->data; + old_str_len = strlen(p); + if (old_str_len > 0) + last_old_char = p[old_str_len - 1]; + else + last_old_char = '\0'; + + /* Is this old set freezed? */ + if (last_old_char == FREEZED_CHAR) + { + /* if shorter match. we can discard it */ + if ((old_str_len - 1) < resultlen) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "discard this old set because shorter match: %s", + old->data); +#endif + continue; + } + +#ifdef RPR_DEBUG + elog(DEBUG1, "keep this old set: %s", old->data); +#endif + + /* move the old set to new_str_set */ + string_set_add(new_str_set, old); + old_str_set->str_set[i] = NULL; + continue; + } + /* Can this old set be discarded? */ + else if (last_old_char == DISCARD_CHAR) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "discard this old set: %s", old->data); +#endif + continue; + } + +#ifdef RPR_DEBUG + elog(DEBUG1, "str->data: %s", str->data); +#endif + + /* + * loop over each pattern variable initial char in the input + * set. + */ + for (p = str->data; *p; p++) + { + /* + * Optimization. Check if the row's pattern variable + * initial character position is greater than or equal to + * the old set's last pattern variable initial character + * position. For example, if the old set's last pattern + * variable initials are "ab", then the new pattern + * variable initial can be "b" or "c" but can not be "a", + * if the initials in PATTERN is something like "a b c" or + * "a b+ c+" etc. This optimization is possible when we + * only allow "+" quantifier. + */ + if (variable_pos_compare(variable_pos, last_old_char, *p)) + { + /* copy source string */ + new = makeStringInfo(); + enlargeStringInfo(new, old->len + 1); + appendStringInfoString(new, old->data); + /* add pattern variable char */ + appendStringInfoChar(new, *p); +#ifdef RPR_DEBUG + elog(DEBUG1, "old_str: %s new_str: %s", + old->data, new->data); +#endif + + /* + * Adhoc optimization. If the first letter in the + * input string is the first and second position one + * and there's no associated quatifier '+', then we + * can dicard the input because there's no chace to + * expand the string further. + * + * For example, pattern "abc" cannot match "aa". + */ +#ifdef RPR_DEBUG + elog(DEBUG1, "pattern[1]:%c pattern[2]:%c new[0]:%c new[1]:%c", + pattern[1], pattern[2], new->data[0], new->data[1]); +#endif + if (pattern[1] == new->data[0] && + pattern[1] == new->data[1] && + pattern[2] != '+' && + pattern[1] != pattern[2]) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "discard this new data: %s", + new->data); +#endif + pfree(new->data); + pfree(new); + continue; + } + + /* add new one to string set */ + string_set_add(new_str_set, new); + } + else + { + /* + * We are freezing this pattern string. Since there's + * no chance to expand the string further, we perform + * pattern matching against the string. If it does not + * match, we can discard it. + */ + len = do_pattern_match(pattern, old->data); + + if (len <= 0) + { + /* no match. we can discard it */ + continue; + } + + else if (len <= resultlen) + { + /* shorter match. we can discard it */ + continue; + } + else + { + /* match length is the longest so far */ + + int new_index; + + /* remember the longest match */ + resultlen = len; + + /* freeze the pattern string */ + new = makeStringInfo(); + enlargeStringInfo(new, old->len + 1); + appendStringInfoString(new, old->data); + /* add freezed mark */ + appendStringInfoChar(new, FREEZED_CHAR); +#ifdef RPR_DEBUG + elog(DEBUG1, "old_str: %s new_str: %s", old->data, new->data); +#endif + string_set_add(new_str_set, new); + + /* + * Search new_str_set to find out freezed entries + * that have shorter match length. Mark them as + * "discard" so that they are discarded in the + * next round. + */ + + /* new_index_size should be the one before */ + new_str_size = + string_set_get_size(new_str_set) - 1; + + /* loop over new_str_set */ + for (new_index = 0; new_index < new_str_size; + new_index++) + { + char new_last_char; + int new_str_len; + + new = string_set_get(new_str_set, new_index); + new_str_len = strlen(new->data); + if (new_str_len > 0) + { + new_last_char = + new->data[new_str_len - 1]; + if (new_last_char == FREEZED_CHAR && + (new_str_len - 1) <= len) + { + /* + * mark this set to discard in the + * next round + */ + appendStringInfoChar(new, DISCARD_CHAR); +#ifdef RPR_DEBUG + elog(DEBUG1, "add discard char: %s", new->data); +#endif + } + } + } + } + } + } + } + /* we no longer need old string set */ + string_set_discard(old_str_set); + } + } + + /* + * Perform pattern matching to find out the longest match. + */ + new_str_size = string_set_get_size(new_str_set); +#ifdef RPR_DEBUG + elog(DEBUG1, "new_str_size: %d", new_str_size); +#endif + len = 0; + resultlen = 0; + + for (index = 0; index < new_str_size; index++) + { + StringInfo s; + + s = string_set_get(new_str_set, index); + if (s == NULL) + continue; /* no data */ + +#ifdef RPR_DEBUG + elog(DEBUG1, "target string: %s", s->data); +#endif + len = do_pattern_match(pattern, s->data); + if (len > resultlen) + { + /* remember the longest match */ + resultlen = len; + + /* + * If the size of result set is equal to the number of rows in the + * set, we are done because it's not possible that the number of + * matching rows exceeds the number of rows in the set. + */ + if (resultlen >= set_size) + break; + } + } + + /* we no longer need new string set */ + string_set_discard(new_str_set); + + return resultlen; +} + +/* + * do_pattern_match + * perform pattern match using pattern against encoded_str. + * returns matching number of rows if matching is succeeded. + * Otherwise returns 0. + */ +static +int +do_pattern_match(char *pattern, char *encoded_str) +{ + Datum d; + text *res; + char *substr; + int len = 0; + text *pattern_text, + *encoded_str_text; + + pattern_text = cstring_to_text(pattern); + encoded_str_text = cstring_to_text(encoded_str); + + /* + * We first perform pattern matching using regexp_instr, then call + * textregexsubstr to get matched substring to know how long the matched + * string is. That is the number of rows in the reduced window frame. The + * reason why we can't call textregexsubstr in the first place is, it + * errors out if pattern does not match. + */ + if (DatumGetInt32(DirectFunctionCall2Coll( + regexp_instr, DEFAULT_COLLATION_OID, + PointerGetDatum(encoded_str_text), + PointerGetDatum(pattern_text)))) + { + d = DirectFunctionCall2Coll(textregexsubstr, + DEFAULT_COLLATION_OID, + PointerGetDatum(encoded_str_text), + PointerGetDatum(pattern_text)); + if (d != 0) + { + res = DatumGetTextPP(d); + substr = text_to_cstring(res); + len = strlen(substr); + pfree(substr); + } + } + pfree(encoded_str_text); + pfree(pattern_text); + + return len; +} + +/* + * evaluate_pattern + * Evaluate expression associated with PATTERN variable vname. current_pos is + * relative row position in a frame (starting from 0). If vname is evaluated + * to true, initial letters associated with vname is appended to + * encode_str. result is out paramater representing the expression evaluation + * result is true of false. + *--------- + * Return values are: + * >=0: the last match absolute row position + * otherwise out of frame. + *--------- + */ +static +int64 +evaluate_pattern(WindowObject winobj, int64 current_pos, + char *vname, StringInfo encoded_str, bool *result) +{ + WindowAggState *winstate = winobj->winstate; + ExprContext *econtext = winstate->ss.ps.ps_ExprContext; + ListCell *lc1, + *lc2, + *lc3; + ExprState *pat; + Datum eval_result; + bool out_of_frame = false; + bool isnull; + TupleTableSlot *slot; + + forthree(lc1, winstate->defineVariableList, + lc2, winstate->defineClauseList, + lc3, winstate->defineInitial) + { + char initial; /* initial letter associated with vname */ + char *name = strVal(lfirst(lc1)); + + if (strcmp(vname, name)) + continue; + + initial = *(strVal(lfirst(lc3))); + + /* set expression to evaluate */ + pat = lfirst(lc2); + + /* get current, previous and next tuples */ + if (!get_slots(winobj, current_pos)) + { + out_of_frame = true; + } + else + { + /* evaluate the expression */ + eval_result = ExecEvalExpr(pat, econtext, &isnull); + if (isnull) + { + /* expression is NULL */ +#ifdef RPR_DEBUG + elog(DEBUG1, "expression for %s is NULL at row: " INT64_FORMAT, + vname, current_pos); +#endif + *result = false; + } + else + { + if (!DatumGetBool(eval_result)) + { + /* expression is false */ +#ifdef RPR_DEBUG + elog(DEBUG1, "expression for %s is false at row: " INT64_FORMAT, + vname, current_pos); +#endif + *result = false; + } + else + { + /* expression is true */ +#ifdef RPR_DEBUG + elog(DEBUG1, "expression for %s is true at row: " INT64_FORMAT, + vname, current_pos); +#endif + appendStringInfoChar(encoded_str, initial); + *result = true; + } + } + + slot = winstate->temp_slot_1; + if (slot != winstate->null_slot) + ExecClearTuple(slot); + slot = winstate->prev_slot; + if (slot != winstate->null_slot) + ExecClearTuple(slot); + slot = winstate->next_slot; + if (slot != winstate->null_slot) + ExecClearTuple(slot); + + break; + } + + if (out_of_frame) + { + *result = false; + return -1; + } + } + return current_pos; +} + +/* + * get_slots + * Get current, previous and next tuples. + * Returns false if current row is out of partition/full frame. + */ +static +bool +get_slots(WindowObject winobj, int64 current_pos) +{ + WindowAggState *winstate = winobj->winstate; + TupleTableSlot *slot; + int ret; + ExprContext *econtext; + + econtext = winstate->ss.ps.ps_ExprContext; + + /* set up current row tuple slot */ + slot = winstate->temp_slot_1; + if (!window_gettupleslot(winobj, current_pos, slot)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "current row is out of partition at:" INT64_FORMAT, + current_pos); +#endif + return false; + } + ret = row_is_in_frame(winstate, current_pos, slot); + if (ret <= 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "current row is out of frame at: " INT64_FORMAT, + current_pos); +#endif + ExecClearTuple(slot); + return false; + } + econtext->ecxt_outertuple = slot; + + /* for PREV */ + if (current_pos > 0) + { + slot = winstate->prev_slot; + if (!window_gettupleslot(winobj, current_pos - 1, slot)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "previous row is out of partition at: " INT64_FORMAT, + current_pos - 1); +#endif + econtext->ecxt_scantuple = winstate->null_slot; + } + else + { + ret = row_is_in_frame(winstate, current_pos - 1, slot); + if (ret <= 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "previous row is out of frame at: " INT64_FORMAT, + current_pos - 1); +#endif + ExecClearTuple(slot); + econtext->ecxt_scantuple = winstate->null_slot; + } + else + { + econtext->ecxt_scantuple = slot; + } + } + } + else + econtext->ecxt_scantuple = winstate->null_slot; + + /* for NEXT */ + slot = winstate->next_slot; + if (!window_gettupleslot(winobj, current_pos + 1, slot)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "next row is out of partiton at: " INT64_FORMAT, + current_pos + 1); +#endif + econtext->ecxt_innertuple = winstate->null_slot; + } + else + { + ret = row_is_in_frame(winstate, current_pos + 1, slot); + if (ret <= 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "next row is out of frame at: " INT64_FORMAT, + current_pos + 1); +#endif + ExecClearTuple(slot); + econtext->ecxt_innertuple = winstate->null_slot; + } + else + econtext->ecxt_innertuple = slot; + } + return true; +} + +/* + * pattern_initial + * Return pattern variable initial character + * matching with pattern variable name vname. + * If not found, return 0. + */ +static +char +pattern_initial(WindowAggState *winstate, char *vname) +{ + char initial; + char *name; + ListCell *lc1, + *lc2; + + forboth(lc1, winstate->defineVariableList, + lc2, winstate->defineInitial) + { + name = strVal(lfirst(lc1)); /* DEFINE variable name */ + initial = *(strVal(lfirst(lc2))); /* DEFINE variable initial */ + + + if (!strcmp(name, vname)) + return initial; /* found */ + } + return 0; +} + +/* + * string_set_init + * Create dynamic set of StringInfo. + */ +static +StringSet * string_set_init(void) +{ +/* Initial allocation size of str_set */ +#define STRING_SET_ALLOC_SIZE 1024 + + StringSet *string_set; + Size set_size; + + string_set = palloc0(sizeof(StringSet)); + string_set->set_index = 0; + set_size = STRING_SET_ALLOC_SIZE; + string_set->str_set = palloc(set_size * sizeof(StringInfo)); + string_set->set_size = set_size; + + return string_set; +} + +/* + * string_set_add + * Add StringInfo str to StringSet string_set. + */ +static +void +string_set_add(StringSet * string_set, StringInfo str) +{ + Size set_size; + + set_size = string_set->set_size; + if (string_set->set_index >= set_size) + { + set_size *= 2; + string_set->str_set = repalloc(string_set->str_set, + set_size * sizeof(StringInfo)); + string_set->set_size = set_size; + } + + string_set->str_set[string_set->set_index++] = str; + + return; +} + +/* + * string_set_get + * Returns StringInfo specified by index. + * If there's no data yet, returns NULL. + */ +static +StringInfo +string_set_get(StringSet * string_set, int index) +{ + /* no data? */ + if (index == 0 && string_set->set_index == 0) + return NULL; + + if (index < 0 || index >= string_set->set_index) + elog(ERROR, "invalid index: %d", index); + + return string_set->str_set[index]; +} + +/* + * string_set_get_size + * Returns the size of StringSet. + */ +static +int +string_set_get_size(StringSet * string_set) +{ + return string_set->set_index; +} + +/* + * string_set_discard + * Discard StringSet. + * All memory including StringSet itself is freed. + */ +static +void +string_set_discard(StringSet * string_set) +{ + int i; + + for (i = 0; i < string_set->set_index; i++) + { + StringInfo str = string_set->str_set[i]; + + if (str) + { + pfree(str->data); + pfree(str); + } + } + pfree(string_set->str_set); + pfree(string_set); +} + +/* + * variable_pos_init + * Create and initialize variable postion structure + */ +static +VariablePos * variable_pos_init(void) +{ + VariablePos *variable_pos; + + variable_pos = palloc(sizeof(VariablePos) * NUM_ALPHABETS); + MemSet(variable_pos, -1, sizeof(VariablePos) * NUM_ALPHABETS); + return variable_pos; +} + +/* + * variable_pos_register + * Register pattern variable whose initial is initial into postion index. + * pos is position of initial. + * If pos is already registered, register it at next empty slot. + */ +static +void +variable_pos_register(VariablePos * variable_pos, char initial, int pos) +{ + int index = initial - 'a'; + int slot; + int i; + + if (pos < 0 || pos > NUM_ALPHABETS) + elog(ERROR, "initial is not valid char: %c", initial); + + for (i = 0; i < NUM_ALPHABETS; i++) + { + slot = variable_pos[index].pos[i]; + if (slot < 0) + { + /* empty slot found */ + variable_pos[index].pos[i] = pos; + return; + } + } + elog(ERROR, "no empty slot for initial: %c", initial); +} + +/* + * variable_pos_compare + * Returns true if initial1 can be followed by initial2 + */ +static +bool +variable_pos_compare(VariablePos * variable_pos, char initial1, char initial2) +{ + int index1, + index2; + int pos1, + pos2; + + for (index1 = 0;; index1++) + { + pos1 = variable_pos_fetch(variable_pos, initial1, index1); + if (pos1 < 0) + break; + + for (index2 = 0;; index2++) + { + pos2 = variable_pos_fetch(variable_pos, initial2, index2); + if (pos2 < 0) + break; + if (pos1 <= pos2) + return true; + } + } + return false; +} + +/* + * variable_pos_fetch + * Fetch position of pattern variable whose initial is initial, and whose index + * is index. If no postion was registered by initial, index, returns -1. + */ +static +int +variable_pos_fetch(VariablePos * variable_pos, char initial, int index) +{ + int pos = initial - 'a'; + + if (pos < 0 || pos > NUM_ALPHABETS) + elog(ERROR, "initial is not valid char: %c", initial); + + if (index < 0 || index > NUM_ALPHABETS) + elog(ERROR, "index is not valid: %d", index); + + return variable_pos[pos].pos[index]; +} + +/* + * variable_pos_discard + * Discard VariablePos + */ +static +void +variable_pos_discard(VariablePos * variable_pos) +{ + pfree(variable_pos); +} diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c index 473c61569f..92c528d38c 100644 --- a/src/backend/utils/adt/windowfuncs.c +++ b/src/backend/utils/adt/windowfuncs.c @@ -13,6 +13,9 @@ */ #include "postgres.h" +#include "catalog/pg_collation_d.h" +#include "executor/executor.h" +#include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "nodes/supportnodes.h" #include "utils/fmgrprotos.h" @@ -37,11 +40,19 @@ typedef struct int64 remainder; /* (total rows) % (bucket num) */ } ntile_context; +/* + * rpr process information. + * Used for AFTER MATCH SKIP PAST LAST ROW + */ +typedef struct SkipContext +{ + int64 pos; /* last row absolute position */ +} SkipContext; + static bool rank_up(WindowObject winobj); static Datum leadlag_common(FunctionCallInfo fcinfo, bool forward, bool withoffset, bool withdefault); - /* * utility routine for *_rank functions. */ @@ -674,7 +685,7 @@ window_last_value(PG_FUNCTION_ARGS) bool isnull; result = WinGetFuncArgInFrame(winobj, 0, - 0, WINDOW_SEEK_TAIL, true, + 0, WINDOW_SEEK_TAIL, false, &isnull, NULL); if (isnull) PG_RETURN_NULL(); @@ -714,3 +725,25 @@ window_nth_value(PG_FUNCTION_ARGS) PG_RETURN_DATUM(result); } + +/* + * prev + * Dummy function to invoke RPR's navigation operator "PREV". + * This is *not* a window function. + */ +Datum +window_prev(PG_FUNCTION_ARGS) +{ + PG_RETURN_DATUM(PG_GETARG_DATUM(0)); +} + +/* + * next + * Dummy function to invoke RPR's navigation operation "NEXT". + * This is *not* a window function. + */ +Datum +window_next(PG_FUNCTION_ARGS) +{ + PG_RETURN_DATUM(PG_GETARG_DATUM(0)); +} diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 2a9f2105b1..595ef7502e 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10479,6 +10479,12 @@ { oid => '3114', descr => 'fetch the Nth row value', proname => 'nth_value', prokind => 'w', prorettype => 'anyelement', proargtypes => 'anyelement int4', prosrc => 'window_nth_value' }, +{ oid => '6122', descr => 'previous value', + proname => 'prev', provolatile => 's', prorettype => 'anyelement', + proargtypes => 'anyelement', prosrc => 'window_prev' }, +{ oid => '6123', descr => 'next value', + proname => 'next', provolatile => 's', prorettype => 'anyelement', + proargtypes => 'anyelement', prosrc => 'window_next' }, # functions for range types { oid => '3832', descr => 'I/O', diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h index 8bc421e7c0..4dd9a17eca 100644 --- a/src/include/nodes/execnodes.h +++ b/src/include/nodes/execnodes.h @@ -2554,6 +2554,11 @@ typedef enum WindowAggStatus * tuples during spool */ } WindowAggStatus; +#define RF_NOT_DETERMINED 0 +#define RF_FRAME_HEAD 1 +#define RF_SKIPPED 2 +#define RF_UNMATCHED 3 + typedef struct WindowAggState { ScanState ss; /* its first field is NodeTag */ @@ -2602,6 +2607,19 @@ typedef struct WindowAggState int64 groupheadpos; /* current row's peer group head position */ int64 grouptailpos; /* " " " " tail position (group end+1) */ + /* these fields are used in Row pattern recognition: */ + RPSkipTo rpSkipTo; /* Row Pattern Skip To type */ + List *patternVariableList; /* list of row pattern variables names + * (list of String) */ + List *patternRegexpList; /* list of row pattern regular expressions + * ('+' or ''. list of String) */ + List *defineVariableList; /* list of row pattern definition + * variables (list of String) */ + List *defineClauseList; /* expression for row pattern definition + * search conditions ExprState list */ + List *defineInitial; /* list of row pattern definition variable + * initials (list of String) */ + MemoryContext partcontext; /* context for partition-lifespan data */ MemoryContext aggcontext; /* shared context for aggregate working data */ MemoryContext curaggcontext; /* current aggregate's working data */ @@ -2638,6 +2656,18 @@ typedef struct WindowAggState TupleTableSlot *agg_row_slot; TupleTableSlot *temp_slot_1; TupleTableSlot *temp_slot_2; + + /* temporary slots for RPR */ + TupleTableSlot *prev_slot; /* PREV row navigation operator */ + TupleTableSlot *next_slot; /* NEXT row navigation operator */ + TupleTableSlot *null_slot; /* all NULL slot */ + + /* + * Each byte corresponds to a row positioned at absolute its pos in + * partition. See above definition for RF_* + */ + char *reduced_frame_map; + int64 alloc_sz; /* size of the map */ } WindowAggState; /* ---------------- -- 2.25.1 ----Next_Part(Wed_May_15_09_02_03_2024_008)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v19-0006-Row-pattern-recognition-patch-docs.patch" ^ permalink raw reply [nested|flat] 54+ messages in thread
end of thread, other threads:[~2024-05-14 23:26 UTC | newest] Thread overview: 54+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/8] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH v23 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/3] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/8] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/9] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH v22 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2018-06-29 07:41 [PATCH v24 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v44 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v29 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v43 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v40 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v42 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v35 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v30 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v41 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v38 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v31 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v33 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v34 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v32 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v57 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v39 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v25 2/8] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v37 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v27 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v28 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2020-03-13 07:58 [PATCH v33 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]> 2024-05-14 23:26 [PATCH v19 5/8] Row pattern recognition patch (executor). Tatsuo Ishii <[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