From efa68e08e74840c0afa4183e14b212b4fffcbbee Mon Sep 17 00:00:00 2001 From: Masahiko Sawada Date: Thu, 4 Apr 2019 11:42:25 +0900 Subject: [PATCH v22 1/2] Add parallel option to VACUUM command In parallel vacuum, we perform both index vacuum and cleanup vacuum with parallel workers. Indivisual indexes are processed by one vacuum process. Therefore parallel vacuum can be used when the table has more than one index. During vacuum execution, the leader process scan heaps while collect dead tuples onto the DSM segment. Before starting either index vacuuming or index cleanup the leader process launch parallel vacuum workers and the leader itself also participates to the parallel execution. After all indexes are processed all vacuum parallel workers exit and the leader process reinitialize the DSM segment while keeping the recorded dead tuples for the next execution. Parallel vacuum can be performed by specifying like VACUUM (PARALLEL 2) tbl, meaning that performing vacuum with 2 parallel worker processes. If the degree of parallelism is omitted it will be determined based on the number of indexes that table has. The parallel vacuum degree is limited by both the number of indexes the table has and max_parallel_maintenance_workers. --- doc/src/sgml/config.sgml | 14 +- doc/src/sgml/ref/vacuum.sgml | 31 ++ src/backend/access/heap/vacuumlazy.c | 894 ++++++++++++++++++++++++++++++---- src/backend/access/transam/parallel.c | 4 + src/backend/commands/vacuum.c | 29 ++ src/backend/parser/gram.y | 1 + src/backend/postmaster/autovacuum.c | 1 + src/bin/psql/tab-complete.c | 3 +- src/include/access/heapam.h | 2 + src/include/commands/vacuum.h | 5 + src/test/regress/expected/vacuum.out | 10 +- src/test/regress/sql/vacuum.sql | 3 + 12 files changed, 886 insertions(+), 111 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index bc1d0f7..0b65d9b 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -2226,13 +2226,13 @@ include_dir 'conf.d' Sets the maximum number of parallel workers that can be - started by a single utility command. Currently, the only - parallel utility command that supports the use of parallel - workers is CREATE INDEX, and only when - building a B-tree index. Parallel workers are taken from the - pool of processes established by , limited by . Note that the requested + started by a single utility command. Currently, the parallel + utility commands that support the use of parallel workers are + CREATE INDEX only when building a B-tree index, + and VACUUM without FULL + option. Parallel workers are taken from the pool of processes + established by , limited + by . Note that the requested number of workers may not actually be available at run time. If this occurs, the utility operation will run with fewer workers than expected. The default value is 2. Setting this diff --git a/doc/src/sgml/ref/vacuum.sgml b/doc/src/sgml/ref/vacuum.sgml index 906d0c2..d3fe0f6 100644 --- a/doc/src/sgml/ref/vacuum.sgml +++ b/doc/src/sgml/ref/vacuum.sgml @@ -32,6 +32,7 @@ VACUUM [ FULL ] [ FREEZE ] [ VERBOSE ] [ ANALYZE ] [ boolean ] DISABLE_PAGE_SKIPPING [ boolean ] SKIP_LOCKED [ boolean ] + PARALLEL [ integer ] and table_and_columns is: @@ -143,6 +144,22 @@ VACUUM [ FULL ] [ FREEZE ] [ VERBOSE ] [ ANALYZE ] [ integer background + workers (for the detail of each vacuum phases, please refer to + ). Only one worker can be used per index. So + parallel workers are launched only when there are at least 2 + indexes in the table. Workers for vacuum launches before starting each phases + and exit at the end of the phase. These behaviors might change in a future release. + This option can not use with FULL option. + + + + + DISABLE_PAGE_SKIPPING @@ -196,6 +213,20 @@ VACUUM [ FULL ] [ FREEZE ] [ VERBOSE ] [ ANALYZE ] [ integer + + + Specifies parallel degree for PARALLEL option. The + value must be at least 1. If the parallel degree + integer is omitted, then + VACUUM decides the number of workers based on number of + indexes on the relation which further limited by + . + + + + + table_name diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c index 392b35e..bacf6e8 100644 --- a/src/backend/access/heap/vacuumlazy.c +++ b/src/backend/access/heap/vacuumlazy.c @@ -22,6 +22,20 @@ * of index scans performed. So we don't use maintenance_work_mem memory for * the TID array, just enough to hold as many heap tuples as fit on one page. * + * Lazy vacuum supports parallel execution with parallel worker processes. In + * parallel lazy vacuum, we perform both index vacuuming and index cleanup with + * parallel worker processes. Individual indexes is processed by one vacuum + * process. At beginning of lazy vacuum (at lazy_scan_heap) we prepare the + * parallel context and initialize the DSM segment that contains shared information + * as well as the memory space for storing dead tuples. When starting either + * index vacuuming or index cleanup, we launch parallel worker processes. Once + * all indexes are processed the parallel worker processes exit and the leader + * process re-initializes the DSM segment while keeping recorded dead tuples. + * Note that all parallel workers live during one either index vacuuming or + * index cleanup but the leader process neither exits from the parallel mode + * nor destroys the parallel context. For updating the index statistics, since + * any updates are not allowed during parallel mode we update the index + * statistics after exited from parallel mode. * * Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California @@ -41,8 +55,10 @@ #include "access/heapam_xlog.h" #include "access/htup_details.h" #include "access/multixact.h" +#include "access/parallel.h" #include "access/transam.h" #include "access/visibilitymap.h" +#include "access/xact.h" #include "access/xlog.h" #include "catalog/storage.h" #include "commands/dbcommands.h" @@ -55,6 +71,7 @@ #include "storage/bufmgr.h" #include "storage/freespace.h" #include "storage/lmgr.h" +#include "tcop/tcopprot.h" #include "utils/lsyscache.h" #include "utils/memutils.h" #include "utils/pg_rusage.h" @@ -110,6 +127,93 @@ */ #define PREFETCH_SIZE ((BlockNumber) 32) +/* + * DSM keys for parallel lazy vacuum. Since we don't need to worry about DSM + * keys conflicting with plan_node_id we can use small integers. + */ +#define PARALLEL_VACUUM_KEY_SHARED 1 +#define PARALLEL_VACUUM_KEY_DEAD_TUPLES 2 +#define PARALLEL_VACUUM_KEY_QUERY_TEXT 3 + +/* + * Macro to check if we in a parallel lazy vacuum. If true, we're in parallel + * mode and prepared the DSM segments. + */ +#define IsInParallelVacuum(lps) (((LVParallelState *) (lps)) != NULL) + +/* + * Structs for an index bulk-deletion statistic that is used for parallel + * lazy vacuum. This is allocated in a DSM segment. + */ +typedef struct LVIndStats +{ + bool updated; /* are the stats updated? */ + IndexBulkDeleteResult stats; +} LVIndStats; + +/* + * LVDeadTuples stores the dead tuple TIDs collected during heap scan. + * This is allocated in a DSM segment when parallel lazy vacuum + * mode, otherwise allocated in a local memory. + */ +typedef struct LVDeadTuples +{ + int max_tuples; /* # slots allocated in array */ + int num_tuples; /* current # of entries */ + /* List of TIDs of tuples we intend to delete */ + /* NB: this list is ordered by TID address */ + ItemPointerData itemptrs[FLEXIBLE_ARRAY_MEMBER]; /* array of ItemPointerData */ +} LVDeadTuples; +#define SizeOfLVDeadTuples offsetof(LVDeadTuples, itemptrs) + sizeof(ItemPointerData) + +/* + * Shared information among parallel workers. So this is allocated in + * a DSM segment. + */ +typedef struct LVShared +{ + /* + * Target table relid and log level. These fields are not modified during + * the lazy vacuum. + */ + Oid relid; + int elevel; + + /* + * An indication for vacuum workers of doing either index vacuuming or + * index cleanup. + */ + bool for_cleanup; + + /* + * Fields for both index vacuuming and index cleanup. + * + * reltuples is the total number of input heap tuples. We set either an + * old live tuples in index vacuuming case or the new live tuples in index + * cleanup case. + * + * estimated_count is true if the reltuples is estimated value. + */ + double reltuples; + bool estimated_count; + + /* + * Variables to control parallel index vacuuming. An variable-sized field + * 'indstats' must come last. + */ + pg_atomic_uint32 nprocessed; + LVIndStats indstats[FLEXIBLE_ARRAY_MEMBER]; +} LVShared; +#define SizeOfLVShared offsetof(LVShared, indstats) + sizeof(LVIndStats) + +/* Struct for parallel lazy vacuum */ +typedef struct LVParallelState +{ + ParallelContext *pcxt; + LVShared *lvshared; + int nworkers_requested; /* user-requested parallel degree */ +} LVParallelState; + typedef struct LVRelStats { /* hasindex = true means two-pass strategy; false means one-pass */ @@ -128,17 +232,12 @@ typedef struct LVRelStats BlockNumber pages_removed; double tuples_deleted; BlockNumber nonempty_pages; /* actually, last nonempty page + 1 */ - /* List of TIDs of tuples we intend to delete */ - /* NB: this list is ordered by TID address */ - int num_dead_tuples; /* current # of entries */ - int max_dead_tuples; /* # slots allocated in array */ - ItemPointer dead_tuples; /* array of ItemPointerData */ + LVDeadTuples *dead_tuples; int num_index_scans; TransactionId latestRemovedXid; bool lock_waiter_detected; } LVRelStats; - /* A few variables that don't seem worth passing around as parameters */ static int elevel = -1; @@ -150,17 +249,18 @@ static BufferAccessStrategy vac_strategy; /* non-export function prototypes */ -static void lazy_scan_heap(Relation onerel, int options, +static void lazy_scan_heap(Relation onerel, VacuumParams *params, LVRelStats *vacrelstats, Relation *Irel, int nindexes, bool aggressive); static void lazy_vacuum_heap(Relation onerel, LVRelStats *vacrelstats, BlockNumber nblocks); static bool lazy_check_needs_freeze(Buffer buf, bool *hastup); static void lazy_vacuum_index(Relation indrel, IndexBulkDeleteResult **stats, - LVRelStats *vacrelstats); + double reltuples, + LVDeadTuples *dead_tuples); static void lazy_cleanup_index(Relation indrel, - IndexBulkDeleteResult *stats, - LVRelStats *vacrelstats); + IndexBulkDeleteResult **stats, + double reltuples, bool estimated_count); static int lazy_vacuum_page(Relation onerel, BlockNumber blkno, Buffer buffer, int tupindex, LVRelStats *vacrelstats, Buffer *vmbuffer); static bool should_attempt_truncation(LVRelStats *vacrelstats); @@ -168,12 +268,35 @@ static void lazy_truncate_heap(Relation onerel, LVRelStats *vacrelstats); static BlockNumber count_nondeletable_pages(Relation onerel, LVRelStats *vacrelstats); static void lazy_space_alloc(LVRelStats *vacrelstats, BlockNumber relblocks); -static void lazy_record_dead_tuple(LVRelStats *vacrelstats, - ItemPointer itemptr); +static void lazy_record_dead_tuple(LVDeadTuples *dead_tuples, ItemPointer itemptr); static bool lazy_tid_reaped(ItemPointer itemptr, void *state); static int vac_cmp_itemptr(const void *left, const void *right); static bool heap_page_is_all_visible(Relation rel, Buffer buf, TransactionId *visibility_cutoff_xid, bool *all_frozen); +static void lazy_update_index_statistics(Relation indrel, IndexBulkDeleteResult *stats); +static LVParallelState *lazy_prepare_parallel(LVRelStats *vacrelstats, Oid relid, + BlockNumber nblocks, int nindexes, + int nrequested); +static void lazy_end_parallel(LVParallelState *lps, Relation *Irel, int nindexes); +static void lazy_begin_parallel_index_vacuum(LVParallelState *lps, LVRelStats *vacrelstats, + bool for_cleanup); +static void lazy_end_parallel_index_vacuum(LVParallelState *lps, bool reinitialize); +static void lazy_vacuum_or_cleanup_indexes(LVRelStats *vacrelstats, Relation *Irel, + int nindexes, + IndexBulkDeleteResult **stats, + LVParallelState *lps, bool for_cleanup); +static void lazy_parallel_vacuum_or_cleanup_indexes(LVRelStats *vacrelstats, + Relation *Irel, + int nindexes, + IndexBulkDeleteResult **stats, + LVParallelState *lps, + bool for_cleanup); +static void do_parallel_vacuum_or_cleanup_indexes(Relation *Irel, int nindexes, + IndexBulkDeleteResult **stats, + LVShared *lvshared, + LVDeadTuples *dead_tuples); +static int compute_parallel_workers(Relation onerel, int nrequested, int nindexes); +static long compute_max_dead_tuples(BlockNumber relblocks, bool hasindex); /* @@ -278,7 +401,7 @@ heap_vacuum_rel(Relation onerel, VacuumParams *params, vacrelstats->hasindex = (nindexes > 0); /* Do the vacuuming */ - lazy_scan_heap(onerel, params->options, vacrelstats, Irel, nindexes, aggressive); + lazy_scan_heap(onerel, params, vacrelstats, Irel, nindexes, aggressive); /* Done with indexes */ vac_close_indexes(nindexes, Irel, NoLock); @@ -480,14 +603,29 @@ vacuum_log_cleanup_info(Relation rel, LVRelStats *vacrelstats) * dead-tuple TIDs, invoke vacuuming of indexes and call lazy_vacuum_heap * to reclaim dead line pointers. * + * If the table has more than one index and parallel lazy vacuum is requested, + * we execute both index vacuuming and index cleanup with parallel workers. + * When allocating the space for lazy scan heap, we enter parallel mode, + * create the parallel context and initailize a DSM segment for dead tuples. + * The dead_tuples points either to a DSM segment in parallel lazy vacuum + * case or to a local memory in single process vacuum case. Before starting + * parallel index vacuuming and parallel index cleanup we launch parallel + * workers. All parallel workers will exit after processed all indexes and + * the leader process re-initialize the parallel context and then re-launch + * them at the next execution. The index statistics are updated by the leader + * after exited from parallel mode since all writes are not allowed during + * parallel mode. + * * If there are no indexes then we can reclaim line pointers on the fly; * dead line pointers need only be retained until all index pointers that * reference them have been killed. */ static void -lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, +lazy_scan_heap(Relation onerel, VacuumParams *params, LVRelStats *vacrelstats, Relation *Irel, int nindexes, bool aggressive) { + LVParallelState *lps = NULL; + LVDeadTuples *dead_tuples; BlockNumber nblocks, blkno; HeapTupleData tuple; @@ -510,6 +648,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, bool skipping_blocks; xl_heap_freeze_tuple *frozen; StringInfoData buf; + int parallel_workers = 0; const int initprog_index[] = { PROGRESS_VACUUM_PHASE, PROGRESS_VACUUM_TOTAL_HEAP_BLKS, @@ -545,13 +684,36 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, vacrelstats->nonempty_pages = 0; vacrelstats->latestRemovedXid = InvalidTransactionId; - lazy_space_alloc(vacrelstats, nblocks); + /* Compute the number of parallel vacuum worker to request */ + if (params->nworkers >= 0) + parallel_workers = compute_parallel_workers(onerel, + params->nworkers, + nindexes); + + if (parallel_workers > 0) + { + /* Enter parallel mode and prepare parallel lazy vacuum */ + lps = lazy_prepare_parallel(vacrelstats, + RelationGetRelid(onerel), + nblocks, nindexes, + parallel_workers); + + /* Remember the user-requested parallel degree to reporting */ + lps->nworkers_requested = params->nworkers; + } + else + { + /* Allocate the memory space for dead tuples locally */ + lazy_space_alloc(vacrelstats, nblocks); + } + + dead_tuples = vacrelstats->dead_tuples; frozen = palloc(sizeof(xl_heap_freeze_tuple) * MaxHeapTuplesPerPage); /* Report that we're scanning the heap, advertising total # of blocks */ initprog_val[0] = PROGRESS_VACUUM_PHASE_SCAN_HEAP; initprog_val[1] = nblocks; - initprog_val[2] = vacrelstats->max_dead_tuples; + initprog_val[2] = dead_tuples->max_tuples; pgstat_progress_update_multi_param(3, initprog_index, initprog_val); /* @@ -599,7 +761,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, * be replayed on any hot standby, where it can be disruptive. */ next_unskippable_block = 0; - if ((options & VACOPT_DISABLE_PAGE_SKIPPING) == 0) + if ((params->options & VACOPT_DISABLE_PAGE_SKIPPING) == 0) { while (next_unskippable_block < nblocks) { @@ -654,7 +816,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, { /* Time to advance next_unskippable_block */ next_unskippable_block++; - if ((options & VACOPT_DISABLE_PAGE_SKIPPING) == 0) + if ((params->options & VACOPT_DISABLE_PAGE_SKIPPING) == 0) { while (next_unskippable_block < nblocks) { @@ -729,8 +891,8 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, * If we are close to overrunning the available space for dead-tuple * TIDs, pause and do a cycle of vacuuming before we tackle this page. */ - if ((vacrelstats->max_dead_tuples - vacrelstats->num_dead_tuples) < MaxHeapTuplesPerPage && - vacrelstats->num_dead_tuples > 0) + if ((dead_tuples->max_tuples - dead_tuples->num_tuples) < MaxHeapTuplesPerPage && + dead_tuples->num_tuples > 0) { const int hvp_index[] = { PROGRESS_VACUUM_PHASE, @@ -758,10 +920,8 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, PROGRESS_VACUUM_PHASE_VACUUM_INDEX); /* Remove index entries */ - for (i = 0; i < nindexes; i++) - lazy_vacuum_index(Irel[i], - &indstats[i], - vacrelstats); + lazy_vacuum_or_cleanup_indexes(vacrelstats, Irel, nindexes, + indstats, lps, false); /* * Report that we are now vacuuming the heap. We also increase @@ -781,7 +941,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, * not to reset latestRemovedXid since we want that value to be * valid. */ - vacrelstats->num_dead_tuples = 0; + dead_tuples->num_tuples = 0; vacrelstats->num_index_scans++; /* @@ -977,7 +1137,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, has_dead_tuples = false; nfrozen = 0; hastup = false; - prev_dead_count = vacrelstats->num_dead_tuples; + prev_dead_count = dead_tuples->num_tuples; maxoff = PageGetMaxOffsetNumber(page); /* @@ -1016,7 +1176,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, */ if (ItemIdIsDead(itemid)) { - lazy_record_dead_tuple(vacrelstats, &(tuple.t_self)); + lazy_record_dead_tuple(dead_tuples, &(tuple.t_self)); all_visible = false; continue; } @@ -1156,7 +1316,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, if (tupgone) { - lazy_record_dead_tuple(vacrelstats, &(tuple.t_self)); + lazy_record_dead_tuple(dead_tuples, &(tuple.t_self)); HeapTupleHeaderAdvanceLatestRemovedXid(tuple.t_data, &vacrelstats->latestRemovedXid); tups_vacuumed += 1; @@ -1225,8 +1385,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, * If there are no indexes then we can vacuum the page right now * instead of doing a second scan. */ - if (nindexes == 0 && - vacrelstats->num_dead_tuples > 0) + if (nindexes == 0 && dead_tuples->num_tuples > 0) { /* Remove tuples from heap */ lazy_vacuum_page(onerel, blkno, buf, 0, vacrelstats, &vmbuffer); @@ -1237,7 +1396,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, * not to reset latestRemovedXid since we want that value to be * valid. */ - vacrelstats->num_dead_tuples = 0; + dead_tuples->num_tuples = 0; vacuumed_pages++; /* @@ -1353,7 +1512,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, * page, so remember its free space as-is. (This path will always be * taken if there are no indexes.) */ - if (vacrelstats->num_dead_tuples == prev_dead_count) + if (dead_tuples->num_tuples == prev_dead_count) RecordPageWithFreeSpace(onerel, blkno, freespace, nblocks); } @@ -1387,7 +1546,7 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, /* If any tuples need to be deleted, perform final vacuum cycle */ /* XXX put a threshold on min number of tuples here? */ - if (vacrelstats->num_dead_tuples > 0) + if (dead_tuples->num_tuples > 0) { const int hvp_index[] = { PROGRESS_VACUUM_PHASE, @@ -1403,10 +1562,8 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, PROGRESS_VACUUM_PHASE_VACUUM_INDEX); /* Remove index entries */ - for (i = 0; i < nindexes; i++) - lazy_vacuum_index(Irel[i], - &indstats[i], - vacrelstats); + lazy_vacuum_or_cleanup_indexes(vacrelstats, Irel, nindexes, + indstats, lps, false); /* Report that we are now vacuuming the heap */ hvp_val[0] = PROGRESS_VACUUM_PHASE_VACUUM_HEAP; @@ -1432,9 +1589,21 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats, pgstat_progress_update_param(PROGRESS_VACUUM_PHASE, PROGRESS_VACUUM_PHASE_INDEX_CLEANUP); - /* Do post-vacuum cleanup and statistics update for each index */ - for (i = 0; i < nindexes; i++) - lazy_cleanup_index(Irel[i], indstats[i], vacrelstats); + /* + * Do post-vacuum cleanup and statistics update for each index if + * we're not in parallel lazy vacuum. If in parallel lazy vacuum, do + * only post-vacum cleanup and then update statistics at the end of + * parallel lazy vacuum. + */ + lazy_vacuum_or_cleanup_indexes(vacrelstats, Irel, nindexes, + indstats, lps, true); + + /* + * If we're in parallel lazy vacuum, end parallel lazy vacuum and + * update index statistics. + */ + if (IsInParallelVacuum(lps)) + lazy_end_parallel(lps, Irel, nindexes); /* If no indexes, make log report that lazy_vacuum_heap would've made */ if (vacuumed_pages) @@ -1501,7 +1670,7 @@ lazy_vacuum_heap(Relation onerel, LVRelStats *vacrelstats, BlockNumber nblocks) npages = 0; tupindex = 0; - while (tupindex < vacrelstats->num_dead_tuples) + while (tupindex < vacrelstats->dead_tuples->num_tuples) { BlockNumber tblk; Buffer buf; @@ -1510,7 +1679,7 @@ lazy_vacuum_heap(Relation onerel, LVRelStats *vacrelstats, BlockNumber nblocks) vacuum_delay_point(); - tblk = ItemPointerGetBlockNumber(&vacrelstats->dead_tuples[tupindex]); + tblk = ItemPointerGetBlockNumber(&vacrelstats->dead_tuples->itemptrs[tupindex]); buf = ReadBufferExtended(onerel, MAIN_FORKNUM, tblk, RBM_NORMAL, vac_strategy); if (!ConditionalLockBufferForCleanup(buf)) @@ -1558,6 +1727,7 @@ static int lazy_vacuum_page(Relation onerel, BlockNumber blkno, Buffer buffer, int tupindex, LVRelStats *vacrelstats, Buffer *vmbuffer) { + LVDeadTuples *dead_tuples = vacrelstats->dead_tuples; Page page = BufferGetPage(buffer); OffsetNumber unused[MaxOffsetNumber]; int uncnt = 0; @@ -1568,16 +1738,16 @@ lazy_vacuum_page(Relation onerel, BlockNumber blkno, Buffer buffer, START_CRIT_SECTION(); - for (; tupindex < vacrelstats->num_dead_tuples; tupindex++) + for (; tupindex < dead_tuples->num_tuples; tupindex++) { BlockNumber tblk; OffsetNumber toff; ItemId itemid; - tblk = ItemPointerGetBlockNumber(&vacrelstats->dead_tuples[tupindex]); + tblk = ItemPointerGetBlockNumber(&dead_tuples->itemptrs[tupindex]); if (tblk != blkno) break; /* past end of tuples for this block */ - toff = ItemPointerGetOffsetNumber(&vacrelstats->dead_tuples[tupindex]); + toff = ItemPointerGetOffsetNumber(&dead_tuples->itemptrs[tupindex]); itemid = PageGetItemId(page, toff); ItemIdSetUnused(itemid); unused[uncnt++] = toff; @@ -1698,6 +1868,153 @@ lazy_check_needs_freeze(Buffer buf, bool *hastup) return false; } +/* + * Vacuum or cleanup indexes with parallel workers. This function must be used + * by the parallel vacuum leader process. + */ +static void +lazy_parallel_vacuum_or_cleanup_indexes(LVRelStats *vacrelstats, Relation *Irel, + int nindexes, IndexBulkDeleteResult **stats, + LVParallelState *lps, bool for_cleanup) +{ + Assert(!IsParallelWorker()); + Assert(IsInParallelVacuum(lps)); + Assert(nindexes > 0); + + /* Launch parallel vacuum workers if we're ready */ + lazy_begin_parallel_index_vacuum(lps, vacrelstats, + for_cleanup); + + /* + * Do index vacuuming or index cleanup with parallel workers or by + * the leader process alone if no workers could not launch. + */ + do_parallel_vacuum_or_cleanup_indexes(Irel, nindexes, stats, + lps->lvshared, + vacrelstats->dead_tuples); + + /* + * Wait for all workers to finish, and prepare for the next index + * vacuuming or index cleanup. + */ + lazy_end_parallel_index_vacuum(lps, !for_cleanup); +} + +/* + * Index vacuuming and index cleanup routine used by both the leader process + * and worker processes. Unlike single process vacuum, we don't update + * index statistics after cleanup index since it is not allowed during + * parallel mode, therefore copy index bulk-deletion results from the local + * memory to the DSM segment and update them at the end of parallel lazy + * vacuum. + */ +static void +do_parallel_vacuum_or_cleanup_indexes(Relation *Irel, int nindexes, + IndexBulkDeleteResult **stats, + LVShared *lvshared, + LVDeadTuples *dead_tuples) +{ + int idx = 0; + + for (;;) + { + /* Get an index number to process */ + idx = pg_atomic_fetch_add_u32(&(lvshared->nprocessed), 1); + + /* Done for all indexes? */ + if (idx >= nindexes) + break; + + /* + * Update the local pointer to the corresponding bulk-deletion result + * if someone already updated it. + */ + if (lvshared->indstats[idx].updated && + stats[idx] == NULL) + stats[idx] = &(lvshared->indstats[idx].stats); + + /* Do vacuum or cleanup one index */ + if (!lvshared->for_cleanup) + lazy_vacuum_index(Irel[idx], &stats[idx], lvshared->reltuples, + dead_tuples); + else + lazy_cleanup_index(Irel[idx], &stats[idx], lvshared->reltuples, + lvshared->estimated_count); + + /* + * We copy the index bulk-deletion results returned from ambulkdelete + * and amvacuumcleanup to the DSM segment because they allocate the + * results locally and it's possible that an index will be vacuumed + * by the different vacuum process at the next time. The copying the + * result normally happens only after the first time of index vacuuming. + * From the second time, we pass the result on the DSM segment so + * that they then update it directly. + * + * Since all vacuum workers write the bulk-deletion result at different + * slot we can write them without locking. + */ + if (!lvshared->indstats[idx].updated && + stats[idx] != NULL) + { + memcpy(&(lvshared->indstats[idx].stats), + stats[idx], sizeof(IndexBulkDeleteResult)); + lvshared->indstats[idx].updated = true; + + /* + * no longer need the locally allocated result and now stats[idx] + * points to the DSM segment. + */ + pfree(stats[idx]); + stats[idx] = &(lvshared->indstats[idx].stats); + } + } +} + +/* + * Vacuum or cleanup indexes. If we're ready for parallel lazy vacuum it's + * performed with parallel workers. So this function must be used by the parallel + * vacuum leader process. + */ +static void +lazy_vacuum_or_cleanup_indexes(LVRelStats *vacrelstats, Relation *Irel, + int nindexes, IndexBulkDeleteResult **stats, + LVParallelState *lps, bool for_cleanup) +{ + int idx; + + Assert(!IsParallelWorker()); + + /* no job if the table has no index */ + if (nindexes <= 0) + return; + + if (IsInParallelVacuum(lps)) + { + /* Do parallel index vacuuming or index cleanup */ + lazy_parallel_vacuum_or_cleanup_indexes(vacrelstats, Irel, + nindexes, stats, + lps, for_cleanup); + return; + } + + /* Do index vacuuming or index cleanup in single vacuum mode */ + for (idx = 0; idx < nindexes; idx++) + { + if (!for_cleanup) + lazy_vacuum_index(Irel[idx], &stats[idx], vacrelstats->old_live_tuples, + vacrelstats->dead_tuples); + else + { + lazy_cleanup_index(Irel[idx], &stats[idx], vacrelstats->new_rel_tuples, + vacrelstats->tupcount_pages < vacrelstats->rel_pages); + + lazy_update_index_statistics(Irel[idx], stats[idx]); + + if (stats[idx]) + pfree(stats[idx]); + } + } +} /* * lazy_vacuum_index() -- vacuum one index relation. @@ -1708,9 +2025,10 @@ lazy_check_needs_freeze(Buffer buf, bool *hastup) static void lazy_vacuum_index(Relation indrel, IndexBulkDeleteResult **stats, - LVRelStats *vacrelstats) + double reltuples, LVDeadTuples *dead_tuples) { IndexVacuumInfo ivinfo; + char *msgfmt; PGRUsage ru0; pg_rusage_init(&ru0); @@ -1720,18 +2038,22 @@ lazy_vacuum_index(Relation indrel, ivinfo.report_progress = false; ivinfo.estimated_count = true; ivinfo.message_level = elevel; - /* We can only provide an approximate value of num_heap_tuples here */ - ivinfo.num_heap_tuples = vacrelstats->old_live_tuples; + ivinfo.num_heap_tuples = reltuples; ivinfo.strategy = vac_strategy; /* Do bulk deletion */ *stats = index_bulk_delete(&ivinfo, *stats, - lazy_tid_reaped, (void *) vacrelstats); + lazy_tid_reaped, (void *) dead_tuples); + + if (IsParallelWorker()) + msgfmt = gettext_noop("scanned index \"%s\" to remove %d row versions by parallel vacuum worker"); + else + msgfmt = gettext_noop("scanned index \"%s\" to remove %d row versions"); ereport(elevel, - (errmsg("scanned index \"%s\" to remove %d row versions", + (errmsg(msgfmt, RelationGetRelationName(indrel), - vacrelstats->num_dead_tuples), + dead_tuples->num_tuples), errdetail_internal("%s", pg_rusage_show(&ru0)))); } @@ -1740,10 +2062,11 @@ lazy_vacuum_index(Relation indrel, */ static void lazy_cleanup_index(Relation indrel, - IndexBulkDeleteResult *stats, - LVRelStats *vacrelstats) + IndexBulkDeleteResult **stats, + double reltuples, bool estimated_count) { IndexVacuumInfo ivinfo; + char *msgfmt; PGRUsage ru0; pg_rusage_init(&ru0); @@ -1751,49 +2074,55 @@ lazy_cleanup_index(Relation indrel, ivinfo.index = indrel; ivinfo.analyze_only = false; ivinfo.report_progress = false; - ivinfo.estimated_count = (vacrelstats->tupcount_pages < vacrelstats->rel_pages); + ivinfo.estimated_count = estimated_count; ivinfo.message_level = elevel; - /* - * Now we can provide a better estimate of total number of surviving - * tuples (we assume indexes are more interested in that than in the - * number of nominally live tuples). - */ - ivinfo.num_heap_tuples = vacrelstats->new_rel_tuples; + ivinfo.num_heap_tuples = reltuples; ivinfo.strategy = vac_strategy; - stats = index_vacuum_cleanup(&ivinfo, stats); + *stats = index_vacuum_cleanup(&ivinfo, *stats); if (!stats) return; - /* - * Now update statistics in pg_class, but only if the index says the count - * is accurate. - */ - if (!stats->estimated_count) - vac_update_relstats(indrel, - stats->num_pages, - stats->num_index_tuples, - 0, - false, - InvalidTransactionId, - InvalidMultiXactId, - false); + if (IsParallelWorker()) + msgfmt = gettext_noop("index \"%s\" now contains %.0f row versions in %u pages, reported by parallel vacuum worker"); + else + msgfmt = gettext_noop("index \"%s\" now contains %.0f row versions in %u pages"); ereport(elevel, - (errmsg("index \"%s\" now contains %.0f row versions in %u pages", + (errmsg(msgfmt, RelationGetRelationName(indrel), - stats->num_index_tuples, - stats->num_pages), + (*stats)->num_index_tuples, + (*stats)->num_pages), errdetail("%.0f index row versions were removed.\n" "%u index pages have been deleted, %u are currently reusable.\n" "%s.", - stats->tuples_removed, - stats->pages_deleted, stats->pages_free, + (*stats)->tuples_removed, + (*stats)->pages_deleted, (*stats)->pages_free, pg_rusage_show(&ru0)))); +} + +/* + * Update index statistics in pg_class if the index says the statistics + * is accurate. + */ +static void +lazy_update_index_statistics(Relation indrel, IndexBulkDeleteResult *stats) +{ + Assert(!IsInParallelMode()); + + if (!stats || stats->estimated_count) + return; - pfree(stats); + vac_update_relstats(indrel, + stats->num_pages, + stats->num_index_tuples, + 0, + false, + InvalidTransactionId, + InvalidMultiXactId, + false); } /* @@ -2098,19 +2427,17 @@ count_nondeletable_pages(Relation onerel, LVRelStats *vacrelstats) } /* - * lazy_space_alloc - space allocation decisions for lazy vacuum - * - * See the comments at the head of this file for rationale. + * Return the maximum number of dead tuples we can record. */ -static void -lazy_space_alloc(LVRelStats *vacrelstats, BlockNumber relblocks) +static long +compute_max_dead_tuples(BlockNumber relblocks, bool hasindex) { long maxtuples; int vac_work_mem = IsAutoVacuumWorkerProcess() && autovacuum_work_mem != -1 ? autovacuum_work_mem : maintenance_work_mem; - if (vacrelstats->hasindex) + if (hasindex) { maxtuples = (vac_work_mem * 1024L) / sizeof(ItemPointerData); maxtuples = Min(maxtuples, INT_MAX); @@ -2124,34 +2451,49 @@ lazy_space_alloc(LVRelStats *vacrelstats, BlockNumber relblocks) maxtuples = Max(maxtuples, MaxHeapTuplesPerPage); } else - { maxtuples = MaxHeapTuplesPerPage; - } - vacrelstats->num_dead_tuples = 0; - vacrelstats->max_dead_tuples = (int) maxtuples; - vacrelstats->dead_tuples = (ItemPointer) - palloc(maxtuples * sizeof(ItemPointerData)); + return maxtuples; +} + +/* + * lazy_space_alloc - space allocation decisions for lazy vacuum + * + * See the comments at the head of this file for rationale. + */ +static void +lazy_space_alloc(LVRelStats *vacrelstats, BlockNumber relblocks) +{ + LVDeadTuples *dead_tuples = NULL; + long maxtuples; + + maxtuples = compute_max_dead_tuples(relblocks, vacrelstats->hasindex); + + dead_tuples = (LVDeadTuples *) + palloc(SizeOfLVDeadTuples + maxtuples * sizeof(ItemPointerData)); + dead_tuples->num_tuples = 0; + dead_tuples->max_tuples = (int) maxtuples; + + vacrelstats->dead_tuples = dead_tuples; } /* * lazy_record_dead_tuple - remember one deletable tuple */ static void -lazy_record_dead_tuple(LVRelStats *vacrelstats, - ItemPointer itemptr) +lazy_record_dead_tuple(LVDeadTuples *dead_tuples, ItemPointer itemptr) { /* * The array shouldn't overflow under normal behavior, but perhaps it * could if we are given a really small maintenance_work_mem. In that * case, just forget the last few tuples (we'll get 'em next time). */ - if (vacrelstats->num_dead_tuples < vacrelstats->max_dead_tuples) + if (dead_tuples->num_tuples < dead_tuples->max_tuples) { - vacrelstats->dead_tuples[vacrelstats->num_dead_tuples] = *itemptr; - vacrelstats->num_dead_tuples++; + dead_tuples->itemptrs[dead_tuples->num_tuples] = *itemptr; + dead_tuples->num_tuples++; pgstat_progress_update_param(PROGRESS_VACUUM_NUM_DEAD_TUPLES, - vacrelstats->num_dead_tuples); + dead_tuples->num_tuples); } } @@ -2165,12 +2507,12 @@ lazy_record_dead_tuple(LVRelStats *vacrelstats, static bool lazy_tid_reaped(ItemPointer itemptr, void *state) { - LVRelStats *vacrelstats = (LVRelStats *) state; + LVDeadTuples *dead_tuples = (LVDeadTuples *) state; ItemPointer res; res = (ItemPointer) bsearch((void *) itemptr, - (void *) vacrelstats->dead_tuples, - vacrelstats->num_dead_tuples, + (void *) dead_tuples->itemptrs, + dead_tuples->num_tuples, sizeof(ItemPointerData), vac_cmp_itemptr); @@ -2318,3 +2660,353 @@ heap_page_is_all_visible(Relation rel, Buffer buf, return all_visible; } + +/* + * Compute the number of parallel worker process to request. Both index vacuuming + * and cleanup index can be executed together with parallel workers if the table + * has more than one index. The relation sizes of table and indexes don't affect + * to the parallel degree for now. + */ +static int +compute_parallel_workers(Relation onerel, int nrequested, int nindexes) +{ + int parallel_workers; + + Assert(nrequested >= 0); + + if (nindexes <= 1) + return 0; + + if (nrequested > 0) + parallel_workers = Min(nrequested, nindexes - 1); + else + { + /* + * The parallel degree is not requested. Compute it based on the + * number of indexes. + */ + parallel_workers = nindexes - 1; + } + + /* cap by max_parallel_maintenace_workers */ + parallel_workers = Min(parallel_workers, max_parallel_maintenance_workers); + + return parallel_workers; +} + +/* + * Enter parallel mode, allocate and initialize a DSM segment. + */ +static LVParallelState * +lazy_prepare_parallel(LVRelStats *vacrelstats, Oid relid, BlockNumber nblocks, + int nindexes, int nrequested) +{ + LVParallelState *lps = (LVParallelState *) palloc(sizeof(LVParallelState)); + LVShared *shared; + ParallelContext *pcxt; + LVDeadTuples *tidmap; + long maxtuples; + char *sharedquery; + Size est_shared; + Size est_deadtuples; + int querylen; + int keys = 0; + + Assert(nrequested > 0); + Assert(nindexes > 0); + + EnterParallelMode(); + pcxt = CreateParallelContext("postgres", "heap_parallel_vacuum_main", + nrequested); + lps->pcxt = pcxt; + Assert(pcxt->nworkers > 0); + + /* Estimate size for shared information -- PARALLEL_VACUUM_KEY_SHARED */ + est_shared = MAXALIGN(add_size(SizeOfLVShared, + mul_size(sizeof(LVIndStats), nindexes))); + shm_toc_estimate_chunk(&pcxt->estimator, est_shared); + keys++; + + /* Estimate size for dead tuples -- PARALLEL_VACUUM_KEY_DEAD_TUPLES */ + maxtuples = compute_max_dead_tuples(nblocks, true); + est_deadtuples = MAXALIGN(add_size(sizeof(LVDeadTuples), + mul_size(sizeof(ItemPointerData), maxtuples))); + shm_toc_estimate_chunk(&pcxt->estimator, est_deadtuples); + keys++; + + shm_toc_estimate_keys(&pcxt->estimator, keys); + + /* Finally, estimate VACUUM_KEY_QUERY_TEXT space */ + querylen = strlen(debug_query_string); + shm_toc_estimate_chunk(&pcxt->estimator, querylen + 1); + shm_toc_estimate_keys(&pcxt->estimator, 1); + + InitializeParallelDSM(pcxt); + + /* prepare shared information */ + shared = (LVShared *) shm_toc_allocate(pcxt->toc, est_shared); + shared->relid = relid; + shared->elevel = elevel; + pg_atomic_init_u32(&(shared->nprocessed), 0); + MemSet(shared->indstats, 0, sizeof(LVIndStats) * nindexes); + shm_toc_insert(pcxt->toc, PARALLEL_VACUUM_KEY_SHARED, shared); + lps->lvshared = shared; + + /* prepare the dead tuple space */ + tidmap = (LVDeadTuples *) shm_toc_allocate(pcxt->toc, est_deadtuples); + tidmap->max_tuples = maxtuples; + tidmap->num_tuples = 0; + MemSet(tidmap->itemptrs, 0, sizeof(ItemPointerData) * maxtuples); + shm_toc_insert(pcxt->toc, PARALLEL_VACUUM_KEY_DEAD_TUPLES, tidmap); + vacrelstats->dead_tuples = tidmap; + + /* Store query string for workers */ + sharedquery = (char *) shm_toc_allocate(pcxt->toc, querylen + 1); + memcpy(sharedquery, debug_query_string, querylen + 1); + sharedquery[querylen] = '\0'; + shm_toc_insert(pcxt->toc, PARALLEL_VACUUM_KEY_QUERY_TEXT, sharedquery); + + lps->nworkers_requested = 0; + + return lps; +} + +/* + * Shutdown workers, destroy the parallel context, and end parallel mode. + * Update index statistics after exited from parallel mode. + */ +static void +lazy_end_parallel(LVParallelState *lps, Relation *Irel, int nindexes) +{ + LVIndStats *copied_indstats = NULL; + int i; + + Assert(!IsParallelWorker()); + Assert(Irel != NULL && nindexes > 0); + + /* + * All writes are not allowed during parallel mode and it might not be + * safe to exit from parallel mode while keeping the parallel context. + * So we copy the index statistics to a temporary space and update + * them after exited from parallel mode. + */ + copied_indstats = palloc(sizeof(LVIndStats) * nindexes); + memcpy(copied_indstats, lps->lvshared->indstats, + sizeof(LVIndStats) * nindexes); + + /* Shutdown worker processes and destroy the parallel context */ + WaitForParallelWorkersToFinish(lps->pcxt); + DestroyParallelContext(lps->pcxt); + ExitParallelMode(); + + for (i = 0; i < nindexes; i++) + { + LVIndStats *s = &(copied_indstats[i]); + + if (s->updated) + lazy_update_index_statistics(Irel[i], &(s->stats)); + } + + pfree(copied_indstats); +} + +/* + * Begin a parallel index vacuuming or index cleanup. Set shared information + * and launch parallel worker processes. + */ +static void +lazy_begin_parallel_index_vacuum(LVParallelState *lps, LVRelStats *vacrelstats, + bool for_cleanup) +{ + StringInfoData buf; + + Assert(!IsParallelWorker()); + + /* Set shared information to tell parallel workers */ + lps->lvshared->for_cleanup = for_cleanup; + if (!for_cleanup) + { + /* We can only provide an approximate value of num_heap_tuples here */ + lps->lvshared->reltuples = vacrelstats->old_live_tuples; + lps->lvshared->estimated_count = true; + } + else + { + /* + * Now we can provide a better estimate of total number of surviving + * tuples (we assume indexes are more interested in that than in the + * number of nominally live tuples). + */ + lps->lvshared->reltuples = vacrelstats->new_rel_tuples; + lps->lvshared->estimated_count = + (vacrelstats->tupcount_pages < vacrelstats->rel_pages); + + } + + /* Launch all parallel workers */ + LaunchParallelWorkers(lps->pcxt); + + initStringInfo(&buf); + + /* Create the log message to report */ + if (lps->pcxt->nworkers_launched == 0) + { + /* + * If no workers launched, the leader process vacuums all indexes alone. + * Since there is hope that we can launch parallel workers in the next + * index vacuuming time we don't end parallel mode yet. + */ + if (for_cleanup) + { + if (lps->nworkers_requested > 0) + appendStringInfo(&buf, + gettext_noop("could not launch parallel vacuum worker for index cleanup (planned: %d, requested: %d)"), + lps->pcxt->nworkers, lps->nworkers_requested); + else + appendStringInfo(&buf, + gettext_noop("could not launch parallel vacuum worker for index cleanup (planned: %d)"), + lps->pcxt->nworkers); + } + else + { + if (lps->nworkers_requested > 0) + appendStringInfo(&buf, + gettext_noop("could not launch parallel vacuum worker for index vacuuming (planned: %d, requested: %d)"), + lps->pcxt->nworkers, lps->nworkers_requested); + else + appendStringInfo(&buf, + gettext_noop("could not launch parallel vacuum worker for index vacuuming (planned: %d)"), + lps->pcxt->nworkers); + } + } + else + { + if (for_cleanup) + { + if (lps->nworkers_requested > 0) + appendStringInfo(&buf, + ngettext("launched %d parallel vacuum worker for index cleanup (planned: %d, requested %d)", + "launched %d parallel vacuum workers for index cleanup (planned: %d, requsted %d)", + lps->pcxt->nworkers_launched), + lps->pcxt->nworkers_launched, + lps->pcxt->nworkers, + lps->nworkers_requested); + else + appendStringInfo(&buf, + ngettext("launched %d parallel vacuum worker for index cleanup (planned: %d)", + "launched %d parallel vacuum workers for index cleanup (planned: %d)", + lps->pcxt->nworkers_launched), + lps->pcxt->nworkers_launched, + lps->pcxt->nworkers); + } + else + { + if (lps->nworkers_requested > 0) + appendStringInfo(&buf, + ngettext("launched %d parallel vacuum worker for index vacuuming (planned: %d, requested %d)", + "launched %d parallel vacuum workers for index vacuuming (planned: %d, requested %d)", + lps->pcxt->nworkers_launched), + lps->pcxt->nworkers_launched, + lps->pcxt->nworkers, + lps->nworkers_requested); + else + appendStringInfo(&buf, + ngettext("launched %d parallel vacuum worker for index vacuuming (planned: %d)", + "launched %d parallel vacuum workers for index vacuuming (planned: %d)", + lps->pcxt->nworkers_launched), + lps->pcxt->nworkers_launched, + lps->pcxt->nworkers); + } + } + + ereport(elevel, (errmsg("%s", buf.data))); + return; +} + +/* + * Wait for all worker processes to finish and reinitialize DSM for + * the next index vacuuming or index cleanup if necessary. + */ +static void +lazy_end_parallel_index_vacuum(LVParallelState *lps, bool reinitialize) +{ + Assert(!IsParallelWorker()); + + WaitForParallelWorkersToFinish(lps->pcxt); + + if (reinitialize) + { + /* Reset the processing count */ + pg_atomic_write_u32(&(lps->lvshared->nprocessed), 0); + + /* + * Reinitialize the parallel context to relaunch parallel workers + * for the next execution. + */ + ReinitializeParallelDSM(lps->pcxt); + } +} + +/* + * Perform work within a launched parallel process. + * + * Parallel vacuum worker processes doesn't report the vacuum progress + * information. + */ +void +heap_parallel_vacuum_main(dsm_segment *seg, shm_toc *toc) +{ + Relation onerel; + Relation *indrels; + LVShared *lvshared; + LVDeadTuples *dead_tuples; + int nindexes; + char *sharedquery; + IndexBulkDeleteResult **stats; + + lvshared = (LVShared *) shm_toc_lookup(toc, PARALLEL_VACUUM_KEY_SHARED, + false); + elevel = lvshared->elevel; + + ereport(DEBUG1, + (errmsg("starting parallel lazy vacuum worker for %s", + lvshared->for_cleanup ? "cleanup" : "vacuuming"))); + + /* Set debug_query_string for individual workers */ + sharedquery = shm_toc_lookup(toc, PARALLEL_VACUUM_KEY_QUERY_TEXT, true); + debug_query_string = sharedquery; + pgstat_report_activity(STATE_RUNNING, debug_query_string); + + /* Open table */ + onerel = heap_open(lvshared->relid, ShareUpdateExclusiveLock); + + /* + * Open all indexes. indrels are sorted in order by OID, which should + * be matched to the leader's one. + */ + vac_open_indexes(onerel, RowExclusiveLock, &nindexes, &indrels); + Assert(nindexes > 0); + + + /* Set dead tuple space */ + dead_tuples = (LVDeadTuples *) shm_toc_lookup(toc, + PARALLEL_VACUUM_KEY_DEAD_TUPLES, + false); + + /* Set cost-based vacuum delay */ + VacuumCostActive = (VacuumCostDelay > 0); + VacuumCostBalance = 0; + VacuumPageHit = 0; + VacuumPageMiss = 0; + VacuumPageDirty = 0; + + stats = (IndexBulkDeleteResult **) + palloc0(nindexes * sizeof(IndexBulkDeleteResult *)); + + /* Do either vacuuming indexes or cleaning indexes */ + do_parallel_vacuum_or_cleanup_indexes(indrels, nindexes, stats, + lvshared, dead_tuples); + + vac_close_indexes(nindexes, indrels, RowExclusiveLock); + heap_close(onerel, ShareUpdateExclusiveLock); +} diff --git a/src/backend/access/transam/parallel.c b/src/backend/access/transam/parallel.c index 55d129a..86511b2 100644 --- a/src/backend/access/transam/parallel.c +++ b/src/backend/access/transam/parallel.c @@ -14,6 +14,7 @@ #include "postgres.h" +#include "access/heapam.h" #include "access/nbtree.h" #include "access/parallel.h" #include "access/session.h" @@ -140,6 +141,9 @@ static const struct }, { "_bt_parallel_build_main", _bt_parallel_build_main + }, + { + "heap_parallel_vacuum_main", heap_parallel_vacuum_main } }; diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c index fd2e47f..9d5cb1c 100644 --- a/src/backend/commands/vacuum.c +++ b/src/backend/commands/vacuum.c @@ -95,6 +95,9 @@ ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel) bool disable_page_skipping = false; ListCell *lc; + /* disable parallel lazy vacuum by default */ + params.nworkers = -1; + /* Parse options list */ foreach(lc, vacstmt->options) { @@ -120,6 +123,27 @@ ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel) full = defGetBoolean(opt); else if (strcmp(opt->defname, "disable_page_skipping") == 0) disable_page_skipping = defGetBoolean(opt); + else if (strcmp(opt->defname, "parallel") == 0) + { + if (opt->arg == NULL) + { + /* + * Parallel lazy vacuum is requested but user didn't specify + * the parallel degree. The parallel degree will be determined + * at the start of lazy vacuum. + */ + params.nworkers = 0; + } + else + { + params.nworkers = defGetInt32(opt); + if (params.nworkers <= 0) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("parallel vacuum degree must be at least 1"), + parser_errposition(pstate, opt->location))); + } + } else ereport(ERROR, (errcode(ERRCODE_SYNTAX_ERROR), @@ -161,6 +185,11 @@ ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel) } } + if ((params.options & VACOPT_FULL) && params.nworkers >= 0) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot specify FULL option with PARALLEL option"))); + /* * All freeze ages are zero if the FREEZE option is given; otherwise pass * them as -1 which means to use the default values. diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y index b51f12d..e61de95 100644 --- a/src/backend/parser/gram.y +++ b/src/backend/parser/gram.y @@ -10581,6 +10581,7 @@ vac_analyze_option_name: vac_analyze_option_arg: opt_boolean_or_string { $$ = (Node *) makeString($1); } + | NumericOnly { $$ = (Node *) $1; } | /* EMPTY */ { $$ = NULL; } ; diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c index fa875db..010a49c 100644 --- a/src/backend/postmaster/autovacuum.c +++ b/src/backend/postmaster/autovacuum.c @@ -2886,6 +2886,7 @@ table_recheck_autovac(Oid relid, HTAB *table_toast_map, (dovacuum ? VACOPT_VACUUM : 0) | (doanalyze ? VACOPT_ANALYZE : 0) | (!wraparound ? VACOPT_SKIP_LOCKED : 0); + tab->at_params.nworkers = -1; /* parallel lazy autovacuum is not supported */ tab->at_params.freeze_min_age = freeze_min_age; tab->at_params.freeze_table_age = freeze_table_age; tab->at_params.multixact_freeze_min_age = multixact_freeze_min_age; diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c index d34bf86..62b3cd5 100644 --- a/src/bin/psql/tab-complete.c +++ b/src/bin/psql/tab-complete.c @@ -3443,7 +3443,8 @@ psql_completion(const char *text, int start, int end) */ if (ends_with(prev_wd, '(') || ends_with(prev_wd, ',')) COMPLETE_WITH("FULL", "FREEZE", "ANALYZE", "VERBOSE", - "DISABLE_PAGE_SKIPPING", "SKIP_LOCKED"); + "DISABLE_PAGE_SKIPPING", "SKIP_LOCKED", + "PARALLEL"); else if (TailMatches("FULL|FREEZE|ANALYZE|VERBOSE|DISABLE_PAGE_SKIPPING|SKIP_LOCKED")) COMPLETE_WITH("ON", "OFF"); } diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h index 4c07775..48df92c 100644 --- a/src/include/access/heapam.h +++ b/src/include/access/heapam.h @@ -14,6 +14,7 @@ #ifndef HEAPAM_H #define HEAPAM_H +#include "access/parallel.h" #include "access/relation.h" /* for backward compatibility */ #include "access/relscan.h" #include "access/sdir.h" @@ -199,6 +200,7 @@ extern Size SyncScanShmemSize(void); struct VacuumParams; extern void heap_vacuum_rel(Relation onerel, struct VacuumParams *params, BufferAccessStrategy bstrategy); +extern void heap_parallel_vacuum_main(dsm_segment *seg, shm_toc *toc); /* in heap/heapam_visibility.c */ extern bool HeapTupleSatisfiesVisibility(HeapTuple stup, Snapshot snapshot, diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h index 77086f3..c4b355a 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -167,6 +167,11 @@ typedef struct VacuumParams int log_min_duration; /* minimum execution threshold in ms at * which verbose logs are activated, -1 * to use default */ + /* + * The number of parallel vacuum workers. -1 by default for no workers + * and 0 for choosing based on the number of indexes. + */ + int nworkers; } VacuumParams; /* GUC parameters */ diff --git a/src/test/regress/expected/vacuum.out b/src/test/regress/expected/vacuum.out index 07d0703..973bb33 100644 --- a/src/test/regress/expected/vacuum.out +++ b/src/test/regress/expected/vacuum.out @@ -80,6 +80,12 @@ CONTEXT: SQL function "do_analyze" statement 1 SQL function "wrap_do_analyze" statement 1 VACUUM FULL vactst; VACUUM (DISABLE_PAGE_SKIPPING) vaccluster; +VACUUM (PARALLEL) vaccluster; +VACUUM (PARALLEL 2) vaccluster; +VACUUM (PARALLEL 0) vaccluster; -- error +ERROR: parallel vacuum degree must be at least 1 +LINE 1: VACUUM (PARALLEL 0) vaccluster; + ^ -- partitioned table CREATE TABLE vacparted (a int, b char) PARTITION BY LIST (a); CREATE TABLE vacparted1 PARTITION OF vacparted FOR VALUES IN (1); @@ -116,9 +122,9 @@ ERROR: column "does_not_exist" of relation "vacparted" does not exist ANALYZE (VERBOSE) does_not_exist; ERROR: relation "does_not_exist" does not exist ANALYZE (nonexistent-arg) does_not_exist; -ERROR: syntax error at or near "-" +ERROR: syntax error at or near "arg" LINE 1: ANALYZE (nonexistent-arg) does_not_exist; - ^ + ^ ANALYZE (nonexistentarg) does_not_exit; ERROR: unrecognized ANALYZE option "nonexistentarg" LINE 1: ANALYZE (nonexistentarg) does_not_exit; diff --git a/src/test/regress/sql/vacuum.sql b/src/test/regress/sql/vacuum.sql index 81f3822..d0c209a 100644 --- a/src/test/regress/sql/vacuum.sql +++ b/src/test/regress/sql/vacuum.sql @@ -61,6 +61,9 @@ VACUUM FULL vaccluster; VACUUM FULL vactst; VACUUM (DISABLE_PAGE_SKIPPING) vaccluster; +VACUUM (PARALLEL) vaccluster; +VACUUM (PARALLEL 2) vaccluster; +VACUUM (PARALLEL 0) vaccluster; -- error -- partitioned table CREATE TABLE vacparted (a int, b char) PARTITION BY LIST (a); -- 2.10.5