From 4150888f2c0953853fce7ae5964b0ad55fa00c31 Mon Sep 17 00:00:00 2001 From: Masahiko Sawada Date: Mon, 4 Mar 2019 09:31:41 +0900 Subject: [PATCH v19 2/3] 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. Parallel vacuum can be performed by specifying like VACUUM (PARALLEL 2) tbl, meaning that performing vacuum with 2 parallel worker processes. Specifying only PARALLEL means that the degree of parallalism will be determined based on the number of indexes the 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 | 30 +- src/backend/access/heap/vacuumlazy.c | 877 ++++++++++++++++++++++++++++++---- src/backend/access/transam/parallel.c | 4 + src/backend/commands/vacuum.c | 26 + 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 | 8 +- src/test/regress/expected/vacuum.out | 10 +- src/test/regress/sql/vacuum.sql | 3 + 12 files changed, 861 insertions(+), 118 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d383de2..3ca3ae8 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 99dda89..91b9c30 100644 --- a/doc/src/sgml/ref/vacuum.sgml +++ b/doc/src/sgml/ref/vacuum.sgml @@ -30,7 +30,7 @@ VACUUM [ FULL ] [ FREEZE ] [ VERBOSE ] [ ANALYZE ] [ boolean ] VERBOSE [ boolean ] ANALYZE [ boolean ] - PARALLEL [ N ] + PARALLEL [ integer ] DISABLE_PAGE_SKIPPING [ boolean ] SKIP_LOCKED [ boolean ] @@ -144,6 +144,20 @@ 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. + Workers for vacuum launches before starting each phases and exit at the end + of the phase. This option can not use with FULL option. + + + + + DISABLE_PAGE_SKIPPING @@ -197,6 +211,20 @@ 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 5c554f9..917a879 100644 --- a/src/backend/access/heap/vacuumlazy.c +++ b/src/backend/access/heap/vacuumlazy.c @@ -22,6 +22,19 @@ * 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 in + * parallel. 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 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. 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 +54,10 @@ #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 +70,7 @@ #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 +126,92 @@ */ #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 + +/* + * Are we in a parallel lazy vacuum? If that's 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, + * or 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 vacuum settings. These fields are not modified + * during the lazy vacuum. + */ + Oid relid; + int elevel; + + /* + * An indication for vacuum workers of doing either vacuuming index 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 or the new live tuples in index cleanup. + * + * 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 +230,12 @@ 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 +247,18 @@ 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 +266,27 @@ 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 bool lazy_begin_parallel_vacuum_index(LVParallelState *lps, LVRelStats *vacrelstats, + bool for_cleanup); +static void lazy_end_parallel_vacuum_index(LVParallelState *lps, bool reinitialize); +static void lazy_vacuum_all_indexes(LVRelStats *vacrelstats, Relation *Irel, int nindexes, + IndexBulkDeleteResult **stats, + LVParallelState *lps, bool for_cleanup); +static void lazy_vacuum_indexes_for_worker(Relation *indrels, int nindexes, + LVShared *lvshared, LVDeadTuples *dead_tuples, + bool for_cleanup); +static int compute_parallel_workers(Relation onerel, int nrequested, int nindexes); +static long compute_max_dead_tuples(BlockNumber relblocks, bool hasindex); /* @@ -261,7 +374,7 @@ 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); @@ -464,14 +577,28 @@ 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; @@ -494,6 +621,7 @@ 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, @@ -529,13 +657,34 @@ 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->options & VACOPT_PARALLEL) != 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); + 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); /* @@ -583,7 +732,7 @@ 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) { @@ -638,7 +787,7 @@ 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) { @@ -713,8 +862,8 @@ 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, @@ -742,10 +891,8 @@ 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_all_indexes(vacrelstats, Irel, nindexes, indstats, + lps, false); /* * Report that we are now vacuuming the heap. We also increase @@ -765,7 +912,7 @@ 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++; /* @@ -961,7 +1108,7 @@ 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); /* @@ -1000,7 +1147,7 @@ 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; } @@ -1140,7 +1287,7 @@ 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; @@ -1209,8 +1356,7 @@ 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); @@ -1221,7 +1367,7 @@ 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++; /* @@ -1337,7 +1483,7 @@ 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); } @@ -1371,7 +1517,7 @@ 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, @@ -1387,10 +1533,8 @@ 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_all_indexes(vacrelstats, Irel, nindexes, indstats, + lps, false); /* Report that we are now vacuuming the heap */ hvp_val[0] = PROGRESS_VACUUM_PHASE_VACUUM_HEAP; @@ -1416,9 +1560,21 @@ 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 after exited + * from parallel mode. + */ + lazy_vacuum_all_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) @@ -1485,7 +1641,7 @@ 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; @@ -1494,7 +1650,7 @@ 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)) @@ -1542,6 +1698,7 @@ 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; @@ -1552,16 +1709,16 @@ 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; @@ -1682,6 +1839,107 @@ lazy_check_needs_freeze(Buffer buf, bool *hastup) return false; } +/* + * Vacuum or cleanup all 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_all_indexes(LVRelStats *vacrelstats, Relation *Irel, int nindexes, + IndexBulkDeleteResult **stats, LVParallelState *lps, + bool for_cleanup) +{ + int nprocessed = 0; + bool do_parallel = false; /* true means workers has been launched */ + int idx; + + Assert(!IsParallelWorker()); + + /* no job if the table has no index */ + if (nindexes <= 0) + return; + + /* Launch parallel vacuum workers if we're ready */ + if (IsInParallelVacuum(lps)) + do_parallel = lazy_begin_parallel_vacuum_index(lps, vacrelstats, + for_cleanup); + + for (;;) + { + /* Get the next index to vacuum */ + if (do_parallel) + idx = pg_atomic_fetch_add_u32(&(lps->lvshared->nprocessed), 1); + else + idx = nprocessed++; + + /* Done for all indexes? */ + if (idx >= nindexes) + break; + + /* + * Update the local pointer to the corresponding bulk-deletion result + * if someone already updated it. + */ + if (IsInParallelVacuum(lps) && + lps->lvshared->indstats[idx].updated && + stats[idx] == NULL) + stats[idx] = &(lps->lvshared->indstats[idx].stats); + + /* Do vacuum or cleanup one index */ + if (!for_cleanup) + lazy_vacuum_index(Irel[idx], &stats[idx], vacrelstats->old_rel_pages, + vacrelstats->dead_tuples); + else + { + lazy_cleanup_index(Irel[idx], &stats[idx], vacrelstats->new_rel_tuples, + vacrelstats->tupcount_pages < vacrelstats->rel_pages); + + if (!IsInParallelVacuum(lps)) + { + /* + * Update index statistics. If in parallel lazy vacuum, we will + * update them after exited from parallel mode. + */ + lazy_update_index_statistics(Irel[idx], stats[idx]); + + if (stats[idx]) + pfree(stats[idx]); + } + } + + /* + * In parallel lazy vacuum, we copy the index bulk-deletion result + * returned from ambulkdelete and amvacuumcleanup to the DSM segment + * if the result on the DSM segment is not updated yet. It's necessary + * 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 update it directly. + * + * Since all vacuum workers write the bulk-deletion result at different + * slot we can write them without locking. + */ + if (IsInParallelVacuum(lps) && + !lps->lvshared->indstats[idx].updated && + stats[idx] != NULL) + { + memcpy(&(lps->lvshared->indstats[idx].stats), + stats[idx], sizeof(IndexBulkDeleteResult)); + lps->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] = &(lps->lvshared->indstats[idx].stats); + } + } + + if (do_parallel) + lazy_end_parallel_vacuum_index(lps, !for_cleanup); +} /* * lazy_vacuum_index() -- vacuum one index relation. @@ -1690,11 +1948,11 @@ lazy_check_needs_freeze(Buffer buf, bool *hastup) * vacrelstats->dead_tuples, and update running statistics. */ static void -lazy_vacuum_index(Relation indrel, - IndexBulkDeleteResult **stats, - LVRelStats *vacrelstats) +lazy_vacuum_index(Relation indrel, IndexBulkDeleteResult **stats, + double reltuples, LVDeadTuples *dead_tuples) { IndexVacuumInfo ivinfo; + char *msg; PGRUsage ru0; pg_rusage_init(&ru0); @@ -1703,18 +1961,21 @@ lazy_vacuum_index(Relation indrel, ivinfo.analyze_only = 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()) + msg = "scanned index \"%s\" to remove %d row versions by parallel vacuum worker"; + else + msg = "scanned index \"%s\" to remove %d row versions"; ereport(elevel, - (errmsg("scanned index \"%s\" to remove %d row versions", + (errmsg(msg, RelationGetRelationName(indrel), - vacrelstats->num_dead_tuples), + dead_tuples->num_tuples), errdetail_internal("%s", pg_rusage_show(&ru0)))); } @@ -1722,60 +1983,65 @@ lazy_vacuum_index(Relation indrel, * lazy_cleanup_index() -- do post-vacuum cleanup for one index relation. */ static void -lazy_cleanup_index(Relation indrel, - IndexBulkDeleteResult *stats, - LVRelStats *vacrelstats) +lazy_cleanup_index(Relation indrel, IndexBulkDeleteResult **stats, + double reltuples, bool estimated_count) { IndexVacuumInfo ivinfo; + char *msg; PGRUsage ru0; pg_rusage_init(&ru0); ivinfo.index = indrel; ivinfo.analyze_only = 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) + 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()) + msg = "index \"%s\" now contains %.0f row versions in %u pages, reported by parallel vacuum worker"; + else + msg = "index \"%s\" now contains %.0f row versions in %u pages"; ereport(elevel, - (errmsg("index \"%s\" now contains %.0f row versions in %u pages", + (errmsg(msg, 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)))); +} - pfree(stats); +/* + * Update index statistics in pg_class, but only if the index says the count + * is accurate. + */ +static void +lazy_update_index_statistics(Relation indrel, IndexBulkDeleteResult *stats) +{ + Assert(!IsInParallelMode()); + + if (!stats || stats->estimated_count) + return; + + vac_update_relstats(indrel, + stats->num_pages, + stats->num_index_tuples, + 0, + false, + InvalidTransactionId, + InvalidMultiXactId, + false); } /* @@ -2080,19 +2346,17 @@ 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); @@ -2106,34 +2370,49 @@ 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); } } @@ -2147,12 +2426,12 @@ 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); @@ -2300,3 +2579,389 @@ 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); + + /* copy the index statistics to a temporary space */ + 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. Return true if at least one worker + * has been launched. + */ +static bool +lazy_begin_parallel_vacuum_index(LVParallelState *lps, LVRelStats *vacrelstats, + bool for_cleanup) +{ + StringInfoData buf; + + Assert(!IsParallelWorker()); + + /* Request workers to do either vacuuming indexes or cleaning indexes */ + lps->lvshared->for_cleanup = for_cleanup; + + if (for_cleanup) + { + /* + * 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); + } + else + { + /* We can only provide an approximate value of num_heap_tuples here */ + lps->lvshared->reltuples = vacrelstats->old_live_tuples; + lps->lvshared->estimated_count = true; + } + + LaunchParallelWorkers(lps->pcxt); + + initStringInfo(&buf); + + /* + * if no workers launched, we vacuum all indexes by the leader process + * alone. Since there is hope that we can launch workers in the next + * execution time we don't want to end parallel mode yet. + */ + if (lps->pcxt->nworkers_launched == 0) + { + if (lps->nworkers_requested > 0) + appendStringInfo(&buf, + "could not launch parallel vacuum worker (planned: %d, requested: %d)", + lps->pcxt->nworkers, lps->nworkers_requested); + else + appendStringInfo(&buf, + "could not launch parallel vacuum worker (planned: %d)", + lps->pcxt->nworkers); + ereport(elevel, (errmsg("%s", buf.data))); + + lazy_end_parallel_vacuum_index(lps, !for_cleanup); + return false; + } + + /* Report parallel vacuum worker information */ + 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 true; +} + +/* + * Wait for all worker processes to finish and reinitialize DSM for + * the next execution. + */ +static void +lazy_end_parallel_vacuum_index(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 DSM space except 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; + + 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"))); + + /* Open relations */ + onerel = heap_open(lvshared->relid, ShareUpdateExclusiveLock); + + /* indrels are sorted in order by OID */ + vac_open_indexes(onerel, RowExclusiveLock, &nindexes, &indrels); + Assert(nindexes > 0); + + /* Set debug_query_string for individual workers */ + sharedquery = shm_toc_lookup(toc, PARALLEL_VACUUM_KEY_QUERY_TEXT, true); + + /* Report the query string from leader */ + debug_query_string = sharedquery; + pgstat_report_activity(STATE_RUNNING, debug_query_string); + + /* Set dead tuple space within worker */ + 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; + + /* Do either vacuuming indexes or cleaning indexes */ + lazy_vacuum_indexes_for_worker(indrels, nindexes, lvshared, + dead_tuples, + lvshared->for_cleanup); + + vac_close_indexes(nindexes, indrels, RowExclusiveLock); + heap_close(onerel, ShareUpdateExclusiveLock); +} + +/* + * Vacuum or cleanup all indexes. This is similar to the lazy_vacuum_all_indexes + * but this function must be used by the parallel vacuum worker processes. + */ +static void +lazy_vacuum_indexes_for_worker(Relation *indrels, int nindexes, + LVShared *lvshared, LVDeadTuples *dead_tuples, + bool for_cleanup) +{ + int idx = 0; + + Assert(IsParallelWorker()); + + for (;;) + { + IndexBulkDeleteResult *stats = NULL; + + /* Get next index to vacuum */ + idx = pg_atomic_fetch_add_u32(&(lvshared->nprocessed), 1); + + /* Done for all indexes? */ + if (idx >= nindexes) + break; + + /* + * If a vacuum process already updated the bulk-deletion result, we + * pass it to index AMs. Otherwise pass NULL as they expect NULL for + * the first time execution. + */ + if (lvshared->indstats[idx].updated) + stats = &(lvshared->indstats[idx].stats); + + /* Do vacuum or cleanup one index */ + if (!for_cleanup) + lazy_vacuum_index(indrels[idx], &stats, lvshared->reltuples, + dead_tuples); + else + lazy_cleanup_index(indrels[idx], &stats, 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 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) + { + memcpy(&(lvshared->indstats[idx].stats), stats, + sizeof(IndexBulkDeleteResult)); + lvshared->indstats[idx].updated = true; + } + } +} 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 72f140e..432a1f3 100644 --- a/src/backend/commands/vacuum.c +++ b/src/backend/commands/vacuum.c @@ -90,6 +90,7 @@ ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel) ListCell *lc; params.options = vacstmt->is_vacuumcmd ? VACOPT_VACUUM : VACOPT_ANALYZE; + params.nworkers = -1; /* Parse options list */ foreach(lc, vacstmt->options) @@ -116,6 +117,25 @@ ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel) params.options |= defGetBoolean(opt) ? VACOPT_FULL : 0; else if (strcmp(opt->defname, "disable_page_skipping") == 0) params.options |= defGetBoolean(opt) ? VACOPT_DISABLE_PAGE_SKIPPING : 0; + else if (strcmp(opt->defname, "parallel") == 0) + { + params.options |= VACOPT_PARALLEL; + + if (opt->arg == NULL) + { + /* User didn't specify the parallel degree */ + 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), @@ -147,6 +167,12 @@ ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, bool isTopLevel) } } + if ((params.options & VACOPT_FULL) && + (params.options & VACOPT_PARALLEL)) + 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 921e7d2..c79d962 100644 --- a/src/backend/parser/gram.y +++ b/src/backend/parser/gram.y @@ -10542,6 +10542,7 @@ 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..22df17f 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 = 0; /* 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 10ae21c..fef80c4 100644 --- a/src/bin/psql/tab-complete.c +++ b/src/bin/psql/tab-complete.c @@ -3429,7 +3429,8 @@ 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 (HeadMatches("VACUUM") && TailMatches("(")) /* "VACUUM (" should be caught above, so assume we want columns */ diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h index eb9e160..3eb7946 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" @@ -219,6 +220,7 @@ 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..e6ce35b 100644 --- a/src/include/commands/vacuum.h +++ b/src/include/commands/vacuum.h @@ -145,7 +145,8 @@ typedef enum VacuumOption VACOPT_FULL = 1 << 4, /* FULL (non-concurrent) vacuum */ VACOPT_SKIP_LOCKED = 1 << 5, /* skip if cannot get lock */ VACOPT_SKIPTOAST = 1 << 6, /* don't process the TOAST table, if any */ - VACOPT_DISABLE_PAGE_SKIPPING = 1 << 7 /* don't skip any pages */ + VACOPT_DISABLE_PAGE_SKIPPING = 1 << 7, /* don't skip any pages */ + VACOPT_PARALLEL = 1 << 8 } VacuumOption; /* @@ -167,6 +168,11 @@ 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