From c40bfce2f812370315ca9ea735b9d3d31384d4d2 Mon Sep 17 00:00:00 2001 From: Alexander Korotkov Date: Mon, 15 Sep 2025 21:12:01 +0300 Subject: [PATCH v11 1/3] Parallel index autovacuum --- src/backend/access/common/reloptions.c | 11 ++ src/backend/commands/vacuumparallel.c | 68 ++++++++- src/backend/postmaster/autovacuum.c | 144 +++++++++++++++++- src/backend/utils/init/globals.c | 1 + src/backend/utils/misc/guc_parameters.dat | 9 ++ src/backend/utils/misc/postgresql.conf.sample | 1 + src/bin/psql/tab-complete.in.c | 1 + src/include/miscadmin.h | 1 + src/include/postmaster/autovacuum.h | 5 + src/include/utils/rel.h | 7 + 10 files changed, 240 insertions(+), 8 deletions(-) diff --git a/src/backend/access/common/reloptions.c b/src/backend/access/common/reloptions.c index 0af3fea68fa..1c98d43c6eb 100644 --- a/src/backend/access/common/reloptions.c +++ b/src/backend/access/common/reloptions.c @@ -222,6 +222,15 @@ static relopt_int intRelOpts[] = }, SPGIST_DEFAULT_FILLFACTOR, SPGIST_MIN_FILLFACTOR, 100 }, + { + { + "autovacuum_parallel_workers", + "Maximum number of parallel autovacuum workers that can be used for processing this table.", + RELOPT_KIND_HEAP, + ShareUpdateExclusiveLock + }, + -1, -1, 1024 + }, { { "autovacuum_vacuum_threshold", @@ -1872,6 +1881,8 @@ default_reloptions(Datum reloptions, bool validate, relopt_kind kind) {"fillfactor", RELOPT_TYPE_INT, offsetof(StdRdOptions, fillfactor)}, {"autovacuum_enabled", RELOPT_TYPE_BOOL, offsetof(StdRdOptions, autovacuum) + offsetof(AutoVacOpts, enabled)}, + {"autovacuum_parallel_workers", RELOPT_TYPE_INT, + offsetof(StdRdOptions, autovacuum) + offsetof(AutoVacOpts, autovacuum_parallel_workers)}, {"autovacuum_vacuum_threshold", RELOPT_TYPE_INT, offsetof(StdRdOptions, autovacuum) + offsetof(AutoVacOpts, vacuum_threshold)}, {"autovacuum_vacuum_max_threshold", RELOPT_TYPE_INT, diff --git a/src/backend/commands/vacuumparallel.c b/src/backend/commands/vacuumparallel.c index 0feea1d30ec..4221e6084f5 100644 --- a/src/backend/commands/vacuumparallel.c +++ b/src/backend/commands/vacuumparallel.c @@ -1,7 +1,9 @@ /*------------------------------------------------------------------------- * * vacuumparallel.c - * Support routines for parallel vacuum execution. + * Support routines for parallel vacuum and autovacuum execution. In the + * future comments, the word "vacuum" will refer to both vacuum and + * autovacuum. * * This file contains routines that are intended to support setting up, using, * and tearing down a ParallelVacuumState. @@ -34,6 +36,7 @@ #include "executor/instrument.h" #include "optimizer/paths.h" #include "pgstat.h" +#include "postmaster/autovacuum.h" #include "storage/bufmgr.h" #include "tcop/tcopprot.h" #include "utils/lsyscache.h" @@ -225,6 +228,8 @@ static int parallel_vacuum_compute_workers(Relation *indrels, int nindexes, int bool *will_parallel_vacuum); static void parallel_vacuum_process_all_indexes(ParallelVacuumState *pvs, int num_index_scans, bool vacuum); +static void parallel_vacuum_process_all_indexes_internal(ParallelVacuumState *pvs, + int num_index_scans, bool vacuum); static void parallel_vacuum_process_safe_indexes(ParallelVacuumState *pvs); static void parallel_vacuum_process_unsafe_indexes(ParallelVacuumState *pvs); static void parallel_vacuum_process_one_index(ParallelVacuumState *pvs, Relation indrel, @@ -373,8 +378,9 @@ parallel_vacuum_init(Relation rel, Relation *indrels, int nindexes, shared->queryid = pgstat_get_my_query_id(); shared->maintenance_work_mem_worker = (nindexes_mwm > 0) ? - maintenance_work_mem / Min(parallel_workers, nindexes_mwm) : - maintenance_work_mem; + vac_work_mem / Min(parallel_workers, nindexes_mwm) : + vac_work_mem; + shared->dead_items_info.max_bytes = vac_work_mem * (size_t) 1024; /* Prepare DSA space for dead items */ @@ -553,12 +559,17 @@ parallel_vacuum_compute_workers(Relation *indrels, int nindexes, int nrequested, int nindexes_parallel_bulkdel = 0; int nindexes_parallel_cleanup = 0; int parallel_workers; + int max_workers; + + max_workers = AmAutoVacuumWorkerProcess() ? + autovacuum_max_parallel_workers : + max_parallel_maintenance_workers; /* * We don't allow performing parallel operation in standalone backend or * when parallelism is disabled. */ - if (!IsUnderPostmaster || max_parallel_maintenance_workers == 0) + if (!IsUnderPostmaster || max_workers == 0) return 0; /* @@ -597,8 +608,8 @@ parallel_vacuum_compute_workers(Relation *indrels, int nindexes, int nrequested, parallel_workers = (nrequested > 0) ? Min(nrequested, nindexes_parallel) : nindexes_parallel; - /* Cap by max_parallel_maintenance_workers */ - parallel_workers = Min(parallel_workers, max_parallel_maintenance_workers); + /* Cap by GUC variable */ + parallel_workers = Min(parallel_workers, max_workers); return parallel_workers; } @@ -610,6 +621,30 @@ parallel_vacuum_compute_workers(Relation *indrels, int nindexes, int nrequested, static void parallel_vacuum_process_all_indexes(ParallelVacuumState *pvs, int num_index_scans, bool vacuum) +{ + /* + * Parallel autovacuum can reserve parallel workers. Use try/catch block + * to make ensure that all workers are released. + */ + PG_TRY(); + { + parallel_vacuum_process_all_indexes_internal(pvs, num_index_scans, + false); + } + PG_CATCH(); + { + /* Release all reserved parallel workers, if any. */ + if (AmAutoVacuumWorkerProcess()) + AutoVacuumReleaseAllParallelWorkers(); + + PG_RE_THROW(); + } + PG_END_TRY(); +} + +static void +parallel_vacuum_process_all_indexes_internal(ParallelVacuumState *pvs, + int num_index_scans, bool vacuum) { int nworkers; PVIndVacStatus new_status; @@ -646,6 +681,13 @@ parallel_vacuum_process_all_indexes(ParallelVacuumState *pvs, int num_index_scan */ nworkers = Min(nworkers, pvs->pcxt->nworkers); + /* + * Reserve workers in autovacuum global state. Note, that we may be given + * fewer workers than we requested. + */ + if (AmAutoVacuumWorkerProcess() && nworkers > 0) + nworkers = AutoVacuumReserveParallelWorkers(nworkers); + /* * Set index vacuum status and mark whether parallel vacuum worker can * process it. @@ -690,6 +732,16 @@ parallel_vacuum_process_all_indexes(ParallelVacuumState *pvs, int num_index_scan LaunchParallelWorkers(pvs->pcxt); + if (AmAutoVacuumWorkerProcess() && + pvs->pcxt->nworkers_launched < nworkers) + { + /* + * Tell autovacuum that we could not launch all the previously + * reserved workers. + */ + AutoVacuumReleaseParallelWorkers(nworkers - pvs->pcxt->nworkers_launched); + } + if (pvs->pcxt->nworkers_launched > 0) { /* @@ -738,6 +790,10 @@ parallel_vacuum_process_all_indexes(ParallelVacuumState *pvs, int num_index_scan for (int i = 0; i < pvs->pcxt->nworkers_launched; i++) InstrAccumParallelQuery(&pvs->buffer_usage[i], &pvs->wal_usage[i]); + + /* Also release all previously reserved parallel autovacuum workers */ + if (AmAutoVacuumWorkerProcess() && pvs->pcxt->nworkers_launched > 0) + AutoVacuumReleaseParallelWorkers(pvs->pcxt->nworkers_launched); } /* diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c index dce4c8c45b9..2bcd2ceb2a9 100644 --- a/src/backend/postmaster/autovacuum.c +++ b/src/backend/postmaster/autovacuum.c @@ -150,6 +150,12 @@ int Log_autovacuum_min_duration = 600000; static double av_storage_param_cost_delay = -1; static int av_storage_param_cost_limit = -1; +/* + * Variable to keep number of currently reserved parallel autovacuum workers. + * It is only relevant for parallel autovacuum leader process. + */ +static int av_nworkers_reserved = 0; + /* Flags set by signal handlers */ static volatile sig_atomic_t got_SIGUSR2 = false; @@ -284,6 +290,8 @@ typedef struct AutoVacuumWorkItem * av_workItems work item array * av_nworkersForBalance the number of autovacuum workers to use when * calculating the per worker cost limit + * av_freeParallelWorkers the number of free parallel autovacuum workers + * av_maxParallelWorkers the maximum number of parallel autovacuum workers * * This struct is protected by AutovacuumLock, except for av_signal and parts * of the worker list (see above). @@ -298,6 +306,8 @@ typedef struct WorkerInfo av_startingWorker; AutoVacuumWorkItem av_workItems[NUM_WORKITEMS]; pg_atomic_uint32 av_nworkersForBalance; + uint32 av_freeParallelWorkers; + uint32 av_maxParallelWorkers; } AutoVacuumShmemStruct; static AutoVacuumShmemStruct *AutoVacuumShmem; @@ -363,6 +373,7 @@ static void autovac_report_workitem(AutoVacuumWorkItem *workitem, static void avl_sigusr2_handler(SIGNAL_ARGS); static bool av_worker_available(void); static void check_av_worker_gucs(void); +static void adjust_free_parallel_workers(int prev_max_parallel_workers); @@ -762,6 +773,8 @@ ProcessAutoVacLauncherInterrupts(void) if (ConfigReloadPending) { int autovacuum_max_workers_prev = autovacuum_max_workers; + int autovacuum_max_parallel_workers_prev = + autovacuum_max_parallel_workers; ConfigReloadPending = false; ProcessConfigFile(PGC_SIGHUP); @@ -778,6 +791,15 @@ ProcessAutoVacLauncherInterrupts(void) if (autovacuum_max_workers_prev != autovacuum_max_workers) check_av_worker_gucs(); + /* + * If autovacuum_max_parallel_workers changed, we must take care of + * the correct value of available parallel autovacuum workers in + * shmem. + */ + if (autovacuum_max_parallel_workers_prev != + autovacuum_max_parallel_workers) + adjust_free_parallel_workers(autovacuum_max_parallel_workers_prev); + /* rebuild the list in case the naptime changed */ rebuild_database_list(InvalidOid); } @@ -2870,8 +2892,12 @@ table_recheck_autovac(Oid relid, HTAB *table_toast_map, */ tab->at_params.index_cleanup = VACOPTVALUE_UNSPECIFIED; tab->at_params.truncate = VACOPTVALUE_UNSPECIFIED; - /* As of now, we don't support parallel vacuum for autovacuum */ - tab->at_params.nworkers = -1; + + /* Decide whether we need to process indexes of table in parallel. */ + tab->at_params.nworkers = avopts + ? avopts->autovacuum_parallel_workers + : -1; + 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; @@ -3352,6 +3378,85 @@ AutoVacuumRequestWork(AutoVacuumWorkItemType type, Oid relationId, return result; } +/* + * In order to meet the 'autovacuum_max_parallel_workers' limit, leader + * autovacuum process must call this function. It returns the number of + * parallel workers that actually can be launched and reserves these workers + * (if any) in global autovacuum state. + * + * NOTE: We will try to provide as many workers as requested, even if caller + * will occupy all available workers. + */ +int +AutoVacuumReserveParallelWorkers(int nworkers) +{ + int nreserved; + + /* Only leader worker can call this function. */ + Assert(AmAutoVacuumWorkerProcess() && !IsParallelWorker()); + + /* + * We can only reserve workers at the beginning of parallel index + * processing, so we must not have any reserved workers right now. + */ + Assert(av_nworkers_reserved == 0); + + LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE); + + /* Provide as many workers as we can. */ + nreserved = Min(AutoVacuumShmem->av_freeParallelWorkers, nworkers); + AutoVacuumShmem->av_freeParallelWorkers -= nworkers; + + /* Remember how many workers we have reserved. */ + av_nworkers_reserved += nworkers; + + LWLockRelease(AutovacuumLock); + return nreserved; +} + +/* + * Leader autovacuum process must call this function in order to update global + * autovacuum state, so other leaders will be able to use these parallel + * workers. + * + * 'nworkers' - how many workers caller wants to release. + */ +void +AutoVacuumReleaseParallelWorkers(int nworkers) +{ + /* Only leader worker can call this function. */ + Assert(AmAutoVacuumWorkerProcess() && !IsParallelWorker()); + + LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE); + + /* + * If the maximum number of parallel workers was reduced during execution, + * we must cap available workers number by its new value. + */ + AutoVacuumShmem->av_freeParallelWorkers = + Min(AutoVacuumShmem->av_freeParallelWorkers + nworkers, + AutoVacuumShmem->av_maxParallelWorkers); + + /* Don't have to remember these workers anymore. */ + av_nworkers_reserved -= nworkers; + + LWLockRelease(AutovacuumLock); +} + +/* + * Same as above, but release *all* parallel workers, that were reserved by + * current leader autovacuum process. + */ +void +AutoVacuumReleaseAllParallelWorkers(void) +{ + /* Only leader worker can call this function. */ + Assert(AmAutoVacuumWorkerProcess() && !IsParallelWorker()); + + if (av_nworkers_reserved > 0) + AutoVacuumReleaseParallelWorkers(av_nworkers_reserved); +} + /* * autovac_init * This is called at postmaster initialization. @@ -3412,6 +3517,10 @@ AutoVacuumShmemInit(void) Assert(!found); AutoVacuumShmem->av_launcherpid = 0; + AutoVacuumShmem->av_maxParallelWorkers = + Min(autovacuum_max_parallel_workers, max_worker_processes); + AutoVacuumShmem->av_freeParallelWorkers = + AutoVacuumShmem->av_maxParallelWorkers; dclist_init(&AutoVacuumShmem->av_freeWorkers); dlist_init(&AutoVacuumShmem->av_runningWorkers); AutoVacuumShmem->av_startingWorker = NULL; @@ -3493,3 +3602,34 @@ check_av_worker_gucs(void) errdetail("The server will only start up to \"autovacuum_worker_slots\" (%d) autovacuum workers at a given time.", autovacuum_worker_slots))); } + +/* + * Make sure that number of free parallel workers corresponds to the + * autovacuum_max_parallel_workers parameter (after it was changed). + */ +static void +adjust_free_parallel_workers(int prev_max_parallel_workers) +{ + LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE); + + /* + * Cap the number of free workers by new parameter's value, if needed. + */ + AutoVacuumShmem->av_freeParallelWorkers = + Min(AutoVacuumShmem->av_freeParallelWorkers, + autovacuum_max_parallel_workers); + + if (autovacuum_max_parallel_workers > prev_max_parallel_workers) + { + /* + * If user wants to increase number of parallel autovacuum workers, we + * must increase number of free workers. + */ + AutoVacuumShmem->av_freeParallelWorkers += + (autovacuum_max_parallel_workers - prev_max_parallel_workers); + } + + AutoVacuumShmem->av_maxParallelWorkers = autovacuum_max_parallel_workers; + + LWLockRelease(AutovacuumLock); +} diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c index d31cb45a058..fd00d6f89dc 100644 --- a/src/backend/utils/init/globals.c +++ b/src/backend/utils/init/globals.c @@ -143,6 +143,7 @@ int NBuffers = 16384; int MaxConnections = 100; int max_worker_processes = 8; int max_parallel_workers = 8; +int autovacuum_max_parallel_workers = 0; int MaxBackends = 0; /* GUC parameters for vacuum */ diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index 6bc6be13d2a..1926218558a 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2112,6 +2112,15 @@ max => 'MAX_BACKENDS', }, +{ name => 'autovacuum_max_parallel_workers', type => 'int', context => 'PGC_SIGHUP', group => 'VACUUM_AUTOVACUUM', + short_desc => 'Maximum number of parallel autovacuum workers, that can be taken from bgworkers pool.', + long_desc => 'This parameter is capped by "max_worker_processes" (not by "autovacuum_max_workers"!).', + variable => 'autovacuum_max_parallel_workers', + boot_val => '0', + min => '0', + max => 'MAX_BACKENDS', +}, + { name => 'max_parallel_maintenance_workers', type => 'int', context => 'PGC_USERSET', group => 'RESOURCES_WORKER_PROCESSES', short_desc => 'Sets the maximum number of parallel processes per maintenance operation.', variable => 'max_parallel_maintenance_workers', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c36fcb9ab61..d277fef1735 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -684,6 +684,7 @@ autovacuum_worker_slots = 16 # autovacuum worker slots to allocate # (change requires restart) #autovacuum_max_workers = 3 # max number of autovacuum subprocesses +#autovacuum_max_parallel_workers = 0 # disabled by default and limited by max_worker_processes #autovacuum_naptime = 1min # time between autovacuum runs #autovacuum_vacuum_threshold = 50 # min number of row updates before # vacuum diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c index 6b20a4404b2..0fb04e08c5d 100644 --- a/src/bin/psql/tab-complete.in.c +++ b/src/bin/psql/tab-complete.in.c @@ -1402,6 +1402,7 @@ static const char *const table_storage_parameters[] = { "autovacuum_multixact_freeze_max_age", "autovacuum_multixact_freeze_min_age", "autovacuum_multixact_freeze_table_age", + "autovacuum_parallel_workers", "autovacuum_vacuum_cost_delay", "autovacuum_vacuum_cost_limit", "autovacuum_vacuum_insert_scale_factor", diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bef98471c3..85926415657 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -177,6 +177,7 @@ extern PGDLLIMPORT int MaxBackends; extern PGDLLIMPORT int MaxConnections; extern PGDLLIMPORT int max_worker_processes; extern PGDLLIMPORT int max_parallel_workers; +extern PGDLLIMPORT int autovacuum_max_parallel_workers; extern PGDLLIMPORT int commit_timestamp_buffers; extern PGDLLIMPORT int multixact_member_buffers; diff --git a/src/include/postmaster/autovacuum.h b/src/include/postmaster/autovacuum.h index e8135f41a1c..904c5ce37d8 100644 --- a/src/include/postmaster/autovacuum.h +++ b/src/include/postmaster/autovacuum.h @@ -64,6 +64,11 @@ pg_noreturn extern void AutoVacWorkerMain(const void *startup_data, size_t start extern bool AutoVacuumRequestWork(AutoVacuumWorkItemType type, Oid relationId, BlockNumber blkno); +/* parallel autovacuum stuff */ +extern int AutoVacuumReserveParallelWorkers(int nworkers); +extern void AutoVacuumReleaseParallelWorkers(int nworkers); +extern void AutoVacuumReleaseAllParallelWorkers(void); + /* shared memory stuff */ extern Size AutoVacuumShmemSize(void); extern void AutoVacuumShmemInit(void); diff --git a/src/include/utils/rel.h b/src/include/utils/rel.h index b552359915f..edd286808bf 100644 --- a/src/include/utils/rel.h +++ b/src/include/utils/rel.h @@ -311,6 +311,13 @@ typedef struct ForeignKeyCacheInfo typedef struct AutoVacOpts { bool enabled; + + /* + * Max number of parallel autovacuum workers. If value is 0 then parallel + * degree will computed based on number of indexes. + */ + int autovacuum_parallel_workers; + int vacuum_threshold; int vacuum_max_threshold; int vacuum_ins_threshold; -- 2.39.5 (Apple Git-154)