public inbox for [email protected]help / color / mirror / Atom feed
[PATCH v49 6/7] Remove the GUC stats_temp_directory 2+ messages / 2 participants [nested] [flat]
* [PATCH v49 6/7] Remove the GUC stats_temp_directory @ 2020-09-29 13:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Kyotaro Horiguchi @ 2020-09-29 13:59 UTC (permalink / raw) The new stats collection system doesn't need temporary directory, so just remove it. pg_stat_statements modified to use pg_stat directory to store its temporary files. As the result basebackup copies the pg_stat_statments' temporary file if exists. --- .../pg_stat_statements/pg_stat_statements.c | 13 +++--- doc/src/sgml/backup.sgml | 2 - doc/src/sgml/config.sgml | 19 -------- doc/src/sgml/storage.sgml | 6 --- src/backend/postmaster/pgstat.c | 10 ----- src/backend/replication/basebackup.c | 36 ---------------- src/backend/utils/misc/guc.c | 43 ------------------- src/backend/utils/misc/postgresql.conf.sample | 1 - src/bin/initdb/initdb.c | 1 - src/bin/pg_rewind/filemap.c | 7 --- src/include/pgstat.h | 3 -- src/test/perl/PostgresNode.pm | 4 -- 12 files changed, 6 insertions(+), 139 deletions(-) diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c index 62cccbfa44..28279f97d5 100644 --- a/contrib/pg_stat_statements/pg_stat_statements.c +++ b/contrib/pg_stat_statements/pg_stat_statements.c @@ -89,14 +89,13 @@ PG_MODULE_MAGIC; #define PGSS_DUMP_FILE PGSTAT_STAT_PERMANENT_DIRECTORY "/pg_stat_statements.stat" /* - * Location of external query text file. We don't keep it in the core - * system's stats_temp_directory. The core system can safely use that GUC - * setting, because the statistics collector temp file paths are set only once - * as part of changing the GUC, but pg_stat_statements has no way of avoiding - * race conditions. Besides, we only expect modest, infrequent I/O for query - * strings, so placing the file on a faster filesystem is not compelling. + * Location of external query text file. We don't keep it in the core system's + * pg_stats. pg_stat_statements has no way of avoiding race conditions even if + * the directory were specified by a GUC. Besides, we only expect modest, + * infrequent I/O for query strings, so placing the file on a faster filesystem + * is not compelling. */ -#define PGSS_TEXT_FILE PG_STAT_TMP_DIR "/pgss_query_texts.stat" +#define PGSS_TEXT_FILE PGSTAT_STAT_PERMANENT_DIRECTORY "/pgss_query_texts.stat" /* Magic number identifying the stats file format */ static const uint32 PGSS_FILE_HEADER = 0x20201218; diff --git a/doc/src/sgml/backup.sgml b/doc/src/sgml/backup.sgml index c5557d5444..875769a57e 100644 --- a/doc/src/sgml/backup.sgml +++ b/doc/src/sgml/backup.sgml @@ -1155,8 +1155,6 @@ SELECT pg_stop_backup(); <filename>pg_snapshots/</filename>, <filename>pg_stat_tmp/</filename>, and <filename>pg_subtrans/</filename> (but not the directories themselves) can be omitted from the backup as they will be initialized on postmaster startup. - If <xref linkend="guc-stats-temp-directory"/> is set and is under the data - directory then the contents of that directory can also be omitted. </para> <para> diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 753b1ab6f9..49372c52d4 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -7488,25 +7488,6 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv; </listitem> </varlistentry> - <varlistentry id="guc-stats-temp-directory" xreflabel="stats_temp_directory"> - <term><varname>stats_temp_directory</varname> (<type>string</type>) - <indexterm> - <primary><varname>stats_temp_directory</varname> configuration parameter</primary> - </indexterm> - </term> - <listitem> - <para> - Sets the directory to store temporary statistics data in. This can be - a path relative to the data directory or an absolute path. The default - is <filename>pg_stat_tmp</filename>. Pointing this at a RAM-based - file system will decrease physical I/O requirements and can lead to - improved performance. - This parameter can only be set in the <filename>postgresql.conf</filename> - file or on the server command line. - </para> - </listitem> - </varlistentry> - </variablelist> </sect2> diff --git a/doc/src/sgml/storage.sgml b/doc/src/sgml/storage.sgml index 3234adb639..6bac5e075e 100644 --- a/doc/src/sgml/storage.sgml +++ b/doc/src/sgml/storage.sgml @@ -120,12 +120,6 @@ Item subsystem</entry> </row> -<row> - <entry><filename>pg_stat_tmp</filename></entry> - <entry>Subdirectory containing temporary files for the statistics - subsystem</entry> -</row> - <row> <entry><filename>pg_subtrans</filename></entry> <entry>Subdirectory containing subtransaction status data</entry> diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c index 320d542859..74ceb12ccb 100644 --- a/src/backend/postmaster/pgstat.c +++ b/src/backend/postmaster/pgstat.c @@ -99,16 +99,6 @@ bool pgstat_track_counts = false; int pgstat_track_functions = TRACK_FUNC_OFF; int pgstat_track_activity_query_size = 1024; -/* ---------- - * Built from GUC parameter - * ---------- - */ -char *pgstat_stat_directory = NULL; - -/* No longer used, but will be removed with GUC */ -char *pgstat_stat_filename = NULL; -char *pgstat_stat_tmpname = NULL; - /* * WAL usage counters saved from pgWALUsage at the previous call to * pgstat_send_wal(). This is used to calculate how much WAL usage diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c index fa7bdbcefa..f0d75f55bd 100644 --- a/src/backend/replication/basebackup.c +++ b/src/backend/replication/basebackup.c @@ -87,9 +87,6 @@ static int basebackup_read_file(int fd, char *buf, size_t nbytes, off_t offset, /* Was the backup currently in-progress initiated in recovery mode? */ static bool backup_started_in_recovery = false; -/* Relative path of temporary statistics directory */ -static char *statrelpath = NULL; - /* * Size of each block sent into the tar stream for larger files. */ @@ -152,13 +149,6 @@ struct exclude_list_item */ static const char *const excludeDirContents[] = { - /* - * Skip temporary statistics files. PG_STAT_TMP_DIR must be skipped even - * when stats_temp_directory is set because PGSS_TEXT_FILE is always - * created there. - */ - PG_STAT_TMP_DIR, - /* * It is generally not useful to backup the contents of this directory * even if the intention is to restore to another primary. See backup.sgml @@ -261,7 +251,6 @@ perform_base_backup(basebackup_options *opt) StringInfo labelfile; StringInfo tblspc_map_file; backup_manifest_info manifest; - int datadirpathlen; List *tablespaces = NIL; backup_total = 0; @@ -284,8 +273,6 @@ perform_base_backup(basebackup_options *opt) Assert(CurrentResourceOwner == NULL); CurrentResourceOwner = ResourceOwnerCreate(NULL, "base backup"); - datadirpathlen = strlen(DataDir); - backup_started_in_recovery = RecoveryInProgress(); labelfile = makeStringInfo(); @@ -314,18 +301,6 @@ perform_base_backup(basebackup_options *opt) tablespaceinfo *ti; int tblspc_streamed = 0; - /* - * Calculate the relative path of temporary statistics directory in - * order to skip the files which are located in that directory later. - */ - if (is_absolute_path(pgstat_stat_directory) && - strncmp(pgstat_stat_directory, DataDir, datadirpathlen) == 0) - statrelpath = psprintf("./%s", pgstat_stat_directory + datadirpathlen + 1); - else if (strncmp(pgstat_stat_directory, "./", 2) != 0) - statrelpath = psprintf("./%s", pgstat_stat_directory); - else - statrelpath = pgstat_stat_directory; - /* Add a node for the base directory at the end */ ti = palloc0(sizeof(tablespaceinfo)); ti->size = -1; @@ -1377,17 +1352,6 @@ sendDir(const char *path, int basepathlen, bool sizeonly, List *tablespaces, if (excludeFound) continue; - /* - * Exclude contents of directory specified by statrelpath if not set - * to the default (pg_stat_tmp) which is caught in the loop above. - */ - if (statrelpath != NULL && strcmp(pathbuf, statrelpath) == 0) - { - elog(DEBUG1, "contents of directory \"%s\" excluded from backup", statrelpath); - size += _tarWriteDir(pathbuf, basepathlen, &statbuf, sizeonly); - continue; - } - /* * We can skip pg_wal, the WAL segments need to be fetched from the * WAL archive anyway. But include it as an empty directory anyway, so diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c index c93dc63d98..8eb7d793ef 100644 --- a/src/backend/utils/misc/guc.c +++ b/src/backend/utils/misc/guc.c @@ -203,7 +203,6 @@ static bool check_autovacuum_work_mem(int *newval, void **extra, GucSource sourc static bool check_effective_io_concurrency(int *newval, void **extra, GucSource source); static bool check_maintenance_io_concurrency(int *newval, void **extra, GucSource source); static bool check_huge_page_size(int *newval, void **extra, GucSource source); -static void assign_pgstat_temp_directory(const char *newval, void *extra); static bool check_application_name(char **newval, void **extra, GucSource source); static void assign_application_name(const char *newval, void *extra); static bool check_cluster_name(char **newval, void **extra, GucSource source); @@ -560,8 +559,6 @@ char *HbaFileName; char *IdentFileName; char *external_pid_file; -char *pgstat_temp_directory; - char *application_name; int tcp_keepalives_idle; @@ -4366,17 +4363,6 @@ static struct config_string ConfigureNamesString[] = NULL, NULL, NULL }, - { - {"stats_temp_directory", PGC_SIGHUP, STATS_ACTIVITY, - gettext_noop("Writes temporary statistics files to the specified directory."), - NULL, - GUC_SUPERUSER_ONLY - }, - &pgstat_temp_directory, - PG_STAT_TMP_DIR, - check_canonical_path, assign_pgstat_temp_directory, NULL - }, - { {"synchronous_standby_names", PGC_SIGHUP, REPLICATION_PRIMARY, gettext_noop("Number of synchronous standbys and list of names of potential synchronous ones."), @@ -11782,35 +11768,6 @@ check_huge_page_size(int *newval, void **extra, GucSource source) return true; } -static void -assign_pgstat_temp_directory(const char *newval, void *extra) -{ - /* check_canonical_path already canonicalized newval for us */ - char *dname; - char *tname; - char *fname; - - /* directory */ - dname = guc_malloc(ERROR, strlen(newval) + 1); /* runtime dir */ - sprintf(dname, "%s", newval); - - /* global stats */ - tname = guc_malloc(ERROR, strlen(newval) + 12); /* /global.tmp */ - sprintf(tname, "%s/global.tmp", newval); - fname = guc_malloc(ERROR, strlen(newval) + 13); /* /global.stat */ - sprintf(fname, "%s/global.stat", newval); - - if (pgstat_stat_directory) - free(pgstat_stat_directory); - pgstat_stat_directory = dname; - if (pgstat_stat_tmpname) - free(pgstat_stat_tmpname); - pgstat_stat_tmpname = tname; - if (pgstat_stat_filename) - free(pgstat_stat_filename); - pgstat_stat_filename = fname; -} - static bool check_application_name(char **newval, void **extra, GucSource source) { diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 9640349a91..40a18bb248 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -588,7 +588,6 @@ #track_io_timing = off #track_functions = none # none, pl, all #track_activity_query_size = 1024 # (change requires restart) -#stats_temp_directory = 'pg_stat_tmp' # - Monitoring - diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 3c1cf78b4f..07a00b8d0d 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -219,7 +219,6 @@ static const char *const subdirs[] = { "pg_replslot", "pg_tblspc", "pg_stat", - "pg_stat_tmp", "pg_xact", "pg_logical", "pg_logical/snapshots", diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 2618b4c957..ab5cb51de7 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -87,13 +87,6 @@ struct exclude_list_item */ static const char *excludeDirContents[] = { - /* - * Skip temporary statistics files. PG_STAT_TMP_DIR must be skipped even - * when stats_temp_directory is set because PGSS_TEXT_FILE is always - * created there. - */ - "pg_stat_tmp", /* defined as PG_STAT_TMP_DIR */ - /* * It is generally not useful to backup the contents of this directory * even if the intention is to restore to another primary. See backup.sgml diff --git a/src/include/pgstat.h b/src/include/pgstat.h index 2e066a648c..39519c2f81 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -33,9 +33,6 @@ #define PGSTAT_STAT_PERMANENT_FILENAME "pg_stat/saved_stats" #define PGSTAT_STAT_PERMANENT_TMPFILE "pg_stat/saved_stats.tmp" -/* Default directory to store temporary statistics data in */ -#define PG_STAT_TMP_DIR "pg_stat_tmp" - /* Values for track_functions GUC variable --- order is significant! */ typedef enum TrackFunctionsLevel { diff --git a/src/test/perl/PostgresNode.pm b/src/test/perl/PostgresNode.pm index 9667f7667e..dd41a43b4e 100644 --- a/src/test/perl/PostgresNode.pm +++ b/src/test/perl/PostgresNode.pm @@ -455,10 +455,6 @@ sub init print $conf TestLib::slurp_file($ENV{TEMP_CONFIG}) if defined $ENV{TEMP_CONFIG}; - # XXX Neutralize any stats_temp_directory in TEMP_CONFIG. Nodes running - # concurrently must not share a stats_temp_directory. - print $conf "stats_temp_directory = 'pg_stat_tmp'\n"; - if ($params{allows_streaming}) { if ($params{allows_streaming} eq "logical") -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0007-Exclude-pg_stat-directory-from-base-backup.patch" ^ permalink raw reply [nested|flat] 2+ messages in thread
* [PATCH v22 1/2] Split vacuumdb to create vacuuming.c/h @ 2025-09-25 12:58 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Álvaro Herrera @ 2025-09-25 12:58 UTC (permalink / raw) This allows these routines to be reused by a future utility heavily based on vacuumdb. Discussion: https://postgr.es/m/[email protected] --- src/bin/scripts/Makefile | 4 +- src/bin/scripts/meson.build | 28 +- src/bin/scripts/vacuumdb.c | 1055 +---------------------------------- src/bin/scripts/vacuuming.c | 1012 +++++++++++++++++++++++++++++++++ src/bin/scripts/vacuuming.h | 68 +++ 5 files changed, 1131 insertions(+), 1036 deletions(-) create mode 100644 src/bin/scripts/vacuuming.c create mode 100644 src/bin/scripts/vacuuming.h diff --git a/src/bin/scripts/Makefile b/src/bin/scripts/Makefile index f6b4d40810b..019ca06455d 100644 --- a/src/bin/scripts/Makefile +++ b/src/bin/scripts/Makefile @@ -28,7 +28,7 @@ createuser: createuser.o common.o $(WIN32RES) | submake-libpq submake-libpgport dropdb: dropdb.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils dropuser: dropuser.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils clusterdb: clusterdb.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils -vacuumdb: vacuumdb.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils +vacuumdb: vacuumdb.o vacuuming.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils reindexdb: reindexdb.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils pg_isready: pg_isready.o common.o $(WIN32RES) | submake-libpq submake-libpgport submake-libpgfeutils @@ -50,7 +50,7 @@ uninstall: clean distclean: rm -f $(addsuffix $(X), $(PROGRAMS)) $(addsuffix .o, $(PROGRAMS)) - rm -f common.o $(WIN32RES) + rm -f common.o vacuuming.o $(WIN32RES) rm -rf tmp_check export with_icu diff --git a/src/bin/scripts/meson.build b/src/bin/scripts/meson.build index 80df7c33257..a4fed59d1c9 100644 --- a/src/bin/scripts/meson.build +++ b/src/bin/scripts/meson.build @@ -12,7 +12,6 @@ binaries = [ 'createuser', 'dropuser', 'clusterdb', - 'vacuumdb', 'reindexdb', 'pg_isready', ] @@ -35,6 +34,33 @@ foreach binary : binaries bin_targets += binary endforeach +vacuuming_common = static_library('libvacuuming_common', + files('common.c', 'vacuuming.c'), + dependencies: [frontend_code, libpq], + kwargs: internal_lib_args, +) + +binaries = [ + 'vacuumdb', +] +foreach binary : binaries + binary_sources = files('@[email protected]'.format(binary)) + + if host_system == 'windows' + binary_sources += rc_bin_gen.process(win32ver_rc, extra_args: [ + '--NAME', binary, + '--FILEDESC', '@0@ - PostgreSQL utility'.format(binary),]) + endif + + binary = executable(binary, + binary_sources, + link_with: [vacuuming_common], + dependencies: [frontend_code, libpq], + kwargs: default_bin_args, + ) + bin_targets += binary +endforeach + tests += { 'name': 'scripts', 'sd': meson.current_source_dir(), diff --git a/src/bin/scripts/vacuumdb.c b/src/bin/scripts/vacuumdb.c index 6e30f223efe..00babc5c9c0 100644 --- a/src/bin/scripts/vacuumdb.c +++ b/src/bin/scripts/vacuumdb.c @@ -14,91 +14,13 @@ #include <limits.h> -#include "catalog/pg_attribute_d.h" -#include "catalog/pg_class_d.h" #include "common.h" -#include "common/connect.h" #include "common/logging.h" -#include "fe_utils/cancel.h" #include "fe_utils/option_utils.h" -#include "fe_utils/parallel_slot.h" -#include "fe_utils/query_utils.h" -#include "fe_utils/simple_list.h" -#include "fe_utils/string_utils.h" - - -/* vacuum options controlled by user flags */ -typedef struct vacuumingOptions -{ - bool analyze_only; - bool verbose; - bool and_analyze; - bool full; - bool freeze; - bool disable_page_skipping; - bool skip_locked; - int min_xid_age; - int min_mxid_age; - int parallel_workers; /* >= 0 indicates user specified the - * parallel degree, otherwise -1 */ - bool no_index_cleanup; - bool force_index_cleanup; - bool do_truncate; - bool process_main; - bool process_toast; - bool skip_database_stats; - char *buffer_usage_limit; - bool missing_stats_only; -} vacuumingOptions; - -/* object filter options */ -typedef enum -{ - OBJFILTER_NONE = 0, /* no filter used */ - OBJFILTER_ALL_DBS = (1 << 0), /* -a | --all */ - OBJFILTER_DATABASE = (1 << 1), /* -d | --dbname */ - OBJFILTER_TABLE = (1 << 2), /* -t | --table */ - OBJFILTER_SCHEMA = (1 << 3), /* -n | --schema */ - OBJFILTER_SCHEMA_EXCLUDE = (1 << 4), /* -N | --exclude-schema */ -} VacObjFilter; - -static VacObjFilter objfilter = OBJFILTER_NONE; - -static SimpleStringList *retrieve_objects(PGconn *conn, - vacuumingOptions *vacopts, - SimpleStringList *objects, - bool echo); - -static void vacuum_one_database(ConnParams *cparams, - vacuumingOptions *vacopts, - int stage, - SimpleStringList *objects, - SimpleStringList **found_objs, - int concurrentCons, - const char *progname, bool echo, bool quiet); - -static void vacuum_all_databases(ConnParams *cparams, - vacuumingOptions *vacopts, - bool analyze_in_stages, - SimpleStringList *objects, - int concurrentCons, - const char *progname, bool echo, bool quiet); - -static void prepare_vacuum_command(PQExpBuffer sql, int serverVersion, - vacuumingOptions *vacopts, const char *table); - -static void run_vacuum_command(PGconn *conn, const char *sql, bool echo, - const char *table); +#include "vacuuming.h" static void help(const char *progname); - -void check_objfilter(void); - -static char *escape_quotes(const char *src); - -/* For analyze-in-stages mode */ -#define ANALYZE_NO_STAGE -1 -#define ANALYZE_NUM_STAGES 3 +static void check_objfilter(VacObjFilter objfilter); int @@ -145,18 +67,16 @@ main(int argc, char *argv[]) int c; const char *dbname = NULL; const char *maintenance_db = NULL; - char *host = NULL; - char *port = NULL; - char *username = NULL; - enum trivalue prompt_password = TRI_DEFAULT; ConnParams cparams; bool echo = false; bool quiet = false; vacuumingOptions vacopts; bool analyze_in_stages = false; SimpleStringList objects = {NULL, NULL}; + VacObjFilter objfilter = OBJFILTER_NONE; int concurrentCons = 1; int tbl_count = 0; + int ret; /* initialize options */ memset(&vacopts, 0, sizeof(vacopts)); @@ -168,13 +88,18 @@ main(int argc, char *argv[]) vacopts.process_main = true; vacopts.process_toast = true; + /* the same for connection parameters */ + memset(&cparams, 0, sizeof(cparams)); + cparams.prompt_password = TRI_DEFAULT; + pg_logging_init(argv[0]); progname = get_progname(argv[0]); set_pglocale_pgservice(argv[0], PG_TEXTDOMAIN("pgscripts")); handle_help_version_opts(argc, argv, "vacuumdb", help); - while ((c = getopt_long(argc, argv, "ad:efFh:j:n:N:p:P:qt:U:vwWzZ", long_options, &optindex)) != -1) + while ((c = getopt_long(argc, argv, "ad:efFh:j:n:N:p:P:qt:U:vwWzZ", + long_options, &optindex)) != -1) { switch (c) { @@ -195,7 +120,7 @@ main(int argc, char *argv[]) vacopts.freeze = true; break; case 'h': - host = pg_strdup(optarg); + cparams.pghost = pg_strdup(optarg); break; case 'j': if (!option_parse_int(optarg, "-j/--jobs", 1, INT_MAX, @@ -211,7 +136,7 @@ main(int argc, char *argv[]) simple_string_list_append(&objects, optarg); break; case 'p': - port = pg_strdup(optarg); + cparams.pgport = pg_strdup(optarg); break; case 'P': if (!option_parse_int(optarg, "-P/--parallel", 0, INT_MAX, @@ -227,16 +152,16 @@ main(int argc, char *argv[]) tbl_count++; break; case 'U': - username = pg_strdup(optarg); + cparams.pguser = pg_strdup(optarg); break; case 'v': vacopts.verbose = true; break; case 'w': - prompt_password = TRI_NO; + cparams.prompt_password = TRI_NO; break; case 'W': - prompt_password = TRI_YES; + cparams.prompt_password = TRI_YES; break; case 'z': vacopts.and_analyze = true; @@ -317,7 +242,7 @@ main(int argc, char *argv[]) * Validate the combination of filters specified in the command-line * options. */ - check_objfilter(); + check_objfilter(objfilter); if (vacopts.analyze_only) { @@ -380,74 +305,18 @@ main(int argc, char *argv[]) pg_fatal("cannot use the \"%s\" option without \"%s\" or \"%s\"", "missing-stats-only", "analyze-only", "analyze-in-stages"); - /* fill cparams except for dbname, which is set below */ - cparams.pghost = host; - cparams.pgport = port; - cparams.pguser = username; - cparams.prompt_password = prompt_password; - cparams.override_dbname = NULL; - - setup_cancel_handler(NULL); - - /* Avoid opening extra connections. */ - if (tbl_count && (concurrentCons > tbl_count)) - concurrentCons = tbl_count; - - if (objfilter & OBJFILTER_ALL_DBS) - { - cparams.dbname = maintenance_db; - - vacuum_all_databases(&cparams, &vacopts, - analyze_in_stages, - &objects, - concurrentCons, - progname, echo, quiet); - } - else - { - if (dbname == NULL) - { - if (getenv("PGDATABASE")) - dbname = getenv("PGDATABASE"); - else if (getenv("PGUSER")) - dbname = getenv("PGUSER"); - else - dbname = get_user_name_or_exit(progname); - } - - cparams.dbname = dbname; - - if (analyze_in_stages) - { - int stage; - SimpleStringList *found_objs = NULL; - - for (stage = 0; stage < ANALYZE_NUM_STAGES; stage++) - { - vacuum_one_database(&cparams, &vacopts, - stage, - &objects, - vacopts.missing_stats_only ? &found_objs : NULL, - concurrentCons, - progname, echo, quiet); - } - } - else - vacuum_one_database(&cparams, &vacopts, - ANALYZE_NO_STAGE, - &objects, NULL, - concurrentCons, - progname, echo, quiet); - } - - exit(0); + ret = vacuuming_main(&cparams, dbname, maintenance_db, &vacopts, + objfilter, &objects, tbl_count, analyze_in_stages, + concurrentCons, + progname, echo, quiet); + exit(ret); } /* * Verify that the filters used at command line are compatible. */ void -check_objfilter(void) +check_objfilter(VacObjFilter objfilter) { if ((objfilter & OBJFILTER_ALL_DBS) && (objfilter & OBJFILTER_DATABASE)) @@ -466,886 +335,6 @@ check_objfilter(void) pg_fatal("cannot vacuum all tables in schema(s) and exclude schema(s) at the same time"); } -/* - * Returns a newly malloc'd version of 'src' with escaped single quotes and - * backslashes. - */ -static char * -escape_quotes(const char *src) -{ - char *result = escape_single_quotes_ascii(src); - - if (!result) - pg_fatal("out of memory"); - return result; -} - -/* - * vacuum_one_database - * - * Process tables in the given database. - * - * There are two ways to specify the list of objects to process: - * - * 1) The "found_objs" parameter is a double pointer to a fully qualified list - * of objects to process, as returned by a previous call to - * vacuum_one_database(). - * - * a) If both "found_objs" (the double pointer) and "*found_objs" (the - * once-dereferenced double pointer) are not NULL, this list takes - * priority, and anything specified in "objects" is ignored. - * - * b) If "found_objs" (the double pointer) is not NULL but "*found_objs" - * (the once-dereferenced double pointer) _is_ NULL, the "objects" - * parameter takes priority, and the results of the catalog query - * described in (2) are stored in "found_objs". - * - * c) If "found_objs" (the double pointer) is NULL, the "objects" - * parameter again takes priority, and the results of the catalog query - * are not saved. - * - * 2) The "objects" parameter is a user-specified list of objects to process. - * When (1b) or (1c) applies, this function performs a catalog query to - * retrieve a fully qualified list of objects to process, as described - * below. - * - * a) If "objects" is not NULL, the catalog query gathers only the objects - * listed in "objects". - * - * b) If "objects" is NULL, all tables in the database are gathered. - * - * Note that this function is only concerned with running exactly one stage - * when in analyze-in-stages mode; caller must iterate on us if necessary. - * - * If concurrentCons is > 1, multiple connections are used to vacuum tables - * in parallel. - */ -static void -vacuum_one_database(ConnParams *cparams, - vacuumingOptions *vacopts, - int stage, - SimpleStringList *objects, - SimpleStringList **found_objs, - int concurrentCons, - const char *progname, bool echo, bool quiet) -{ - PQExpBufferData sql; - PGconn *conn; - SimpleStringListCell *cell; - ParallelSlotArray *sa; - int ntups = 0; - bool failed = false; - const char *initcmd; - SimpleStringList *ret = NULL; - const char *stage_commands[] = { - "SET default_statistics_target=1; SET vacuum_cost_delay=0;", - "SET default_statistics_target=10; RESET vacuum_cost_delay;", - "RESET default_statistics_target;" - }; - const char *stage_messages[] = { - gettext_noop("Generating minimal optimizer statistics (1 target)"), - gettext_noop("Generating medium optimizer statistics (10 targets)"), - gettext_noop("Generating default (full) optimizer statistics") - }; - - Assert(stage == ANALYZE_NO_STAGE || - (stage >= 0 && stage < ANALYZE_NUM_STAGES)); - - conn = connectDatabase(cparams, progname, echo, false, true); - - if (vacopts->disable_page_skipping && PQserverVersion(conn) < 90600) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "disable-page-skipping", "9.6"); - } - - if (vacopts->no_index_cleanup && PQserverVersion(conn) < 120000) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "no-index-cleanup", "12"); - } - - if (vacopts->force_index_cleanup && PQserverVersion(conn) < 120000) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "force-index-cleanup", "12"); - } - - if (!vacopts->do_truncate && PQserverVersion(conn) < 120000) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "no-truncate", "12"); - } - - if (!vacopts->process_main && PQserverVersion(conn) < 160000) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "no-process-main", "16"); - } - - if (!vacopts->process_toast && PQserverVersion(conn) < 140000) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "no-process-toast", "14"); - } - - if (vacopts->skip_locked && PQserverVersion(conn) < 120000) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "skip-locked", "12"); - } - - if (vacopts->min_xid_age != 0 && PQserverVersion(conn) < 90600) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "--min-xid-age", "9.6"); - } - - if (vacopts->min_mxid_age != 0 && PQserverVersion(conn) < 90600) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "--min-mxid-age", "9.6"); - } - - if (vacopts->parallel_workers >= 0 && PQserverVersion(conn) < 130000) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "--parallel", "13"); - } - - if (vacopts->buffer_usage_limit && PQserverVersion(conn) < 160000) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "--buffer-usage-limit", "16"); - } - - if (vacopts->missing_stats_only && PQserverVersion(conn) < 150000) - { - PQfinish(conn); - pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", - "--missing-stats-only", "15"); - } - - /* skip_database_stats is used automatically if server supports it */ - vacopts->skip_database_stats = (PQserverVersion(conn) >= 160000); - - if (!quiet) - { - if (stage != ANALYZE_NO_STAGE) - printf(_("%s: processing database \"%s\": %s\n"), - progname, PQdb(conn), _(stage_messages[stage])); - else - printf(_("%s: vacuuming database \"%s\"\n"), - progname, PQdb(conn)); - fflush(stdout); - } - - /* - * If the caller provided the results of a previous catalog query, just - * use that. Otherwise, run the catalog query ourselves and set the - * return variable if provided. - */ - if (found_objs && *found_objs) - ret = *found_objs; - else - { - ret = retrieve_objects(conn, vacopts, objects, echo); - if (found_objs) - *found_objs = ret; - } - - /* - * Count the number of objects in the catalog query result. If there are - * none, we are done. - */ - for (cell = ret ? ret->head : NULL; cell; cell = cell->next) - ntups++; - - if (ntups == 0) - { - PQfinish(conn); - return; - } - - /* - * Ensure concurrentCons is sane. If there are more connections than - * vacuumable relations, we don't need to use them all. - */ - if (concurrentCons > ntups) - concurrentCons = ntups; - if (concurrentCons <= 0) - concurrentCons = 1; - - /* - * All slots need to be prepared to run the appropriate analyze stage, if - * caller requested that mode. We have to prepare the initial connection - * ourselves before setting up the slots. - */ - if (stage == ANALYZE_NO_STAGE) - initcmd = NULL; - else - { - initcmd = stage_commands[stage]; - executeCommand(conn, initcmd, echo); - } - - /* - * Setup the database connections. We reuse the connection we already have - * for the first slot. If not in parallel mode, the first slot in the - * array contains the connection. - */ - sa = ParallelSlotsSetup(concurrentCons, cparams, progname, echo, initcmd); - ParallelSlotsAdoptConn(sa, conn); - - initPQExpBuffer(&sql); - - cell = ret->head; - do - { - const char *tabname = cell->val; - ParallelSlot *free_slot; - - if (CancelRequested) - { - failed = true; - goto finish; - } - - free_slot = ParallelSlotsGetIdle(sa, NULL); - if (!free_slot) - { - failed = true; - goto finish; - } - - prepare_vacuum_command(&sql, PQserverVersion(free_slot->connection), - vacopts, tabname); - - /* - * Execute the vacuum. All errors are handled in processQueryResult - * through ParallelSlotsGetIdle. - */ - ParallelSlotSetHandler(free_slot, TableCommandResultHandler, NULL); - run_vacuum_command(free_slot->connection, sql.data, - echo, tabname); - - cell = cell->next; - } while (cell != NULL); - - if (!ParallelSlotsWaitCompletion(sa)) - { - failed = true; - goto finish; - } - - /* If we used SKIP_DATABASE_STATS, mop up with ONLY_DATABASE_STATS */ - if (vacopts->skip_database_stats && stage == ANALYZE_NO_STAGE && - !vacopts->analyze_only) - { - const char *cmd = "VACUUM (ONLY_DATABASE_STATS);"; - ParallelSlot *free_slot = ParallelSlotsGetIdle(sa, NULL); - - if (!free_slot) - { - failed = true; - goto finish; - } - - ParallelSlotSetHandler(free_slot, TableCommandResultHandler, NULL); - run_vacuum_command(free_slot->connection, cmd, echo, NULL); - - if (!ParallelSlotsWaitCompletion(sa)) - failed = true; - } - -finish: - ParallelSlotsTerminate(sa); - pg_free(sa); - - termPQExpBuffer(&sql); - - if (failed) - exit(1); -} - -/* - * Prepare the list of tables to process by querying the catalogs. - * - * Since we execute the constructed query with the default search_path (which - * could be unsafe), everything in this query MUST be fully qualified. - * - * First, build a WITH clause for the catalog query if any tables were - * specified, with a set of values made of relation names and their optional - * set of columns. This is used to match any provided column lists with the - * generated qualified identifiers and to filter for the tables provided via - * --table. If a listed table does not exist, the catalog query will fail. - */ -static SimpleStringList * -retrieve_objects(PGconn *conn, vacuumingOptions *vacopts, - SimpleStringList *objects, bool echo) -{ - PQExpBufferData buf; - PQExpBufferData catalog_query; - PGresult *res; - SimpleStringListCell *cell; - SimpleStringList *found_objs = palloc0(sizeof(SimpleStringList)); - bool objects_listed = false; - - initPQExpBuffer(&catalog_query); - for (cell = objects ? objects->head : NULL; cell; cell = cell->next) - { - char *just_table = NULL; - const char *just_columns = NULL; - - if (!objects_listed) - { - appendPQExpBufferStr(&catalog_query, - "WITH listed_objects (object_oid, column_list) " - "AS (\n VALUES ("); - objects_listed = true; - } - else - appendPQExpBufferStr(&catalog_query, ",\n ("); - - if (objfilter & (OBJFILTER_SCHEMA | OBJFILTER_SCHEMA_EXCLUDE)) - { - appendStringLiteralConn(&catalog_query, cell->val, conn); - appendPQExpBufferStr(&catalog_query, "::pg_catalog.regnamespace, "); - } - - if (objfilter & OBJFILTER_TABLE) - { - /* - * Split relation and column names given by the user, this is used - * to feed the CTE with values on which are performed pre-run - * validity checks as well. For now these happen only on the - * relation name. - */ - splitTableColumnsSpec(cell->val, PQclientEncoding(conn), - &just_table, &just_columns); - - appendStringLiteralConn(&catalog_query, just_table, conn); - appendPQExpBufferStr(&catalog_query, "::pg_catalog.regclass, "); - } - - if (just_columns && just_columns[0] != '\0') - appendStringLiteralConn(&catalog_query, just_columns, conn); - else - appendPQExpBufferStr(&catalog_query, "NULL"); - - appendPQExpBufferStr(&catalog_query, "::pg_catalog.text)"); - - pg_free(just_table); - } - - /* Finish formatting the CTE */ - if (objects_listed) - appendPQExpBufferStr(&catalog_query, "\n)\n"); - - appendPQExpBufferStr(&catalog_query, "SELECT c.relname, ns.nspname"); - - if (objects_listed) - appendPQExpBufferStr(&catalog_query, ", listed_objects.column_list"); - - appendPQExpBufferStr(&catalog_query, - " FROM pg_catalog.pg_class c\n" - " JOIN pg_catalog.pg_namespace ns" - " ON c.relnamespace OPERATOR(pg_catalog.=) ns.oid\n" - " CROSS JOIN LATERAL (SELECT c.relkind IN (" - CppAsString2(RELKIND_PARTITIONED_TABLE) ", " - CppAsString2(RELKIND_PARTITIONED_INDEX) ")) as p (inherited)\n" - " LEFT JOIN pg_catalog.pg_class t" - " ON c.reltoastrelid OPERATOR(pg_catalog.=) t.oid\n"); - - /* - * Used to match the tables or schemas listed by the user, completing the - * JOIN clause. - */ - if (objects_listed) - { - appendPQExpBufferStr(&catalog_query, " LEFT JOIN listed_objects" - " ON listed_objects.object_oid" - " OPERATOR(pg_catalog.=) "); - - if (objfilter & OBJFILTER_TABLE) - appendPQExpBufferStr(&catalog_query, "c.oid\n"); - else - appendPQExpBufferStr(&catalog_query, "ns.oid\n"); - } - - /* - * Exclude temporary tables, beginning the WHERE clause. - */ - appendPQExpBufferStr(&catalog_query, - " WHERE c.relpersistence OPERATOR(pg_catalog.!=) " - CppAsString2(RELPERSISTENCE_TEMP) "\n"); - - /* - * Used to match the tables or schemas listed by the user, for the WHERE - * clause. - */ - if (objects_listed) - { - if (objfilter & OBJFILTER_SCHEMA_EXCLUDE) - appendPQExpBufferStr(&catalog_query, - " AND listed_objects.object_oid IS NULL\n"); - else - appendPQExpBufferStr(&catalog_query, - " AND listed_objects.object_oid IS NOT NULL\n"); - } - - /* - * If no tables were listed, filter for the relevant relation types. If - * tables were given via --table, don't bother filtering by relation type. - * Instead, let the server decide whether a given relation can be - * processed in which case the user will know about it. - */ - if ((objfilter & OBJFILTER_TABLE) == 0) - { - /* - * vacuumdb should generally follow the behavior of the underlying - * VACUUM and ANALYZE commands. If analyze_only is true, process - * regular tables, materialized views, and partitioned tables, just - * like ANALYZE (with no specific target tables) does. Otherwise, - * process only regular tables and materialized views, since VACUUM - * skips partitioned tables when no target tables are specified. - */ - if (vacopts->analyze_only) - appendPQExpBufferStr(&catalog_query, - " AND c.relkind OPERATOR(pg_catalog.=) ANY (array[" - CppAsString2(RELKIND_RELATION) ", " - CppAsString2(RELKIND_MATVIEW) ", " - CppAsString2(RELKIND_PARTITIONED_TABLE) "])\n"); - else - appendPQExpBufferStr(&catalog_query, - " AND c.relkind OPERATOR(pg_catalog.=) ANY (array[" - CppAsString2(RELKIND_RELATION) ", " - CppAsString2(RELKIND_MATVIEW) "])\n"); - - } - - /* - * For --min-xid-age and --min-mxid-age, the age of the relation is the - * greatest of the ages of the main relation and its associated TOAST - * table. The commands generated by vacuumdb will also process the TOAST - * table for the relation if necessary, so it does not need to be - * considered separately. - */ - if (vacopts->min_xid_age != 0) - { - appendPQExpBuffer(&catalog_query, - " AND GREATEST(pg_catalog.age(c.relfrozenxid)," - " pg_catalog.age(t.relfrozenxid)) " - " OPERATOR(pg_catalog.>=) '%d'::pg_catalog.int4\n" - " AND c.relfrozenxid OPERATOR(pg_catalog.!=)" - " '0'::pg_catalog.xid\n", - vacopts->min_xid_age); - } - - if (vacopts->min_mxid_age != 0) - { - appendPQExpBuffer(&catalog_query, - " AND GREATEST(pg_catalog.mxid_age(c.relminmxid)," - " pg_catalog.mxid_age(t.relminmxid)) OPERATOR(pg_catalog.>=)" - " '%d'::pg_catalog.int4\n" - " AND c.relminmxid OPERATOR(pg_catalog.!=)" - " '0'::pg_catalog.xid\n", - vacopts->min_mxid_age); - } - - if (vacopts->missing_stats_only) - { - appendPQExpBufferStr(&catalog_query, " AND (\n"); - - /* regular stats */ - appendPQExpBufferStr(&catalog_query, - " EXISTS (SELECT NULL FROM pg_catalog.pg_attribute a\n" - " WHERE a.attrelid OPERATOR(pg_catalog.=) c.oid\n" - " AND a.attnum OPERATOR(pg_catalog.>) 0::pg_catalog.int2\n" - " AND NOT a.attisdropped\n" - " AND a.attstattarget IS DISTINCT FROM 0::pg_catalog.int2\n" - " AND a.attgenerated OPERATOR(pg_catalog.<>) " - CppAsString2(ATTRIBUTE_GENERATED_VIRTUAL) "\n" - " AND NOT EXISTS (SELECT NULL FROM pg_catalog.pg_statistic s\n" - " WHERE s.starelid OPERATOR(pg_catalog.=) a.attrelid\n" - " AND s.staattnum OPERATOR(pg_catalog.=) a.attnum\n" - " AND s.stainherit OPERATOR(pg_catalog.=) p.inherited))\n"); - - /* extended stats */ - appendPQExpBufferStr(&catalog_query, - " OR EXISTS (SELECT NULL FROM pg_catalog.pg_statistic_ext e\n" - " WHERE e.stxrelid OPERATOR(pg_catalog.=) c.oid\n" - " AND e.stxstattarget IS DISTINCT FROM 0::pg_catalog.int2\n" - " AND NOT EXISTS (SELECT NULL FROM pg_catalog.pg_statistic_ext_data d\n" - " WHERE d.stxoid OPERATOR(pg_catalog.=) e.oid\n" - " AND d.stxdinherit OPERATOR(pg_catalog.=) p.inherited))\n"); - - /* expression indexes */ - appendPQExpBufferStr(&catalog_query, - " OR EXISTS (SELECT NULL FROM pg_catalog.pg_attribute a\n" - " JOIN pg_catalog.pg_index i" - " ON i.indexrelid OPERATOR(pg_catalog.=) a.attrelid\n" - " WHERE i.indrelid OPERATOR(pg_catalog.=) c.oid\n" - " AND i.indkey[a.attnum OPERATOR(pg_catalog.-) 1::pg_catalog.int2]" - " OPERATOR(pg_catalog.=) 0::pg_catalog.int2\n" - " AND a.attnum OPERATOR(pg_catalog.>) 0::pg_catalog.int2\n" - " AND NOT a.attisdropped\n" - " AND a.attstattarget IS DISTINCT FROM 0::pg_catalog.int2\n" - " AND NOT EXISTS (SELECT NULL FROM pg_catalog.pg_statistic s\n" - " WHERE s.starelid OPERATOR(pg_catalog.=) a.attrelid\n" - " AND s.staattnum OPERATOR(pg_catalog.=) a.attnum\n" - " AND s.stainherit OPERATOR(pg_catalog.=) p.inherited))\n"); - - /* inheritance and regular stats */ - appendPQExpBufferStr(&catalog_query, - " OR EXISTS (SELECT NULL FROM pg_catalog.pg_attribute a\n" - " WHERE a.attrelid OPERATOR(pg_catalog.=) c.oid\n" - " AND a.attnum OPERATOR(pg_catalog.>) 0::pg_catalog.int2\n" - " AND NOT a.attisdropped\n" - " AND a.attstattarget IS DISTINCT FROM 0::pg_catalog.int2\n" - " AND a.attgenerated OPERATOR(pg_catalog.<>) " - CppAsString2(ATTRIBUTE_GENERATED_VIRTUAL) "\n" - " AND c.relhassubclass\n" - " AND NOT p.inherited\n" - " AND EXISTS (SELECT NULL FROM pg_catalog.pg_inherits h\n" - " WHERE h.inhparent OPERATOR(pg_catalog.=) c.oid)\n" - " AND NOT EXISTS (SELECT NULL FROM pg_catalog.pg_statistic s\n" - " WHERE s.starelid OPERATOR(pg_catalog.=) a.attrelid\n" - " AND s.staattnum OPERATOR(pg_catalog.=) a.attnum\n" - " AND s.stainherit))\n"); - - /* inheritance and extended stats */ - appendPQExpBufferStr(&catalog_query, - " OR EXISTS (SELECT NULL FROM pg_catalog.pg_statistic_ext e\n" - " WHERE e.stxrelid OPERATOR(pg_catalog.=) c.oid\n" - " AND e.stxstattarget IS DISTINCT FROM 0::pg_catalog.int2\n" - " AND c.relhassubclass\n" - " AND NOT p.inherited\n" - " AND EXISTS (SELECT NULL FROM pg_catalog.pg_inherits h\n" - " WHERE h.inhparent OPERATOR(pg_catalog.=) c.oid)\n" - " AND NOT EXISTS (SELECT NULL FROM pg_catalog.pg_statistic_ext_data d\n" - " WHERE d.stxoid OPERATOR(pg_catalog.=) e.oid\n" - " AND d.stxdinherit))\n"); - - appendPQExpBufferStr(&catalog_query, " )\n"); - } - - /* - * Execute the catalog query. We use the default search_path for this - * query for consistency with table lookups done elsewhere by the user. - */ - appendPQExpBufferStr(&catalog_query, " ORDER BY c.relpages DESC;"); - executeCommand(conn, "RESET search_path;", echo); - res = executeQuery(conn, catalog_query.data, echo); - termPQExpBuffer(&catalog_query); - PQclear(executeQuery(conn, ALWAYS_SECURE_SEARCH_PATH_SQL, echo)); - - /* - * Build qualified identifiers for each table, including the column list - * if given. - */ - initPQExpBuffer(&buf); - for (int i = 0; i < PQntuples(res); i++) - { - appendPQExpBufferStr(&buf, - fmtQualifiedIdEnc(PQgetvalue(res, i, 1), - PQgetvalue(res, i, 0), - PQclientEncoding(conn))); - - if (objects_listed && !PQgetisnull(res, i, 2)) - appendPQExpBufferStr(&buf, PQgetvalue(res, i, 2)); - - simple_string_list_append(found_objs, buf.data); - resetPQExpBuffer(&buf); - } - termPQExpBuffer(&buf); - PQclear(res); - - return found_objs; -} - -/* - * Vacuum/analyze all connectable databases. - * - * In analyze-in-stages mode, we process all databases in one stage before - * moving on to the next stage. That ensure minimal stats are available - * quickly everywhere before generating more detailed ones. - */ -static void -vacuum_all_databases(ConnParams *cparams, - vacuumingOptions *vacopts, - bool analyze_in_stages, - SimpleStringList *objects, - int concurrentCons, - const char *progname, bool echo, bool quiet) -{ - PGconn *conn; - PGresult *result; - int stage; - int i; - - conn = connectMaintenanceDatabase(cparams, progname, echo); - result = executeQuery(conn, - "SELECT datname FROM pg_database WHERE datallowconn AND datconnlimit <> -2 ORDER BY 1;", - echo); - PQfinish(conn); - - if (analyze_in_stages) - { - SimpleStringList **found_objs = NULL; - - if (vacopts->missing_stats_only) - found_objs = palloc0(PQntuples(result) * sizeof(SimpleStringList *)); - - /* - * When analyzing all databases in stages, we analyze them all in the - * fastest stage first, so that initial statistics become available - * for all of them as soon as possible. - * - * This means we establish several times as many connections, but - * that's a secondary consideration. - */ - for (stage = 0; stage < ANALYZE_NUM_STAGES; stage++) - { - for (i = 0; i < PQntuples(result); i++) - { - cparams->override_dbname = PQgetvalue(result, i, 0); - - vacuum_one_database(cparams, vacopts, - stage, - objects, - vacopts->missing_stats_only ? &found_objs[i] : NULL, - concurrentCons, - progname, echo, quiet); - } - } - } - else - { - for (i = 0; i < PQntuples(result); i++) - { - cparams->override_dbname = PQgetvalue(result, i, 0); - - vacuum_one_database(cparams, vacopts, - ANALYZE_NO_STAGE, - objects, NULL, - concurrentCons, - progname, echo, quiet); - } - } - - PQclear(result); -} - -/* - * Construct a vacuum/analyze command to run based on the given options, in the - * given string buffer, which may contain previous garbage. - * - * The table name used must be already properly quoted. The command generated - * depends on the server version involved and it is semicolon-terminated. - */ -static void -prepare_vacuum_command(PQExpBuffer sql, int serverVersion, - vacuumingOptions *vacopts, const char *table) -{ - const char *paren = " ("; - const char *comma = ", "; - const char *sep = paren; - - resetPQExpBuffer(sql); - - if (vacopts->analyze_only) - { - appendPQExpBufferStr(sql, "ANALYZE"); - - /* parenthesized grammar of ANALYZE is supported since v11 */ - if (serverVersion >= 110000) - { - if (vacopts->skip_locked) - { - /* SKIP_LOCKED is supported since v12 */ - Assert(serverVersion >= 120000); - appendPQExpBuffer(sql, "%sSKIP_LOCKED", sep); - sep = comma; - } - if (vacopts->verbose) - { - appendPQExpBuffer(sql, "%sVERBOSE", sep); - sep = comma; - } - if (vacopts->buffer_usage_limit) - { - Assert(serverVersion >= 160000); - appendPQExpBuffer(sql, "%sBUFFER_USAGE_LIMIT '%s'", sep, - vacopts->buffer_usage_limit); - sep = comma; - } - if (sep != paren) - appendPQExpBufferChar(sql, ')'); - } - else - { - if (vacopts->verbose) - appendPQExpBufferStr(sql, " VERBOSE"); - } - } - else - { - appendPQExpBufferStr(sql, "VACUUM"); - - /* parenthesized grammar of VACUUM is supported since v9.0 */ - if (serverVersion >= 90000) - { - if (vacopts->disable_page_skipping) - { - /* DISABLE_PAGE_SKIPPING is supported since v9.6 */ - Assert(serverVersion >= 90600); - appendPQExpBuffer(sql, "%sDISABLE_PAGE_SKIPPING", sep); - sep = comma; - } - if (vacopts->no_index_cleanup) - { - /* "INDEX_CLEANUP FALSE" has been supported since v12 */ - Assert(serverVersion >= 120000); - Assert(!vacopts->force_index_cleanup); - appendPQExpBuffer(sql, "%sINDEX_CLEANUP FALSE", sep); - sep = comma; - } - if (vacopts->force_index_cleanup) - { - /* "INDEX_CLEANUP TRUE" has been supported since v12 */ - Assert(serverVersion >= 120000); - Assert(!vacopts->no_index_cleanup); - appendPQExpBuffer(sql, "%sINDEX_CLEANUP TRUE", sep); - sep = comma; - } - if (!vacopts->do_truncate) - { - /* TRUNCATE is supported since v12 */ - Assert(serverVersion >= 120000); - appendPQExpBuffer(sql, "%sTRUNCATE FALSE", sep); - sep = comma; - } - if (!vacopts->process_main) - { - /* PROCESS_MAIN is supported since v16 */ - Assert(serverVersion >= 160000); - appendPQExpBuffer(sql, "%sPROCESS_MAIN FALSE", sep); - sep = comma; - } - if (!vacopts->process_toast) - { - /* PROCESS_TOAST is supported since v14 */ - Assert(serverVersion >= 140000); - appendPQExpBuffer(sql, "%sPROCESS_TOAST FALSE", sep); - sep = comma; - } - if (vacopts->skip_database_stats) - { - /* SKIP_DATABASE_STATS is supported since v16 */ - Assert(serverVersion >= 160000); - appendPQExpBuffer(sql, "%sSKIP_DATABASE_STATS", sep); - sep = comma; - } - if (vacopts->skip_locked) - { - /* SKIP_LOCKED is supported since v12 */ - Assert(serverVersion >= 120000); - appendPQExpBuffer(sql, "%sSKIP_LOCKED", sep); - sep = comma; - } - if (vacopts->full) - { - appendPQExpBuffer(sql, "%sFULL", sep); - sep = comma; - } - if (vacopts->freeze) - { - appendPQExpBuffer(sql, "%sFREEZE", sep); - sep = comma; - } - if (vacopts->verbose) - { - appendPQExpBuffer(sql, "%sVERBOSE", sep); - sep = comma; - } - if (vacopts->and_analyze) - { - appendPQExpBuffer(sql, "%sANALYZE", sep); - sep = comma; - } - if (vacopts->parallel_workers >= 0) - { - /* PARALLEL is supported since v13 */ - Assert(serverVersion >= 130000); - appendPQExpBuffer(sql, "%sPARALLEL %d", sep, - vacopts->parallel_workers); - sep = comma; - } - if (vacopts->buffer_usage_limit) - { - Assert(serverVersion >= 160000); - appendPQExpBuffer(sql, "%sBUFFER_USAGE_LIMIT '%s'", sep, - vacopts->buffer_usage_limit); - sep = comma; - } - if (sep != paren) - appendPQExpBufferChar(sql, ')'); - } - else - { - if (vacopts->full) - appendPQExpBufferStr(sql, " FULL"); - if (vacopts->freeze) - appendPQExpBufferStr(sql, " FREEZE"); - if (vacopts->verbose) - appendPQExpBufferStr(sql, " VERBOSE"); - if (vacopts->and_analyze) - appendPQExpBufferStr(sql, " ANALYZE"); - } - } - - appendPQExpBuffer(sql, " %s;", table); -} - -/* - * Send a vacuum/analyze command to the server, returning after sending the - * command. - * - * Any errors during command execution are reported to stderr. - */ -static void -run_vacuum_command(PGconn *conn, const char *sql, bool echo, - const char *table) -{ - bool status; - - if (echo) - printf("%s\n", sql); - - status = PQsendQuery(conn, sql) == 1; - - if (!status) - { - if (table) - pg_log_error("vacuuming of table \"%s\" in database \"%s\" failed: %s", - table, PQdb(conn), PQerrorMessage(conn)); - else - pg_log_error("vacuuming of database \"%s\" failed: %s", - PQdb(conn), PQerrorMessage(conn)); - } -} static void help(const char *progname) diff --git a/src/bin/scripts/vacuuming.c b/src/bin/scripts/vacuuming.c new file mode 100644 index 00000000000..b9f2e507557 --- /dev/null +++ b/src/bin/scripts/vacuuming.c @@ -0,0 +1,1012 @@ +/*------------------------------------------------------------------------- + * vacuuming.c + * Helper routines for vacuumdb + * + * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/bin/scripts/vacuuming.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres_fe.h" + +#include "catalog/pg_attribute_d.h" +#include "catalog/pg_class_d.h" +#include "common/connect.h" +#include "common/logging.h" +#include "fe_utils/cancel.h" +#include "fe_utils/option_utils.h" +#include "fe_utils/parallel_slot.h" +#include "fe_utils/query_utils.h" +#include "fe_utils/string_utils.h" +#include "vacuuming.h" + + +static int vacuum_one_database(ConnParams *cparams, + vacuumingOptions *vacopts, + int stage, + VacObjFilter objfilter, + SimpleStringList *objects, + SimpleStringList **found_objs, + int concurrentCons, + const char *progname, bool echo, bool quiet); +static int vacuum_all_databases(ConnParams *cparams, + vacuumingOptions *vacopts, + bool analyze_in_stages, + VacObjFilter objfilter, + SimpleStringList *objects, + int concurrentCons, + const char *progname, bool echo, bool quiet); +static SimpleStringList *retrieve_objects(PGconn *conn, + vacuumingOptions *vacopts, + VacObjFilter objfilter, + SimpleStringList *objects, + bool echo); +static void prepare_vacuum_command(PGconn *conn, PQExpBuffer sql, + vacuumingOptions *vacopts, const char *table); +static void run_vacuum_command(PGconn *conn, const char *sql, bool echo, + const char *table); + +/* + * Executes vacuum/analyze as indicated, or dies in case of failure. + */ +int +vacuuming_main(ConnParams *cparams, const char *dbname, + const char *maintenance_db, vacuumingOptions *vacopts, + VacObjFilter objfilter, SimpleStringList *objects, + int tbl_count, bool analyze_in_stages, int concurrentCons, + const char *progname, bool echo, bool quiet) +{ + setup_cancel_handler(NULL); + + /* Avoid opening extra connections. */ + if (tbl_count && (concurrentCons > tbl_count)) + concurrentCons = tbl_count; + + if (objfilter & OBJFILTER_ALL_DBS) + { + cparams->dbname = maintenance_db; + + return vacuum_all_databases(cparams, vacopts, + analyze_in_stages, + objfilter, objects, + concurrentCons, + progname, echo, quiet); + } + else + { + if (dbname == NULL) + { + if (getenv("PGDATABASE")) + dbname = getenv("PGDATABASE"); + else if (getenv("PGUSER")) + dbname = getenv("PGUSER"); + else + dbname = get_user_name_or_exit(progname); + } + + cparams->dbname = dbname; + + if (analyze_in_stages) + { + SimpleStringList *found_objs = NULL; + + for (int stage = 0; stage < ANALYZE_NUM_STAGES; stage++) + { + int ret; + + ret = vacuum_one_database(cparams, vacopts, + stage, + objfilter, objects, + vacopts->missing_stats_only ? &found_objs : NULL, + concurrentCons, + progname, echo, quiet); + if (ret != 0) + return ret; + } + + return EXIT_SUCCESS; + } + else + return vacuum_one_database(cparams, vacopts, + ANALYZE_NO_STAGE, + objfilter, objects, NULL, + concurrentCons, + progname, echo, quiet); + } +} + + +/* + * vacuum_one_database + * + * Process tables in the given database. + * + * There are two ways to specify the list of objects to process: + * + * 1) The "found_objs" parameter is a double pointer to a fully qualified list + * of objects to process, as returned by a previous call to + * vacuum_one_database(). + * + * a) If both "found_objs" (the double pointer) and "*found_objs" (the + * once-dereferenced double pointer) are not NULL, this list takes + * priority, and anything specified in "objects" is ignored. + * + * b) If "found_objs" (the double pointer) is not NULL but "*found_objs" + * (the once-dereferenced double pointer) _is_ NULL, the "objects" + * parameter takes priority, and the results of the catalog query + * described in (2) are stored in "found_objs". + * + * c) If "found_objs" (the double pointer) is NULL, the "objects" + * parameter again takes priority, and the results of the catalog query + * are not saved. + * + * 2) The "objects" parameter is a user-specified list of objects to process. + * When (1b) or (1c) applies, this function performs a catalog query to + * retrieve a fully qualified list of objects to process, as described + * below. + * + * a) If "objects" is not NULL, the catalog query gathers only the objects + * listed in "objects". + * + * b) If "objects" is NULL, all tables in the database are gathered. + * + * Note that this function is only concerned with running exactly one stage + * when in analyze-in-stages mode; caller must iterate on us if necessary. + * + * If concurrentCons is > 1, multiple connections are used to vacuum tables + * in parallel. + */ +static int +vacuum_one_database(ConnParams *cparams, + vacuumingOptions *vacopts, + int stage, + VacObjFilter objfilter, SimpleStringList *objects, + SimpleStringList **found_objs, + int concurrentCons, + const char *progname, bool echo, bool quiet) +{ + PQExpBufferData sql; + PGconn *conn; + SimpleStringListCell *cell; + ParallelSlotArray *sa; + int ntups = 0; + const char *initcmd; + SimpleStringList *retobjs = NULL; + int ret = EXIT_SUCCESS; + const char *stage_commands[] = { + "SET default_statistics_target=1; SET vacuum_cost_delay=0;", + "SET default_statistics_target=10; RESET vacuum_cost_delay;", + "RESET default_statistics_target;" + }; + const char *stage_messages[] = { + gettext_noop("Generating minimal optimizer statistics (1 target)"), + gettext_noop("Generating medium optimizer statistics (10 targets)"), + gettext_noop("Generating default (full) optimizer statistics") + }; + + Assert(stage == ANALYZE_NO_STAGE || + (stage >= 0 && stage < ANALYZE_NUM_STAGES)); + + conn = connectDatabase(cparams, progname, echo, false, true); + + if (vacopts->disable_page_skipping && PQserverVersion(conn) < 90600) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "disable-page-skipping", "9.6"); + } + + if (vacopts->no_index_cleanup && PQserverVersion(conn) < 120000) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "no-index-cleanup", "12"); + } + + if (vacopts->force_index_cleanup && PQserverVersion(conn) < 120000) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "force-index-cleanup", "12"); + } + + if (!vacopts->do_truncate && PQserverVersion(conn) < 120000) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "no-truncate", "12"); + } + + if (!vacopts->process_main && PQserverVersion(conn) < 160000) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "no-process-main", "16"); + } + + if (!vacopts->process_toast && PQserverVersion(conn) < 140000) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "no-process-toast", "14"); + } + + if (vacopts->skip_locked && PQserverVersion(conn) < 120000) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "skip-locked", "12"); + } + + if (vacopts->min_xid_age != 0 && PQserverVersion(conn) < 90600) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "--min-xid-age", "9.6"); + } + + if (vacopts->min_mxid_age != 0 && PQserverVersion(conn) < 90600) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "--min-mxid-age", "9.6"); + } + + if (vacopts->parallel_workers >= 0 && PQserverVersion(conn) < 130000) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "--parallel", "13"); + } + + if (vacopts->buffer_usage_limit && PQserverVersion(conn) < 160000) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "--buffer-usage-limit", "16"); + } + + if (vacopts->missing_stats_only && PQserverVersion(conn) < 150000) + { + PQfinish(conn); + pg_fatal("cannot use the \"%s\" option on server versions older than PostgreSQL %s", + "--missing-stats-only", "15"); + } + + /* skip_database_stats is used automatically if server supports it */ + vacopts->skip_database_stats = (PQserverVersion(conn) >= 160000); + + if (!quiet) + { + if (stage != ANALYZE_NO_STAGE) + printf(_("%s: processing database \"%s\": %s\n"), + progname, PQdb(conn), _(stage_messages[stage])); + else + printf(_("%s: vacuuming database \"%s\"\n"), + progname, PQdb(conn)); + fflush(stdout); + } + + /* + * If the caller provided the results of a previous catalog query, just + * use that. Otherwise, run the catalog query ourselves and set the + * return variable if provided. + */ + if (found_objs && *found_objs) + retobjs = *found_objs; + else + { + retobjs = retrieve_objects(conn, vacopts, objfilter, objects, echo); + if (found_objs) + *found_objs = retobjs; + } + + /* + * Count the number of objects in the catalog query result. If there are + * none, we are done. + */ + for (cell = retobjs ? retobjs->head : NULL; cell; cell = cell->next) + ntups++; + + if (ntups == 0) + { + PQfinish(conn); + return EXIT_SUCCESS; + } + + /* + * Ensure concurrentCons is sane. If there are more connections than + * vacuumable relations, we don't need to use them all. + */ + if (concurrentCons > ntups) + concurrentCons = ntups; + if (concurrentCons <= 0) + concurrentCons = 1; + + /* + * All slots need to be prepared to run the appropriate analyze stage, if + * caller requested that mode. We have to prepare the initial connection + * ourselves before setting up the slots. + */ + if (stage == ANALYZE_NO_STAGE) + initcmd = NULL; + else + { + initcmd = stage_commands[stage]; + executeCommand(conn, initcmd, echo); + } + + /* + * Setup the database connections. We reuse the connection we already have + * for the first slot. If not in parallel mode, the first slot in the + * array contains the connection. + */ + sa = ParallelSlotsSetup(concurrentCons, cparams, progname, echo, initcmd); + ParallelSlotsAdoptConn(sa, conn); + + initPQExpBuffer(&sql); + + cell = retobjs->head; + do + { + const char *tabname = cell->val; + ParallelSlot *free_slot; + + if (CancelRequested) + { + ret = EXIT_FAILURE; + goto finish; + } + + free_slot = ParallelSlotsGetIdle(sa, NULL); + if (!free_slot) + { + ret = EXIT_FAILURE; + goto finish; + } + + prepare_vacuum_command(free_slot->connection, &sql, + vacopts, tabname); + + /* + * Execute the vacuum. All errors are handled in processQueryResult + * through ParallelSlotsGetIdle. + */ + ParallelSlotSetHandler(free_slot, TableCommandResultHandler, NULL); + run_vacuum_command(free_slot->connection, sql.data, + echo, tabname); + + cell = cell->next; + } while (cell != NULL); + + if (!ParallelSlotsWaitCompletion(sa)) + { + ret = EXIT_FAILURE; + goto finish; + } + + /* If we used SKIP_DATABASE_STATS, mop up with ONLY_DATABASE_STATS */ + if (vacopts->skip_database_stats && stage == ANALYZE_NO_STAGE && + !vacopts->analyze_only) + { + const char *cmd = "VACUUM (ONLY_DATABASE_STATS);"; + ParallelSlot *free_slot = ParallelSlotsGetIdle(sa, NULL); + + if (!free_slot) + { + ret = EXIT_FAILURE; + goto finish; + } + + ParallelSlotSetHandler(free_slot, TableCommandResultHandler, NULL); + run_vacuum_command(free_slot->connection, cmd, echo, NULL); + + if (!ParallelSlotsWaitCompletion(sa)) + ret = EXIT_FAILURE; + } + +finish: + ParallelSlotsTerminate(sa); + pg_free(sa); + + termPQExpBuffer(&sql); + + return ret; +} + +/* + * Vacuum/analyze all connectable databases. + * + * In analyze-in-stages mode, we process all databases in one stage before + * moving on to the next stage. That ensure minimal stats are available + * quickly everywhere before generating more detailed ones. + */ +static int +vacuum_all_databases(ConnParams *cparams, + vacuumingOptions *vacopts, + bool analyze_in_stages, + VacObjFilter objfilter, + SimpleStringList *objects, + int concurrentCons, + const char *progname, bool echo, bool quiet) +{ + PGconn *conn; + PGresult *result; + + conn = connectMaintenanceDatabase(cparams, progname, echo); + result = executeQuery(conn, + "SELECT datname FROM pg_database WHERE datallowconn AND datconnlimit <> -2 ORDER BY 1;", + echo); + PQfinish(conn); + + if (analyze_in_stages) + { + SimpleStringList **found_objs = NULL; + + if (vacopts->missing_stats_only) + found_objs = palloc0(PQntuples(result) * sizeof(SimpleStringList *)); + + /* + * When analyzing all databases in stages, we analyze them all in the + * fastest stage first, so that initial statistics become available + * for all of them as soon as possible. + * + * This means we establish several times as many connections, but + * that's a secondary consideration. + */ + for (int stage = 0; stage < ANALYZE_NUM_STAGES; stage++) + { + for (int i = 0; i < PQntuples(result); i++) + { + int ret; + + cparams->override_dbname = PQgetvalue(result, i, 0); + ret = vacuum_one_database(cparams, vacopts, + stage, + objfilter, objects, + vacopts->missing_stats_only ? &found_objs[i] : NULL, + concurrentCons, + progname, echo, quiet); + if (ret != EXIT_SUCCESS) + return ret; + } + } + } + else + { + for (int i = 0; i < PQntuples(result); i++) + { + int ret; + + cparams->override_dbname = PQgetvalue(result, i, 0); + ret = vacuum_one_database(cparams, vacopts, + ANALYZE_NO_STAGE, + objfilter, objects, + NULL, + concurrentCons, + progname, echo, quiet); + if (ret != EXIT_SUCCESS) + return ret; + } + } + + PQclear(result); + + return EXIT_SUCCESS; +} + +/* + * Prepare the list of tables to process by querying the catalogs. + * + * Since we execute the constructed query with the default search_path (which + * could be unsafe), everything in this query MUST be fully qualified. + * + * First, build a WITH clause for the catalog query if any tables were + * specified, with a set of values made of relation names and their optional + * set of columns. This is used to match any provided column lists with the + * generated qualified identifiers and to filter for the tables provided via + * --table. If a listed table does not exist, the catalog query will fail. + */ +static SimpleStringList * +retrieve_objects(PGconn *conn, vacuumingOptions *vacopts, + VacObjFilter objfilter, SimpleStringList *objects, bool echo) +{ + PQExpBufferData buf; + PQExpBufferData catalog_query; + PGresult *res; + SimpleStringListCell *cell; + SimpleStringList *found_objs = palloc0(sizeof(SimpleStringList)); + bool objects_listed = false; + + initPQExpBuffer(&catalog_query); + for (cell = objects ? objects->head : NULL; cell; cell = cell->next) + { + char *just_table = NULL; + const char *just_columns = NULL; + + if (!objects_listed) + { + appendPQExpBufferStr(&catalog_query, + "WITH listed_objects (object_oid, column_list) AS (\n" + " VALUES ("); + objects_listed = true; + } + else + appendPQExpBufferStr(&catalog_query, ",\n ("); + + if (objfilter & (OBJFILTER_SCHEMA | OBJFILTER_SCHEMA_EXCLUDE)) + { + appendStringLiteralConn(&catalog_query, cell->val, conn); + appendPQExpBufferStr(&catalog_query, "::pg_catalog.regnamespace, "); + } + + if (objfilter & OBJFILTER_TABLE) + { + /* + * Split relation and column names given by the user, this is used + * to feed the CTE with values on which are performed pre-run + * validity checks as well. For now these happen only on the + * relation name. + */ + splitTableColumnsSpec(cell->val, PQclientEncoding(conn), + &just_table, &just_columns); + + appendStringLiteralConn(&catalog_query, just_table, conn); + appendPQExpBufferStr(&catalog_query, "::pg_catalog.regclass, "); + } + + if (just_columns && just_columns[0] != '\0') + appendStringLiteralConn(&catalog_query, just_columns, conn); + else + appendPQExpBufferStr(&catalog_query, "NULL"); + + appendPQExpBufferStr(&catalog_query, "::pg_catalog.text)"); + + pg_free(just_table); + } + + /* Finish formatting the CTE */ + if (objects_listed) + appendPQExpBufferStr(&catalog_query, "\n)\n"); + + appendPQExpBufferStr(&catalog_query, "SELECT c.relname, ns.nspname"); + + if (objects_listed) + appendPQExpBufferStr(&catalog_query, ", listed_objects.column_list"); + + appendPQExpBufferStr(&catalog_query, + " FROM pg_catalog.pg_class c\n" + " JOIN pg_catalog.pg_namespace ns" + " ON c.relnamespace OPERATOR(pg_catalog.=) ns.oid\n" + " CROSS JOIN LATERAL (SELECT c.relkind IN (" + CppAsString2(RELKIND_PARTITIONED_TABLE) ", " + CppAsString2(RELKIND_PARTITIONED_INDEX) ")) as p (inherited)\n" + " LEFT JOIN pg_catalog.pg_class t" + " ON c.reltoastrelid OPERATOR(pg_catalog.=) t.oid\n"); + + /* + * Used to match the tables or schemas listed by the user, completing the + * JOIN clause. + */ + if (objects_listed) + { + appendPQExpBufferStr(&catalog_query, " LEFT JOIN listed_objects" + " ON listed_objects.object_oid" + " OPERATOR(pg_catalog.=) "); + + if (objfilter & OBJFILTER_TABLE) + appendPQExpBufferStr(&catalog_query, "c.oid\n"); + else + appendPQExpBufferStr(&catalog_query, "ns.oid\n"); + } + + /* + * Exclude temporary tables, beginning the WHERE clause. + */ + appendPQExpBufferStr(&catalog_query, + " WHERE c.relpersistence OPERATOR(pg_catalog.!=) " + CppAsString2(RELPERSISTENCE_TEMP) "\n"); + + /* + * Used to match the tables or schemas listed by the user, for the WHERE + * clause. + */ + if (objects_listed) + { + if (objfilter & OBJFILTER_SCHEMA_EXCLUDE) + appendPQExpBufferStr(&catalog_query, + " AND listed_objects.object_oid IS NULL\n"); + else + appendPQExpBufferStr(&catalog_query, + " AND listed_objects.object_oid IS NOT NULL\n"); + } + + /* + * If no tables were listed, filter for the relevant relation types. If + * tables were given via --table, don't bother filtering by relation type. + * Instead, let the server decide whether a given relation can be + * processed in which case the user will know about it. + */ + if ((objfilter & OBJFILTER_TABLE) == 0) + { + /* + * vacuumdb should generally follow the behavior of the underlying + * VACUUM and ANALYZE commands. If analyze_only is true, process + * regular tables, materialized views, and partitioned tables, just + * like ANALYZE (with no specific target tables) does. Otherwise, + * process only regular tables and materialized views, since VACUUM + * skips partitioned tables when no target tables are specified. + */ + if (vacopts->analyze_only) + appendPQExpBufferStr(&catalog_query, + " AND c.relkind OPERATOR(pg_catalog.=) ANY (array[" + CppAsString2(RELKIND_RELATION) ", " + CppAsString2(RELKIND_MATVIEW) ", " + CppAsString2(RELKIND_PARTITIONED_TABLE) "])\n"); + else + appendPQExpBufferStr(&catalog_query, + " AND c.relkind OPERATOR(pg_catalog.=) ANY (array[" + CppAsString2(RELKIND_RELATION) ", " + CppAsString2(RELKIND_MATVIEW) "])\n"); + } + + /* + * For --min-xid-age and --min-mxid-age, the age of the relation is the + * greatest of the ages of the main relation and its associated TOAST + * table. The commands generated by vacuumdb will also process the TOAST + * table for the relation if necessary, so it does not need to be + * considered separately. + */ + if (vacopts->min_xid_age != 0) + { + appendPQExpBuffer(&catalog_query, + " AND GREATEST(pg_catalog.age(c.relfrozenxid)," + " pg_catalog.age(t.relfrozenxid)) " + " OPERATOR(pg_catalog.>=) '%d'::pg_catalog.int4\n" + " AND c.relfrozenxid OPERATOR(pg_catalog.!=)" + " '0'::pg_catalog.xid\n", + vacopts->min_xid_age); + } + + if (vacopts->min_mxid_age != 0) + { + appendPQExpBuffer(&catalog_query, + " AND GREATEST(pg_catalog.mxid_age(c.relminmxid)," + " pg_catalog.mxid_age(t.relminmxid)) OPERATOR(pg_catalog.>=)" + " '%d'::pg_catalog.int4\n" + " AND c.relminmxid OPERATOR(pg_catalog.!=)" + " '0'::pg_catalog.xid\n", + vacopts->min_mxid_age); + } + + if (vacopts->missing_stats_only) + { + appendPQExpBufferStr(&catalog_query, " AND (\n"); + + /* regular stats */ + appendPQExpBufferStr(&catalog_query, + " EXISTS (SELECT NULL FROM pg_catalog.pg_attribute a\n" + " WHERE a.attrelid OPERATOR(pg_catalog.=) c.oid\n" + " AND a.attnum OPERATOR(pg_catalog.>) 0::pg_catalog.int2\n" + " AND NOT a.attisdropped\n" + " AND a.attstattarget IS DISTINCT FROM 0::pg_catalog.int2\n" + " AND a.attgenerated OPERATOR(pg_catalog.<>) " + CppAsString2(ATTRIBUTE_GENERATED_VIRTUAL) "\n" + " AND NOT EXISTS (SELECT NULL FROM pg_catalog.pg_statistic s\n" + " WHERE s.starelid OPERATOR(pg_catalog.=) a.attrelid\n" + " AND s.staattnum OPERATOR(pg_catalog.=) a.attnum\n" + " AND s.stainherit OPERATOR(pg_catalog.=) p.inherited))\n"); + + /* extended stats */ + appendPQExpBufferStr(&catalog_query, + " OR EXISTS (SELECT NULL FROM pg_catalog.pg_statistic_ext e\n" + " WHERE e.stxrelid OPERATOR(pg_catalog.=) c.oid\n" + " AND e.stxstattarget IS DISTINCT FROM 0::pg_catalog.int2\n" + " AND NOT EXISTS (SELECT NULL FROM pg_catalog.pg_statistic_ext_data d\n" + " WHERE d.stxoid OPERATOR(pg_catalog.=) e.oid\n" + " AND d.stxdinherit OPERATOR(pg_catalog.=) p.inherited))\n"); + + /* expression indexes */ + appendPQExpBufferStr(&catalog_query, + " OR EXISTS (SELECT NULL FROM pg_catalog.pg_attribute a\n" + " JOIN pg_catalog.pg_index i" + " ON i.indexrelid OPERATOR(pg_catalog.=) a.attrelid\n" + " WHERE i.indrelid OPERATOR(pg_catalog.=) c.oid\n" + " AND i.indkey[a.attnum OPERATOR(pg_catalog.-) 1::pg_catalog.int2]" + " OPERATOR(pg_catalog.=) 0::pg_catalog.int2\n" + " AND a.attnum OPERATOR(pg_catalog.>) 0::pg_catalog.int2\n" + " AND NOT a.attisdropped\n" + " AND a.attstattarget IS DISTINCT FROM 0::pg_catalog.int2\n" + " AND NOT EXISTS (SELECT NULL FROM pg_catalog.pg_statistic s\n" + " WHERE s.starelid OPERATOR(pg_catalog.=) a.attrelid\n" + " AND s.staattnum OPERATOR(pg_catalog.=) a.attnum\n" + " AND s.stainherit OPERATOR(pg_catalog.=) p.inherited))\n"); + + /* inheritance and regular stats */ + appendPQExpBufferStr(&catalog_query, + " OR EXISTS (SELECT NULL FROM pg_catalog.pg_attribute a\n" + " WHERE a.attrelid OPERATOR(pg_catalog.=) c.oid\n" + " AND a.attnum OPERATOR(pg_catalog.>) 0::pg_catalog.int2\n" + " AND NOT a.attisdropped\n" + " AND a.attstattarget IS DISTINCT FROM 0::pg_catalog.int2\n" + " AND a.attgenerated OPERATOR(pg_catalog.<>) " + CppAsString2(ATTRIBUTE_GENERATED_VIRTUAL) "\n" + " AND c.relhassubclass\n" + " AND NOT p.inherited\n" + " AND EXISTS (SELECT NULL FROM pg_catalog.pg_inherits h\n" + " WHERE h.inhparent OPERATOR(pg_catalog.=) c.oid)\n" + " AND NOT EXISTS (SELECT NULL FROM pg_catalog.pg_statistic s\n" + " WHERE s.starelid OPERATOR(pg_catalog.=) a.attrelid\n" + " AND s.staattnum OPERATOR(pg_catalog.=) a.attnum\n" + " AND s.stainherit))\n"); + + /* inheritance and extended stats */ + appendPQExpBufferStr(&catalog_query, + " OR EXISTS (SELECT NULL FROM pg_catalog.pg_statistic_ext e\n" + " WHERE e.stxrelid OPERATOR(pg_catalog.=) c.oid\n" + " AND e.stxstattarget IS DISTINCT FROM 0::pg_catalog.int2\n" + " AND c.relhassubclass\n" + " AND NOT p.inherited\n" + " AND EXISTS (SELECT NULL FROM pg_catalog.pg_inherits h\n" + " WHERE h.inhparent OPERATOR(pg_catalog.=) c.oid)\n" + " AND NOT EXISTS (SELECT NULL FROM pg_catalog.pg_statistic_ext_data d\n" + " WHERE d.stxoid OPERATOR(pg_catalog.=) e.oid\n" + " AND d.stxdinherit))\n"); + + appendPQExpBufferStr(&catalog_query, " )\n"); + } + + /* + * Execute the catalog query. We use the default search_path for this + * query for consistency with table lookups done elsewhere by the user. + */ + appendPQExpBufferStr(&catalog_query, " ORDER BY c.relpages DESC;"); + executeCommand(conn, "RESET search_path;", echo); + res = executeQuery(conn, catalog_query.data, echo); + termPQExpBuffer(&catalog_query); + PQclear(executeQuery(conn, ALWAYS_SECURE_SEARCH_PATH_SQL, echo)); + + /* + * Build qualified identifiers for each table, including the column list + * if given. + */ + initPQExpBuffer(&buf); + for (int i = 0; i < PQntuples(res); i++) + { + appendPQExpBufferStr(&buf, + fmtQualifiedIdEnc(PQgetvalue(res, i, 1), + PQgetvalue(res, i, 0), + PQclientEncoding(conn))); + + if (objects_listed && !PQgetisnull(res, i, 2)) + appendPQExpBufferStr(&buf, PQgetvalue(res, i, 2)); + + simple_string_list_append(found_objs, buf.data); + resetPQExpBuffer(&buf); + } + termPQExpBuffer(&buf); + PQclear(res); + + return found_objs; +} + +/* + * Construct a vacuum/analyze command to run based on the given + * options, in the given string buffer, which may contain previous garbage. + * + * The table name used must be already properly quoted. The command generated + * depends on the server version involved and it is semicolon-terminated. + */ +static void +prepare_vacuum_command(PGconn *conn, PQExpBuffer sql, + vacuumingOptions *vacopts, const char *table) +{ + int serverVersion = PQserverVersion(conn); + const char *paren = " ("; + const char *comma = ", "; + const char *sep = paren; + + resetPQExpBuffer(sql); + + if (vacopts->analyze_only) + { + appendPQExpBufferStr(sql, "ANALYZE"); + + /* parenthesized grammar of ANALYZE is supported since v11 */ + if (serverVersion >= 110000) + { + if (vacopts->skip_locked) + { + /* SKIP_LOCKED is supported since v12 */ + Assert(serverVersion >= 120000); + appendPQExpBuffer(sql, "%sSKIP_LOCKED", sep); + sep = comma; + } + if (vacopts->verbose) + { + appendPQExpBuffer(sql, "%sVERBOSE", sep); + sep = comma; + } + if (vacopts->buffer_usage_limit) + { + Assert(serverVersion >= 160000); + appendPQExpBuffer(sql, "%sBUFFER_USAGE_LIMIT '%s'", sep, + vacopts->buffer_usage_limit); + sep = comma; + } + if (sep != paren) + appendPQExpBufferChar(sql, ')'); + } + else + { + if (vacopts->verbose) + appendPQExpBufferStr(sql, " VERBOSE"); + } + } + else + { + appendPQExpBufferStr(sql, "VACUUM"); + + /* parenthesized grammar of VACUUM is supported since v9.0 */ + if (serverVersion >= 90000) + { + if (vacopts->disable_page_skipping) + { + /* DISABLE_PAGE_SKIPPING is supported since v9.6 */ + Assert(serverVersion >= 90600); + appendPQExpBuffer(sql, "%sDISABLE_PAGE_SKIPPING", sep); + sep = comma; + } + if (vacopts->no_index_cleanup) + { + /* "INDEX_CLEANUP FALSE" has been supported since v12 */ + Assert(serverVersion >= 120000); + Assert(!vacopts->force_index_cleanup); + appendPQExpBuffer(sql, "%sINDEX_CLEANUP FALSE", sep); + sep = comma; + } + if (vacopts->force_index_cleanup) + { + /* "INDEX_CLEANUP TRUE" has been supported since v12 */ + Assert(serverVersion >= 120000); + Assert(!vacopts->no_index_cleanup); + appendPQExpBuffer(sql, "%sINDEX_CLEANUP TRUE", sep); + sep = comma; + } + if (!vacopts->do_truncate) + { + /* TRUNCATE is supported since v12 */ + Assert(serverVersion >= 120000); + appendPQExpBuffer(sql, "%sTRUNCATE FALSE", sep); + sep = comma; + } + if (!vacopts->process_main) + { + /* PROCESS_MAIN is supported since v16 */ + Assert(serverVersion >= 160000); + appendPQExpBuffer(sql, "%sPROCESS_MAIN FALSE", sep); + sep = comma; + } + if (!vacopts->process_toast) + { + /* PROCESS_TOAST is supported since v14 */ + Assert(serverVersion >= 140000); + appendPQExpBuffer(sql, "%sPROCESS_TOAST FALSE", sep); + sep = comma; + } + if (vacopts->skip_database_stats) + { + /* SKIP_DATABASE_STATS is supported since v16 */ + Assert(serverVersion >= 160000); + appendPQExpBuffer(sql, "%sSKIP_DATABASE_STATS", sep); + sep = comma; + } + if (vacopts->skip_locked) + { + /* SKIP_LOCKED is supported since v12 */ + Assert(serverVersion >= 120000); + appendPQExpBuffer(sql, "%sSKIP_LOCKED", sep); + sep = comma; + } + if (vacopts->full) + { + appendPQExpBuffer(sql, "%sFULL", sep); + sep = comma; + } + if (vacopts->freeze) + { + appendPQExpBuffer(sql, "%sFREEZE", sep); + sep = comma; + } + if (vacopts->verbose) + { + appendPQExpBuffer(sql, "%sVERBOSE", sep); + sep = comma; + } + if (vacopts->and_analyze) + { + appendPQExpBuffer(sql, "%sANALYZE", sep); + sep = comma; + } + if (vacopts->parallel_workers >= 0) + { + /* PARALLEL is supported since v13 */ + Assert(serverVersion >= 130000); + appendPQExpBuffer(sql, "%sPARALLEL %d", sep, + vacopts->parallel_workers); + sep = comma; + } + if (vacopts->buffer_usage_limit) + { + Assert(serverVersion >= 160000); + appendPQExpBuffer(sql, "%sBUFFER_USAGE_LIMIT '%s'", sep, + vacopts->buffer_usage_limit); + sep = comma; + } + if (sep != paren) + appendPQExpBufferChar(sql, ')'); + } + else + { + if (vacopts->full) + appendPQExpBufferStr(sql, " FULL"); + if (vacopts->freeze) + appendPQExpBufferStr(sql, " FREEZE"); + if (vacopts->verbose) + appendPQExpBufferStr(sql, " VERBOSE"); + if (vacopts->and_analyze) + appendPQExpBufferStr(sql, " ANALYZE"); + } + } + + appendPQExpBuffer(sql, " %s;", table); +} + +/* + * Send a vacuum/analyze command to the server, returning after sending the + * command. + * + * Any errors during command execution are reported to stderr. + */ +static void +run_vacuum_command(PGconn *conn, const char *sql, bool echo, + const char *table) +{ + bool status; + + if (echo) + printf("%s\n", sql); + + status = PQsendQuery(conn, sql) == 1; + + if (!status) + { + if (table) + { + pg_log_error("vacuuming of table \"%s\" in database \"%s\" failed: %s", + table, PQdb(conn), PQerrorMessage(conn)); + } + else + { + pg_log_error("vacuuming of database \"%s\" failed: %s", + PQdb(conn), PQerrorMessage(conn)); + } + } +} + +/* + * Returns a newly malloc'd version of 'src' with escaped single quotes and + * backslashes. + */ +char * +escape_quotes(const char *src) +{ + char *result = escape_single_quotes_ascii(src); + + if (!result) + pg_fatal("out of memory"); + return result; +} diff --git a/src/bin/scripts/vacuuming.h b/src/bin/scripts/vacuuming.h new file mode 100644 index 00000000000..021953e153a --- /dev/null +++ b/src/bin/scripts/vacuuming.h @@ -0,0 +1,68 @@ +/*------------------------------------------------------------------------- + * + * vacuuming.h + * Common declarations for vacuuming.c + * + * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/bin/scripts/vacuuming.h + * + *------------------------------------------------------------------------- + */ +#ifndef VACUUMING_H +#define VACUUMING_H + +#include "common.h" +#include "fe_utils/connect_utils.h" +#include "fe_utils/simple_list.h" + +/* For analyze-in-stages mode */ +#define ANALYZE_NO_STAGE -1 +#define ANALYZE_NUM_STAGES 3 + +/* vacuum options controlled by user flags */ +typedef struct vacuumingOptions +{ + bool analyze_only; + bool verbose; + bool and_analyze; + bool full; + bool freeze; + bool disable_page_skipping; + bool skip_locked; + int min_xid_age; + int min_mxid_age; + int parallel_workers; /* >= 0 indicates user specified the + * parallel degree, otherwise -1 */ + bool no_index_cleanup; + bool force_index_cleanup; + bool do_truncate; + bool process_main; + bool process_toast; + bool skip_database_stats; + char *buffer_usage_limit; + bool missing_stats_only; +} vacuumingOptions; + +/* object filter options */ +typedef enum +{ + OBJFILTER_NONE = 0, /* no filter used */ + OBJFILTER_ALL_DBS = (1 << 0), /* -a | --all */ + OBJFILTER_DATABASE = (1 << 1), /* -d | --dbname */ + OBJFILTER_TABLE = (1 << 2), /* -t | --table */ + OBJFILTER_SCHEMA = (1 << 3), /* -n | --schema */ + OBJFILTER_SCHEMA_EXCLUDE = (1 << 4), /* -N | --exclude-schema */ +} VacObjFilter; + +extern int vacuuming_main(ConnParams *cparams, const char *dbname, + const char *maintenance_db, vacuumingOptions *vacopts, + VacObjFilter objfilter, SimpleStringList *objects, + int tbl_count, bool analyze_in_stages, + int concurrentCons, + const char *progname, bool echo, bool quiet); + +extern char *escape_quotes(const char *src); + +#endif /* VACUUMING_H */ base-commit: e849bd551c323a384f2b14d20a1b7bfaa6127ed7 -- 2.47.3 --52vaejy5wnlkvc5v Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v22-0002-Add-REPACK-command.patch" ^ permalink raw reply [nested|flat] 2+ messages in thread
end of thread, other threads:[~2025-09-25 12:58 UTC | newest] Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-09-29 13:59 [PATCH v49 6/7] Remove the GUC stats_temp_directory Kyotaro Horiguchi <[email protected]> 2025-09-25 12:58 [PATCH v22 1/2] Split vacuumdb to create vacuuming.c/h Álvaro Herrera <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox