agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH 2/4] Syscache usage tracking feature. 176+ messages / 3 participants [nested] [flat]
* [PATCH 2/4] Syscache usage tracking feature. @ 2018-10-16 06:48 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Kyotaro Horiguchi @ 2018-10-16 06:48 UTC (permalink / raw) Collects syscache usage statictics and show it using the view pg_stat_syscache. The feature is controlled by the GUC variable track_syscache_usage_interval. --- doc/src/sgml/config.sgml | 15 ++ src/backend/catalog/system_views.sql | 17 +++ src/backend/postmaster/pgstat.c | 201 ++++++++++++++++++++++++-- src/backend/tcop/postgres.c | 23 +++ src/backend/utils/adt/pgstatfuncs.c | 134 +++++++++++++++++ src/backend/utils/cache/catcache.c | 115 +++++++++++---- src/backend/utils/cache/syscache.c | 24 +++ src/backend/utils/init/globals.c | 1 + src/backend/utils/init/postinit.c | 11 ++ src/backend/utils/misc/guc.c | 10 ++ src/backend/utils/misc/postgresql.conf.sample | 1 + src/include/catalog/pg_proc.dat | 9 ++ src/include/miscadmin.h | 1 + src/include/pgstat.h | 6 +- src/include/utils/catcache.h | 9 +- src/include/utils/syscache.h | 19 +++ src/include/utils/timeout.h | 1 + src/test/regress/expected/rules.out | 24 ++- 18 files changed, 576 insertions(+), 45 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d0d2374944..5ff3ebeb4e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -6687,6 +6687,21 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv; </listitem> </varlistentry> + <varlistentry id="guc-track-syscache-usage-interval" xreflabel="track_syscache_usage_interval"> + <term><varname>track_syscache_usage_interval</varname> (<type>integer</type>) + <indexterm> + <primary><varname>track_syscache_usage_interval</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the interval to collect system cache usage statistics in + milliseconds. This parameter is 0 by default, which means disabled. + Only superusers can change this setting. + </para> + </listitem> + </varlistentry> + <varlistentry id="guc-track-io-timing" xreflabel="track_io_timing"> <term><varname>track_io_timing</varname> (<type>boolean</type>) <indexterm> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 3e229c693c..f5d1aaf96f 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -906,6 +906,22 @@ CREATE VIEW pg_stat_progress_vacuum AS FROM pg_stat_get_progress_info('VACUUM') AS S LEFT JOIN pg_database D ON S.datid = D.oid; +CREATE VIEW pg_stat_syscache AS + SELECT + S.pid AS pid, + S.relid::regclass AS relname, + S.indid::regclass AS cache_name, + S.size AS size, + S.ntup AS ntuples, + S.searches AS searches, + S.hits AS hits, + S.neg_hits AS neg_hits, + S.ageclass AS ageclass, + S.last_update AS last_update + FROM pg_stat_activity A + JOIN LATERAL (SELECT A.pid, * FROM pg_get_syscache_stats(A.pid)) S + ON (A.pid = S.pid); + CREATE VIEW pg_user_mappings AS SELECT U.oid AS umid, @@ -1185,6 +1201,7 @@ GRANT EXECUTE ON FUNCTION pg_ls_waldir() TO pg_monitor; GRANT EXECUTE ON FUNCTION pg_ls_archive_statusdir() TO pg_monitor; GRANT EXECUTE ON FUNCTION pg_ls_tmpdir() TO pg_monitor; GRANT EXECUTE ON FUNCTION pg_ls_tmpdir(oid) TO pg_monitor; +GRANT EXECUTE ON FUNCTION pg_get_syscache_stats(int) TO pg_monitor; GRANT pg_read_all_settings TO pg_monitor; GRANT pg_read_all_stats TO pg_monitor; diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c index 81c6499251..a1939958b7 100644 --- a/src/backend/postmaster/pgstat.c +++ b/src/backend/postmaster/pgstat.c @@ -66,6 +66,7 @@ #include "utils/ps_status.h" #include "utils/rel.h" #include "utils/snapmgr.h" +#include "utils/syscache.h" #include "utils/timestamp.h" @@ -124,6 +125,7 @@ bool pgstat_track_activities = false; bool pgstat_track_counts = false; int pgstat_track_functions = TRACK_FUNC_OFF; +int pgstat_track_syscache_usage_interval = 0; int pgstat_track_activity_query_size = 1024; /* ---------- @@ -236,6 +238,11 @@ typedef struct TwoPhasePgStatRecord bool t_truncated; /* was the relation truncated? */ } TwoPhasePgStatRecord; +/* bitmap symbols to specify target file types remove */ +#define PGSTAT_REMFILE_DBSTAT 1 /* remove only databsae stats files */ +#define PGSTAT_REMFILE_SYSCACHE 2 /* remove only syscache stats files */ +#define PGSTAT_REMFILE_ALL 3 /* remove both type of files */ + /* * Info about current "snapshot" of stats file */ @@ -335,6 +342,7 @@ static void pgstat_recv_funcpurge(PgStat_MsgFuncpurge *msg, int len); static void pgstat_recv_recoveryconflict(PgStat_MsgRecoveryConflict *msg, int len); static void pgstat_recv_deadlock(PgStat_MsgDeadlock *msg, int len); static void pgstat_recv_tempfile(PgStat_MsgTempFile *msg, int len); +static void pgstat_remove_syscache_statsfile(void); /* ------------------------------------------------------------ * Public functions called from postmaster follow @@ -630,10 +638,13 @@ startup_failed: } /* - * subroutine for pgstat_reset_all + * remove stats files + * + * clean up stats files in specified directory. target is one of + * PGSTAT_REFILE_DBSTAT/SYSCACHE/ALL and restricts files to remove. */ static void -pgstat_reset_remove_files(const char *directory) +pgstat_reset_remove_files(const char *directory, int target) { DIR *dir; struct dirent *entry; @@ -644,25 +655,39 @@ pgstat_reset_remove_files(const char *directory) { int nchars; Oid tmp_oid; + int filetype = 0; /* * Skip directory entries that don't match the file names we write. * See get_dbstat_filename for the database-specific pattern. */ if (strncmp(entry->d_name, "global.", 7) == 0) + { + filetype = PGSTAT_REMFILE_DBSTAT; nchars = 7; + } else { + char head[2]; + nchars = 0; - (void) sscanf(entry->d_name, "db_%u.%n", - &tmp_oid, &nchars); - if (nchars <= 0) - continue; + (void) sscanf(entry->d_name, "%c%c_%u.%n", + head, head + 1, &tmp_oid, &nchars); + /* %u allows leading whitespace, so reject that */ - if (strchr("0123456789", entry->d_name[3]) == NULL) + if (nchars < 3 || !isdigit(entry->d_name[3])) continue; + + if (strncmp(head, "db", 2) == 0) + filetype = PGSTAT_REMFILE_DBSTAT; + else if (strncmp(head, "cc", 2) == 0) + filetype = PGSTAT_REMFILE_SYSCACHE; } + /* skip if this is not a target */ + if ((filetype & target) == 0) + continue; + if (strcmp(entry->d_name + nchars, "tmp") != 0 && strcmp(entry->d_name + nchars, "stat") != 0) continue; @@ -683,8 +708,9 @@ pgstat_reset_remove_files(const char *directory) void pgstat_reset_all(void) { - pgstat_reset_remove_files(pgstat_stat_directory); - pgstat_reset_remove_files(PGSTAT_STAT_PERMANENT_DIRECTORY); + pgstat_reset_remove_files(pgstat_stat_directory, PGSTAT_REMFILE_ALL); + pgstat_reset_remove_files(PGSTAT_STAT_PERMANENT_DIRECTORY, + PGSTAT_REMFILE_ALL); } #ifdef EXEC_BACKEND @@ -2963,6 +2989,10 @@ pgstat_beshutdown_hook(int code, Datum arg) if (OidIsValid(MyDatabaseId)) pgstat_report_stat(true); + /* clear syscache statistics files and temprary settings */ + if (MyBackendId != InvalidBackendId) + pgstat_remove_syscache_statsfile(); + /* * Clear my status entry, following the protocol of bumping st_changecount * before and after. We use a volatile pointer here to ensure the @@ -4287,6 +4317,9 @@ PgstatCollectorMain(int argc, char *argv[]) pgStatRunningInCollector = true; pgStatDBHash = pgstat_read_statsfiles(InvalidOid, true, true); + /* Remove left-over syscache stats files */ + pgstat_reset_remove_files(pgstat_stat_directory, PGSTAT_REMFILE_SYSCACHE); + /* * Loop to process messages until we get SIGQUIT or detect ungraceful * death of our parent postmaster. @@ -6377,3 +6410,153 @@ pgstat_clip_activity(const char *raw_activity) return activity; } + +/* + * return the filename for a syscache stat file; filename is the output + * buffer, of length len. + */ +void +pgstat_get_syscachestat_filename(bool permanent, bool tempname, int backendid, + char *filename, int len) +{ + int printed; + + /* NB -- pgstat_reset_remove_files knows about the pattern this uses */ + printed = snprintf(filename, len, "%s/cc_%u.%s", + permanent ? PGSTAT_STAT_PERMANENT_DIRECTORY : + pgstat_stat_directory, + backendid, + tempname ? "tmp" : "stat"); + if (printed >= len) + elog(ERROR, "overlength pgstat path"); +} + +/* removes syscache stats files of this backend */ +static void +pgstat_remove_syscache_statsfile(void) +{ + char fname[MAXPGPATH]; + + pgstat_get_syscachestat_filename(false, false, MyBackendId, + fname, MAXPGPATH); + unlink(fname); /* don't care of the result */ +} + +/* + * pgstat_write_syscache_stats() - + * Write the syscache statistics files. + * + * If 'force' is false, this function skips writing a file and resturns the + * time remaining in the current interval in milliseconds. If'force' is true, + * writes a file regardless of the remaining time and reset the interval. + */ +long +pgstat_write_syscache_stats(bool force) +{ + static TimestampTz last_report = 0; + TimestampTz now; + long elapsed; + long secs; + int usecs; + int cacheId; + FILE *fpout; + char statfile[MAXPGPATH]; + char tmpfile[MAXPGPATH]; + + /* Return if we don't want it */ + if (!force && pgstat_track_syscache_usage_interval <= 0) + { + /* disabled. remove the statistics file if any */ + if (last_report > 0) + { + last_report = 0; + pgstat_remove_syscache_statsfile(); + } + return 0; + } + + /* Check aginst the interval */ + now = GetCurrentTransactionStopTimestamp(); + TimestampDifference(last_report, now, &secs, &usecs); + elapsed = secs * 1000 + usecs / 1000; + + if (!force && elapsed < pgstat_track_syscache_usage_interval) + { + /* not yet the time, inform the remaining time to the caller */ + return pgstat_track_syscache_usage_interval - elapsed; + } + + /* now update the stats */ + last_report = now; + + pgstat_get_syscachestat_filename(false, true, + MyBackendId, tmpfile, MAXPGPATH); + pgstat_get_syscachestat_filename(false, false, + MyBackendId, statfile, MAXPGPATH); + + /* + * This function can be called from ProcessInterrupts(). Inhibit recursive + * interrupts to avoid recursive entry. + */ + HOLD_INTERRUPTS(); + + fpout = AllocateFile(tmpfile, PG_BINARY_W); + if (fpout == NULL) + { + ereport(LOG, + (errcode_for_file_access(), + errmsg("could not open temporary statistics file \"%s\": %m", + tmpfile))); + /* + * Failure writing this file is not critical. Just skip this time and + * tell caller to wait for the next interval. + */ + RESUME_INTERRUPTS(); + return pgstat_track_syscache_usage_interval; + } + + /* write out every catcache stats */ + for (cacheId = 0 ; cacheId < SysCacheSize ; cacheId++) + { + SysCacheStats *stats; + + stats = SysCacheGetStats(cacheId); + Assert (stats); + + /* write error is checked later using ferror() */ + fputc('T', fpout); + (void)fwrite(&cacheId, sizeof(int), 1, fpout); + (void)fwrite(&last_report, sizeof(TimestampTz), 1, fpout); + (void)fwrite(stats, sizeof(*stats), 1, fpout); + } + fputc('E', fpout); + + if (ferror(fpout)) + { + ereport(LOG, + (errcode_for_file_access(), + errmsg("could not write syscache statistics file \"%s\": %m", + tmpfile))); + FreeFile(fpout); + unlink(tmpfile); + } + else if (FreeFile(fpout) < 0) + { + ereport(LOG, + (errcode_for_file_access(), + errmsg("could not close syscache statistics file \"%s\": %m", + tmpfile))); + unlink(tmpfile); + } + else if (rename(tmpfile, statfile) < 0) + { + ereport(LOG, + (errcode_for_file_access(), + errmsg("could not rename syscache statistics file \"%s\" to \"%s\": %m", + tmpfile, statfile))); + unlink(tmpfile); + } + + RESUME_INTERRUPTS(); + return 0; +} diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c index 36cfd507b2..fb77a0ce4c 100644 --- a/src/backend/tcop/postgres.c +++ b/src/backend/tcop/postgres.c @@ -3157,6 +3157,12 @@ ProcessInterrupts(void) } + if (IdleSyscacheStatsUpdateTimeoutPending) + { + IdleSyscacheStatsUpdateTimeoutPending = false; + pgstat_write_syscache_stats(true); + } + if (ParallelMessagePending) HandleParallelMessages(); } @@ -3733,6 +3739,7 @@ PostgresMain(int argc, char *argv[], sigjmp_buf local_sigjmp_buf; volatile bool send_ready_for_query = true; bool disable_idle_in_transaction_timeout = false; + bool disable_idle_catcache_update_timeout = false; /* Initialize startup process environment if necessary. */ if (!IsUnderPostmaster) @@ -4173,9 +4180,19 @@ PostgresMain(int argc, char *argv[], } else { + long timeout; + ProcessCompletedNotifies(); pgstat_report_stat(false); + timeout = pgstat_write_syscache_stats(false); + + if (timeout > 0) + { + disable_idle_catcache_update_timeout = true; + enable_timeout_after(IDLE_CATCACHE_UPDATE_TIMEOUT, + timeout); + } set_ps_display("idle", false); pgstat_report_activity(STATE_IDLE, NULL); } @@ -4218,6 +4235,12 @@ PostgresMain(int argc, char *argv[], disable_idle_in_transaction_timeout = false; } + if (disable_idle_catcache_update_timeout) + { + disable_timeout(IDLE_CATCACHE_UPDATE_TIMEOUT, false); + disable_idle_catcache_update_timeout = false; + } + /* * (6) check for any other interesting events that happened while we * slept. diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index b6ba856ebe..6526cfefb4 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -14,6 +14,8 @@ */ #include "postgres.h" +#include <sys/stat.h> + #include "access/htup_details.h" #include "catalog/pg_authid.h" #include "catalog/pg_type.h" @@ -28,6 +30,7 @@ #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inet.h" +#include "utils/syscache.h" #include "utils/timestamp.h" #define UINT32_ACCESS_ONCE(var) ((uint32)(*((volatile uint32 *)&(var)))) @@ -1899,3 +1902,134 @@ pg_stat_get_archiver(PG_FUNCTION_ARGS) PG_RETURN_DATUM(HeapTupleGetDatum( heap_form_tuple(tupdesc, values, nulls))); } + +Datum +pgstat_get_syscache_stats(PG_FUNCTION_ARGS) +{ +#define PG_GET_SYSCACHE_SIZE 9 + int pid = PG_GETARG_INT32(0); + ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; + TupleDesc tupdesc; + Tuplestorestate *tupstore; + MemoryContext per_query_ctx; + MemoryContext oldcontext; + PgBackendStatus *beentry; + int beid; + char fname[MAXPGPATH]; + FILE *fpin; + char c; + + if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("set-valued function called in context that cannot accept a set"))); + if (!(rsinfo->allowedModes & SFRM_Materialize)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("materialize mode required, but it is not " \ + "allowed in this context"))); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + + per_query_ctx = rsinfo->econtext->ecxt_per_query_memory; + + oldcontext = MemoryContextSwitchTo(per_query_ctx); + tupstore = tuplestore_begin_heap(true, false, work_mem); + rsinfo->returnMode = SFRM_Materialize; + rsinfo->setResult = tupstore; + rsinfo->setDesc = tupdesc; + + MemoryContextSwitchTo(oldcontext); + + /* find beentry for given pid*/ + beentry = NULL; + for (beid = 1; + (beentry = pgstat_fetch_stat_beentry(beid)) && + beentry->st_procpid != pid ; + beid++); + + /* + * we silently return empty result on failure or insufficient privileges + */ + if (!beentry || + (!has_privs_of_role(GetUserId(), beentry->st_userid) && + !is_member_of_role(GetUserId(), DEFAULT_ROLE_READ_ALL_STATS))) + goto no_data; + + pgstat_get_syscachestat_filename(false, false, beid, fname, MAXPGPATH); + + if ((fpin = AllocateFile(fname, PG_BINARY_R)) == NULL) + { + if (errno != ENOENT) + ereport(WARNING, + (errcode_for_file_access(), + errmsg("could not open statistics file \"%s\": %m", + fname))); + /* also return empty on no statistics file */ + goto no_data; + } + + /* read the statistics file into tuplestore */ + while ((c = fgetc(fpin)) == 'T') + { + TimestampTz last_update; + SysCacheStats stats; + int cacheid; + Datum values[PG_GET_SYSCACHE_SIZE]; + bool nulls[PG_GET_SYSCACHE_SIZE] = {0}; + Datum datums[SYSCACHE_STATS_NAGECLASSES * 2]; + bool arrnulls[SYSCACHE_STATS_NAGECLASSES * 2] = {0}; + int dims[] = {SYSCACHE_STATS_NAGECLASSES, 2}; + int lbs[] = {1, 1}; + ArrayType *arr; + int i, j; + + fread(&cacheid, sizeof(int), 1, fpin); + fread(&last_update, sizeof(TimestampTz), 1, fpin); + if (fread(&stats, 1, sizeof(stats), fpin) != sizeof(stats)) + { + ereport(WARNING, + (errmsg("corrupted syscache statistics file \"%s\"", + fname))); + goto no_data; + } + + i = 0; + values[i++] = ObjectIdGetDatum(stats.reloid); + values[i++] = ObjectIdGetDatum(stats.indoid); + values[i++] = Int64GetDatum(stats.size); + values[i++] = Int64GetDatum(stats.ntuples); + values[i++] = Int64GetDatum(stats.nsearches); + values[i++] = Int64GetDatum(stats.nhits); + values[i++] = Int64GetDatum(stats.nneg_hits); + + for (j = 0 ; j < SYSCACHE_STATS_NAGECLASSES ; j++) + { + datums[j * 2] = Int32GetDatum((int32) stats.ageclasses[j]); + datums[j * 2 + 1] = Int32GetDatum((int32) stats.nclass_entries[j]); + } + + arr = construct_md_array(datums, arrnulls, 2, dims, lbs, + INT4OID, sizeof(int32), true, 'i'); + values[i++] = PointerGetDatum(arr); + + values[i++] = TimestampTzGetDatum(last_update); + + Assert (i == PG_GET_SYSCACHE_SIZE); + + tuplestore_putvalues(tupstore, tupdesc, values, nulls); + } + + /* check for the end of file. abandon the result if file is broken */ + if (c != 'E' || fgetc(fpin) != EOF) + tuplestore_clear(tupstore); + + FreeFile(fpin); + +no_data: + tuplestore_donestoring(tupstore); + return (Datum) 0; +} diff --git a/src/backend/utils/cache/catcache.c b/src/backend/utils/cache/catcache.c index 769e173844..1da1589a5d 100644 --- a/src/backend/utils/cache/catcache.c +++ b/src/backend/utils/cache/catcache.c @@ -89,6 +89,10 @@ static CatCacheHeader *CacheHdr = NULL; /* Timestamp used for any operation on caches. */ TimestampTz catcacheclock = 0; +/* age classes for pruning */ +static double ageclass[SYSCACHE_STATS_NAGECLASSES] + = {0.05, 0.1, 1.0, 2.0, 3.0, 0.0}; + static inline HeapTuple SearchCatCacheInternal(CatCache *cache, int nkeys, Datum v1, Datum v2, @@ -619,9 +623,7 @@ CatCacheInvalidate(CatCache *cache, uint32 hashValue) else CatCacheRemoveCTup(cache, ct); CACHE1_elog(DEBUG2, "CatCacheInvalidate: invalidated"); -#ifdef CATCACHE_STATS cache->cc_invals++; -#endif /* could be multiple matches, so keep looking! */ } } @@ -697,9 +699,7 @@ ResetCatalogCache(CatCache *cache) } else CatCacheRemoveCTup(cache, ct); -#ifdef CATCACHE_STATS cache->cc_invals++; -#endif } } } @@ -906,10 +906,11 @@ CatCacheCleanupOldEntries(CatCache *cp) * cache_prune_min_age. The index of nremoved_entry is the value of the * clock-sweep counter, which takes from 0 up to 2. */ - double ageclass[] = {0.05, 0.1, 1.0, 2.0, 3.0, 0.0}; - int nentries[] = {0, 0, 0, 0, 0, 0}; + int nentries[SYSCACHE_STATS_NAGECLASSES] = {0, 0, 0, 0, 0, 0}; int nremoved_entry[3] = {0, 0, 0}; int j; + + Assert(ageclass[SYSCACHE_STATS_NAGECLASSES - 1] == 0.0); #endif /* Return immediately if no pruning is wanted */ @@ -923,7 +924,11 @@ CatCacheCleanupOldEntries(CatCache *cp) if (hash_size + cp->cc_tupsize < (Size) cache_memory_target * 1024L) return false; - /* Search the whole hash for entries to remove */ + /* + * Search the whole hash for entries to remove. This is a quite time + * consuming task during catcache lookup, but accetable since now we are + * going to expand the hash table. + */ for (i = 0; i < cp->cc_nbuckets; i++) { dlist_mutable_iter iter; @@ -936,21 +941,21 @@ CatCacheCleanupOldEntries(CatCache *cp) /* - * Calculate the duration from the time of the last access to the - * "current" time. Since catcacheclock is not advanced within a - * transaction, the entries that are accessed within the current - * transaction won't be pruned. + * Calculate the duration from the time from the last access to + * the "current" time. Since catcacheclock is not advanced within + * a transaction, the entries that are accessed within the current + * transaction always get 0 as the result. */ TimestampDifference(ct->lastaccess, catcacheclock, &entry_age, &us); #ifdef CATCACHE_STATS /* count catcache entries for each age class */ ntotal++; - for (j = 0 ; - ageclass[j] != 0.0 && - entry_age > cache_prune_min_age * ageclass[j] ; - j++); - if (ageclass[j] == 0.0) j--; + + j = 0; + while (j < SYSCACHE_STATS_NAGECLASSES - 1 && + entry_age > cache_prune_min_age * ageclass[j]) + j++; nentries[j]++; #endif @@ -981,14 +986,17 @@ CatCacheCleanupOldEntries(CatCache *cp) } #ifdef CATCACHE_STATS + StaticAssertStmt(SYSCACHE_STATS_NAGECLASSES == 6, + "number of syscache age class must be 6"); ereport(DEBUG1, - (errmsg ("removed %d/%d, age(-%.0fs:%d, -%.0fs:%d, *-%.0fs:%d, -%.0fs:%d, -%.0fs:%d) naccessed(0:%d, 1:%d, 2:%d)", + (errmsg ("removed %d/%d, age(-%.0fs:%d, -%.0fs:%d, *-%.0fs:%d, -%.0fs:%d, -%.0fs:%d, rest:%d) naccessed(0:%d, 1:%d, 2:%d)", nremoved, ntotal, ageclass[0] * cache_prune_min_age, nentries[0], ageclass[1] * cache_prune_min_age, nentries[1], ageclass[2] * cache_prune_min_age, nentries[2], ageclass[3] * cache_prune_min_age, nentries[3], ageclass[4] * cache_prune_min_age, nentries[4], + nentries[5], nremoved_entry[0], nremoved_entry[1], nremoved_entry[2]), errhidestmt(true))); #endif @@ -1365,9 +1373,7 @@ SearchCatCacheInternal(CatCache *cache, if (unlikely(cache->cc_tupdesc == NULL)) CatalogCacheInitializeCache(cache); -#ifdef CATCACHE_STATS cache->cc_searches++; -#endif /* Initialize local parameter array */ arguments[0] = v1; @@ -1427,9 +1433,7 @@ SearchCatCacheInternal(CatCache *cache, CACHE3_elog(DEBUG2, "SearchCatCache(%s): found in bucket %d", cache->cc_relname, hashIndex); -#ifdef CATCACHE_STATS cache->cc_hits++; -#endif return &ct->tuple; } @@ -1438,9 +1442,7 @@ SearchCatCacheInternal(CatCache *cache, CACHE3_elog(DEBUG2, "SearchCatCache(%s): found neg entry in bucket %d", cache->cc_relname, hashIndex); -#ifdef CATCACHE_STATS cache->cc_neg_hits++; -#endif return NULL; } @@ -1568,9 +1570,7 @@ SearchCatCacheMiss(CatCache *cache, CACHE3_elog(DEBUG2, "SearchCatCache(%s): put in bucket %d", cache->cc_relname, hashIndex); -#ifdef CATCACHE_STATS cache->cc_newloads++; -#endif return &ct->tuple; } @@ -1681,9 +1681,7 @@ SearchCatCacheList(CatCache *cache, Assert(nkeys > 0 && nkeys < cache->cc_nkeys); -#ifdef CATCACHE_STATS cache->cc_lsearches++; -#endif /* Initialize local parameter array */ arguments[0] = v1; @@ -1740,9 +1738,7 @@ SearchCatCacheList(CatCache *cache, CACHE2_elog(DEBUG2, "SearchCatCacheList(%s): found list", cache->cc_relname); -#ifdef CATCACHE_STATS cache->cc_lhits++; -#endif return cl; } @@ -2250,3 +2246,64 @@ PrintCatCacheListLeakWarning(CatCList *list) list->my_cache->cc_relname, list->my_cache->id, list, list->refcount); } + +/* + * CatCacheGetStats - fill in SysCacheStats struct. + * + * This is a support routine for SysCacheGetStats, substantially fills in the + * result. The classification here is based on the same criteria to + * CatCacheCleanupOldEntries(). + */ +void +CatCacheGetStats(CatCache *cache, SysCacheStats *stats) +{ + int i, j; + + Assert(ageclass[SYSCACHE_STATS_NAGECLASSES - 1] == 0.0); + + /* fill in the stats struct */ + stats->size = cache->cc_tupsize + cache->cc_nbuckets * sizeof(dlist_head); + stats->ntuples = cache->cc_ntup; + stats->nsearches = cache->cc_searches; + stats->nhits = cache->cc_hits; + stats->nneg_hits = cache->cc_neg_hits; + + /* cache_prune_min_age can be changed on-session, fill it every time */ + for (i = 0 ; i < SYSCACHE_STATS_NAGECLASSES ; i++) + stats->ageclasses[i] = (int) (cache_prune_min_age * ageclass[i]); + + /* + * nth element in nclass_entries stores the number of cache entries that + * have lived unaccessed for corresponding multiple in ageclass of + * cache_prune_min_age. + */ + memset(stats->nclass_entries, 0, sizeof(int) * SYSCACHE_STATS_NAGECLASSES); + + /* Scan the whole hash */ + for (i = 0; i < cache->cc_nbuckets; i++) + { + dlist_mutable_iter iter; + + dlist_foreach_modify(iter, &cache->cc_bucket[i]) + { + CatCTup *ct = dlist_container(CatCTup, cache_elem, iter.cur); + long entry_age; + int us; + + /* + * Calculate the duration from the time from the last access to + * the "current" time. Since catcacheclock is not advanced within + * a transaction, the entries that are accessed within the current + * transaction won't be pruned. + */ + TimestampDifference(ct->lastaccess, catcacheclock, &entry_age, &us); + + j = 0; + while (j < SYSCACHE_STATS_NAGECLASSES - 1 && + entry_age > stats->ageclasses[j]) + j++; + + stats->nclass_entries[j]++; + } + } +} diff --git a/src/backend/utils/cache/syscache.c b/src/backend/utils/cache/syscache.c index ac98c19155..7b38a06708 100644 --- a/src/backend/utils/cache/syscache.c +++ b/src/backend/utils/cache/syscache.c @@ -20,6 +20,9 @@ */ #include "postgres.h" +#include <sys/stat.h> +#include <unistd.h> + #include "access/htup_details.h" #include "access/sysattr.h" #include "catalog/indexing.h" @@ -1534,6 +1537,27 @@ RelationSupportsSysCache(Oid relid) return false; } +/* + * SysCacheGetStats - returns stats of specified syscache + * + * This routine returns the address of its local static memory. + */ +SysCacheStats * +SysCacheGetStats(int cacheId) +{ + static SysCacheStats stats; + + Assert(cacheId >=0 && cacheId < SysCacheSize); + + memset(&stats, 0, sizeof(stats)); + + stats.reloid = cacheinfo[cacheId].reloid; + stats.indoid = cacheinfo[cacheId].indoid; + + CatCacheGetStats(SysCache[cacheId], &stats); + + return &stats; +} /* * OID comparator for pg_qsort diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c index fd51934aaf..f039ecd805 100644 --- a/src/backend/utils/init/globals.c +++ b/src/backend/utils/init/globals.c @@ -32,6 +32,7 @@ volatile sig_atomic_t QueryCancelPending = false; volatile sig_atomic_t ProcDiePending = false; volatile sig_atomic_t ClientConnectionLost = false; volatile sig_atomic_t IdleInTransactionSessionTimeoutPending = false; +volatile sig_atomic_t IdleSyscacheStatsUpdateTimeoutPending = false; volatile sig_atomic_t ConfigReloadPending = false; volatile uint32 InterruptHoldoffCount = 0; volatile uint32 QueryCancelHoldoffCount = 0; diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c index c0b6231458..dee7f19475 100644 --- a/src/backend/utils/init/postinit.c +++ b/src/backend/utils/init/postinit.c @@ -72,6 +72,7 @@ static void ShutdownPostgres(int code, Datum arg); static void StatementTimeoutHandler(void); static void LockTimeoutHandler(void); static void IdleInTransactionSessionTimeoutHandler(void); +static void IdleSyscacheStatsUpdateTimeoutHandler(void); static bool ThereIsAtLeastOneRole(void); static void process_startup_options(Port *port, bool am_superuser); static void process_settings(Oid databaseid, Oid roleid); @@ -628,6 +629,8 @@ InitPostgres(const char *in_dbname, Oid dboid, const char *username, RegisterTimeout(LOCK_TIMEOUT, LockTimeoutHandler); RegisterTimeout(IDLE_IN_TRANSACTION_SESSION_TIMEOUT, IdleInTransactionSessionTimeoutHandler); + RegisterTimeout(IDLE_CATCACHE_UPDATE_TIMEOUT, + IdleSyscacheStatsUpdateTimeoutHandler); } /* @@ -1239,6 +1242,14 @@ IdleInTransactionSessionTimeoutHandler(void) SetLatch(MyLatch); } +static void +IdleSyscacheStatsUpdateTimeoutHandler(void) +{ + IdleSyscacheStatsUpdateTimeoutPending = true; + InterruptPending = true; + SetLatch(MyLatch); +} + /* * Returns true if at least one role is defined in this database cluster. */ diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c index 06c589f725..32e41253a6 100644 --- a/src/backend/utils/misc/guc.c +++ b/src/backend/utils/misc/guc.c @@ -3168,6 +3168,16 @@ static struct config_int ConfigureNamesInt[] = NULL, NULL, NULL }, + { + {"track_syscache_usage_interval", PGC_SUSET, STATS_COLLECTOR, + gettext_noop("Sets the interval between syscache usage collection, in milliseconds. Zero disables syscache usage tracking."), + NULL + }, + &pgstat_track_syscache_usage_interval, + 0, 0, INT_MAX / 2, + NULL, NULL, NULL + }, + { {"gin_pending_list_limit", PGC_USERSET, CLIENT_CONN_STATEMENT, gettext_noop("Sets the maximum size of the pending list for GIN index."), diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 108d332f2c..4d4fb42251 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -560,6 +560,7 @@ #track_io_timing = off #track_functions = none # none, pl, all #track_activity_query_size = 1024 # (change requires restart) +#track_syscache_usage_interval = 0 # zero disables tracking #stats_temp_directory = 'pg_stat_tmp' diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index b8de13f03b..6099a828d2 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -9669,6 +9669,15 @@ proargmodes => '{o,o,o,o,o,o,o,o,o,o,o}', proargnames => '{slot_name,plugin,slot_type,datoid,temporary,active,active_pid,xmin,catalog_xmin,restart_lsn,confirmed_flush_lsn}', prosrc => 'pg_get_replication_slots' }, +{ oid => '3425', + descr => 'syscache statistics', + proname => 'pg_get_syscache_stats', prorows => '100', proisstrict => 'f', + proretset => 't', provolatile => 'v', prorettype => 'record', + proargtypes => 'int4', + proallargtypes => '{int4,oid,oid,int8,int8,int8,int8,int8,_int4,timestamptz}', + proargmodes => '{i,o,o,o,o,o,o,o,o,o}', + proargnames => '{pid,relid,indid,size,ntup,searches,hits,neg_hits,ageclass,last_update}', + prosrc => 'pgstat_get_syscache_stats' }, { oid => '3786', descr => 'set up a logical replication slot', proname => 'pg_create_logical_replication_slot', provolatile => 'v', proparallel => 'u', prorettype => 'record', proargtypes => 'name name bool', diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index c9e35003a5..69b9a976f0 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -82,6 +82,7 @@ extern PGDLLIMPORT volatile sig_atomic_t InterruptPending; extern PGDLLIMPORT volatile sig_atomic_t QueryCancelPending; extern PGDLLIMPORT volatile sig_atomic_t ProcDiePending; extern PGDLLIMPORT volatile sig_atomic_t IdleInTransactionSessionTimeoutPending; +extern PGDLLIMPORT volatile sig_atomic_t IdleSyscacheStatsUpdateTimeoutPending; extern PGDLLIMPORT volatile sig_atomic_t ConfigReloadPending; extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost; diff --git a/src/include/pgstat.h b/src/include/pgstat.h index 88a75fb798..b6bfd7d644 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -1144,6 +1144,7 @@ extern bool pgstat_track_activities; extern bool pgstat_track_counts; extern int pgstat_track_functions; extern PGDLLIMPORT int pgstat_track_activity_query_size; +extern int pgstat_track_syscache_usage_interval; extern char *pgstat_stat_directory; extern char *pgstat_stat_tmpname; extern char *pgstat_stat_filename; @@ -1228,7 +1229,8 @@ extern PgStat_BackendFunctionEntry *find_funcstat_entry(Oid func_id); extern void pgstat_initstats(Relation rel); extern char *pgstat_clip_activity(const char *raw_activity); - +extern void pgstat_get_syscachestat_filename(bool permanent, + bool tempname, int backendid, char *filename, int len); /* ---------- * pgstat_report_wait_start() - * @@ -1363,5 +1365,5 @@ extern PgStat_StatFuncEntry *pgstat_fetch_stat_funcentry(Oid funcid); extern int pgstat_fetch_stat_numbackends(void); extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void); extern PgStat_GlobalStats *pgstat_fetch_global(void); - +extern long pgstat_write_syscache_stats(bool force); #endif /* PGSTAT_H */ diff --git a/src/include/utils/catcache.h b/src/include/utils/catcache.h index 5d24809900..4d51975920 100644 --- a/src/include/utils/catcache.h +++ b/src/include/utils/catcache.h @@ -65,10 +65,8 @@ typedef struct catcache int cc_tupsize; /* total amount of catcache tuples */ /* - * Keep these at the end, so that compiling catcache.c with CATCACHE_STATS - * doesn't break ABI for other modules + * Statistics entries */ -#ifdef CATCACHE_STATS long cc_searches; /* total # searches against this cache */ long cc_hits; /* # of matches against existing entry */ long cc_neg_hits; /* # of matches against negative entry */ @@ -81,7 +79,6 @@ typedef struct catcache long cc_invals; /* # of entries invalidated from cache */ long cc_lsearches; /* total # list-searches */ long cc_lhits; /* # of matches against existing lists */ -#endif } CatCache; @@ -254,4 +251,8 @@ extern void PrepareToInvalidateCacheTuple(Relation relation, extern void PrintCatCacheLeakWarning(HeapTuple tuple); extern void PrintCatCacheListLeakWarning(CatCList *list); +/* defined in syscache.h */ +typedef struct syscachestats SysCacheStats; +extern void CatCacheGetStats(CatCache *cache, SysCacheStats *syscachestats); + #endif /* CATCACHE_H */ diff --git a/src/include/utils/syscache.h b/src/include/utils/syscache.h index 95ee48954e..71b399c902 100644 --- a/src/include/utils/syscache.h +++ b/src/include/utils/syscache.h @@ -112,6 +112,24 @@ enum SysCacheIdentifier #define SysCacheSize (USERMAPPINGUSERSERVER + 1) }; +#define SYSCACHE_STATS_NAGECLASSES 6 +/* Struct for catcache tracking information */ +typedef struct syscachestats +{ + Oid reloid; /* target relation */ + Oid indoid; /* index */ + size_t size; /* size of the catcache */ + int ntuples; /* number of tuples resides in the catcache */ + int nsearches; /* number of searches */ + int nhits; /* number of cache hits */ + int nneg_hits; /* number of negative cache hits */ + /* age classes in seconds */ + int ageclasses[SYSCACHE_STATS_NAGECLASSES]; + /* number of tuples fall into the corresponding age class */ + int nclass_entries[SYSCACHE_STATS_NAGECLASSES]; +} SysCacheStats; + + extern void InitCatalogCache(void); extern void InitCatalogCachePhase2(void); @@ -164,6 +182,7 @@ extern void SysCacheInvalidate(int cacheId, uint32 hashValue); extern bool RelationInvalidatesSnapshotsOnly(Oid relid); extern bool RelationHasSysCache(Oid relid); extern bool RelationSupportsSysCache(Oid relid); +extern SysCacheStats *SysCacheGetStats(int cacheId); /* * The use of the macros below rather than direct calls to the corresponding diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h index 9244a2a7b7..0ab441a364 100644 --- a/src/include/utils/timeout.h +++ b/src/include/utils/timeout.h @@ -31,6 +31,7 @@ typedef enum TimeoutId STANDBY_TIMEOUT, STANDBY_LOCK_TIMEOUT, IDLE_IN_TRANSACTION_SESSION_TIMEOUT, + IDLE_CATCACHE_UPDATE_TIMEOUT, /* First user-definable timeout reason */ USER_TIMEOUT, /* Maximum number of timeout reasons */ diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index 2c8e21baa7..7bd77e9972 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1921,6 +1921,28 @@ pg_stat_sys_tables| SELECT pg_stat_all_tables.relid, pg_stat_all_tables.autoanalyze_count FROM pg_stat_all_tables WHERE ((pg_stat_all_tables.schemaname = ANY (ARRAY['pg_catalog'::name, 'information_schema'::name])) OR (pg_stat_all_tables.schemaname ~ '^pg_toast'::text)); +pg_stat_syscache| SELECT s.pid, + (s.relid)::regclass AS relname, + (s.indid)::regclass AS cache_name, + s.size, + s.ntup AS ntuples, + s.searches, + s.hits, + s.neg_hits, + s.ageclass, + s.last_update + FROM (pg_stat_activity a + JOIN LATERAL ( SELECT a.pid, + pg_get_syscache_stats.relid, + pg_get_syscache_stats.indid, + pg_get_syscache_stats.size, + pg_get_syscache_stats.ntup, + pg_get_syscache_stats.searches, + pg_get_syscache_stats.hits, + pg_get_syscache_stats.neg_hits, + pg_get_syscache_stats.ageclass, + pg_get_syscache_stats.last_update + FROM pg_get_syscache_stats(a.pid) pg_get_syscache_stats(relid, indid, size, ntup, searches, hits, neg_hits, ageclass, last_update)) s ON ((a.pid = s.pid))); pg_stat_user_functions| SELECT p.oid AS funcid, n.nspname AS schemaname, p.proname AS funcname, @@ -2352,7 +2374,7 @@ pg_settings|pg_settings_n|CREATE RULE pg_settings_n AS ON UPDATE TO pg_catalog.pg_settings DO INSTEAD NOTHING; pg_settings|pg_settings_u|CREATE RULE pg_settings_u AS ON UPDATE TO pg_catalog.pg_settings - WHERE (new.name = old.name) DO SELECT set_config(old.name, new.setting, false) AS set_config; + WHERE (new.name = old.name) DO SELECT set_config(old.name, new.setting, false, false) AS set_config; rtest_emp|rtest_emp_del|CREATE RULE rtest_emp_del AS ON DELETE TO public.rtest_emp DO INSERT INTO rtest_emplog (ename, who, action, newsal, oldsal) VALUES (old.ename, CURRENT_USER, 'fired'::bpchar, '$0.00'::money, old.salary); -- 2.16.3 ----Next_Part(Wed_Feb_06_15_17_59_2019_321)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v10-0003-PoC-add-prune-by-number-of-entries-feature.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v4 01/12] Change section heading to better reflect saving a result in variable(s) @ 2023-09-24 20:49 Karl O. Pinc <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Karl O. Pinc @ 2023-09-24 20:49 UTC (permalink / raw) The current section title of "Executing a Command with a Single-Row Result" does not reflect what the section is really about. Other sections make clear how to _execute_ commands, single-row result or not. What this section is about is how to _save_ a single row of results into variable(s). It would be nice to talk about saving results into variables in the section heading but I couldn't come up with anything pithy. "Saving a Single-Row of a Command's Result" seems good enough, especially since there's few other places to save results other than in variables. --- doc/src/sgml/plpgsql.sgml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/src/sgml/plpgsql.sgml b/doc/src/sgml/plpgsql.sgml index f55e901c7e..8747e84245 100644 --- a/doc/src/sgml/plpgsql.sgml +++ b/doc/src/sgml/plpgsql.sgml @@ -1126,7 +1126,7 @@ PERFORM create_mv('cs_session_page_requests_mv', my_query); </sect2> <sect2 id="plpgsql-statements-sql-onerow"> - <title>Executing a Command with a Single-Row Result</title> + <title>Saving a Single-Row of a Command's Result</title> <indexterm zone="plpgsql-statements-sql-onerow"> <primary>SELECT INTO</primary> -- 2.30.2 --MP_/OOXZvOwbpccKfGOtE9/SwX6 Content-Type: text/x-patch Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename=v4-0002-Change-section-heading-to-better-describe-referen.patch ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v52 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --gp2pyozrd5pweboh Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v52-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v53 7/7] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 92759f33969..6ba86384312 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qr3jlalmmcpkiodg-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v54 5/5] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 86 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 ++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 117 insertions(+), 63 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index d3fea738ca3..a90d163e416 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d1be6c60e88..ec3a2cd441d 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3382,7 +3382,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index c85166ba849..39cbb0252f4 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index dc46a372ead..06efcaa60b2 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -328,6 +329,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 9533515a63b..47679161b67 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -575,7 +587,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2430,7 +2450,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..9d7d675fa96 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index a315c4ab8ab..bf82b8f6048 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2071,6 +2071,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 6d0337853e0..fb75990609e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..489af7d8d6c 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --cdhh4t7ukb6tnjoq-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v50 8/8] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 78 ++++++++++++------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 6 +- 12 files changed, 96 insertions(+), 46 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index fdb77df0fdb..a87626a01b6 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d6e446d582d..2fc30008f59 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3383,7 +3383,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..1bc7f3f600d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..49fb10df038 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,9 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ +int TotalMaxReplicationSlots = 0; /* sum of both */ /* * Invalidate replication slots that have remained idle longer than this @@ -191,12 +194,14 @@ ReplicationSlotsShmemSize(void) { Size size = 0; - if (max_replication_slots == 0) + TotalMaxReplicationSlots = max_replication_slots + max_repack_replication_slots; + + if (TotalMaxReplicationSlots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(TotalMaxReplicationSlots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +214,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +228,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +378,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +386,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +439,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = repack ? max_replication_slots : 0; + endpoint = repack ? TotalMaxReplicationSlots : max_replication_slots; + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +456,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -548,7 +561,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +589,7 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + TotalMaxReplicationSlots); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,7 +1676,11 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* + * FIXME how to relax this for repack in a way that doesn't mess + * everything up? + */ + if (TotalMaxReplicationSlots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); @@ -2224,7 +2241,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (TotalMaxReplicationSlots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2249,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2354,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2455,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (TotalMaxReplicationSlots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2885,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *slot; @@ -2910,6 +2927,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..cdb4dbd87c9 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < TotalMaxReplicationSlots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < TotalMaxReplicationSlots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index e556b8844d8..8eb251659b0 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2c5e98d1d4d..9e9a390a01b 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..88953576894 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,9 +324,13 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; +/* only for slotfuncs.c, slotsync.c etc */ +extern int TotalMaxReplicationSlots; + /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); extern void ReplicationSlotsShmemInit(void); @@ -334,7 +338,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --brnevsqjnuzpyok4-- ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v56 2/3] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 2 +- src/backend/commands/repack_worker.c | 7 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/logical.c | 8 +- .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 84 ++++++++++++------- src/backend/replication/slotfuncs.c | 19 +++-- src/backend/replication/walsender.c | 9 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/logical.h | 3 +- src/include/replication/slot.h | 5 +- 15 files changed, 116 insertions(+), 62 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 3324d2d3c49..3435732646e 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4639,6 +4639,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index e993dfb3108..c532a39ee07 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 17b639b3b44..5e97fcf3818 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3357,7 +3357,7 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index 94d034970b5..ea330310e27 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -212,7 +212,7 @@ repack_setup_logical_decoding(Oid relid) * Make sure we can use logical decoding. */ CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(true); /* * A single backend should not execute multiple REPACK commands at a time, @@ -221,8 +221,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); @@ -233,6 +233,7 @@ repack_setup_logical_decoding(Oid relid) ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME, NIL, true, + true, InvalidXLogRecPtr, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 9e75a3e04ee..7adf4dbe0d1 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 8ceaf64d164..d8e02c53558 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi * decoding. */ void -CheckLogicalDecodingRequirements(void) +CheckLogicalDecodingRequirements(bool repack) { - CheckSlotRequirements(); + CheckSlotRequirements(repack); /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() @@ -304,6 +304,7 @@ StartupDecodingContext(List *output_plugin_options, * output_plugin_options -- contains options passed to the output plugin * need_full_snapshot -- if true, must obtain a snapshot able to read all * tables; if false, one that can read only catalogs is acceptable. + * for_repack -- if true, we're going to be decoding for REPACK. * restart_lsn -- if given as invalid, it's this routine's responsibility to * mark WAL as reserved by setting a convenient restart_lsn for the slot. * Otherwise, we set for decoding to start from the given LSN without @@ -324,6 +325,7 @@ LogicalDecodingContext * CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, @@ -340,7 +342,7 @@ CreateInitDecodingContext(const char *plugin, * On a standby, this check is also required while creating the slot. * Check the comments in the function. */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(for_repack); /* shorter lines... */ slot = MyReplicationSlot; diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 9760818941d..512013b0ef0 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); if (PG_ARGISNULL(0)) ereport(ERROR, diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 8b53bd3ac7f..ae900f13467 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -434,7 +434,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -823,6 +823,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1707,7 +1708,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index a1f37e59dbc..e6722fc0212 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -160,6 +160,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -199,12 +201,13 @@ ReplicationSlotsShmemRequest(void *arg) { Size size; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(max_replication_slots + max_repack_replication_slots, + sizeof(ReplicationSlot))); ShmemRequestStruct(.name = "ReplicationSlot Ctl", .size = size, .ptr = (void **) &ReplicationSlotCtl, @@ -217,7 +220,7 @@ ReplicationSlotsShmemRequest(void *arg) static void ReplicationSlotsShmemInit(void *arg) { - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -366,6 +369,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -373,10 +377,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -425,12 +430,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -438,7 +447,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -448,7 +459,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -541,7 +553,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -569,7 +581,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -863,7 +876,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1245,7 +1258,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1300,7 +1313,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1367,12 +1380,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1447,11 +1460,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1508,13 +1521,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1611,11 +1624,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1649,17 +1662,24 @@ CheckLogicalSlotExists(void) * slots. */ void -CheckSlotRequirements(void) +CheckSlotRequirements(bool repack) { /* * NB: Adding a new requirement likely means that RestoreSlotFromDisk() * needs the same check. */ - if (max_replication_slots == 0) + if (!repack && max_replication_slots == 0) ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("replication slots can only be used if \"%s\" > 0", + "max_replication_slots")); + + if (repack && max_repack_replication_slots == 0) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("REPACK can only be used if \"%s\" > 0", + "max_repack_replication_slots")); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2210,7 +2230,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2218,7 +2238,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2323,7 +2343,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2424,7 +2444,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..16fbd383735 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); create_physical_replication_slot(NameStr(*name), immediately_reserve, @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ctx = CreateInitDecodingContext(plugin, NIL, false, /* just catalogs is OK */ + false, /* not repack */ restart_lsn, XL_ROUTINE(.page_read = read_local_xlog_page, .segment_open = wal_segment_open, @@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); create_logical_replication_slot(NameStr(*name), NameStr(*plugin), @@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS) CheckSlotPermissions(); - CheckSlotRequirements(); + CheckSlotRequirements(false); ReplicationSlotDrop(NameStr(*name), true); @@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) CheckSlotPermissions(); if (logical_slot) - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); else - CheckSlotRequirements(); + CheckSlotRequirements(false); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); @@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index b4a2117a7f9..bad45adb004 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1241,7 +1241,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1261,7 +1261,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(cmd->kind == REPLICATION_KIND_LOGICAL); - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); /* * Initially create persistent slot as ephemeral - that allows us to @@ -1272,7 +1272,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the @@ -1330,6 +1330,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) Assert(IsLogicalDecodingEnabled()); ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot, + false, InvalidXLogRecPtr, XL_ROUTINE(.page_read = logical_read_xlog_page, .segment_open = WalSndSegmentOpen, @@ -1487,7 +1488,7 @@ StartLogicalReplication(StartReplicationCmd *cmd) QueryCompletion qc; /* make sure that our requirements are still fulfilled */ - CheckLogicalDecodingRequirements(); + CheckLogicalDecodingRequirements(false); Assert(!MyReplicationSlot); diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fcb6ab80583..632f3ba4989 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2079,6 +2079,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index e3e462f3efb..2e10eb4a36a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index bc9d4ece672..bc075b16741 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext } LogicalDecodingContext; -extern void CheckLogicalDecodingRequirements(void); +extern void CheckLogicalDecodingRequirements(bool repack); extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin, List *output_plugin_options, bool need_full_snapshot, + bool for_repack, XLogRecPtr restart_lsn, XLogReaderRoutine *xl_routine, LogicalOutputPluginWriterPrepareWrite prepare_write, diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 1a3557de607..77c8d0975b6 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,13 +324,14 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); @@ -373,7 +374,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname extern void StartupReplicationSlots(void); extern void CheckPointReplicationSlots(bool is_shutdown); -extern void CheckSlotRequirements(void); +extern void CheckSlotRequirements(bool repack); extern void CheckSlotPermissions(void); extern ReplicationSlotInvalidationCause GetSlotInvalidationCause(const char *cause_name); -- 2.47.3 --qs77q6fpwolne4ds Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v56-0003-Error-out-any-process-that-would-block-at-REPACK.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
* [PATCH v51 09/10] Reserve replication slots specifically for REPACK @ 2026-04-01 17:54 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 176+ messages in thread From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw) This allows REPACK to not interfere with other operations that use replication slots. This eases configurability. --- doc/src/sgml/config.sgml | 16 ++++ doc/src/sgml/ref/repack.sgml | 6 +- src/backend/commands/repack.c | 3 +- src/backend/commands/repack_worker.c | 4 +- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/slotsync.c | 5 +- src/backend/replication/slot.c | 80 +++++++++++-------- src/backend/replication/slotfuncs.c | 8 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/misc/guc_parameters.dat | 8 ++ src/backend/utils/misc/postgresql.conf.sample | 2 + src/include/replication/slot.h | 3 +- 12 files changed, 93 insertions(+), 48 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 422ba304982..a67dd6b9eb1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows </listitem> </varlistentry> + <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots"> + <term><varname>max_repack_replication_slots</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the maximum number of replication slots for use of + the <command>REPACK</command> command. The default is 5. + This parameter can only be set at server start. + </para> + </listitem> + </varlistentry> + + <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots"> <term><varname>max_replication_slots</varname> (<type>integer</type>) <indexterm> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml index bec18c44cc8..1424446ba7c 100644 --- a/doc/src/sgml/ref/repack.sgml +++ b/doc/src/sgml/ref/repack.sgml @@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING <listitem> <para> - The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link> - configuration parameter does not allow for creation of an additional - replication slot. + The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link> + configuration parameter does not allow for the creation of an + additional replication slot. </para> </listitem> </itemizedlist> diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index d4c1f0e7652..d932d526235 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3381,7 +3381,8 @@ start_repack_decoding_worker(Oid relid) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), - errhint("You might need to increase \"%s\".", "max_worker_processes")); + /* FIXME rename to max_repack_processes? */ + errhint("You might need to increase \"%s\".", "max_repack_replication_slots")); decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c index ff34e246469..610592a05b0 100644 --- a/src/backend/commands/repack_worker.c +++ b/src/backend/commands/repack_worker.c @@ -233,8 +233,8 @@ repack_setup_logical_decoding(Oid relid) * RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); - ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, - false); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true, + false, false); EnsureLogicalDecodingEnabled(); diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 09964198550..d83125afd0d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void) errmsg("creating replication conflict detection slot")); ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false, - false, false); + false, false, false); init_conflict_slot_xmin(); } diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index e75db69e3f6..28c89c5e10d 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -425,7 +425,7 @@ get_local_synced_slots(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid, */ ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY, remote_slot->two_phase, + false, remote_slot->failover, true); @@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index d553bd5dbff..2c6c6773ad2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -152,6 +152,8 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int max_repack_replication_slots = 5; /* the maximum number of slots + * for REPACK */ /* * Invalidate replication slots that have remained idle longer than this @@ -189,14 +191,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel); Size ReplicationSlotsShmemSize(void) { + int totalslots = max_replication_slots + max_repack_replication_slots; Size size = 0; - if (max_replication_slots == 0) + if (totalslots == 0) return size; size = offsetof(ReplicationSlotCtlData, replication_slots); size = add_size(size, - mul_size(max_replication_slots, sizeof(ReplicationSlot))); + mul_size(totalslots, sizeof(ReplicationSlot))); return size; } @@ -209,7 +212,7 @@ ReplicationSlotsShmemInit(void) { bool found; - if (max_replication_slots == 0) + if (max_replication_slots + max_repack_replication_slots == 0) return; ReplicationSlotCtl = (ReplicationSlotCtlData *) @@ -223,7 +226,7 @@ ReplicationSlotsShmemInit(void) /* First time through, so initialize */ MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize()); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i]; @@ -373,6 +376,7 @@ IsSlotForConflictCheck(const char *name) * db_specific: logical decoding is db specific; if the slot is going to * be used for that pass true, otherwise false. * two_phase: If enabled, allows decoding of prepared transactions. + * repack: If true, use a slot from the pool for REPACK. * failover: If enabled, allows the slot to be synced to standbys so * that logical replication can be resumed after failover. * synced: True if the slot is synchronized from the primary server. @@ -380,10 +384,11 @@ IsSlotForConflictCheck(const char *name) void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, bool synced) + bool two_phase, bool repack, bool failover, bool synced) { ReplicationSlot *slot = NULL; - int i; + int startpoint, + endpoint; Assert(MyReplicationSlot == NULL); @@ -432,12 +437,16 @@ ReplicationSlotCreate(const char *name, bool db_specific, LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* - * Check for name collision, and identify an allocatable slot. We need to - * hold ReplicationSlotControlLock in shared mode for this, so that nobody - * else can change the in_use flags while we're looking at them. + * Check for name collision (across the whole array), and identify an + * allocatable slot (in the array slice specific to our current use case: + * either general, or REPACK only). We need to hold + * ReplicationSlotControlLock in shared mode for this, so that nobody else + * can change the in_use flags while we're looking at them. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + startpoint = !repack ? 0 : max_replication_slots; + endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0); + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -445,7 +454,9 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_DUPLICATE_OBJECT), errmsg("replication slot \"%s\" already exists", name))); - if (!s->in_use && slot == NULL) + + if (i >= startpoint && i < endpoint && + !s->in_use && slot == NULL) slot = s; } LWLockRelease(ReplicationSlotControlLock); @@ -455,7 +466,8 @@ ReplicationSlotCreate(const char *name, bool db_specific, ereport(ERROR, (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("all replication slots are in use"), - errhint("Free one or increase \"max_replication_slots\"."))); + errhint("Free one or increase \"%s\".", + repack ? "max_repack_replication_slots" : "max_replication_slots"))); /* * Since this slot is not in use, nobody should be looking at any part of @@ -548,7 +560,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock) if (need_lock) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -576,7 +588,8 @@ int ReplicationSlotIndex(ReplicationSlot *slot) { Assert(slot >= ReplicationSlotCtl->replication_slots && - slot < ReplicationSlotCtl->replication_slots + max_replication_slots); + slot < ReplicationSlotCtl->replication_slots + + (max_replication_slots + max_repack_replication_slots)); return slot - ReplicationSlotCtl->replication_slots; } @@ -870,7 +883,7 @@ ReplicationSlotCleanup(bool synced_only) restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; @@ -1252,7 +1265,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked) if (!already_locked) LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; TransactionId effective_xmin; @@ -1307,7 +1320,7 @@ ReplicationSlotsComputeRequiredLSN(void) Assert(ReplicationSlotCtl != NULL); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; XLogRecPtr restart_lsn; @@ -1374,12 +1387,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void) XLogRecPtr result = InvalidXLogRecPtr; int i; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return InvalidXLogRecPtr; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; XLogRecPtr restart_lsn; @@ -1454,11 +1467,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive) *nslots = *nactive = 0; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; @@ -1515,13 +1528,13 @@ ReplicationSlotsDropDBSlots(Oid dboid) bool found_valid_logicalslot; bool dropped = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; char *slotname; @@ -1618,11 +1631,11 @@ CheckLogicalSlotExists(void) { bool found = false; - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s; bool invalidated; @@ -1663,10 +1676,12 @@ CheckSlotRequirements(void) * needs the same check. */ - if (max_replication_slots == 0) + /* XXX we should be able to check exactly which type of slot we need */ + if (max_replication_slots + max_repack_replication_slots == 0) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("replication slots can only be used if \"max_replication_slots\" > 0"))); + errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0", + "max_replication_slots", "max_repack_replication_slots"))); if (wal_level < WAL_LEVEL_REPLICA) ereport(ERROR, @@ -2224,7 +2239,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0); Assert(possible_causes != RS_INVAL_NONE); - if (max_replication_slots == 0) + if (max_replication_slots == 0 && max_repack_replication_slots == 0) return invalidated; XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN); @@ -2232,7 +2247,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes, restart: found_valid_logicalslot = false; LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; bool released_lock = false; @@ -2337,7 +2352,7 @@ CheckPointReplicationSlots(bool is_shutdown) */ LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED); - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; char path[MAXPGPATH]; @@ -2438,7 +2453,7 @@ StartupReplicationSlots(void) FreeDir(replication_dir); /* currently no slots exist, we're done. */ - if (max_replication_slots <= 0) + if (max_replication_slots + max_repack_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ @@ -2868,7 +2883,7 @@ RestoreSlotFromDisk(const char *name) errhint("Change \"wal_level\" to be \"replica\" or higher."))); /* nothing can be active yet, don't lock anything */ - for (i = 0; i < max_replication_slots; i++) + for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *slot; @@ -2910,6 +2925,7 @@ RestoreSlotFromDisk(const char *name) break; } + /* XXX might be misleading if the slots previously in use were REPACK. */ if (!restored) ereport(FATAL, (errmsg("too many replication slots active before shutdown"), diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 9f5e4f998fe..78dd3c4ea66 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve, /* acquire replication slot, this will check for conflicting names */ ReplicationSlotCreate(name, false, temporary ? RS_TEMPORARY : RS_PERSISTENT, false, - false, false); + false, false, false); if (immediately_reserve) { @@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin, */ ReplicationSlotCreate(name, true, temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase, - failover, false); + false, failover, false); /* * Ensure the logical decoding is enabled before initializing the logical @@ -270,7 +270,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) currlsn = GetXLogWriteRecPtr(); LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); - for (slotno = 0; slotno < max_replication_slots; slotno++) + for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++) { ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno]; ReplicationSlot slot_contents; @@ -665,7 +665,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot) * managed to create the new slot, we advance the new slot's restart_lsn * to the source slot's updated restart_lsn the second time we lock it. */ - for (int i = 0; i < max_replication_slots; i++) + for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 2bb3f34dc6d..75ef3419a15 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) { ReplicationSlotCreate(cmd->slotname, false, cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT, - false, false, false); + false, false, false, false); if (reserve_wal) { @@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) */ ReplicationSlotCreate(cmd->slotname, true, cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL, - two_phase, failover, false); + two_phase, false, failover, false); /* * Do options check early so that we can bail before calling the diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat index fc0900efe5f..857be159f5c 100644 --- a/src/backend/utils/misc/guc_parameters.dat +++ b/src/backend/utils/misc/guc_parameters.dat @@ -2070,6 +2070,14 @@ max => 'MAX_BACKENDS', }, +{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', + short_desc => 'Sets the maximum number of replication slots for use by REPACK.', + variable => 'max_repack_replication_slots', + boot_val => '5', + min => '0', + max => 'MAX_BACKENDS', +}, + /* see max_wal_senders */ { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING', short_desc => 'Sets the maximum number of simultaneously defined replication slots.', diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index c8194c27aa7..9c3c5d16361 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -348,6 +348,8 @@ # (change requires restart) #max_replication_slots = 10 # max number of replication slots # (change requires restart) +#max_repack_replication_slots = 5 # max number of replication slots for REPACK + # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables #idle_replication_slot_timeout = 0 # in seconds; 0 disables diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 4b4709f6e2c..c316a01a807 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; +extern PGDLLIMPORT int max_repack_replication_slots; extern PGDLLIMPORT char *synchronized_standby_slots; extern PGDLLIMPORT int idle_replication_slot_timeout_secs; @@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void); /* management of individual slots */ extern void ReplicationSlotCreate(const char *name, bool db_specific, ReplicationSlotPersistency persistency, - bool two_phase, bool failover, + bool two_phase, bool repack, bool failover, bool synced); extern void ReplicationSlotPersist(void); extern void ReplicationSlotDrop(const char *name, bool nowait); -- 2.47.3 --r2slln3zpmilwu22 Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v51-0010-CheckLogicalDecodingRequirements-be-specific-abo.patch" ^ permalink raw reply [nested|flat] 176+ messages in thread
end of thread, other threads:[~2026-04-01 17:54 UTC | newest] Thread overview: 176+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2018-10-16 06:48 [PATCH 2/4] Syscache usage tracking feature. Kyotaro Horiguchi <[email protected]> 2023-09-24 20:49 [PATCH v4 01/12] Change section heading to better reflect saving a result in variable(s) Karl O. Pinc <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v51 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v53 7/7] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v56 2/3] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v54 5/5] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v52 09/10] Reserve replication slots specifically for REPACK Álvaro Herrera <[email protected]> 2026-04-01 17:54 [PATCH v50 8/8] Reserve replication slots specifically for REPACK 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