diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 82eaf89a6b..d301d9c5c3 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -269,6 +269,14 @@ postgres: user database host + + pg_stat_archiverpg_stat_archiver + One row only, showing statistics about the + WAL archiver process's activity. See + for details. + + + pg_stat_bgwriterpg_stat_bgwriter One row only, showing statistics about the @@ -648,6 +656,63 @@ postgres: user database host + + <structname>pg_stat_archiver</structname> View + + + + + Column + Type + Description + + + + + + archived_count + bigint + Number of WAL files that have been successfully archived + + + last_archived_wal + text + Name of the last WAL file successfully archived + + + last_archived_time + timestamp with time zone + Time of the last successful archive operation + + + failed_count + bigint + Number of failed attempts for archiving WAL files + + + last_failed_wal + text + Name of the WAL file of the last failed archival operation + + + last_failed_time + timestamp with time zone + Time of the last failed archival operation + + + stats_reset + timestamp with time zone + Time at which these statistics were last reset + + + +
+ + + The pg_stat_archiver view will always have a + single row, containing data about the archiver process of the cluster. + + <structname>pg_stat_bgwriter</structname> View @@ -1613,6 +1678,8 @@ postgres: user database host pg_stat_reset_shared('bgwriter') will zero all the counters shown in the pg_stat_bgwriter view. + Calling pg_stat_reset_shared('archiver') will zero all the + counters shown in the pg_stat_archiver view. diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 043d1181fd..277af61f9d 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -672,6 +672,17 @@ CREATE VIEW pg_stat_xact_user_functions AS WHERE P.prolang != 12 -- fast check to eliminate built-in functions AND pg_stat_get_xact_function_calls(P.oid) IS NOT NULL; +CREATE VIEW pg_stat_archiver AS + SELECT + s.archived_count, + s.last_archived_wal, + s.last_archived_time, + s.failed_count, + s.last_failed_wal, + s.last_failed_time, + s.stats_reset + FROM pg_stat_get_archiver() s; + CREATE VIEW pg_stat_bgwriter AS SELECT pg_stat_get_bgwriter_timed_checkpoints() AS checkpoints_timed, diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 2fd7a012df..cf2ce46516 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -36,6 +36,7 @@ #include "access/xlog_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" +#include "pgstat.h" #include "postmaster/fork_process.h" #include "postmaster/pgarch.h" #include "postmaster/postmaster.h" @@ -58,19 +59,6 @@ #define PGARCH_RESTART_INTERVAL 10 /* How often to attempt to restart a * failed archiver; in seconds. */ -/* ---------- - * Archiver control info. - * - * We expect that archivable files within pg_xlog will have names between - * MIN_XFN_CHARS and MAX_XFN_CHARS in length, consisting only of characters - * appearing in VALID_XFN_CHARS. The status files in archive_status have - * corresponding names with ".ready" or ".done" appended. - * ---------- - */ -#define MIN_XFN_CHARS 16 -#define MAX_XFN_CHARS 40 -#define VALID_XFN_CHARS "0123456789ABCDEF.history.backup" - #define NUM_ARCHIVE_RETRIES 3 @@ -496,10 +484,17 @@ pgarch_ArchiverCopyLoop(void) { /* successful */ pgarch_archiveDone(xlog); + + /* Tell the collector about the WAL file that we successfully archived */ + pgstat_send_archiver(xlog, false); + break; /* out of inner retry loop */ } else { + /* Tell the collector about the WAL file that we failed to archive */ + pgstat_send_archiver(xlog, true); + if (++failures >= NUM_ARCHIVE_RETRIES) { ereport(WARNING, diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c index 1c3b481015..305d126912 100644 --- a/src/backend/postmaster/pgstat.c +++ b/src/backend/postmaster/pgstat.c @@ -221,6 +221,7 @@ static int localNumBackends = 0; * Contains statistics that are not collected per database * or per table. */ +static PgStat_ArchiverStats archiverStats; static PgStat_GlobalStats globalStats; /* Write request info for each database */ @@ -292,6 +293,7 @@ static void pgstat_recv_resetsinglecounter(PgStat_MsgResetsinglecounter *msg, in static void pgstat_recv_autovac(PgStat_MsgAutovacStart *msg, int len); static void pgstat_recv_vacuum(PgStat_MsgVacuum *msg, int len); static void pgstat_recv_analyze(PgStat_MsgAnalyze *msg, int len); +static void pgstat_recv_archiver(PgStat_MsgArchiver *msg, int len); static void pgstat_recv_bgwriter(PgStat_MsgBgWriter *msg, int len); static void pgstat_recv_funcstat(PgStat_MsgFuncstat *msg, int len); static void pgstat_recv_funcpurge(PgStat_MsgFuncpurge *msg, int len); @@ -1257,13 +1259,15 @@ pgstat_reset_shared_counters(const char *target) (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), errmsg("must be superuser to reset statistics counters"))); - if (strcmp(target, "bgwriter") == 0) + if (strcmp(target, "archiver") == 0) + msg.m_resettarget = RESET_ARCHIVER; + else if (strcmp(target, "bgwriter") == 0) msg.m_resettarget = RESET_BGWRITER; else ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("unrecognized reset target: \"%s\"", target), - errhint("Target must be \"bgwriter\"."))); + errhint("Target must be \"archiver\" or \"bgwriter\"."))); pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETSHAREDCOUNTER); pgstat_send(&msg, sizeof(msg)); @@ -2321,6 +2325,23 @@ pgstat_fetch_stat_numbackends(void) return localNumBackends; } +/* + * --------- + * pgstat_fetch_stat_archiver() - + * + * Support function for the SQL-callable pgstat* functions. Returns + * a pointer to the archiver statistics struct. + * --------- + */ +PgStat_ArchiverStats * +pgstat_fetch_stat_archiver(void) +{ + backend_read_statsfile(); + + return &archiverStats; +} + + /* * --------- * pgstat_fetch_global() - @@ -3035,6 +3056,28 @@ pgstat_send(void *msg, int len) #endif } +/* ---------- + * pgstat_send_archiver() - + * + * Tell the collector about the WAL file that we successfully + * archived or failed to archive. + * ---------- + */ +void +pgstat_send_archiver(const char *xlog, bool failed) +{ + PgStat_MsgArchiver msg; + + /* + * Prepare and send the message + */ + pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_ARCHIVER); + msg.m_failed = failed; + strncpy(msg.m_xlog, xlog, sizeof(msg.m_xlog)); + msg.m_timestamp = GetCurrentTimestamp(); + pgstat_send(&msg, sizeof(msg)); +} + /* ---------- * pgstat_send_bgwriter() - * @@ -3278,6 +3321,10 @@ PgstatCollectorMain(int argc, char *argv[]) pgstat_recv_analyze((PgStat_MsgAnalyze *) &msg, len); break; + case PGSTAT_MTYPE_ARCHIVER: + pgstat_recv_archiver((PgStat_MsgArchiver *) &msg, len); + break; + case PGSTAT_MTYPE_BGWRITER: pgstat_recv_bgwriter((PgStat_MsgBgWriter *) &msg, len); break; @@ -3562,6 +3609,12 @@ pgstat_write_statsfiles(bool permanent, bool allDbs) rc = fwrite(&globalStats, sizeof(globalStats), 1, fpout); (void) rc; /* we'll check for error with ferror */ + /* + * Write archiver stats struct + */ + rc = fwrite(&archiverStats, sizeof(archiverStats), 1, fpout); + (void) rc; /* we'll check for error with ferror */ + /* * Walk through the database table. */ @@ -3828,16 +3881,18 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) HASH_ELEM | HASH_FUNCTION | HASH_CONTEXT); /* - * Clear out global statistics so they start from zero in case we can't - * load an existing statsfile. + * Clear out global and archiver statistics so they start from zero + * in case we can't load an existing statsfile. */ memset(&globalStats, 0, sizeof(globalStats)); + memset(&archiverStats, 0, sizeof(archiverStats)); /* * Set the current timestamp (will be kept only in case we can't load an * existing statsfile). */ globalStats.stat_reset_timestamp = GetCurrentTimestamp(); + archiverStats.stat_reset_timestamp = globalStats.stat_reset_timestamp; /* * Try to open the stats file. If it doesn't exist, the backends simply @@ -3879,6 +3934,16 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) goto done; } + /* + * Read archiver stats struct + */ + if (fread(&archiverStats, 1, sizeof(archiverStats), fpin) != sizeof(archiverStats)) + { + ereport(pgStatRunningInCollector ? LOG : WARNING, + (errmsg("corrupted statistics file \"%s\"", statfile))); + goto done; + } + /* * We found an existing collector stats file. Read it and put all the * hashtable entries into place. @@ -4159,7 +4224,7 @@ done: * stats_timestamp value. * * - if there's no db stat entry (e.g. for a new or inactive database), - * there's no stat_timestamp value, but also nothing to write so we return + * there's no stats_timestamp value, but also nothing to write so we return * the timestamp of the global statfile. * ---------- */ @@ -4169,6 +4234,7 @@ pgstat_read_db_statsfile_timestamp(Oid databaseid, bool permanent, { PgStat_StatDBEntry dbentry; PgStat_GlobalStats myGlobalStats; + PgStat_ArchiverStats myArchiverStats; FILE *fpin; int32 format_id; const char *statfile = permanent ? PGSTAT_STAT_PERMANENT_FILENAME : pgstat_stat_filename; @@ -4211,6 +4277,18 @@ pgstat_read_db_statsfile_timestamp(Oid databaseid, bool permanent, return false; } + /* + * Read archiver stats struct + */ + if (fread(&myArchiverStats, 1, sizeof(myArchiverStats), + fpin) != sizeof(myArchiverStats)) + { + ereport(pgStatRunningInCollector ? LOG : WARNING, + (errmsg("corrupted statistics file \"%s\"", statfile))); + FreeFile(fpin); + return false; + } + /* By default, we're going to return the timestamp of the global file. */ *ts = myGlobalStats.stats_timestamp; @@ -4738,6 +4816,12 @@ pgstat_recv_resetsharedcounter(PgStat_MsgResetsharedcounter *msg, int len) memset(&globalStats, 0, sizeof(globalStats)); globalStats.stat_reset_timestamp = GetCurrentTimestamp(); } + else if (msg->m_resettarget == RESET_ARCHIVER) + { + /* Reset the archiver statistics for the cluster. */ + memset(&archiverStats, 0, sizeof(archiverStats)); + archiverStats.stat_reset_timestamp = GetCurrentTimestamp(); + } /* * Presumably the sender of this message validated the target, don't @@ -4867,6 +4951,33 @@ pgstat_recv_analyze(PgStat_MsgAnalyze *msg, int len) } +/* ---------- + * pgstat_recv_archiver() - + * + * Process a ARCHIVER message. + * ---------- + */ +static void +pgstat_recv_archiver(PgStat_MsgArchiver *msg, int len) +{ + if (msg->m_failed) + { + /* Failed archival attempt */ + ++archiverStats.failed_count; + memcpy(archiverStats.last_failed_wal, msg->m_xlog, + sizeof(archiverStats.last_failed_wal)); + archiverStats.last_failed_timestamp = msg->m_timestamp; + } + else + { + /* Successful archival operation */ + ++archiverStats.archived_count; + memcpy(archiverStats.last_archived_wal, msg->m_xlog, + sizeof(archiverStats.last_archived_wal)); + archiverStats.last_archived_timestamp = msg->m_timestamp; + } +} + /* ---------- * pgstat_recv_bgwriter() - * diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index 2b8f5ee1e6..29fc134858 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -87,6 +87,8 @@ extern Datum pg_stat_get_db_temp_bytes(PG_FUNCTION_ARGS); extern Datum pg_stat_get_db_blk_read_time(PG_FUNCTION_ARGS); extern Datum pg_stat_get_db_blk_write_time(PG_FUNCTION_ARGS); +extern Datum pg_stat_get_archiver(PG_FUNCTION_ARGS); + extern Datum pg_stat_get_bgwriter_timed_checkpoints(PG_FUNCTION_ARGS); extern Datum pg_stat_get_bgwriter_requested_checkpoints(PG_FUNCTION_ARGS); extern Datum pg_stat_get_checkpoint_write_time(PG_FUNCTION_ARGS); @@ -1712,3 +1714,70 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS) PG_RETURN_VOID(); } + +Datum +pg_stat_get_archiver(PG_FUNCTION_ARGS) +{ + TupleDesc tupdesc; + Datum values[7]; + bool nulls[7]; + PgStat_ArchiverStats *archiver_stats; + + /* Initialise values and NULL flags arrays */ + MemSet(values, 0, sizeof(values)); + MemSet(nulls, 0, sizeof(nulls)); + + /* Initialise attributes information in the tuple descriptor */ + tupdesc = CreateTemplateTupleDesc(7, false); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "archived_count", + INT8OID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 2, "last_archived_wal", + TEXTOID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 3, "last_archived_time", + TIMESTAMPTZOID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 4, "failed_count", + INT8OID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 5, "last_failed_wal", + TEXTOID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 6, "last_failed_time", + TIMESTAMPTZOID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 7, "stats_reset", + TIMESTAMPTZOID, -1, 0); + + BlessTupleDesc(tupdesc); + + /* Get statistics about the archiver process */ + archiver_stats = pgstat_fetch_stat_archiver(); + + /* Fill values and NULLs */ + values[0] = Int64GetDatum(archiver_stats->archived_count); + if (archiver_stats->last_archived_wal == 0) + nulls[1] = true; + else + values[1] = CStringGetTextDatum(archiver_stats->last_archived_wal); + + if (archiver_stats->last_archived_timestamp == 0) + nulls[2] = true; + else + values[2] = TimestampTzGetDatum(archiver_stats->last_archived_timestamp); + + values[3] = Int64GetDatum(archiver_stats->failed_count); + if (archiver_stats->last_failed_wal == 0) + nulls[4] = true; + else + values[4] = CStringGetTextDatum(archiver_stats->last_failed_wal); + + if (archiver_stats->last_failed_timestamp == 0) + nulls[5] = true; + else + values[5] = TimestampTzGetDatum(archiver_stats->last_failed_timestamp); + + if (archiver_stats->stat_reset_timestamp == 0) + nulls[6] = true; + else + values[6] = TimestampTzGetDatum(archiver_stats->stat_reset_timestamp); + + /* Returns the record as Datum */ + PG_RETURN_DATUM(HeapTupleGetDatum( + heap_form_tuple(tupdesc, values, nulls))); +} diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h index ad9774c285..2a050ca885 100644 --- a/src/include/catalog/pg_proc.h +++ b/src/include/catalog/pg_proc.h @@ -2702,6 +2702,8 @@ DATA(insert OID = 2844 ( pg_stat_get_db_blk_read_time PGNSP PGUID 12 1 0 0 0 f DESCR("statistics: block read time, in msec"); DATA(insert OID = 2845 ( pg_stat_get_db_blk_write_time PGNSP PGUID 12 1 0 0 0 f f f f t f s 1 0 701 "26" _null_ _null_ _null_ _null_ pg_stat_get_db_blk_write_time _null_ _null_ _null_ )); DESCR("statistics: block write time, in msec"); +DATA(insert OID = 3195 ( pg_stat_get_archiver PGNSP PGUID 12 1 0 0 0 f f f f f f s 0 0 2249 "" "{20,25,1184,20,25,1184,1184}" "{o,o,o,o,o,o,o}" "{archived_count,last_archived_wal,last_archived_time,failed_count,last_failed_wal,last_failed_time,stats_reset}" _null_ pg_stat_get_archiver _null_ _null_ _null_ )); +DESCR("statistics: information about WAL archiver"); DATA(insert OID = 2769 ( pg_stat_get_bgwriter_timed_checkpoints PGNSP PGUID 12 1 0 0 0 f f f f t f s 0 0 20 "" _null_ _null_ _null_ _null_ pg_stat_get_bgwriter_timed_checkpoints _null_ _null_ _null_ )); DESCR("statistics: number of timed checkpoints started by the bgwriter"); DATA(insert OID = 2770 ( pg_stat_get_bgwriter_requested_checkpoints PGNSP PGUID 12 1 0 0 0 f f f f t f s 0 0 20 "" _null_ _null_ _null_ _null_ pg_stat_get_bgwriter_requested_checkpoints _null_ _null_ _null_ )); diff --git a/src/include/pgstat.h b/src/include/pgstat.h index 0b458e59bb..2024b7994a 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -15,6 +15,7 @@ #include "fmgr.h" #include "libpq/pqcomm.h" #include "portability/instr_time.h" +#include "postmaster/pgarch.h" #include "utils/hsearch.h" #include "utils/relcache.h" @@ -44,6 +45,7 @@ typedef enum StatMsgType PGSTAT_MTYPE_AUTOVAC_START, PGSTAT_MTYPE_VACUUM, PGSTAT_MTYPE_ANALYZE, + PGSTAT_MTYPE_ARCHIVER, PGSTAT_MTYPE_BGWRITER, PGSTAT_MTYPE_FUNCSTAT, PGSTAT_MTYPE_FUNCPURGE, @@ -102,6 +104,7 @@ typedef struct PgStat_TableCounts /* Possible targets for resetting cluster-wide shared values */ typedef enum PgStat_Shared_Reset_Target { + RESET_ARCHIVER, RESET_BGWRITER } PgStat_Shared_Reset_Target; @@ -355,6 +358,18 @@ typedef struct PgStat_MsgAnalyze } PgStat_MsgAnalyze; +/* ---------- + * PgStat_MsgArchiver Sent by the archiver to update statistics. + * ---------- + */ +typedef struct PgStat_MsgArchiver +{ + PgStat_MsgHdr m_hdr; + bool m_failed; /* Failed attempt */ + char m_xlog[MAX_XFN_CHARS + 1]; + TimestampTz m_timestamp; +} PgStat_MsgArchiver; + /* ---------- * PgStat_MsgBgWriter Sent by the bgwriter to update statistics. * ---------- @@ -502,6 +517,7 @@ typedef union PgStat_Msg PgStat_MsgAutovacStart msg_autovacuum; PgStat_MsgVacuum msg_vacuum; PgStat_MsgAnalyze msg_analyze; + PgStat_MsgArchiver msg_archiver; PgStat_MsgBgWriter msg_bgwriter; PgStat_MsgFuncstat msg_funcstat; PgStat_MsgFuncpurge msg_funcpurge; @@ -518,7 +534,7 @@ typedef union PgStat_Msg * ------------------------------------------------------------ */ -#define PGSTAT_FILE_FORMAT_ID 0x01A5BC9B +#define PGSTAT_FILE_FORMAT_ID 0x01A5BC9C /* ---------- * PgStat_StatDBEntry The collector's data per database @@ -611,6 +627,20 @@ typedef struct PgStat_StatFuncEntry } PgStat_StatFuncEntry; +/* + * Archiver statistics kept in the stats collector + */ +typedef struct PgStat_ArchiverStats +{ + PgStat_Counter archived_count; /* archival successes */ + char last_archived_wal[MAX_XFN_CHARS + 1]; /* last WAL file archived */ + TimestampTz last_archived_timestamp; /* last archival success time */ + PgStat_Counter failed_count; /* failed archival attempts */ + char last_failed_wal[MAX_XFN_CHARS + 1]; /* WAL file involved in last failure */ + TimestampTz last_failed_timestamp; /* last archival failure time */ + TimestampTz stat_reset_timestamp; +} PgStat_ArchiverStats; + /* * Global statistics kept in the stats collector */ @@ -863,6 +893,7 @@ extern void pgstat_twophase_postcommit(TransactionId xid, uint16 info, extern void pgstat_twophase_postabort(TransactionId xid, uint16 info, void *recdata, uint32 len); +extern void pgstat_send_archiver(const char *xlog, bool failed); extern void pgstat_send_bgwriter(void); /* ---------- @@ -875,6 +906,7 @@ extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid); extern PgBackendStatus *pgstat_fetch_stat_beentry(int beid); 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); #endif /* PGSTAT_H */ diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index 44582bb718..482546c185 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -13,6 +13,19 @@ #ifndef _PGARCH_H #define _PGARCH_H +/* ---------- + * Archiver control info. + * + * We expect that archivable files within pg_xlog will have names between + * MIN_XFN_CHARS and MAX_XFN_CHARS in length, consisting only of characters + * appearing in VALID_XFN_CHARS. The status files in archive_status have + * corresponding names with ".ready" or ".done" appended. + * ---------- + */ +#define MIN_XFN_CHARS 16 +#define MAX_XFN_CHARS 40 +#define VALID_XFN_CHARS "0123456789ABCDEF.history.backup" + /* ---------- * Functions called from postmaster * ---------- diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index 9f089e3f4f..540373dc48 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1640,6 +1640,14 @@ pg_stat_all_tables| SELECT c.oid AS relid, LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace))) WHERE (c.relkind = ANY (ARRAY['r'::"char", 't'::"char", 'm'::"char"])) GROUP BY c.oid, n.nspname, c.relname; +pg_stat_archiver| SELECT s.archived_count, + s.last_archived_wal, + s.last_archived_time, + s.failed_count, + s.last_failed_wal, + s.last_failed_time, + s.stats_reset + FROM pg_stat_get_archiver() s(archived_count, last_archived_wal, last_archived_time, failed_count, last_failed_wal, last_failed_time, stats_reset); pg_stat_bgwriter| SELECT pg_stat_get_bgwriter_timed_checkpoints() AS checkpoints_timed, pg_stat_get_bgwriter_requested_checkpoints() AS checkpoints_req, pg_stat_get_checkpoint_write_time() AS checkpoint_write_time,