From c4b92df8f6010cce2c0ecc26be905b5ec83f6023 Mon Sep 17 00:00:00 2001 From: Kyotaro Horiguchi Date: Mon, 12 Nov 2018 17:26:33 +0900 Subject: [PATCH 4/7] Shared-memory based stats collector This replaces the means to share server statistics numbers from file to dynamic shared memory. Every backend directly reads and writres to the stats tables. Stats collector process is removed. Updates of shared stats happens with the intervals not shorter than 500ms and not longer than 1s. If the shared memory data is busy and a backend cannot obtain lock immediately, usually the differences are stashed into "pending stats" on local memory and merged with the number at the next chance. --- src/backend/access/transam/xlog.c | 4 +- src/backend/postmaster/autovacuum.c | 59 +- src/backend/postmaster/bgwriter.c | 4 +- src/backend/postmaster/checkpointer.c | 24 +- src/backend/postmaster/pgarch.c | 4 +- src/backend/postmaster/pgstat.c | 4204 ++++++++++--------------- src/backend/postmaster/postmaster.c | 80 +- src/backend/replication/logical/tablesync.c | 9 +- src/backend/replication/logical/worker.c | 4 +- src/backend/storage/buffer/bufmgr.c | 8 +- src/backend/storage/ipc/dsm.c | 24 +- src/backend/storage/ipc/ipci.c | 6 + src/backend/storage/lmgr/lwlock.c | 3 + src/backend/storage/lmgr/lwlocknames.txt | 1 + src/backend/tcop/postgres.c | 27 +- src/backend/utils/adt/pgstatfuncs.c | 50 +- src/backend/utils/init/globals.c | 1 + src/backend/utils/init/postinit.c | 11 + src/backend/utils/misc/guc.c | 41 - src/backend/utils/misc/postgresql.conf.sample | 1 - src/bin/pg_basebackup/t/010_pg_basebackup.pl | 2 +- src/include/miscadmin.h | 2 +- src/include/pgstat.h | 437 +-- src/include/storage/dsm.h | 3 + src/include/storage/lwlock.h | 3 + src/include/utils/timeout.h | 1 + src/test/modules/worker_spi/worker_spi.c | 2 +- 27 files changed, 1928 insertions(+), 3087 deletions(-) diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 7eed5866d2..e52ae54821 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -8587,9 +8587,9 @@ LogCheckpointEnd(bool restartpoint) &sync_secs, &sync_usecs); /* Accumulate checkpoint timing summary data, in milliseconds. */ - BgWriterStats.m_checkpoint_write_time += + BgWriterStats.checkpoint_write_time += write_secs * 1000 + write_usecs / 1000; - BgWriterStats.m_checkpoint_sync_time += + BgWriterStats.checkpoint_sync_time += sync_secs * 1000 + sync_usecs / 1000; /* diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c index 978089575b..10e707e9a1 100644 --- a/src/backend/postmaster/autovacuum.c +++ b/src/backend/postmaster/autovacuum.c @@ -977,7 +977,7 @@ rebuild_database_list(Oid newdb) PgStat_StatDBEntry *entry; /* only consider this database if it has a pgstat entry */ - entry = pgstat_fetch_stat_dbentry(newdb); + entry = pgstat_fetch_stat_dbentry(newdb, true); if (entry != NULL) { /* we assume it isn't found because the hash was just created */ @@ -986,6 +986,7 @@ rebuild_database_list(Oid newdb) /* hash_search already filled in the key */ db->adl_score = score++; /* next_worker is filled in later */ + pfree(entry); } } @@ -1001,7 +1002,7 @@ rebuild_database_list(Oid newdb) * skip databases with no stat entries -- in particular, this gets rid * of dropped databases */ - entry = pgstat_fetch_stat_dbentry(avdb->adl_datid); + entry = pgstat_fetch_stat_dbentry(avdb->adl_datid, true); if (entry == NULL) continue; @@ -1013,6 +1014,7 @@ rebuild_database_list(Oid newdb) db->adl_score = score++; /* next_worker is filled in later */ } + pfree(entry); } /* finally, insert all qualifying databases not previously inserted */ @@ -1025,7 +1027,7 @@ rebuild_database_list(Oid newdb) PgStat_StatDBEntry *entry; /* only consider databases with a pgstat entry */ - entry = pgstat_fetch_stat_dbentry(avdb->adw_datid); + entry = pgstat_fetch_stat_dbentry(avdb->adw_datid, true); if (entry == NULL) continue; @@ -1037,6 +1039,7 @@ rebuild_database_list(Oid newdb) db->adl_score = score++; /* next_worker is filled in later */ } + pfree(entry); } nelems = score; @@ -1235,7 +1238,7 @@ do_start_worker(void) continue; /* ignore not-at-risk DBs */ /* Find pgstat entry if any */ - tmp->adw_entry = pgstat_fetch_stat_dbentry(tmp->adw_datid); + tmp->adw_entry = pgstat_fetch_stat_dbentry(tmp->adw_datid, true); /* * Skip a database with no pgstat entry; it means it hasn't seen any @@ -1273,16 +1276,22 @@ do_start_worker(void) break; } } - if (skipit) - continue; + if (!skipit) + { + /* Remember the db with oldest autovac time. */ + if (avdb == NULL || + tmp->adw_entry->last_autovac_time < + avdb->adw_entry->last_autovac_time) + { + if (avdb) + pfree(avdb->adw_entry); + avdb = tmp; + } + } - /* - * Remember the db with oldest autovac time. (If we are here, both - * tmp->entry and db->entry must be non-null.) - */ - if (avdb == NULL || - tmp->adw_entry->last_autovac_time < avdb->adw_entry->last_autovac_time) - avdb = tmp; + /* Immediately free it if not used */ + if(avdb != tmp) + pfree(tmp->adw_entry); } /* Found a database -- process it */ @@ -1971,7 +1980,7 @@ do_autovacuum(void) * may be NULL if we couldn't find an entry (only happens if we are * forcing a vacuum for anti-wrap purposes). */ - dbentry = pgstat_fetch_stat_dbentry(MyDatabaseId); + dbentry = pgstat_fetch_stat_dbentry(MyDatabaseId, true); /* Start a transaction so our commands have one to play into. */ StartTransactionCommand(); @@ -2021,7 +2030,7 @@ do_autovacuum(void) MemoryContextSwitchTo(AutovacMemCxt); /* The database hash where pgstat keeps shared relations */ - shared = pgstat_fetch_stat_dbentry(InvalidOid); + shared = pgstat_fetch_stat_dbentry(InvalidOid, true); classRel = heap_open(RelationRelationId, AccessShareLock); @@ -2107,6 +2116,8 @@ do_autovacuum(void) relation_needs_vacanalyze(relid, relopts, classForm, tabentry, effective_multixact_freeze_max_age, &dovacuum, &doanalyze, &wraparound); + if (tabentry) + pfree(tabentry); /* Relations that need work are added to table_oids */ if (dovacuum || doanalyze) @@ -2186,10 +2197,11 @@ do_autovacuum(void) /* Fetch the pgstat entry for this table */ tabentry = get_pgstat_tabentry_relid(relid, classForm->relisshared, shared, dbentry); - relation_needs_vacanalyze(relid, relopts, classForm, tabentry, effective_multixact_freeze_max_age, &dovacuum, &doanalyze, &wraparound); + if (tabentry) + pfree(tabentry); /* ignore analyze for toast tables */ if (dovacuum) @@ -2758,12 +2770,10 @@ get_pgstat_tabentry_relid(Oid relid, bool isshared, PgStat_StatDBEntry *shared, if (isshared) { if (PointerIsValid(shared)) - tabentry = hash_search(shared->tables, &relid, - HASH_FIND, NULL); + tabentry = backend_get_tab_entry(shared, relid, true); } else if (PointerIsValid(dbentry)) - tabentry = hash_search(dbentry->tables, &relid, - HASH_FIND, NULL); + tabentry = backend_get_tab_entry(dbentry, relid, true); return tabentry; } @@ -2795,8 +2805,8 @@ table_recheck_autovac(Oid relid, HTAB *table_toast_map, /* use fresh stats */ autovac_refresh_stats(); - shared = pgstat_fetch_stat_dbentry(InvalidOid); - dbentry = pgstat_fetch_stat_dbentry(MyDatabaseId); + shared = pgstat_fetch_stat_dbentry(InvalidOid, true); + dbentry = pgstat_fetch_stat_dbentry(MyDatabaseId, true); /* fetch the relation's relcache entry */ classTup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid)); @@ -2827,6 +2837,8 @@ table_recheck_autovac(Oid relid, HTAB *table_toast_map, relation_needs_vacanalyze(relid, avopts, classForm, tabentry, effective_multixact_freeze_max_age, &dovacuum, &doanalyze, &wraparound); + if (tabentry) + pfree(tabentry); /* ignore ANALYZE for toast tables */ if (classForm->relkind == RELKIND_TOASTVALUE) @@ -2917,7 +2929,8 @@ table_recheck_autovac(Oid relid, HTAB *table_toast_map, } heap_freetuple(classTup); - + pfree(shared); + pfree(dbentry); return tab; } diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c index b1e9bb2c53..a4b1079e60 100644 --- a/src/backend/postmaster/bgwriter.c +++ b/src/backend/postmaster/bgwriter.c @@ -271,9 +271,9 @@ BackgroundWriterMain(void) can_hibernate = BgBufferSync(&wb_context); /* - * Send off activity statistics to the stats collector + * Update activity statistics. */ - pgstat_send_bgwriter(); + pgstat_update_bgwriter(); if (FirstCallSinceLastCheckpoint()) { diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c index 1a033093c5..9235390bc6 100644 --- a/src/backend/postmaster/checkpointer.c +++ b/src/backend/postmaster/checkpointer.c @@ -376,7 +376,7 @@ CheckpointerMain(void) { checkpoint_requested = false; do_checkpoint = true; - BgWriterStats.m_requested_checkpoints++; + BgWriterStats.requested_checkpoints++; } if (shutdown_requested) { @@ -402,7 +402,7 @@ CheckpointerMain(void) if (elapsed_secs >= CheckPointTimeout) { if (!do_checkpoint) - BgWriterStats.m_timed_checkpoints++; + BgWriterStats.timed_checkpoints++; do_checkpoint = true; flags |= CHECKPOINT_CAUSE_TIME; } @@ -520,13 +520,13 @@ CheckpointerMain(void) CheckArchiveTimeout(); /* - * Send off activity statistics to the stats collector. (The reason - * why we re-use bgwriter-related code for this is that the bgwriter - * and checkpointer used to be just one process. It's probably not - * worth the trouble to split the stats support into two independent - * stats message types.) + * Update activity statistics. (The reason why we re-use + * bgwriter-related code for this is that the bgwriter and + * checkpointer used to be just one process. It's probably not worth + * the trouble to split the stats support into two independent + * functions.) */ - pgstat_send_bgwriter(); + pgstat_update_bgwriter(); /* * Sleep until we are signaled or it's time for another checkpoint or @@ -694,9 +694,9 @@ CheckpointWriteDelay(int flags, double progress) CheckArchiveTimeout(); /* - * Report interim activity statistics to the stats collector. + * Register interim activity statistics. */ - pgstat_send_bgwriter(); + pgstat_update_bgwriter(); /* * This sleep used to be connected to bgwriter_delay, typically 200ms. @@ -1296,8 +1296,8 @@ AbsorbFsyncRequests(void) LWLockAcquire(CheckpointerCommLock, LW_EXCLUSIVE); /* Transfer stats counts into pending pgstats message */ - BgWriterStats.m_buf_written_backend += CheckpointerShmem->num_backend_writes; - BgWriterStats.m_buf_fsync_backend += CheckpointerShmem->num_backend_fsync; + BgWriterStats.buf_written_backend += CheckpointerShmem->num_backend_writes; + BgWriterStats.buf_fsync_backend += CheckpointerShmem->num_backend_fsync; CheckpointerShmem->num_backend_writes = 0; CheckpointerShmem->num_backend_fsync = 0; diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 0b41857014..7d4e528096 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -414,7 +414,7 @@ pgarch_ArchiverCopyLoop(void) * Tell the collector about the WAL file that we successfully * archived */ - pgstat_send_archiver(xlog, false); + pgstat_update_archiver(xlog, false); break; /* out of inner retry loop */ } @@ -424,7 +424,7 @@ pgarch_ArchiverCopyLoop(void) * Tell the collector about the WAL file that we failed to * archive */ - pgstat_send_archiver(xlog, true); + pgstat_update_archiver(xlog, true); if (++failures >= NUM_ARCHIVE_RETRIES) { diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c index 4fd874ad77..7f8c2111d0 100644 --- a/src/backend/postmaster/pgstat.c +++ b/src/backend/postmaster/pgstat.c @@ -1,15 +1,10 @@ /* ---------- * pgstat.c * - * All the statistics collector stuff hacked up in one big, ugly file. + * Statistics collector facility. * - * TODO: - Separate collector, postmaster and backend stuff - * into different files. - * - * - Add some automatic call for pgstat vacuuming. - * - * - Add a pgstat config column to pg_database, so this - * entire thing can be enabled/disabled on a per db basis. + * Statistics data is stored in dynamic shared memory. Every backends + * updates and read it individually. * * Copyright (c) 2001-2018, PostgreSQL Global Development Group * @@ -19,92 +14,59 @@ #include "postgres.h" #include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#ifdef HAVE_SYS_SELECT_H -#include -#endif #include "pgstat.h" #include "access/heapam.h" #include "access/htup_details.h" -#include "access/transam.h" #include "access/twophase_rmgr.h" #include "access/xact.h" #include "catalog/pg_database.h" #include "catalog/pg_proc.h" -#include "common/ip.h" #include "libpq/libpq.h" -#include "libpq/pqsignal.h" -#include "mb/pg_wchar.h" #include "miscadmin.h" #include "pg_trace.h" #include "postmaster/autovacuum.h" -#include "postmaster/fork_process.h" -#include "postmaster/postmaster.h" #include "replication/walsender.h" -#include "storage/backendid.h" -#include "storage/dsm.h" -#include "storage/fd.h" #include "storage/ipc.h" -#include "storage/latch.h" #include "storage/lmgr.h" -#include "storage/pg_shmem.h" #include "storage/procsignal.h" #include "storage/sinvaladt.h" #include "utils/ascii.h" #include "utils/guc.h" #include "utils/memutils.h" -#include "utils/ps_status.h" -#include "utils/rel.h" #include "utils/snapmgr.h" -#include "utils/timestamp.h" -#include "utils/tqual.h" - /* ---------- * Timer definitions. * ---------- */ -#define PGSTAT_STAT_INTERVAL 500 /* Minimum time between stats file - * updates; in milliseconds. */ - -#define PGSTAT_RETRY_DELAY 10 /* How long to wait between checks for a - * new file; in milliseconds. */ - -#define PGSTAT_MAX_WAIT_TIME 10000 /* Maximum time to wait for a stats - * file update; in milliseconds. */ - -#define PGSTAT_INQ_INTERVAL 640 /* How often to ping the collector for a - * new file; in milliseconds. */ - -#define PGSTAT_RESTART_INTERVAL 60 /* How often to attempt to restart a - * failed statistics collector; in - * seconds. */ - -#define PGSTAT_POLL_LOOP_COUNT (PGSTAT_MAX_WAIT_TIME / PGSTAT_RETRY_DELAY) -#define PGSTAT_INQ_LOOP_COUNT (PGSTAT_INQ_INTERVAL / PGSTAT_RETRY_DELAY) - -/* Minimum receive buffer size for the collector's socket. */ -#define PGSTAT_MIN_RCVBUF (100 * 1024) +#define PGSTAT_STAT_MIN_INTERVAL 500 /* Minimum time between stats data + * updates; in milliseconds. */ +#define PGSTAT_STAT_MAX_INTERVAL 1000 /* Maximum time between stats data + * updates; in milliseconds. */ /* ---------- * The initial size hints for the hash tables used in the collector. * ---------- */ -#define PGSTAT_DB_HASH_SIZE 16 #define PGSTAT_TAB_HASH_SIZE 512 #define PGSTAT_FUNCTION_HASH_SIZE 512 +/* + * Operation mode of pgstat_get_db_entry. + */ +#define PGSTAT_FETCH_SHARED 0 +#define PGSTAT_FETCH_EXCLUSIVE 1 +#define PGSTAT_FETCH_NOWAIT 2 + +typedef enum +{ + PGSTAT_ENTRY_NOT_FOUND, + PGSTAT_ENTRY_FOUND, + PGSTAT_ENTRY_LOCK_FAILED +} pg_stat_table_result_status; /* ---------- * Total number of backends including auxiliary @@ -132,27 +94,65 @@ int pgstat_track_activity_query_size = 1024; * ---------- */ char *pgstat_stat_directory = NULL; -char *pgstat_stat_filename = NULL; -char *pgstat_stat_tmpname = NULL; + +/* Shared stats bootstrap infomation */ +typedef struct StatsShmemStruct { + dsa_handle stats_dsa_handle; + dshash_table_handle db_stats_handle; + dsa_pointer global_stats; + dsa_pointer archiver_stats; +} StatsShmemStruct; + /* * BgWriter global statistics counters (unused in other processes). * Stored directly in a stats message structure so it can be sent * without needing to copy things around. We assume this inits to zeroes. */ -PgStat_MsgBgWriter BgWriterStats; +PgStat_BgWriter BgWriterStats; /* ---------- * Local data * ---------- */ -NON_EXEC_STATIC pgsocket pgStatSock = PGINVALID_SOCKET; +static StatsShmemStruct * StatsShmem = NULL; +static dsa_area *area = NULL; +static dshash_table *db_stats; +static HTAB *snapshot_db_stats; +static MemoryContext stats_cxt; -static struct sockaddr_storage pgStatAddr; +/* + * report withholding facility. + * + * some report items are withholded if required lock is not acquired + * immediately. + */ +static bool pgstat_pending_recoveryconflict = false; +static bool pgstat_pending_deadlock = false; +static bool pgstat_pending_tempfile = false; -static time_t last_pgstat_start_time; - -static bool pgStatRunningInCollector = false; +/* dshash parameter for each type of table */ +static const dshash_parameters dsh_dbparams = { + sizeof(Oid), + sizeof(PgStat_StatDBEntry), + dshash_memcmp, + dshash_memhash, + LWTRANCHE_STATS_DB +}; +static const dshash_parameters dsh_tblparams = { + sizeof(Oid), + sizeof(PgStat_StatTabEntry), + dshash_memcmp, + dshash_memhash, + LWTRANCHE_STATS_FUNC_TABLE +}; +static const dshash_parameters dsh_funcparams = { + sizeof(Oid), + sizeof(PgStat_StatFuncEntry), + dshash_memcmp, + dshash_memhash, + LWTRANCHE_STATS_FUNC_TABLE +}; /* * Structures in which backends store per-table info that's waiting to be @@ -189,18 +189,14 @@ typedef struct TabStatHashEntry * Hash table for O(1) t_id -> tsa_entry lookup */ static HTAB *pgStatTabHash = NULL; +static HTAB *pgStatPendingTabHash = NULL; /* * Backends store per-function info that's waiting to be sent to the collector * in this hash table (indexed by function OID). */ static HTAB *pgStatFunctions = NULL; - -/* - * Indicates if backend has some function stats that it hasn't yet - * sent to the collector. - */ -static bool have_function_stats = false; +static HTAB *pgStatPendingFunctions = NULL; /* * Tuple insertion/deletion counts for an open transaction can't be propagated @@ -237,6 +233,12 @@ typedef struct TwoPhasePgStatRecord bool t_truncated; /* was the relation truncated? */ } TwoPhasePgStatRecord; +typedef struct +{ + dshash_table *tabhash; + PgStat_StatDBEntry *dbentry; +} pgstat_apply_tabstat_context; + /* * Info about current "snapshot" of stats file */ @@ -250,23 +252,15 @@ static LocalPgBackendStatus *localBackendStatusTable = NULL; static int localNumBackends = 0; /* - * Cluster wide statistics, kept in the stats collector. - * Contains statistics that are not collected per database - * or per table. + * Cluster wide statistics. + * Contains statistics that are not collected per database or per table. + * shared_* are the statistics maintained by pgstats and snapshot_* are the + * snapshots taken on backends. */ -static PgStat_ArchiverStats archiverStats; -static PgStat_GlobalStats globalStats; - -/* - * List of OIDs of databases we need to write out. If an entry is InvalidOid, - * it means to write only the shared-catalog stats ("DB 0"); otherwise, we - * will write both that DB's data and the shared stats. - */ -static List *pending_write_requests = NIL; - -/* Signal handler flags */ -static volatile bool need_exit = false; -static volatile bool got_SIGHUP = false; +static PgStat_ArchiverStats *shared_archiverStats; +static PgStat_ArchiverStats *snapshot_archiverStats; +static PgStat_GlobalStats *shared_globalStats; +static PgStat_GlobalStats *snapshot_globalStats; /* * Total time charged to functions so far in the current backend. @@ -280,32 +274,41 @@ static instr_time total_func_time; * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgstat_forkexec(void); -#endif - -NON_EXEC_STATIC void PgstatCollectorMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgstat_exit(SIGNAL_ARGS); +/* functions used in backends */ static void pgstat_beshutdown_hook(int code, Datum arg); -static void pgstat_sighup_handler(SIGNAL_ARGS); -static PgStat_StatDBEntry *pgstat_get_db_entry(Oid databaseid, bool create); -static PgStat_StatTabEntry *pgstat_get_tab_entry(PgStat_StatDBEntry *dbentry, - Oid tableoid, bool create); -static void pgstat_write_statsfiles(bool permanent, bool allDbs); -static void pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry, bool permanent); -static HTAB *pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep); -static void pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, bool permanent); -static void backend_read_statsfile(void); +static PgStat_StatDBEntry *pgstat_get_db_entry(Oid databaseid, int op, + pg_stat_table_result_status *status); +static PgStat_StatTabEntry *pgstat_get_tab_entry(dshash_table *table, Oid tableoid, bool create); +static void pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry); +static void pgstat_read_db_statsfile(Oid databaseid, dshash_table *tabhash, dshash_table *funchash); + +/* functions used in backends */ +static bool backend_snapshot_global_stats(void); +static PgStat_StatFuncEntry *backend_get_func_etnry(PgStat_StatDBEntry *dbent, Oid funcid, bool oneshot); static void pgstat_read_current_status(void); -static bool pgstat_write_statsfile_needed(void); -static bool pgstat_db_requested(Oid databaseid); +static void pgstat_postmaster_shutdown(int code, Datum arg); +static void pgstat_apply_pending_tabstats(bool shared, bool force, + pgstat_apply_tabstat_context *cxt); +static bool pgstat_apply_tabstat(pgstat_apply_tabstat_context *cxt, + PgStat_TableStatus *entry, bool nowait); +static void pgstat_merge_tabentry(PgStat_TableStatus *deststat, + PgStat_TableStatus *srcstat, + bool init); +static void pgstat_update_funcstats(bool force, PgStat_StatDBEntry *dbentry); +static void pgstat_reset_all_counters(void); +static void pgstat_cleanup_recovery_conflict(PgStat_StatDBEntry *dbentry); +static void pgstat_cleanup_deadlock(PgStat_StatDBEntry *dbentry); +static void pgstat_cleanup_tempfile(PgStat_StatDBEntry *dbentry); + +static inline void pgstat_merge_backendstats_to_funcentry( + PgStat_StatFuncEntry *dest, PgStat_BackendFunctionEntry *src, bool init); +static inline void pgstat_merge_funcentry( + PgStat_StatFuncEntry *dest, PgStat_StatFuncEntry *src, bool init); -static void pgstat_send_tabstat(PgStat_MsgTabstat *tsmsg); -static void pgstat_send_funcstats(void); static HTAB *pgstat_collect_oids(Oid catalogid); - +static void reset_dbentry_counters(PgStat_StatDBEntry *dbentry); static PgStat_TableStatus *get_tabstat_entry(Oid rel_id, bool isshared); static void pgstat_setup_memcxt(void); @@ -316,320 +319,16 @@ static const char *pgstat_get_wait_ipc(WaitEventIPC w); static const char *pgstat_get_wait_timeout(WaitEventTimeout w); static const char *pgstat_get_wait_io(WaitEventIO w); -static void pgstat_setheader(PgStat_MsgHdr *hdr, StatMsgType mtype); -static void pgstat_send(void *msg, int len); - -static void pgstat_recv_inquiry(PgStat_MsgInquiry *msg, int len); -static void pgstat_recv_tabstat(PgStat_MsgTabstat *msg, int len); -static void pgstat_recv_tabpurge(PgStat_MsgTabpurge *msg, int len); -static void pgstat_recv_dropdb(PgStat_MsgDropdb *msg, int len); -static void pgstat_recv_resetcounter(PgStat_MsgResetcounter *msg, int len); -static void pgstat_recv_resetsharedcounter(PgStat_MsgResetsharedcounter *msg, int len); -static void pgstat_recv_resetsinglecounter(PgStat_MsgResetsinglecounter *msg, int len); -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); -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 bool pgstat_update_tabentry(dshash_table *tabhash, + PgStat_TableStatus *stat, bool nowait); +static void pgstat_update_dbentry(PgStat_StatDBEntry *dbentry, + PgStat_TableStatus *stat); /* ------------------------------------------------------------ * Public functions called from postmaster follow * ------------------------------------------------------------ */ -/* ---------- - * pgstat_init() - - * - * Called from postmaster at startup. Create the resources required - * by the statistics collector process. If unable to do so, do not - * fail --- better to let the postmaster start with stats collection - * disabled. - * ---------- - */ -void -pgstat_init(void) -{ - ACCEPT_TYPE_ARG3 alen; - struct addrinfo *addrs = NULL, - *addr, - hints; - int ret; - fd_set rset; - struct timeval tv; - char test_byte; - int sel_res; - int tries = 0; - -#define TESTBYTEVAL ((char) 199) - - /* - * This static assertion verifies that we didn't mess up the calculations - * involved in selecting maximum payload sizes for our UDP messages. - * Because the only consequence of overrunning PGSTAT_MAX_MSG_SIZE would - * be silent performance loss from fragmentation, it seems worth having a - * compile-time cross-check that we didn't. - */ - StaticAssertStmt(sizeof(PgStat_Msg) <= PGSTAT_MAX_MSG_SIZE, - "maximum stats message size exceeds PGSTAT_MAX_MSG_SIZE"); - - /* - * Create the UDP socket for sending and receiving statistic messages - */ - hints.ai_flags = AI_PASSIVE; - hints.ai_family = AF_UNSPEC; - hints.ai_socktype = SOCK_DGRAM; - hints.ai_protocol = 0; - hints.ai_addrlen = 0; - hints.ai_addr = NULL; - hints.ai_canonname = NULL; - hints.ai_next = NULL; - ret = pg_getaddrinfo_all("localhost", NULL, &hints, &addrs); - if (ret || !addrs) - { - ereport(LOG, - (errmsg("could not resolve \"localhost\": %s", - gai_strerror(ret)))); - goto startup_failed; - } - - /* - * On some platforms, pg_getaddrinfo_all() may return multiple addresses - * only one of which will actually work (eg, both IPv6 and IPv4 addresses - * when kernel will reject IPv6). Worse, the failure may occur at the - * bind() or perhaps even connect() stage. So we must loop through the - * results till we find a working combination. We will generate LOG - * messages, but no error, for bogus combinations. - */ - for (addr = addrs; addr; addr = addr->ai_next) - { -#ifdef HAVE_UNIX_SOCKETS - /* Ignore AF_UNIX sockets, if any are returned. */ - if (addr->ai_family == AF_UNIX) - continue; -#endif - - if (++tries > 1) - ereport(LOG, - (errmsg("trying another address for the statistics collector"))); - - /* - * Create the socket. - */ - if ((pgStatSock = socket(addr->ai_family, SOCK_DGRAM, 0)) == PGINVALID_SOCKET) - { - ereport(LOG, - (errcode_for_socket_access(), - errmsg("could not create socket for statistics collector: %m"))); - continue; - } - - /* - * Bind it to a kernel assigned port on localhost and get the assigned - * port via getsockname(). - */ - if (bind(pgStatSock, addr->ai_addr, addr->ai_addrlen) < 0) - { - ereport(LOG, - (errcode_for_socket_access(), - errmsg("could not bind socket for statistics collector: %m"))); - closesocket(pgStatSock); - pgStatSock = PGINVALID_SOCKET; - continue; - } - - alen = sizeof(pgStatAddr); - if (getsockname(pgStatSock, (struct sockaddr *) &pgStatAddr, &alen) < 0) - { - ereport(LOG, - (errcode_for_socket_access(), - errmsg("could not get address of socket for statistics collector: %m"))); - closesocket(pgStatSock); - pgStatSock = PGINVALID_SOCKET; - continue; - } - - /* - * Connect the socket to its own address. This saves a few cycles by - * not having to respecify the target address on every send. This also - * provides a kernel-level check that only packets from this same - * address will be received. - */ - if (connect(pgStatSock, (struct sockaddr *) &pgStatAddr, alen) < 0) - { - ereport(LOG, - (errcode_for_socket_access(), - errmsg("could not connect socket for statistics collector: %m"))); - closesocket(pgStatSock); - pgStatSock = PGINVALID_SOCKET; - continue; - } - - /* - * Try to send and receive a one-byte test message on the socket. This - * is to catch situations where the socket can be created but will not - * actually pass data (for instance, because kernel packet filtering - * rules prevent it). - */ - test_byte = TESTBYTEVAL; - -retry1: - if (send(pgStatSock, &test_byte, 1, 0) != 1) - { - if (errno == EINTR) - goto retry1; /* if interrupted, just retry */ - ereport(LOG, - (errcode_for_socket_access(), - errmsg("could not send test message on socket for statistics collector: %m"))); - closesocket(pgStatSock); - pgStatSock = PGINVALID_SOCKET; - continue; - } - - /* - * There could possibly be a little delay before the message can be - * received. We arbitrarily allow up to half a second before deciding - * it's broken. - */ - for (;;) /* need a loop to handle EINTR */ - { - FD_ZERO(&rset); - FD_SET(pgStatSock, &rset); - - tv.tv_sec = 0; - tv.tv_usec = 500000; - sel_res = select(pgStatSock + 1, &rset, NULL, NULL, &tv); - if (sel_res >= 0 || errno != EINTR) - break; - } - if (sel_res < 0) - { - ereport(LOG, - (errcode_for_socket_access(), - errmsg("select() failed in statistics collector: %m"))); - closesocket(pgStatSock); - pgStatSock = PGINVALID_SOCKET; - continue; - } - if (sel_res == 0 || !FD_ISSET(pgStatSock, &rset)) - { - /* - * This is the case we actually think is likely, so take pains to - * give a specific message for it. - * - * errno will not be set meaningfully here, so don't use it. - */ - ereport(LOG, - (errcode(ERRCODE_CONNECTION_FAILURE), - errmsg("test message did not get through on socket for statistics collector"))); - closesocket(pgStatSock); - pgStatSock = PGINVALID_SOCKET; - continue; - } - - test_byte++; /* just make sure variable is changed */ - -retry2: - if (recv(pgStatSock, &test_byte, 1, 0) != 1) - { - if (errno == EINTR) - goto retry2; /* if interrupted, just retry */ - ereport(LOG, - (errcode_for_socket_access(), - errmsg("could not receive test message on socket for statistics collector: %m"))); - closesocket(pgStatSock); - pgStatSock = PGINVALID_SOCKET; - continue; - } - - if (test_byte != TESTBYTEVAL) /* strictly paranoia ... */ - { - ereport(LOG, - (errcode(ERRCODE_INTERNAL_ERROR), - errmsg("incorrect test message transmission on socket for statistics collector"))); - closesocket(pgStatSock); - pgStatSock = PGINVALID_SOCKET; - continue; - } - - /* If we get here, we have a working socket */ - break; - } - - /* Did we find a working address? */ - if (!addr || pgStatSock == PGINVALID_SOCKET) - goto startup_failed; - - /* - * Set the socket to non-blocking IO. This ensures that if the collector - * falls behind, statistics messages will be discarded; backends won't - * block waiting to send messages to the collector. - */ - if (!pg_set_noblock(pgStatSock)) - { - ereport(LOG, - (errcode_for_socket_access(), - errmsg("could not set statistics collector socket to nonblocking mode: %m"))); - goto startup_failed; - } - - /* - * Try to ensure that the socket's receive buffer is at least - * PGSTAT_MIN_RCVBUF bytes, so that it won't easily overflow and lose - * data. Use of UDP protocol means that we are willing to lose data under - * heavy load, but we don't want it to happen just because of ridiculously - * small default buffer sizes (such as 8KB on older Windows versions). - */ - { - int old_rcvbuf; - int new_rcvbuf; - ACCEPT_TYPE_ARG3 rcvbufsize = sizeof(old_rcvbuf); - - if (getsockopt(pgStatSock, SOL_SOCKET, SO_RCVBUF, - (char *) &old_rcvbuf, &rcvbufsize) < 0) - { - elog(LOG, "getsockopt(SO_RCVBUF) failed: %m"); - /* if we can't get existing size, always try to set it */ - old_rcvbuf = 0; - } - - new_rcvbuf = PGSTAT_MIN_RCVBUF; - if (old_rcvbuf < new_rcvbuf) - { - if (setsockopt(pgStatSock, SOL_SOCKET, SO_RCVBUF, - (char *) &new_rcvbuf, sizeof(new_rcvbuf)) < 0) - elog(LOG, "setsockopt(SO_RCVBUF) failed: %m"); - } - } - - pg_freeaddrinfo_all(hints.ai_family, addrs); - - return; - -startup_failed: - ereport(LOG, - (errmsg("disabling statistics collector for lack of working socket"))); - - if (addrs) - pg_freeaddrinfo_all(hints.ai_family, addrs); - - if (pgStatSock != PGINVALID_SOCKET) - closesocket(pgStatSock); - pgStatSock = PGINVALID_SOCKET; - - /* - * Adjust GUC variables to suppress useless activity, and for debugging - * purposes (seeing track_counts off is a clue that we failed here). We - * use PGC_S_OVERRIDE because there is no point in trying to turn it back - * on from postgresql.conf without a restart. - */ - SetConfigOption("track_counts", "off", PGC_INTERNAL, PGC_S_OVERRIDE); -} - /* * subroutine for pgstat_reset_all */ @@ -678,119 +377,54 @@ pgstat_reset_remove_files(const char *directory) /* * pgstat_reset_all() - * - * Remove the stats files. This is currently used only if WAL - * recovery is needed after a crash. + * Remove the stats files and on-memory counters. This is currently used only + * if WAL recovery is needed after a crash. */ void pgstat_reset_all(void) { - pgstat_reset_remove_files(pgstat_stat_directory); pgstat_reset_remove_files(PGSTAT_STAT_PERMANENT_DIRECTORY); + pgstat_reset_all_counters(); } -#ifdef EXEC_BACKEND - -/* - * pgstat_forkexec() - +/* ---------- + * pgstat_create_shared_stats() - * - * Format up the arglist for, then fork and exec, statistics collector process + * create shared stats memory + * ---------- */ -static pid_t -pgstat_forkexec(void) +static void +pgstat_create_shared_stats(void) { - char *av[10]; - int ac = 0; + MemoryContext oldcontext; - av[ac++] = "postgres"; - av[ac++] = "--forkcol"; - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + Assert(StatsShmem->stats_dsa_handle == DSM_HANDLE_INVALID); - av[ac] = NULL; - Assert(ac < lengthof(av)); + /* lives for the lifetime of the process */ + oldcontext = MemoryContextSwitchTo(TopMemoryContext); + area = dsa_create(LWTRANCHE_STATS_DSA); + dsa_pin_mapping(area); - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ + db_stats = dshash_create(area, &dsh_dbparams, 0); + /* create shared area and write bootstrap information */ + StatsShmem->stats_dsa_handle = dsa_get_handle(area); + StatsShmem->global_stats = + dsa_allocate0(area, sizeof(PgStat_GlobalStats)); + StatsShmem->archiver_stats = + dsa_allocate0(area, sizeof(PgStat_ArchiverStats)); + StatsShmem->db_stats_handle = + dshash_get_hash_table_handle(db_stats); -/* - * pgstat_start() - - * - * Called from postmaster at startup or after an existing collector - * died. Attempt to fire up a fresh statistics collector. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgstat_start(void) -{ - time_t curtime; - pid_t pgStatPid; - - /* - * Check that the socket is there, else pgstat_init failed and we can do - * nothing useful. - */ - if (pgStatSock == PGINVALID_SOCKET) - return 0; - - /* - * Do nothing if too soon since last collector start. This is a safety - * valve to protect against continuous respawn attempts if the collector - * is dying immediately at launch. Note that since we will be re-called - * from the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgstat_start_time) < - (unsigned int) PGSTAT_RESTART_INTERVAL) - return 0; - last_pgstat_start_time = curtime; - - /* - * Okay, fork off the collector. - */ -#ifdef EXEC_BACKEND - switch ((pgStatPid = pgstat_forkexec())) -#else - switch ((pgStatPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork statistics collector: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgstatCollectorMain(0, NULL); - break; -#endif - - default: - return (int) pgStatPid; - } - - /* shouldn't get here */ - return 0; + /* connect to the memory */ + snapshot_db_stats = NULL; + shared_globalStats = (PgStat_GlobalStats *) + dsa_get_address(area, StatsShmem->global_stats); + shared_archiverStats = (PgStat_ArchiverStats *) + dsa_get_address(area, StatsShmem->archiver_stats); + MemoryContextSwitchTo(oldcontext); } -void -allow_immediate_pgstat_restart(void) -{ - last_pgstat_start_time = 0; -} /* ------------------------------------------------------------ * Public functions used by backends follow @@ -802,41 +436,107 @@ allow_immediate_pgstat_restart(void) * pgstat_report_stat() - * * Must be called by processes that performs DML: tcop/postgres.c, logical - * receiver processes, SPI worker, etc. to send the so far collected - * per-table and function usage statistics to the collector. Note that this - * is called only when not within a transaction, so it is fair to use - * transaction stop time as an approximation of current time. - * ---------- + * receiver processes, SPI worker, etc. to apply the so far collected + * per-table and function usage statistics to the shared statistics hashes. + * + * This requires taking some locks on the shared statistics hashes and some + * of updates may be withholded on lock failure. Pending updates are + * retried in later call of this function and finally cleaned up by calling + * this function with force = true or PGSTAT_STAT_MAX_INTERVAL milliseconds + * was elapsed since last cleanup. On the other hand updates by regular + * backends happen with the interval not shorter than + * PGSTAT_STAT_MIN_INTERVAL when force = false. + * + * Returns time in milliseconds until the next update time. + * + * Note that this is called only when not within a transaction, so it is fair + * to use transaction stop time as an approximation of current time. + * ---------- */ -void -pgstat_report_stat(bool force) +long +pgstat_update_stat(bool force) { /* we assume this inits to all zeroes: */ - static const PgStat_TableCounts all_zeroes; static TimestampTz last_report = 0; - + static TimestampTz oldest_pending = 0; TimestampTz now; - PgStat_MsgTabstat regular_msg; - PgStat_MsgTabstat shared_msg; TabStatusArray *tsa; - int i; + pgstat_apply_tabstat_context cxt; + bool other_pending_stats = false; + long elapsed; + long secs; + int usecs; + + if (pgstat_pending_recoveryconflict || + pgstat_pending_deadlock || + pgstat_pending_tempfile || + pgStatPendingFunctions) + other_pending_stats = true; /* Don't expend a clock check if nothing to do */ - if ((pgStatTabList == NULL || pgStatTabList->tsa_used == 0) && - pgStatXactCommit == 0 && pgStatXactRollback == 0 && - !have_function_stats) - return; + if (!other_pending_stats && !pgStatPendingTabHash && + (pgStatTabList == NULL || pgStatTabList->tsa_used == 0) && + pgStatXactCommit == 0 && pgStatXactRollback == 0) + return 0; - /* - * Don't send a message unless it's been at least PGSTAT_STAT_INTERVAL - * msec since we last sent one, or the caller wants to force stats out. - */ now = GetCurrentTransactionStopTimestamp(); - if (!force && - !TimestampDifferenceExceeds(last_report, now, PGSTAT_STAT_INTERVAL)) - return; + + if (!force) + { + /* + * Don't update shared stats unless it's been at least + * PGSTAT_STAT_MIN_INTERVAL msec since we last updated one. + * Returns time to wait in the case. + */ + TimestampDifference(last_report, now, &secs, &usecs); + elapsed = secs * 1000 + usecs /1000; + + if(elapsed < PGSTAT_STAT_MIN_INTERVAL) + { + /* we know we have some statistics */ + if (oldest_pending == 0) + oldest_pending = now; + + return PGSTAT_STAT_MIN_INTERVAL - elapsed; + } + + + /* + * Don't keep pending stats for longer than PGSTAT_STAT_MAX_INTERVAL. + */ + if (oldest_pending > 0) + { + TimestampDifference(oldest_pending, now, &secs, &usecs); + elapsed = secs * 1000 + usecs /1000; + + if(elapsed > PGSTAT_STAT_MAX_INTERVAL) + force = true; + } + } + last_report = now; + /* setup stats update context*/ + cxt.dbentry = NULL; + cxt.tabhash = NULL; + + /* Forecibly update other stats if any. */ + if (other_pending_stats) + { + cxt.dbentry = + pgstat_get_db_entry(MyDatabaseId, PGSTAT_FETCH_EXCLUSIVE, NULL); + + /* clean up pending statistics if any */ + if (pgStatPendingFunctions) + pgstat_update_funcstats(true, cxt.dbentry); + if (pgstat_pending_recoveryconflict) + pgstat_cleanup_recovery_conflict(cxt.dbentry); + if (pgstat_pending_deadlock) + pgstat_cleanup_deadlock(cxt.dbentry); + if (pgstat_pending_tempfile) + pgstat_cleanup_tempfile(cxt.dbentry); + } + /* * Destroy pgStatTabHash before we start invalidating PgStat_TableEntry * entries it points to. (Should we fail partway through the loop below, @@ -849,23 +549,55 @@ pgstat_report_stat(bool force) pgStatTabHash = NULL; /* - * Scan through the TabStatusArray struct(s) to find tables that actually - * have counts, and build messages to send. We have to separate shared - * relations from regular ones because the databaseid field in the message - * header has to depend on that. + * XX: We cannot lock two dshash entries at once. Since we must keep lock + * while tables stats are being updated we have no choice other than + * separating jobs for shared table stats and that of egular tables. + * Looping over the array twice isapparently ineffcient and more efficient + * way is expected. */ - regular_msg.m_databaseid = MyDatabaseId; - shared_msg.m_databaseid = InvalidOid; - regular_msg.m_nentries = 0; - shared_msg.m_nentries = 0; + + /* The first call of the followings uses dbentry obtained above if any.*/ + pgstat_apply_pending_tabstats(false, force, &cxt); + pgstat_apply_pending_tabstats(true, force, &cxt); + + /* zero out TableStatus structs after use */ + for (tsa = pgStatTabList; tsa != NULL; tsa = tsa->tsa_next) + { + MemSet(tsa->tsa_entries, 0, + tsa->tsa_used * sizeof(PgStat_TableStatus)); + tsa->tsa_used = 0; + } + + /* record oldest pending update time */ + if (pgStatPendingTabHash == NULL) + oldest_pending = 0; + else if (oldest_pending == 0) + oldest_pending = now; + + return 0; +} + +/* + * Subroutine for pgstat_update_stat. + * + * Appies table stats in table status array merging with pending stats if any. + * If force is true waits until required locks to be acquired. Elsewise stats + * merged stats as pending sats and it will be processed in the next chance. + */ +static void +pgstat_apply_pending_tabstats(bool shared, bool force, + pgstat_apply_tabstat_context *cxt) +{ + static const PgStat_TableCounts all_zeroes; + TabStatusArray *tsa; + int i; for (tsa = pgStatTabList; tsa != NULL; tsa = tsa->tsa_next) { for (i = 0; i < tsa->tsa_used; i++) { PgStat_TableStatus *entry = &tsa->tsa_entries[i]; - PgStat_MsgTabstat *this_msg; - PgStat_TableEntry *this_ent; + PgStat_TableStatus *pentry = NULL; /* Shouldn't have any pending transaction-dependent counts */ Assert(entry->trans == NULL); @@ -878,178 +610,440 @@ pgstat_report_stat(bool force) sizeof(PgStat_TableCounts)) == 0) continue; - /* - * OK, insert data into the appropriate message, and send if full. - */ - this_msg = entry->t_shared ? &shared_msg : ®ular_msg; - this_ent = &this_msg->m_entry[this_msg->m_nentries]; - this_ent->t_id = entry->t_id; - memcpy(&this_ent->t_counts, &entry->t_counts, - sizeof(PgStat_TableCounts)); - if (++this_msg->m_nentries >= PGSTAT_NUM_TABENTRIES) + /* Skip if this entry is not match the request */ + if (entry->t_shared != shared) + continue; + + /* if pending update exists, it should be applied along with */ + if (pgStatPendingTabHash != NULL) { - pgstat_send_tabstat(this_msg); - this_msg->m_nentries = 0; + pentry = hash_search(pgStatPendingTabHash, + (void *) entry, HASH_FIND, NULL); + + if (pentry) + { + /* merge new update into pending updates */ + pgstat_merge_tabentry(pentry, entry, false); + entry = pentry; + } + } + + /* try to apply the merged stats */ + if (pgstat_apply_tabstat(cxt, entry, !force)) + { + /* succeeded. remove it if it was pending stats */ + if (pentry && entry != pentry) + hash_search(pgStatPendingTabHash, + (void *) pentry, HASH_REMOVE, NULL); + } + else if (!pentry) + { + /* failed and there was no pending entry, create new one. */ + bool found; + + if (pgStatPendingTabHash == NULL) + { + HASHCTL ctl; + + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(Oid); + ctl.entrysize = sizeof(PgStat_TableStatus); + pgStatPendingTabHash = + hash_create("pgstat pending table stats hash", + TABSTAT_QUANTUM, + &ctl, + HASH_ELEM | HASH_BLOBS); + } + + pentry = hash_search(pgStatPendingTabHash, + (void *) entry, HASH_ENTER, &found); + Assert (!found); + + *pentry = *entry; } } - /* zero out TableStatus structs after use */ - MemSet(tsa->tsa_entries, 0, - tsa->tsa_used * sizeof(PgStat_TableStatus)); - tsa->tsa_used = 0; + } + + /* if any pending stats exists, try to clean it up */ + if (pgStatPendingTabHash != NULL) + { + HASH_SEQ_STATUS pstat; + PgStat_TableStatus *pentry; + + hash_seq_init(&pstat, pgStatPendingTabHash); + while((pentry = (PgStat_TableStatus *) hash_seq_search(&pstat)) != NULL) + { + /* Skip if this entry is not match the request */ + if (pentry->t_shared != shared) + continue; + + /* apply pending entry and remove on success */ + if (pgstat_apply_tabstat(cxt, pentry, !force)) + hash_search(pgStatPendingTabHash, + (void *) pentry, HASH_REMOVE, NULL); + } + + /* destroy the hash if no entry is left */ + if (hash_get_num_entries(pgStatPendingTabHash) == 0) + { + hash_destroy(pgStatPendingTabHash); + pgStatPendingTabHash = NULL; + } + } + + if (cxt->tabhash) + dshash_detach(cxt->tabhash); + if (cxt->dbentry) + dshash_release_lock(db_stats, cxt->dbentry); + cxt->tabhash = NULL; + cxt->dbentry = NULL; +} + + +/* + * pgstat_apply_tabstat: update shared stats entry using given entry + * + * If nowait is true, just returns false on lock failure. Dshashes for table + * and function stats are kept attached and stored in ctx. The caller must + * detach them after use. + */ +bool +pgstat_apply_tabstat(pgstat_apply_tabstat_context *cxt, + PgStat_TableStatus *entry, bool nowait) +{ + Oid dboid = entry->t_shared ? InvalidOid : MyDatabaseId; + int table_mode = PGSTAT_FETCH_EXCLUSIVE; + bool updated = false; + + if (nowait) + table_mode |= PGSTAT_FETCH_NOWAIT; + + /* + * We need to keep lock on dbentries for regular tables to avoid race + * condition with drop database. So we hold it in the context variable. We + * don't need that for shared tables. + */ + if (!cxt->dbentry) + cxt->dbentry = pgstat_get_db_entry(dboid, table_mode, NULL); + + /* we cannot acquire lock, just return */ + if (!cxt->dbentry) + return false; + + /* attach shared stats table if not yet */ + if (!cxt->tabhash) + { + /* apply database stats */ + if (!entry->t_shared) + { + /* Update database-wide stats */ + cxt->dbentry->n_xact_commit += pgStatXactCommit; + cxt->dbentry->n_xact_rollback += pgStatXactRollback; + cxt->dbentry->n_block_read_time += pgStatBlockReadTime; + cxt->dbentry->n_block_write_time += pgStatBlockWriteTime; + pgStatXactCommit = 0; + pgStatXactRollback = 0; + pgStatBlockReadTime = 0; + pgStatBlockWriteTime = 0; + } + + cxt->tabhash = + dshash_attach(area, &dsh_tblparams, cxt->dbentry->tables, 0); } /* - * Send partial messages. Make sure that any pending xact commit/abort - * gets counted, even if there are no table stats to send. + * If we have access to the required data, try update table stats first. + * Update database stats only if the first step suceeded. */ - if (regular_msg.m_nentries > 0 || - pgStatXactCommit > 0 || pgStatXactRollback > 0) - pgstat_send_tabstat(®ular_msg); - if (shared_msg.m_nentries > 0) - pgstat_send_tabstat(&shared_msg); + if (pgstat_update_tabentry(cxt->tabhash, entry, nowait)) + { + pgstat_update_dbentry(cxt->dbentry, entry); + updated = true; + } - /* Now, send function statistics */ - pgstat_send_funcstats(); + return updated; } /* - * Subroutine for pgstat_report_stat: finish and send a tabstat message + * pgstat_merge_tabentry: subroutine for pgstat_update_stat + * + * Merge srcstat into deststat. Existing value in deststat is cleard if + * init is true. */ static void -pgstat_send_tabstat(PgStat_MsgTabstat *tsmsg) +pgstat_merge_tabentry(PgStat_TableStatus *deststat, + PgStat_TableStatus *srcstat, + bool init) { - int n; - int len; + Assert (deststat != srcstat); - /* It's unlikely we'd get here with no socket, but maybe not impossible */ - if (pgStatSock == PGINVALID_SOCKET) - return; - - /* - * Report and reset accumulated xact commit/rollback and I/O timings - * whenever we send a normal tabstat message - */ - if (OidIsValid(tsmsg->m_databaseid)) - { - tsmsg->m_xact_commit = pgStatXactCommit; - tsmsg->m_xact_rollback = pgStatXactRollback; - tsmsg->m_block_read_time = pgStatBlockReadTime; - tsmsg->m_block_write_time = pgStatBlockWriteTime; - pgStatXactCommit = 0; - pgStatXactRollback = 0; - pgStatBlockReadTime = 0; - pgStatBlockWriteTime = 0; - } + if (init) + deststat->t_counts = srcstat->t_counts; else { - tsmsg->m_xact_commit = 0; - tsmsg->m_xact_rollback = 0; - tsmsg->m_block_read_time = 0; - tsmsg->m_block_write_time = 0; + PgStat_TableCounts *dest = &deststat->t_counts; + PgStat_TableCounts *src = &srcstat->t_counts; + + dest->t_numscans += src->t_numscans; + dest->t_tuples_returned += src->t_tuples_returned; + dest->t_tuples_fetched += src->t_tuples_fetched; + dest->t_tuples_inserted += src->t_tuples_inserted; + dest->t_tuples_updated += src->t_tuples_updated; + dest->t_tuples_deleted += src->t_tuples_deleted; + dest->t_tuples_hot_updated += src->t_tuples_hot_updated; + dest->t_truncated |= src->t_truncated; + + /* If table was truncated, first reset the live/dead counters */ + if (src->t_truncated) + { + dest->t_delta_live_tuples = 0; + dest->t_delta_dead_tuples = 0; + } + dest->t_delta_live_tuples += src->t_delta_live_tuples; + dest->t_delta_dead_tuples += src->t_delta_dead_tuples; + dest->t_changed_tuples += src->t_changed_tuples; + dest->t_blocks_fetched += src->t_blocks_fetched; + dest->t_blocks_hit += src->t_blocks_hit; } - - n = tsmsg->m_nentries; - len = offsetof(PgStat_MsgTabstat, m_entry[0]) + - n * sizeof(PgStat_TableEntry); - - pgstat_setheader(&tsmsg->m_hdr, PGSTAT_MTYPE_TABSTAT); - pgstat_send(tsmsg, len); } - + /* - * Subroutine for pgstat_report_stat: populate and send a function stat message + * pgstat_update_funcstats: subroutine for pgstat_update_stat + * + * updates a function stat */ static void -pgstat_send_funcstats(void) +pgstat_update_funcstats(bool force, PgStat_StatDBEntry *dbentry) { /* we assume this inits to all zeroes: */ static const PgStat_FunctionCounts all_zeroes; + pg_stat_table_result_status status = 0; + dshash_table *funchash; + bool nowait = !force; + bool release_db = false; + int table_op = PGSTAT_FETCH_EXCLUSIVE; - PgStat_MsgFuncstat msg; - PgStat_BackendFunctionEntry *entry; - HASH_SEQ_STATUS fstat; - - if (pgStatFunctions == NULL) + if (pgStatFunctions == NULL && pgStatPendingFunctions == NULL) return; - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_FUNCSTAT); - msg.m_databaseid = MyDatabaseId; - msg.m_nentries = 0; + if (nowait) + table_op += PGSTAT_FETCH_NOWAIT; - hash_seq_init(&fstat, pgStatFunctions); - while ((entry = (PgStat_BackendFunctionEntry *) hash_seq_search(&fstat)) != NULL) + /* find the shared function stats table */ + if (!dbentry) { - PgStat_FunctionEntry *m_ent; - - /* Skip it if no counts accumulated since last time */ - if (memcmp(&entry->f_counts, &all_zeroes, - sizeof(PgStat_FunctionCounts)) == 0) - continue; - - /* need to convert format of time accumulators */ - m_ent = &msg.m_entry[msg.m_nentries]; - m_ent->f_id = entry->f_id; - m_ent->f_numcalls = entry->f_counts.f_numcalls; - m_ent->f_total_time = INSTR_TIME_GET_MICROSEC(entry->f_counts.f_total_time); - m_ent->f_self_time = INSTR_TIME_GET_MICROSEC(entry->f_counts.f_self_time); - - if (++msg.m_nentries >= PGSTAT_NUM_FUNCENTRIES) - { - pgstat_send(&msg, offsetof(PgStat_MsgFuncstat, m_entry[0]) + - msg.m_nentries * sizeof(PgStat_FunctionEntry)); - msg.m_nentries = 0; - } - - /* reset the entry's counts */ - MemSet(&entry->f_counts, 0, sizeof(PgStat_FunctionCounts)); + dbentry = pgstat_get_db_entry(MyDatabaseId, table_op, &status); + release_db = true; } - if (msg.m_nentries > 0) - pgstat_send(&msg, offsetof(PgStat_MsgFuncstat, m_entry[0]) + - msg.m_nentries * sizeof(PgStat_FunctionEntry)); + /* lock failure, return. */ + if (status == PGSTAT_ENTRY_LOCK_FAILED) + return; - have_function_stats = false; + /* create hash if not yet */ + if (dbentry->functions == DSM_HANDLE_INVALID) + { + funchash = dshash_create(area, &dsh_funcparams, 0); + dbentry->functions = dshash_get_hash_table_handle(funchash); + } + else + funchash = dshash_attach(area, &dsh_funcparams, dbentry->functions, 0); + + /* + * First, we empty the transaction stats. Just move numbers to pending + * stats if any. Elsewise try to directly update the shared stats but + * create a new pending entry on lock failure. + */ + if (pgStatFunctions) + { + HASH_SEQ_STATUS fstat; + PgStat_BackendFunctionEntry *bestat; + + hash_seq_init(&fstat, pgStatFunctions); + while ((bestat = (PgStat_BackendFunctionEntry *) hash_seq_search(&fstat)) != NULL) + { + bool found; + bool init = false; + PgStat_StatFuncEntry *funcent = NULL; + + /* Skip it if no counts accumulated since last time */ + if (memcmp(&bestat->f_counts, &all_zeroes, + sizeof(PgStat_FunctionCounts)) == 0) + continue; + + /* find pending entry */ + if (pgStatPendingFunctions) + funcent = (PgStat_StatFuncEntry *) + hash_search(pgStatPendingFunctions, + (void *) &(bestat->f_id), HASH_FIND, NULL); + + if (!funcent) + { + /* pending entry not found, find shared stats entry */ + funcent = (PgStat_StatFuncEntry *) + dshash_find_or_insert_extended(funchash, + (void *) &(bestat->f_id), + &found, nowait); + if (funcent) + init = !found; + else + { + /* no shared stats entry. create a new pending one */ + funcent = (PgStat_StatFuncEntry *) + hash_search(pgStatPendingFunctions, + (void *) &(bestat->f_id), HASH_ENTER, NULL); + init = true; + } + } + Assert (funcent != NULL); + + pgstat_merge_backendstats_to_funcentry(funcent, bestat, init); + + /* reset used counts */ + MemSet(&bestat->f_counts, 0, sizeof(PgStat_FunctionCounts)); + } + } + + /* Second, apply pending stats numbers to shared table */ + if (pgStatPendingFunctions) + { + HASH_SEQ_STATUS fstat; + PgStat_StatFuncEntry *pendent; + + hash_seq_init(&fstat, pgStatPendingFunctions); + while ((pendent = (PgStat_StatFuncEntry *) hash_seq_search(&fstat)) != NULL) + { + PgStat_StatFuncEntry *funcent; + bool found; + + funcent = (PgStat_StatFuncEntry *) + dshash_find_or_insert_extended(funchash, + (void *) &(pendent->functionid), + &found, nowait); + if (funcent) + { + pgstat_merge_funcentry(pendent, funcent, !found); + hash_search(pgStatPendingFunctions, + (void *) &(pendent->functionid), HASH_REMOVE, NULL); + } + } + + /* destroy the hsah if no entry remains */ + if (hash_get_num_entries(pgStatPendingFunctions) == 0) + { + hash_destroy(pgStatPendingFunctions); + pgStatPendingFunctions = NULL; + } + } + + if (release_db) + dshash_release_lock(db_stats, dbentry); } +/* + * pgstat_merge_backendstats_to_funcentry: subroutine for + * pgstat_update_funcstats + * + * Merges BackendFunctionEntry into StatFuncEntry + */ +static inline void +pgstat_merge_backendstats_to_funcentry(PgStat_StatFuncEntry *dest, + PgStat_BackendFunctionEntry *src, + bool init) +{ + if (init) + { + /* + * If it's a new function entry, initialize counters to the values + * we just got. + */ + dest->f_numcalls = src->f_counts.f_numcalls; + dest->f_total_time = + INSTR_TIME_GET_MICROSEC(src->f_counts.f_total_time); + dest->f_self_time = + INSTR_TIME_GET_MICROSEC(src->f_counts.f_self_time); + } + else + { + /* + * Otherwise add the values to the existing entry. + */ + dest->f_numcalls += src->f_counts.f_numcalls; + dest->f_total_time += + INSTR_TIME_GET_MICROSEC(src->f_counts.f_total_time); + dest->f_self_time += + INSTR_TIME_GET_MICROSEC(src->f_counts.f_self_time); + } +} + +/* + * pgstat_merge_funcentry: subroutine for pgstat_update_funcstats + * + * Merges two StatFuncEntrys + */ +static inline void +pgstat_merge_funcentry(PgStat_StatFuncEntry *dest, PgStat_StatFuncEntry *src, + bool init) +{ + if (init) + { + /* + * If it's a new function entry, initialize counters to the values + * we just got. + */ + dest->f_numcalls = src->f_numcalls; + dest->f_total_time = src->f_total_time; + dest->f_self_time = src->f_self_time; + } + else + { + /* + * Otherwise add the values to the existing entry. + */ + dest->f_numcalls += src->f_numcalls; + dest->f_total_time += src->f_total_time; + dest->f_self_time += src->f_self_time; + } +} + + /* ---------- * pgstat_vacuum_stat() - * - * Will tell the collector about objects he can get rid of. + * Remove objects he can get rid of. * ---------- */ void pgstat_vacuum_stat(void) { - HTAB *htab; - PgStat_MsgTabpurge msg; - PgStat_MsgFuncpurge f_msg; - HASH_SEQ_STATUS hstat; + HTAB *oidtab; + dshash_table *dshtable; + dshash_seq_status dshstat; PgStat_StatDBEntry *dbentry; PgStat_StatTabEntry *tabentry; PgStat_StatFuncEntry *funcentry; - int len; - if (pgStatSock == PGINVALID_SOCKET) + /* we don't collect statistics under standalone mode */ + if (!IsUnderPostmaster) return; - /* - * If not done for this transaction, read the statistics collector stats - * file into some hash tables. - */ - backend_read_statsfile(); + /* If not done for this transaction, take a snapshot of stats */ + if (!backend_snapshot_global_stats()) + return; /* * Read pg_database and make a list of OIDs of all existing databases */ - htab = pgstat_collect_oids(DatabaseRelationId); + oidtab = pgstat_collect_oids(DatabaseRelationId); /* - * Search the database hash table for dead databases and tell the - * collector to drop them. + * Search the database hash table for dead databases and drop them + * from the hash. */ - hash_seq_init(&hstat, pgStatDBHash); - while ((dbentry = (PgStat_StatDBEntry *) hash_seq_search(&hstat)) != NULL) + + dshash_seq_init(&dshstat, db_stats, false, true); + while ((dbentry = (PgStat_StatDBEntry *) dshash_seq_next(&dshstat)) != NULL) { Oid dbid = dbentry->databaseid; @@ -1057,148 +1051,86 @@ pgstat_vacuum_stat(void) /* the DB entry for shared tables (with InvalidOid) is never dropped */ if (OidIsValid(dbid) && - hash_search(htab, (void *) &dbid, HASH_FIND, NULL) == NULL) + hash_search(oidtab, (void *) &dbid, HASH_FIND, NULL) == NULL) pgstat_drop_database(dbid); } /* Clean up */ - hash_destroy(htab); + hash_destroy(oidtab); /* * Lookup our own database entry; if not found, nothing more to do. */ - dbentry = (PgStat_StatDBEntry *) hash_search(pgStatDBHash, - (void *) &MyDatabaseId, - HASH_FIND, NULL); - if (dbentry == NULL || dbentry->tables == NULL) + dbentry = pgstat_get_db_entry(MyDatabaseId, PGSTAT_FETCH_EXCLUSIVE, NULL); + if (!dbentry) return; - + /* * Similarly to above, make a list of all known relations in this DB. */ - htab = pgstat_collect_oids(RelationRelationId); - - /* - * Initialize our messages table counter to zero - */ - msg.m_nentries = 0; + oidtab = pgstat_collect_oids(RelationRelationId); /* * Check for all tables listed in stats hashtable if they still exist. + * Stats cache is useless here so directly search the shared hash. */ - hash_seq_init(&hstat, dbentry->tables); - while ((tabentry = (PgStat_StatTabEntry *) hash_seq_search(&hstat)) != NULL) + dshtable = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0); + dshash_seq_init(&dshstat, dshtable, false, true); + while ((tabentry = (PgStat_StatTabEntry *) dshash_seq_next(&dshstat)) != NULL) { Oid tabid = tabentry->tableid; CHECK_FOR_INTERRUPTS(); - if (hash_search(htab, (void *) &tabid, HASH_FIND, NULL) != NULL) + if (hash_search(oidtab, (void *) &tabid, HASH_FIND, NULL) != NULL) continue; - /* - * Not there, so add this table's Oid to the message - */ - msg.m_tableid[msg.m_nentries++] = tabid; - - /* - * If the message is full, send it out and reinitialize to empty - */ - if (msg.m_nentries >= PGSTAT_NUM_TABPURGE) - { - len = offsetof(PgStat_MsgTabpurge, m_tableid[0]) - + msg.m_nentries * sizeof(Oid); - - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TABPURGE); - msg.m_databaseid = MyDatabaseId; - pgstat_send(&msg, len); - - msg.m_nentries = 0; - } - } - - /* - * Send the rest - */ - if (msg.m_nentries > 0) - { - len = offsetof(PgStat_MsgTabpurge, m_tableid[0]) - + msg.m_nentries * sizeof(Oid); - - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TABPURGE); - msg.m_databaseid = MyDatabaseId; - pgstat_send(&msg, len); + /* Not there, so purge this table */ + dshash_delete_entry(dshtable, tabentry); } + dshash_detach(dshtable); /* Clean up */ - hash_destroy(htab); + hash_destroy(oidtab); /* * Now repeat the above steps for functions. However, we needn't bother * in the common case where no function stats are being collected. */ - if (dbentry->functions != NULL && - hash_get_num_entries(dbentry->functions) > 0) + if (dbentry->functions != DSM_HANDLE_INVALID) { - htab = pgstat_collect_oids(ProcedureRelationId); + dshtable = dshash_attach(area, &dsh_funcparams, dbentry->functions, 0); + oidtab = pgstat_collect_oids(ProcedureRelationId); - pgstat_setheader(&f_msg.m_hdr, PGSTAT_MTYPE_FUNCPURGE); - f_msg.m_databaseid = MyDatabaseId; - f_msg.m_nentries = 0; - - hash_seq_init(&hstat, dbentry->functions); - while ((funcentry = (PgStat_StatFuncEntry *) hash_seq_search(&hstat)) != NULL) + dshash_seq_init(&dshstat, dshtable, false, true); + while ((funcentry = (PgStat_StatFuncEntry *) dshash_seq_next(&dshstat)) != NULL) { Oid funcid = funcentry->functionid; CHECK_FOR_INTERRUPTS(); - if (hash_search(htab, (void *) &funcid, HASH_FIND, NULL) != NULL) + if (hash_search(oidtab, (void *) &funcid, HASH_FIND, NULL) != NULL) continue; - /* - * Not there, so add this function's Oid to the message - */ - f_msg.m_functionid[f_msg.m_nentries++] = funcid; - - /* - * If the message is full, send it out and reinitialize to empty - */ - if (f_msg.m_nentries >= PGSTAT_NUM_FUNCPURGE) - { - len = offsetof(PgStat_MsgFuncpurge, m_functionid[0]) - + f_msg.m_nentries * sizeof(Oid); - - pgstat_send(&f_msg, len); - - f_msg.m_nentries = 0; - } + /* Not there, so remove this function */ + dshash_delete_entry(dshtable, funcentry); } - /* - * Send the rest - */ - if (f_msg.m_nentries > 0) - { - len = offsetof(PgStat_MsgFuncpurge, m_functionid[0]) - + f_msg.m_nentries * sizeof(Oid); + hash_destroy(oidtab); - pgstat_send(&f_msg, len); - } - - hash_destroy(htab); + dshash_detach(dshtable); } + dshash_release_lock(db_stats, dbentry); } -/* ---------- +/* * pgstat_collect_oids() - * * Collect the OIDs of all objects listed in the specified system catalog - * into a temporary hash table. Caller should hash_destroy the result - * when done with it. (However, we make the table in CurrentMemoryContext - * so that it will be freed properly in event of an error.) - * ---------- + * into a temporary hash table. Caller should hash_destroy the result after + * use. (However, we make the table in CurrentMemoryContext so that it will + * be freed properly in event of an error.) */ static HTAB * pgstat_collect_oids(Oid catalogid) @@ -1241,62 +1173,54 @@ pgstat_collect_oids(Oid catalogid) /* ---------- * pgstat_drop_database() - * - * Tell the collector that we just dropped a database. - * (If the message gets lost, we will still clean the dead DB eventually - * via future invocations of pgstat_vacuum_stat().) + * Remove entry for the database that we just dropped. + * + * If some stats update happens after this, this entry will re-created but + * we will still clean the dead DB eventually via future invocations of + * pgstat_vacuum_stat(). * ---------- */ + void pgstat_drop_database(Oid databaseid) { - PgStat_MsgDropdb msg; + PgStat_StatDBEntry *dbentry; - if (pgStatSock == PGINVALID_SOCKET) - return; + Assert (OidIsValid(databaseid)); + Assert(db_stats); - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_DROPDB); - msg.m_databaseid = databaseid; - pgstat_send(&msg, sizeof(msg)); + /* + * Lookup the database in the hashtable with exclusive lock. + */ + dbentry = pgstat_get_db_entry(databaseid, PGSTAT_FETCH_EXCLUSIVE, NULL); + + /* + * If found, remove it (along with the db statfile). + */ + if (dbentry) + { + if (dbentry->tables != DSM_HANDLE_INVALID) + { + dshash_table *tbl = + dshash_attach(area, &dsh_tblparams, dbentry->tables, 0); + dshash_destroy(tbl); + } + if (dbentry->functions != DSM_HANDLE_INVALID) + { + dshash_table *tbl = + dshash_attach(area, &dsh_funcparams, dbentry->functions, 0); + dshash_destroy(tbl); + } + + dshash_delete_entry(db_stats, (void *)dbentry); + } } -/* ---------- - * pgstat_drop_relation() - - * - * Tell the collector that we just dropped a relation. - * (If the message gets lost, we will still clean the dead entry eventually - * via future invocations of pgstat_vacuum_stat().) - * - * Currently not used for lack of any good place to call it; we rely - * entirely on pgstat_vacuum_stat() to clean out stats for dead rels. - * ---------- - */ -#ifdef NOT_USED -void -pgstat_drop_relation(Oid relid) -{ - PgStat_MsgTabpurge msg; - int len; - - if (pgStatSock == PGINVALID_SOCKET) - return; - - msg.m_tableid[0] = relid; - msg.m_nentries = 1; - - len = offsetof(PgStat_MsgTabpurge, m_tableid[0]) + sizeof(Oid); - - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TABPURGE); - msg.m_databaseid = MyDatabaseId; - pgstat_send(&msg, len); -} -#endif /* NOT_USED */ - - /* ---------- * pgstat_reset_counters() - * - * Tell the statistics collector to reset counters for our database. + * Reset counters for our database. * * Permission checking for this function is managed through the normal * GRANT system. @@ -1305,20 +1229,51 @@ pgstat_drop_relation(Oid relid) void pgstat_reset_counters(void) { - PgStat_MsgResetcounter msg; + PgStat_StatDBEntry *dbentry; + pg_stat_table_result_status status; - if (pgStatSock == PGINVALID_SOCKET) + Assert(db_stats); + + /* + * Lookup the database in the hashtable. Nothing to do if not there. + */ + dbentry = pgstat_get_db_entry(MyDatabaseId, PGSTAT_FETCH_EXCLUSIVE, &status); + + if (!dbentry) return; - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETCOUNTER); - msg.m_databaseid = MyDatabaseId; - pgstat_send(&msg, sizeof(msg)); + /* + * We simply throw away all the database's table entries by recreating a + * new hash table for them. + */ + if (dbentry->tables != DSM_HANDLE_INVALID) + { + dshash_table *t = + dshash_attach(area, &dsh_tblparams, dbentry->tables, 0); + dshash_destroy(t); + dbentry->tables = DSM_HANDLE_INVALID; + } + if (dbentry->functions != DSM_HANDLE_INVALID) + { + dshash_table *t = + dshash_attach(area, &dsh_funcparams, dbentry->functions, 0); + dshash_destroy(t); + dbentry->functions = DSM_HANDLE_INVALID; + } + + /* + * Reset database-level stats, too. This creates empty hash tables for + * tables and functions. + */ + reset_dbentry_counters(dbentry); + + dshash_release_lock(db_stats, dbentry); } /* ---------- * pgstat_reset_shared_counters() - * - * Tell the statistics collector to reset cluster-wide shared counters. + * Reset cluster-wide shared counters. * * Permission checking for this function is managed through the normal * GRANT system. @@ -1327,29 +1282,37 @@ pgstat_reset_counters(void) void pgstat_reset_shared_counters(const char *target) { - PgStat_MsgResetsharedcounter msg; - - if (pgStatSock == PGINVALID_SOCKET) - return; + Assert(db_stats); + /* Reset the archiver statistics for the cluster. */ if (strcmp(target, "archiver") == 0) - msg.m_resettarget = RESET_ARCHIVER; + { + LWLockAcquire(StatsLock, LW_EXCLUSIVE); + + memset(shared_archiverStats, 0, sizeof(*shared_archiverStats)); + shared_archiverStats->stat_reset_timestamp = GetCurrentTimestamp(); + } else if (strcmp(target, "bgwriter") == 0) - msg.m_resettarget = RESET_BGWRITER; + { + LWLockAcquire(StatsLock, LW_EXCLUSIVE); + + /* Reset the global background writer statistics for the cluster. */ + memset(shared_globalStats, 0, sizeof(*shared_globalStats)); + shared_globalStats->stat_reset_timestamp = GetCurrentTimestamp(); + } else ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("unrecognized reset target: \"%s\"", target), errhint("Target must be \"archiver\" or \"bgwriter\"."))); - - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETSHAREDCOUNTER); - pgstat_send(&msg, sizeof(msg)); + + LWLockRelease(StatsLock); } /* ---------- * pgstat_reset_single_counter() - * - * Tell the statistics collector to reset a single counter. + * Reset a single counter. * * Permission checking for this function is managed through the normal * GRANT system. @@ -1358,17 +1321,90 @@ pgstat_reset_shared_counters(const char *target) void pgstat_reset_single_counter(Oid objoid, PgStat_Single_Reset_Type type) { - PgStat_MsgResetsinglecounter msg; + PgStat_StatDBEntry *dbentry; + - if (pgStatSock == PGINVALID_SOCKET) + Assert(db_stats); + + dbentry = pgstat_get_db_entry(MyDatabaseId, PGSTAT_FETCH_EXCLUSIVE, NULL); + + if (!dbentry) return; - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETSINGLECOUNTER); - msg.m_databaseid = MyDatabaseId; - msg.m_resettype = type; - msg.m_objectid = objoid; + /* Set the reset timestamp for the whole database */ + dbentry->stat_reset_timestamp = GetCurrentTimestamp(); - pgstat_send(&msg, sizeof(msg)); + /* Remove object if it exists, ignore it if not */ + if (type == RESET_TABLE) + { + dshash_table *t = + dshash_attach(area, &dsh_tblparams, dbentry->tables, 0); + dshash_delete_key(t, (void *) &objoid); + } + + if (type == RESET_FUNCTION && dbentry->functions != DSM_HANDLE_INVALID) + { + dshash_table *t = + dshash_attach(area, &dsh_funcparams, dbentry->functions, 0); + dshash_delete_key(t, (void *) &objoid); + } + + dshash_release_lock(db_stats, dbentry); +} + +/* + * pgstat_reset_all_counters: subroutine for pgstat_reset_all + * + * clear all counters on shared memory + */ +static void +pgstat_reset_all_counters(void) +{ + dshash_seq_status dshstat; + PgStat_StatDBEntry *dbentry; + + Assert (db_stats); + + LWLockAcquire(StatsLock, LW_EXCLUSIVE); + dshash_seq_init(&dshstat, db_stats, false, true); + while ((dbentry = (PgStat_StatDBEntry *) dshash_seq_next(&dshstat)) != NULL) + { + /* + * We simply throw away all the database's table hashes + */ + if (dbentry->tables != DSM_HANDLE_INVALID) + { + dshash_table *t = + dshash_attach(area, &dsh_tblparams, dbentry->tables, 0); + dshash_destroy(t); + dbentry->tables = DSM_HANDLE_INVALID; + } + if (dbentry->functions != DSM_HANDLE_INVALID) + { + dshash_table *t = + dshash_attach(area, &dsh_funcparams, dbentry->functions, 0); + dshash_destroy(t); + dbentry->functions = DSM_HANDLE_INVALID; + } + + /* + * Reset database-level stats, too. This creates empty hash tables + * for tables and functions. + */ + reset_dbentry_counters(dbentry); + dshash_release_lock(db_stats, dbentry); + + } + + /* + * Reset global counters + */ + memset(shared_globalStats, 0, sizeof(*shared_globalStats)); + memset(shared_archiverStats, 0, sizeof(*shared_archiverStats)); + shared_globalStats->stat_reset_timestamp = + shared_archiverStats->stat_reset_timestamp = GetCurrentTimestamp(); + + LWLockRelease(StatsLock); } /* ---------- @@ -1382,48 +1418,75 @@ pgstat_reset_single_counter(Oid objoid, PgStat_Single_Reset_Type type) void pgstat_report_autovac(Oid dboid) { - PgStat_MsgAutovacStart msg; + PgStat_StatDBEntry *dbentry; - if (pgStatSock == PGINVALID_SOCKET) + Assert(db_stats); + + if (!pgstat_track_counts || !IsUnderPostmaster) return; - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_AUTOVAC_START); - msg.m_databaseid = dboid; - msg.m_start_time = GetCurrentTimestamp(); + /* + * Store the last autovacuum time in the database's hashtable entry. + */ + dbentry = pgstat_get_db_entry(dboid, PGSTAT_FETCH_EXCLUSIVE, NULL); - pgstat_send(&msg, sizeof(msg)); + dbentry->last_autovac_time = GetCurrentTimestamp(); + + dshash_release_lock(db_stats, dbentry); } /* --------- * pgstat_report_vacuum() - * - * Tell the collector about the table we just vacuumed. + * Repot about the table we just vacuumed. * --------- */ void pgstat_report_vacuum(Oid tableoid, bool shared, PgStat_Counter livetuples, PgStat_Counter deadtuples) { - PgStat_MsgVacuum msg; + Oid dboid; + PgStat_StatDBEntry *dbentry; + PgStat_StatTabEntry *tabentry; + dshash_table *table; - if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts) + Assert(db_stats); + + if (!pgstat_track_counts || !IsUnderPostmaster) return; - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_VACUUM); - msg.m_databaseid = shared ? InvalidOid : MyDatabaseId; - msg.m_tableoid = tableoid; - msg.m_autovacuum = IsAutoVacuumWorkerProcess(); - msg.m_vacuumtime = GetCurrentTimestamp(); - msg.m_live_tuples = livetuples; - msg.m_dead_tuples = deadtuples; - pgstat_send(&msg, sizeof(msg)); + dboid = shared ? InvalidOid : MyDatabaseId; + + /* + * Store the data in the table's hashtable entry. + */ + dbentry = pgstat_get_db_entry(dboid, PGSTAT_FETCH_EXCLUSIVE, NULL); + table = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0); + tabentry = pgstat_get_tab_entry(table, tableoid, true); + + tabentry->n_live_tuples = livetuples; + tabentry->n_dead_tuples = deadtuples; + + if (IsAutoVacuumWorkerProcess()) + { + tabentry->autovac_vacuum_timestamp = GetCurrentTimestamp(); + tabentry->autovac_vacuum_count++; + } + else + { + tabentry->vacuum_timestamp = GetCurrentTimestamp(); + tabentry->vacuum_count++; + } + dshash_release_lock(table, tabentry); + dshash_detach(table); + dshash_release_lock(db_stats, dbentry); } /* -------- * pgstat_report_analyze() - * - * Tell the collector about the table we just analyzed. + * Report about the table we just analyzed. * * Caller must provide new live- and dead-tuples estimates, as well as a * flag indicating whether to reset the changes_since_analyze counter. @@ -1434,9 +1497,14 @@ pgstat_report_analyze(Relation rel, PgStat_Counter livetuples, PgStat_Counter deadtuples, bool resetcounter) { - PgStat_MsgAnalyze msg; + Oid dboid; + PgStat_StatDBEntry *dbentry; + PgStat_StatTabEntry *tabentry; + dshash_table *table; - if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts) + Assert(db_stats); + + if (!pgstat_track_counts || !IsUnderPostmaster) return; /* @@ -1465,114 +1533,228 @@ pgstat_report_analyze(Relation rel, deadtuples = Max(deadtuples, 0); } - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_ANALYZE); - msg.m_databaseid = rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId; - msg.m_tableoid = RelationGetRelid(rel); - msg.m_autovacuum = IsAutoVacuumWorkerProcess(); - msg.m_resetcounter = resetcounter; - msg.m_analyzetime = GetCurrentTimestamp(); - msg.m_live_tuples = livetuples; - msg.m_dead_tuples = deadtuples; - pgstat_send(&msg, sizeof(msg)); + dboid = rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId; + + /* + * Store the data in the table's hashtable entry. + */ + dbentry = pgstat_get_db_entry(dboid, PGSTAT_FETCH_EXCLUSIVE, NULL); + + table = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0); + tabentry = pgstat_get_tab_entry(table, RelationGetRelid(rel), true); + + tabentry->n_live_tuples = livetuples; + tabentry->n_dead_tuples = deadtuples; + + /* + * If commanded, reset changes_since_analyze to zero. This forgets any + * changes that were committed while the ANALYZE was in progress, but we + * have no good way to estimate how many of those there were. + */ + if (resetcounter) + tabentry->changes_since_analyze = 0; + + if (IsAutoVacuumWorkerProcess()) + { + tabentry->autovac_analyze_timestamp = GetCurrentTimestamp(); + tabentry->autovac_analyze_count++; + } + else + { + tabentry->analyze_timestamp = GetCurrentTimestamp(); + tabentry->analyze_count++; + } + dshash_release_lock(table, tabentry); + dshash_detach(table); + dshash_release_lock(db_stats, dbentry); } /* -------- * pgstat_report_recovery_conflict() - * - * Tell the collector about a Hot Standby recovery conflict. + * Report a Hot Standby recovery conflict. * -------- */ +static int pending_conflict_tablespace = 0; +static int pending_conflict_lock = 0; +static int pending_conflict_snapshot = 0; +static int pending_conflict_bufferpin = 0; +static int pending_conflict_startup_deadlock = 0; + void pgstat_report_recovery_conflict(int reason) { - PgStat_MsgRecoveryConflict msg; + PgStat_StatDBEntry *dbentry; + pg_stat_table_result_status status; - if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts) + Assert(db_stats); + + if (!pgstat_track_counts || !IsUnderPostmaster) return; - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RECOVERYCONFLICT); - msg.m_databaseid = MyDatabaseId; - msg.m_reason = reason; - pgstat_send(&msg, sizeof(msg)); + pgstat_pending_recoveryconflict = true; + + switch (reason) + { + case PROCSIG_RECOVERY_CONFLICT_DATABASE: + + /* + * Since we drop the information about the database as soon as it + * replicates, there is no point in counting these conflicts. + */ + break; + case PROCSIG_RECOVERY_CONFLICT_TABLESPACE: + pending_conflict_tablespace++; + break; + case PROCSIG_RECOVERY_CONFLICT_LOCK: + pending_conflict_lock++; + break; + case PROCSIG_RECOVERY_CONFLICT_SNAPSHOT: + pending_conflict_snapshot++; + break; + case PROCSIG_RECOVERY_CONFLICT_BUFFERPIN: + pending_conflict_bufferpin++; + break; + case PROCSIG_RECOVERY_CONFLICT_STARTUP_DEADLOCK: + pending_conflict_startup_deadlock++; + break; + } + + dbentry = pgstat_get_db_entry(MyDatabaseId, + PGSTAT_FETCH_EXCLUSIVE | PGSTAT_FETCH_NOWAIT, + &status); + + if (status == PGSTAT_ENTRY_LOCK_FAILED) + return; + + pgstat_cleanup_recovery_conflict(dbentry); + + dshash_release_lock(db_stats, dbentry); +} + +/* + * clean up function for pending recovery conflicts + */ +static void +pgstat_cleanup_recovery_conflict(PgStat_StatDBEntry *dbentry) +{ + dbentry->n_conflict_tablespace += pending_conflict_tablespace; + dbentry->n_conflict_lock += pending_conflict_lock; + dbentry->n_conflict_snapshot += pending_conflict_snapshot; + dbentry->n_conflict_bufferpin += pending_conflict_bufferpin; + dbentry->n_conflict_startup_deadlock += pending_conflict_startup_deadlock; + + pending_conflict_tablespace = 0; + pending_conflict_lock = 0; + pending_conflict_snapshot = 0; + pending_conflict_bufferpin = 0; + pending_conflict_startup_deadlock = 0; + + pgstat_pending_recoveryconflict = false; } /* -------- * pgstat_report_deadlock() - * - * Tell the collector about a deadlock detected. + * Report a deadlock detected. * -------- */ +static int pending_deadlocks = 0; + void pgstat_report_deadlock(void) { - PgStat_MsgDeadlock msg; + PgStat_StatDBEntry *dbentry; + pg_stat_table_result_status status; - if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts) + Assert(db_stats); + + if (!pgstat_track_counts || !IsUnderPostmaster) return; - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_DEADLOCK); - msg.m_databaseid = MyDatabaseId; - pgstat_send(&msg, sizeof(msg)); + pending_deadlocks++; + pgstat_pending_deadlock = true; + + dbentry = pgstat_get_db_entry(MyDatabaseId, + PGSTAT_FETCH_EXCLUSIVE | PGSTAT_FETCH_NOWAIT, + &status); + + if (status == PGSTAT_ENTRY_LOCK_FAILED) + return; + + pgstat_cleanup_deadlock(dbentry); + + dshash_release_lock(db_stats, dbentry); +} + +/* + * clean up function for pending dead locks + */ +static void +pgstat_cleanup_deadlock(PgStat_StatDBEntry *dbentry) +{ + dbentry->n_deadlocks += pending_deadlocks; + pending_deadlocks = 0; + pgstat_pending_deadlock = false; } /* -------- * pgstat_report_tempfile() - * - * Tell the collector about a temporary file. + * Report a temporary file. * -------- */ +static size_t pending_filesize = 0; +static size_t pending_files = 0; + void pgstat_report_tempfile(size_t filesize) { - PgStat_MsgTempFile msg; + PgStat_StatDBEntry *dbentry; + pg_stat_table_result_status status; - if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts) + Assert(db_stats); + + if (!pgstat_track_counts || !IsUnderPostmaster) return; - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TEMPFILE); - msg.m_databaseid = MyDatabaseId; - msg.m_filesize = filesize; - pgstat_send(&msg, sizeof(msg)); -} + if (filesize > 0) /* Is't there a case where filesize is really 0? */ + { + pgstat_pending_tempfile = true; + pending_filesize += filesize; /* needs check overflow */ + pending_files++; + } - -/* ---------- - * pgstat_ping() - - * - * Send some junk data to the collector to increase traffic. - * ---------- - */ -void -pgstat_ping(void) -{ - PgStat_MsgDummy msg; - - if (pgStatSock == PGINVALID_SOCKET) + if (!pgstat_pending_tempfile) return; - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_DUMMY); - pgstat_send(&msg, sizeof(msg)); + dbentry = pgstat_get_db_entry(MyDatabaseId, + PGSTAT_FETCH_EXCLUSIVE | PGSTAT_FETCH_NOWAIT, + &status); + + if (status == PGSTAT_ENTRY_LOCK_FAILED) + return; + + pgstat_cleanup_tempfile(dbentry); + + dshash_release_lock(db_stats, dbentry); } -/* ---------- - * pgstat_send_inquiry() - - * - * Notify collector that we need fresh data. - * ---------- +/* + * clean up function for temporary files */ static void -pgstat_send_inquiry(TimestampTz clock_time, TimestampTz cutoff_time, Oid databaseid) +pgstat_cleanup_tempfile(PgStat_StatDBEntry *dbentry) { - PgStat_MsgInquiry msg; - pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_INQUIRY); - msg.clock_time = clock_time; - msg.cutoff_time = cutoff_time; - msg.databaseid = databaseid; - pgstat_send(&msg, sizeof(msg)); + dbentry->n_temp_bytes += pending_filesize; + dbentry->n_temp_files += pending_files; + pending_filesize = 0; + pending_files = 0; + pgstat_pending_tempfile = false; + } - /* * Initialize function call usage data. * Called by the executor before invoking a function. @@ -1688,9 +1870,6 @@ pgstat_end_function_usage(PgStat_FunctionCallUsage *fcu, bool finalize) fs->f_numcalls++; fs->f_total_time = f_total; INSTR_TIME_ADD(fs->f_self_time, f_self); - - /* indicate that we have something to send */ - have_function_stats = true; } @@ -1712,6 +1891,15 @@ pgstat_initstats(Relation rel) Oid rel_id = rel->rd_id; char relkind = rel->rd_rel->relkind; + Assert(db_stats); + + if (!pgstat_track_counts || !IsUnderPostmaster) + { + /* We're not counting at all */ + rel->pgstat_info = NULL; + return; + } + /* We only count stats for things that have storage */ if (!(relkind == RELKIND_RELATION || relkind == RELKIND_MATVIEW || @@ -1723,13 +1911,6 @@ pgstat_initstats(Relation rel) return; } - if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts) - { - /* We're not counting at all */ - rel->pgstat_info = NULL; - return; - } - /* * If we already set up this relation in the current transaction, nothing * to do. @@ -2373,34 +2554,6 @@ pgstat_twophase_postabort(TransactionId xid, uint16 info, rec->tuples_inserted + rec->tuples_updated; } - -/* ---------- - * pgstat_fetch_stat_dbentry() - - * - * Support function for the SQL-callable pgstat* functions. Returns - * the collected statistics for one database or NULL. NULL doesn't mean - * that the database doesn't exist, it is just not yet known by the - * collector, so the caller is better off to report ZERO instead. - * ---------- - */ -PgStat_StatDBEntry * -pgstat_fetch_stat_dbentry(Oid dbid) -{ - /* - * If not done for this transaction, read the statistics collector stats - * file into some hash tables. - */ - backend_read_statsfile(); - - /* - * Lookup the requested database; return NULL if not found - */ - return (PgStat_StatDBEntry *) hash_search(pgStatDBHash, - (void *) &dbid, - HASH_FIND, NULL); -} - - /* ---------- * pgstat_fetch_stat_tabentry() - * @@ -2413,47 +2566,28 @@ pgstat_fetch_stat_dbentry(Oid dbid) PgStat_StatTabEntry * pgstat_fetch_stat_tabentry(Oid relid) { - Oid dbid; PgStat_StatDBEntry *dbentry; PgStat_StatTabEntry *tabentry; - /* - * If not done for this transaction, read the statistics collector stats - * file into some hash tables. - */ - backend_read_statsfile(); + /* Lookup our database, then look in its table hash table. */ + dbentry = pgstat_fetch_stat_dbentry(MyDatabaseId, false); + if (dbentry == NULL) + return NULL; - /* - * Lookup our database, then look in its table hash table. - */ - dbid = MyDatabaseId; - dbentry = (PgStat_StatDBEntry *) hash_search(pgStatDBHash, - (void *) &dbid, - HASH_FIND, NULL); - if (dbentry != NULL && dbentry->tables != NULL) - { - tabentry = (PgStat_StatTabEntry *) hash_search(dbentry->tables, - (void *) &relid, - HASH_FIND, NULL); - if (tabentry) - return tabentry; - } + tabentry = backend_get_tab_entry(dbentry, relid, false); + if (tabentry != NULL) + return tabentry; /* * If we didn't find it, maybe it's a shared table. */ - dbid = InvalidOid; - dbentry = (PgStat_StatDBEntry *) hash_search(pgStatDBHash, - (void *) &dbid, - HASH_FIND, NULL); - if (dbentry != NULL && dbentry->tables != NULL) - { - tabentry = (PgStat_StatTabEntry *) hash_search(dbentry->tables, - (void *) &relid, - HASH_FIND, NULL); - if (tabentry) - return tabentry; - } + dbentry = pgstat_fetch_stat_dbentry(InvalidOid, false); + if (dbentry == NULL) + return NULL; + + tabentry = backend_get_tab_entry(dbentry, relid, false); + if (tabentry != NULL) + return tabentry; return NULL; } @@ -2472,18 +2606,14 @@ pgstat_fetch_stat_funcentry(Oid func_id) PgStat_StatDBEntry *dbentry; PgStat_StatFuncEntry *funcentry = NULL; - /* load the stats file if needed */ - backend_read_statsfile(); + /* Lookup our database, then find the requested function */ + dbentry = pgstat_get_db_entry(MyDatabaseId, PGSTAT_FETCH_SHARED, NULL); + if (dbentry == NULL) + return NULL; - /* Lookup our database, then find the requested function. */ - dbentry = pgstat_fetch_stat_dbentry(MyDatabaseId); - if (dbentry != NULL && dbentry->functions != NULL) - { - funcentry = (PgStat_StatFuncEntry *) hash_search(dbentry->functions, - (void *) &func_id, - HASH_FIND, NULL); - } + funcentry = backend_get_func_etnry(dbentry, func_id, false); + dshash_release_lock(db_stats, dbentry); return funcentry; } @@ -2558,9 +2688,11 @@ pgstat_fetch_stat_numbackends(void) PgStat_ArchiverStats * pgstat_fetch_stat_archiver(void) { - backend_read_statsfile(); + /* If not done for this transaction, take a stats snapshot */ + if (!backend_snapshot_global_stats()) + return NULL; - return &archiverStats; + return snapshot_archiverStats; } @@ -2575,9 +2707,11 @@ pgstat_fetch_stat_archiver(void) PgStat_GlobalStats * pgstat_fetch_global(void) { - backend_read_statsfile(); + /* If not done for this transaction, take a stats snapshot */ + if (!backend_snapshot_global_stats()) + return NULL; - return &globalStats; + return snapshot_globalStats; } @@ -2767,7 +2901,7 @@ pgstat_initialize(void) } /* Set up a process-exit hook to clean up */ - on_shmem_exit(pgstat_beshutdown_hook, 0); + before_shmem_exit(pgstat_beshutdown_hook, 0); } /* ---------- @@ -2959,7 +3093,7 @@ pgstat_beshutdown_hook(int code, Datum arg) * during failed backend starts might never get counted.) */ if (OidIsValid(MyDatabaseId)) - pgstat_report_stat(true); + pgstat_update_stat(true); /* * Clear my status entry, following the protocol of bumping st_changecount @@ -3226,7 +3360,8 @@ pgstat_read_current_status(void) #endif int i; - Assert(!pgStatRunningInCollector); + Assert(IsUnderPostmaster); + if (localBackendStatusTable) return; /* already done */ @@ -4146,96 +4281,68 @@ pgstat_get_backend_desc(BackendType backendType) * ------------------------------------------------------------ */ - /* ---------- - * pgstat_setheader() - + * pgstat_update_archiver() - * - * Set common header fields in a statistics message + * Update the stats data about the WAL file that we successfully archived or + * failed to archive. * ---------- */ -static void -pgstat_setheader(PgStat_MsgHdr *hdr, StatMsgType mtype) +void +pgstat_update_archiver(const char *xlog, bool failed) { - hdr->m_type = mtype; -} - - -/* ---------- - * pgstat_send() - - * - * Send out one statistics message to the collector - * ---------- - */ -static void -pgstat_send(void *msg, int len) -{ - int rc; - - if (pgStatSock == PGINVALID_SOCKET) - return; - - ((PgStat_MsgHdr *) msg)->m_size = len; - - /* We'll retry after EINTR, but ignore all other failures */ - do + if (failed) { - rc = send(pgStatSock, msg, len, 0); - } while (rc < 0 && errno == EINTR); - -#ifdef USE_ASSERT_CHECKING - /* In debug builds, log send failures ... */ - if (rc < 0) - elog(LOG, "could not send to statistics collector: %m"); -#endif + /* Failed archival attempt */ + ++shared_archiverStats->failed_count; + memcpy(shared_archiverStats->last_failed_wal, xlog, + sizeof(shared_archiverStats->last_failed_wal)); + shared_archiverStats->last_failed_timestamp = GetCurrentTimestamp(); + } + else + { + /* Successful archival operation */ + ++shared_archiverStats->archived_count; + memcpy(shared_archiverStats->last_archived_wal, xlog, + sizeof(shared_archiverStats->last_archived_wal)); + shared_archiverStats->last_archived_timestamp = GetCurrentTimestamp(); + } } /* ---------- - * pgstat_send_archiver() - + * pgstat_update_bgwriter() - * - * Tell the collector about the WAL file that we successfully - * archived or failed to archive. + * Update bgwriter statistics * ---------- */ 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() - - * - * Send bgwriter statistics to the collector - * ---------- - */ -void -pgstat_send_bgwriter(void) +pgstat_update_bgwriter(void) { /* We assume this initializes to zeroes */ - static const PgStat_MsgBgWriter all_zeroes; + static const PgStat_BgWriter all_zeroes; + + PgStat_BgWriter *s = &BgWriterStats; /* * This function can be called even if nothing at all has happened. In * this case, avoid sending a completely empty message to the stats * collector. */ - if (memcmp(&BgWriterStats, &all_zeroes, sizeof(PgStat_MsgBgWriter)) == 0) + if (memcmp(&BgWriterStats, &all_zeroes, sizeof(PgStat_BgWriter)) == 0) return; - /* - * Prepare and send the message - */ - pgstat_setheader(&BgWriterStats.m_hdr, PGSTAT_MTYPE_BGWRITER); - pgstat_send(&BgWriterStats, sizeof(BgWriterStats)); + LWLockAcquire(StatsLock, LW_EXCLUSIVE); + shared_globalStats->timed_checkpoints += s->timed_checkpoints; + shared_globalStats->requested_checkpoints += s->requested_checkpoints; + shared_globalStats->checkpoint_write_time += s->checkpoint_write_time; + shared_globalStats->checkpoint_sync_time += s->checkpoint_sync_time; + shared_globalStats->buf_written_checkpoints += s->buf_written_checkpoints; + shared_globalStats->buf_written_clean += s->buf_written_clean; + shared_globalStats->maxwritten_clean += s->maxwritten_clean; + shared_globalStats->buf_written_backend += s->buf_written_backend; + shared_globalStats->buf_fsync_backend += s->buf_fsync_backend; + shared_globalStats->buf_alloc += s->buf_alloc; + LWLockRelease(StatsLock); /* * Clear out the statistics buffer, so it can be re-used. @@ -4243,302 +4350,15 @@ pgstat_send_bgwriter(void) MemSet(&BgWriterStats, 0, sizeof(BgWriterStats)); } - -/* ---------- - * PgstatCollectorMain() - - * - * Start up the statistics collector process. This is the body of the - * postmaster child process. - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. - * ---------- - */ -NON_EXEC_STATIC void -PgstatCollectorMain(int argc, char *argv[]) -{ - int len; - PgStat_Msg msg; - int wr; - - /* - * Ignore all signals usually bound to some action in the postmaster, - * except SIGHUP and SIGQUIT. Note we don't need a SIGUSR1 handler to - * support latch operations, because we only use a local latch. - */ - pqsignal(SIGHUP, pgstat_sighup_handler); - pqsignal(SIGINT, SIG_IGN); - pqsignal(SIGTERM, SIG_IGN); - pqsignal(SIGQUIT, pgstat_exit); - pqsignal(SIGALRM, SIG_IGN); - pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, SIG_IGN); - pqsignal(SIGUSR2, SIG_IGN); - pqsignal(SIGCHLD, SIG_DFL); - pqsignal(SIGTTIN, SIG_DFL); - pqsignal(SIGTTOU, SIG_DFL); - pqsignal(SIGCONT, SIG_DFL); - pqsignal(SIGWINCH, SIG_DFL); - PG_SETMASK(&UnBlockSig); - - /* - * Identify myself via ps - */ - init_ps_display("stats collector", "", "", ""); - - /* - * Read in existing stats files or initialize the stats to zero. - */ - pgStatRunningInCollector = true; - pgStatDBHash = pgstat_read_statsfiles(InvalidOid, true, true); - - /* - * Loop to process messages until we get SIGQUIT or detect ungraceful - * death of our parent postmaster. - * - * For performance reasons, we don't want to do ResetLatch/WaitLatch after - * every message; instead, do that only after a recv() fails to obtain a - * message. (This effectively means that if backends are sending us stuff - * like mad, we won't notice postmaster death until things slack off a - * bit; which seems fine.) To do that, we have an inner loop that - * iterates as long as recv() succeeds. We do recognize got_SIGHUP inside - * the inner loop, which means that such interrupts will get serviced but - * the latch won't get cleared until next time there is a break in the - * action. - */ - for (;;) - { - /* Clear any already-pending wakeups */ - ResetLatch(MyLatch); - - /* - * Quit if we get SIGQUIT from the postmaster. - */ - if (need_exit) - break; - - /* - * Inner loop iterates as long as we keep getting messages, or until - * need_exit becomes set. - */ - while (!need_exit) - { - /* - * Reload configuration if we got SIGHUP from the postmaster. - */ - if (got_SIGHUP) - { - got_SIGHUP = false; - ProcessConfigFile(PGC_SIGHUP); - } - - /* - * Write the stats file(s) if a new request has arrived that is - * not satisfied by existing file(s). - */ - if (pgstat_write_statsfile_needed()) - pgstat_write_statsfiles(false, false); - - /* - * Try to receive and process a message. This will not block, - * since the socket is set to non-blocking mode. - * - * XXX On Windows, we have to force pgwin32_recv to cooperate, - * despite the previous use of pg_set_noblock() on the socket. - * This is extremely broken and should be fixed someday. - */ -#ifdef WIN32 - pgwin32_noblock = 1; -#endif - - len = recv(pgStatSock, (char *) &msg, - sizeof(PgStat_Msg), 0); - -#ifdef WIN32 - pgwin32_noblock = 0; -#endif - - if (len < 0) - { - if (errno == EAGAIN || errno == EWOULDBLOCK || errno == EINTR) - break; /* out of inner loop */ - ereport(ERROR, - (errcode_for_socket_access(), - errmsg("could not read statistics message: %m"))); - } - - /* - * We ignore messages that are smaller than our common header - */ - if (len < sizeof(PgStat_MsgHdr)) - continue; - - /* - * The received length must match the length in the header - */ - if (msg.msg_hdr.m_size != len) - continue; - - /* - * O.K. - we accept this message. Process it. - */ - switch (msg.msg_hdr.m_type) - { - case PGSTAT_MTYPE_DUMMY: - break; - - case PGSTAT_MTYPE_INQUIRY: - pgstat_recv_inquiry((PgStat_MsgInquiry *) &msg, len); - break; - - case PGSTAT_MTYPE_TABSTAT: - pgstat_recv_tabstat((PgStat_MsgTabstat *) &msg, len); - break; - - case PGSTAT_MTYPE_TABPURGE: - pgstat_recv_tabpurge((PgStat_MsgTabpurge *) &msg, len); - break; - - case PGSTAT_MTYPE_DROPDB: - pgstat_recv_dropdb((PgStat_MsgDropdb *) &msg, len); - break; - - case PGSTAT_MTYPE_RESETCOUNTER: - pgstat_recv_resetcounter((PgStat_MsgResetcounter *) &msg, - len); - break; - - case PGSTAT_MTYPE_RESETSHAREDCOUNTER: - pgstat_recv_resetsharedcounter( - (PgStat_MsgResetsharedcounter *) &msg, - len); - break; - - case PGSTAT_MTYPE_RESETSINGLECOUNTER: - pgstat_recv_resetsinglecounter( - (PgStat_MsgResetsinglecounter *) &msg, - len); - break; - - case PGSTAT_MTYPE_AUTOVAC_START: - pgstat_recv_autovac((PgStat_MsgAutovacStart *) &msg, len); - break; - - case PGSTAT_MTYPE_VACUUM: - pgstat_recv_vacuum((PgStat_MsgVacuum *) &msg, len); - break; - - case PGSTAT_MTYPE_ANALYZE: - 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; - - case PGSTAT_MTYPE_FUNCSTAT: - pgstat_recv_funcstat((PgStat_MsgFuncstat *) &msg, len); - break; - - case PGSTAT_MTYPE_FUNCPURGE: - pgstat_recv_funcpurge((PgStat_MsgFuncpurge *) &msg, len); - break; - - case PGSTAT_MTYPE_RECOVERYCONFLICT: - pgstat_recv_recoveryconflict((PgStat_MsgRecoveryConflict *) &msg, len); - break; - - case PGSTAT_MTYPE_DEADLOCK: - pgstat_recv_deadlock((PgStat_MsgDeadlock *) &msg, len); - break; - - case PGSTAT_MTYPE_TEMPFILE: - pgstat_recv_tempfile((PgStat_MsgTempFile *) &msg, len); - break; - - default: - break; - } - } /* end of inner message-processing loop */ - - /* Sleep until there's something to do */ -#ifndef WIN32 - wr = WaitLatchOrSocket(MyLatch, - WL_LATCH_SET | WL_POSTMASTER_DEATH | WL_SOCKET_READABLE, - pgStatSock, -1L, - WAIT_EVENT_PGSTAT_MAIN); -#else - - /* - * Windows, at least in its Windows Server 2003 R2 incarnation, - * sometimes loses FD_READ events. Waking up and retrying the recv() - * fixes that, so don't sleep indefinitely. This is a crock of the - * first water, but until somebody wants to debug exactly what's - * happening there, this is the best we can do. The two-second - * timeout matches our pre-9.2 behavior, and needs to be short enough - * to not provoke "using stale statistics" complaints from - * backend_read_statsfile. - */ - wr = WaitLatchOrSocket(MyLatch, - WL_LATCH_SET | WL_POSTMASTER_DEATH | WL_SOCKET_READABLE | WL_TIMEOUT, - pgStatSock, - 2 * 1000L /* msec */ , - WAIT_EVENT_PGSTAT_MAIN); -#endif - - /* - * Emergency bailout if postmaster has died. This is to avoid the - * necessity for manual cleanup of all postmaster children. - */ - if (wr & WL_POSTMASTER_DEATH) - break; - } /* end of outer loop */ - - /* - * Save the final stats to reuse at next startup. - */ - pgstat_write_statsfiles(true, true); - - exit(0); -} - - -/* SIGQUIT signal handler for collector process */ -static void -pgstat_exit(SIGNAL_ARGS) -{ - int save_errno = errno; - - need_exit = true; - SetLatch(MyLatch); - - errno = save_errno; -} - -/* SIGHUP handler for collector process */ -static void -pgstat_sighup_handler(SIGNAL_ARGS) -{ - int save_errno = errno; - - got_SIGHUP = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* - * Subroutine to clear stats in a database entry + * Subroutine to reset stats in a shared database entry * * Tables and functions hashes are initialized to empty. */ static void reset_dbentry_counters(PgStat_StatDBEntry *dbentry) { - HASHCTL hash_ctl; + dshash_table *tbl; dbentry->n_xact_commit = 0; dbentry->n_xact_rollback = 0; @@ -4564,20 +4384,17 @@ reset_dbentry_counters(PgStat_StatDBEntry *dbentry) dbentry->stat_reset_timestamp = GetCurrentTimestamp(); dbentry->stats_timestamp = 0; - memset(&hash_ctl, 0, sizeof(hash_ctl)); - hash_ctl.keysize = sizeof(Oid); - hash_ctl.entrysize = sizeof(PgStat_StatTabEntry); - dbentry->tables = hash_create("Per-database table", - PGSTAT_TAB_HASH_SIZE, - &hash_ctl, - HASH_ELEM | HASH_BLOBS); - hash_ctl.keysize = sizeof(Oid); - hash_ctl.entrysize = sizeof(PgStat_StatFuncEntry); - dbentry->functions = hash_create("Per-database function", - PGSTAT_FUNCTION_HASH_SIZE, - &hash_ctl, - HASH_ELEM | HASH_BLOBS); + Assert(dbentry->tables == DSM_HANDLE_INVALID); + tbl = dshash_create(area, &dsh_tblparams, 0); + dbentry->tables = dshash_get_hash_table_handle(tbl); + dshash_detach(tbl); + + Assert(dbentry->functions == DSM_HANDLE_INVALID); + /* we create function hash as needed */ + + dbentry->snapshot_tables = NULL; + dbentry->snapshot_functions = NULL; } /* @@ -4586,47 +4403,76 @@ reset_dbentry_counters(PgStat_StatDBEntry *dbentry) * Else, return NULL. */ static PgStat_StatDBEntry * -pgstat_get_db_entry(Oid databaseid, bool create) +pgstat_get_db_entry(Oid databaseid, int op, pg_stat_table_result_status *status) { PgStat_StatDBEntry *result; - bool found; - HASHACTION action = (create ? HASH_ENTER : HASH_FIND); + bool nowait = ((op & PGSTAT_FETCH_NOWAIT) != 0); + bool lock_acquired = true; + bool found = true; - /* Lookup or create the hash table entry for this database */ - result = (PgStat_StatDBEntry *) hash_search(pgStatDBHash, - &databaseid, - action, &found); - - if (!create && !found) + if (!IsUnderPostmaster) return NULL; - /* - * If not found, initialize the new one. This creates empty hash tables - * for tables and functions, too. - */ - if (!found) - reset_dbentry_counters(result); + /* Lookup or create the hash table entry for this database */ + if (op & PGSTAT_FETCH_EXCLUSIVE) + { + result = (PgStat_StatDBEntry *) + dshash_find_or_insert_extended(db_stats, &databaseid, + &found, nowait); + if (result == NULL) + lock_acquired = false; + else if (!found) + { + /* + * If not found, initialize the new one. This creates empty hash + * tables for tables and functions, too. + */ + reset_dbentry_counters(result); + } + } + else + { + result = (PgStat_StatDBEntry *) + dshash_find_extended(db_stats, &databaseid, + &lock_acquired, true, nowait); + if (result == NULL) + found = false; + } + + /* Set return status if requested */ + if (status) + { + if (!lock_acquired) + { + Assert(nowait); + *status = PGSTAT_ENTRY_LOCK_FAILED; + } + else if (!found) + *status = PGSTAT_ENTRY_NOT_FOUND; + else + *status = PGSTAT_ENTRY_FOUND; + } return result; } - /* * Lookup the hash table entry for the specified table. If no hash * table entry exists, initialize it, if the create parameter is true. * Else, return NULL. */ static PgStat_StatTabEntry * -pgstat_get_tab_entry(PgStat_StatDBEntry *dbentry, Oid tableoid, bool create) +pgstat_get_tab_entry(dshash_table *table, Oid tableoid, bool create) { PgStat_StatTabEntry *result; bool found; - HASHACTION action = (create ? HASH_ENTER : HASH_FIND); /* Lookup or create the hash table entry for this table */ - result = (PgStat_StatTabEntry *) hash_search(dbentry->tables, - &tableoid, - action, &found); + if (create) + result = (PgStat_StatTabEntry *) + dshash_find_or_insert(table, &tableoid, &found); + else + result = (PgStat_StatTabEntry *) dshash_find(table, &tableoid, false); if (!create && !found) return NULL; @@ -4662,29 +4508,23 @@ pgstat_get_tab_entry(PgStat_StatDBEntry *dbentry, Oid tableoid, bool create) /* ---------- * pgstat_write_statsfiles() - - * Write the global statistics file, as well as requested DB files. - * - * 'permanent' specifies writing to the permanent files not temporary ones. - * When true (happens only when the collector is shutting down), also remove - * the temporary files so that backends starting up under a new postmaster - * can't read old data before the new collector is ready. - * - * When 'allDbs' is false, only the requested databases (listed in - * pending_write_requests) will be written; otherwise, all databases - * will be written. + * Write the global statistics file, as well as DB files. * ---------- */ -static void -pgstat_write_statsfiles(bool permanent, bool allDbs) +void +pgstat_write_statsfiles(void) { - HASH_SEQ_STATUS hstat; + dshash_seq_status hstat; PgStat_StatDBEntry *dbentry; FILE *fpout; int32 format_id; - const char *tmpfile = permanent ? PGSTAT_STAT_PERMANENT_TMPFILE : pgstat_stat_tmpname; - const char *statfile = permanent ? PGSTAT_STAT_PERMANENT_FILENAME : pgstat_stat_filename; + const char *tmpfile = PGSTAT_STAT_PERMANENT_TMPFILE; + const char *statfile = PGSTAT_STAT_PERMANENT_FILENAME; int rc; + /* should be called from postmaster */ + Assert(!IsUnderPostmaster); + elog(DEBUG2, "writing stats file \"%s\"", statfile); /* @@ -4703,7 +4543,7 @@ pgstat_write_statsfiles(bool permanent, bool allDbs) /* * Set the timestamp of the stats file. */ - globalStats.stats_timestamp = GetCurrentTimestamp(); + shared_globalStats->stats_timestamp = GetCurrentTimestamp(); /* * Write the file header --- currently just a format ID. @@ -4715,32 +4555,29 @@ pgstat_write_statsfiles(bool permanent, bool allDbs) /* * Write global stats struct */ - rc = fwrite(&globalStats, sizeof(globalStats), 1, fpout); + rc = fwrite(shared_globalStats, sizeof(*shared_globalStats), 1, fpout); (void) rc; /* we'll check for error with ferror */ /* * Write archiver stats struct */ - rc = fwrite(&archiverStats, sizeof(archiverStats), 1, fpout); + rc = fwrite(shared_archiverStats, sizeof(*shared_archiverStats), 1, fpout); (void) rc; /* we'll check for error with ferror */ /* * Walk through the database table. */ - hash_seq_init(&hstat, pgStatDBHash); - while ((dbentry = (PgStat_StatDBEntry *) hash_seq_search(&hstat)) != NULL) + dshash_seq_init(&hstat, db_stats, false, false); + while ((dbentry = (PgStat_StatDBEntry *) dshash_seq_next(&hstat)) != NULL) { /* * Write out the table and function stats for this DB into the * appropriate per-DB stat file, if required. */ - if (allDbs || pgstat_db_requested(dbentry->databaseid)) - { - /* Make DB's timestamp consistent with the global stats */ - dbentry->stats_timestamp = globalStats.stats_timestamp; + /* Make DB's timestamp consistent with the global stats */ + dbentry->stats_timestamp = shared_globalStats->stats_timestamp; - pgstat_write_db_statsfile(dbentry, permanent); - } + pgstat_write_db_statsfile(dbentry); /* * Write out the DB entry. We don't write the tables or functions @@ -4783,16 +4620,6 @@ pgstat_write_statsfiles(bool permanent, bool allDbs) tmpfile, statfile))); unlink(tmpfile); } - - if (permanent) - unlink(pgstat_stat_filename); - - /* - * Now throw away the list of requests. Note that requests sent after we - * started the write are still waiting on the network socket. - */ - list_free(pending_write_requests); - pending_write_requests = NIL; } /* @@ -4800,15 +4627,14 @@ pgstat_write_statsfiles(bool permanent, bool allDbs) * of length len. */ static void -get_dbstat_filename(bool permanent, bool tempname, Oid databaseid, +get_dbstat_filename(bool tempname, Oid databaseid, char *filename, int len) { int printed; /* NB -- pgstat_reset_remove_files knows about the pattern this uses */ printed = snprintf(filename, len, "%s/db_%u.%s", - permanent ? PGSTAT_STAT_PERMANENT_DIRECTORY : - pgstat_stat_directory, + PGSTAT_STAT_PERMANENT_DIRECTORY, databaseid, tempname ? "tmp" : "stat"); if (printed >= len) @@ -4826,10 +4652,10 @@ get_dbstat_filename(bool permanent, bool tempname, Oid databaseid, * ---------- */ static void -pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry, bool permanent) +pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry) { - HASH_SEQ_STATUS tstat; - HASH_SEQ_STATUS fstat; + dshash_seq_status tstat; + dshash_seq_status fstat; PgStat_StatTabEntry *tabentry; PgStat_StatFuncEntry *funcentry; FILE *fpout; @@ -4838,9 +4664,10 @@ pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry, bool permanent) int rc; char tmpfile[MAXPGPATH]; char statfile[MAXPGPATH]; + dshash_table *tbl; - get_dbstat_filename(permanent, true, dbid, tmpfile, MAXPGPATH); - get_dbstat_filename(permanent, false, dbid, statfile, MAXPGPATH); + get_dbstat_filename(true, dbid, tmpfile, MAXPGPATH); + get_dbstat_filename(false, dbid, statfile, MAXPGPATH); elog(DEBUG2, "writing stats file \"%s\"", statfile); @@ -4867,23 +4694,30 @@ pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry, bool permanent) /* * Walk through the database's access stats per table. */ - hash_seq_init(&tstat, dbentry->tables); - while ((tabentry = (PgStat_StatTabEntry *) hash_seq_search(&tstat)) != NULL) + tbl = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0); + dshash_seq_init(&tstat, tbl, false, false); + while ((tabentry = (PgStat_StatTabEntry *) dshash_seq_next(&tstat)) != NULL) { fputc('T', fpout); rc = fwrite(tabentry, sizeof(PgStat_StatTabEntry), 1, fpout); (void) rc; /* we'll check for error with ferror */ } + dshash_detach(tbl); /* * Walk through the database's function stats table. */ - hash_seq_init(&fstat, dbentry->functions); - while ((funcentry = (PgStat_StatFuncEntry *) hash_seq_search(&fstat)) != NULL) + if (dbentry->functions != DSM_HANDLE_INVALID) { - fputc('F', fpout); - rc = fwrite(funcentry, sizeof(PgStat_StatFuncEntry), 1, fpout); - (void) rc; /* we'll check for error with ferror */ + tbl = dshash_attach(area, &dsh_funcparams, dbentry->functions, 0); + dshash_seq_init(&fstat, tbl, false, false); + while ((funcentry = (PgStat_StatFuncEntry *) dshash_seq_next(&fstat)) != NULL) + { + fputc('F', fpout); + rc = fwrite(funcentry, sizeof(PgStat_StatFuncEntry), 1, fpout); + (void) rc; /* we'll check for error with ferror */ + } + dshash_detach(tbl); } /* @@ -4918,47 +4752,30 @@ pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry, bool permanent) tmpfile, statfile))); unlink(tmpfile); } - - if (permanent) - { - get_dbstat_filename(false, false, dbid, statfile, MAXPGPATH); - - elog(DEBUG2, "removing temporary stats file \"%s\"", statfile); - unlink(statfile); - } } /* ---------- * pgstat_read_statsfiles() - * - * Reads in some existing statistics collector files and returns the - * databases hash table that is the top level of the data. + * Reads in some existing statistics collector files into the shared stats + * hash. * - * If 'onlydb' is not InvalidOid, it means we only want data for that DB - * plus the shared catalogs ("DB 0"). We'll still populate the DB hash - * table for all databases, but we don't bother even creating table/function - * hash tables for other databases. - * - * 'permanent' specifies reading from the permanent files not temporary ones. - * When true (happens only when the collector is starting up), remove the - * files after reading; the in-memory status is now authoritative, and the - * files would be out of date in case somebody else reads them. - * - * If a 'deep' read is requested, table/function stats are read, otherwise - * the table/function hash tables remain empty. * ---------- */ -static HTAB * -pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) +void +pgstat_read_statsfiles(void) { PgStat_StatDBEntry *dbentry; PgStat_StatDBEntry dbbuf; - HASHCTL hash_ctl; - HTAB *dbhash; FILE *fpin; int32 format_id; bool found; - const char *statfile = permanent ? PGSTAT_STAT_PERMANENT_FILENAME : pgstat_stat_filename; + const char *statfile = PGSTAT_STAT_PERMANENT_FILENAME; + dshash_table *tblstats = NULL; + dshash_table *funcstats = NULL; + + /* should be called from postmaster */ + Assert(!IsUnderPostmaster); /* * The tables will live in pgStatLocalContext. @@ -4966,28 +4783,18 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) pgstat_setup_memcxt(); /* - * Create the DB hashtable + * Create the DB hashtable and global stas area */ - memset(&hash_ctl, 0, sizeof(hash_ctl)); - hash_ctl.keysize = sizeof(Oid); - hash_ctl.entrysize = sizeof(PgStat_StatDBEntry); - hash_ctl.hcxt = pgStatLocalContext; - dbhash = hash_create("Databases hash", PGSTAT_DB_HASH_SIZE, &hash_ctl, - HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); - - /* - * 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)); + /* Hold lock so that no other process looks empty stats */ + LWLockAcquire(StatsLock, LW_EXCLUSIVE); + pgstat_create_shared_stats(); /* * 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; + shared_globalStats->stat_reset_timestamp = GetCurrentTimestamp(); + shared_archiverStats->stat_reset_timestamp = shared_globalStats->stat_reset_timestamp; /* * Try to open the stats file. If it doesn't exist, the backends simply @@ -5001,11 +4808,12 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) if ((fpin = AllocateFile(statfile, PG_BINARY_R)) == NULL) { if (errno != ENOENT) - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errcode_for_file_access(), errmsg("could not open statistics file \"%s\": %m", statfile))); - return dbhash; + LWLockRelease(StatsLock); + return; } /* @@ -5014,7 +4822,7 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) if (fread(&format_id, 1, sizeof(format_id), fpin) != sizeof(format_id) || format_id != PGSTAT_FILE_FORMAT_ID) { - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); goto done; } @@ -5022,11 +4830,12 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) /* * Read global stats struct */ - if (fread(&globalStats, 1, sizeof(globalStats), fpin) != sizeof(globalStats)) + if (fread(shared_globalStats, 1, sizeof(*shared_globalStats), fpin) != + sizeof(*shared_globalStats)) { - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); - memset(&globalStats, 0, sizeof(globalStats)); + memset(shared_globalStats, 0, sizeof(*shared_globalStats)); goto done; } @@ -5037,17 +4846,17 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) * file's timestamp is less than PGSTAT_STAT_INTERVAL ago, but that's not * an unusual scenario. */ - if (pgStatRunningInCollector) - globalStats.stats_timestamp = 0; + shared_globalStats->stats_timestamp = 0; /* * Read archiver stats struct */ - if (fread(&archiverStats, 1, sizeof(archiverStats), fpin) != sizeof(archiverStats)) + if (fread(shared_archiverStats, 1, sizeof(*shared_archiverStats), fpin) != + sizeof(*shared_archiverStats)) { - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); - memset(&archiverStats, 0, sizeof(archiverStats)); + memset(shared_archiverStats, 0, sizeof(*shared_archiverStats)); goto done; } @@ -5067,7 +4876,7 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) if (fread(&dbbuf, 1, offsetof(PgStat_StatDBEntry, tables), fpin) != offsetof(PgStat_StatDBEntry, tables)) { - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); goto done; @@ -5076,21 +4885,23 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) /* * Add to the DB hash */ - dbentry = (PgStat_StatDBEntry *) hash_search(dbhash, - (void *) &dbbuf.databaseid, - HASH_ENTER, - &found); + dbentry = (PgStat_StatDBEntry *) + dshash_find_or_insert(db_stats, (void *) &dbbuf.databaseid, + &found); if (found) { - ereport(pgStatRunningInCollector ? LOG : WARNING, + dshash_release_lock(db_stats, dbentry); + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); goto done; } memcpy(dbentry, &dbbuf, sizeof(PgStat_StatDBEntry)); - dbentry->tables = NULL; - dbentry->functions = NULL; + dbentry->tables = DSM_HANDLE_INVALID; + dbentry->functions = DSM_HANDLE_INVALID; + dbentry->snapshot_tables = NULL; + dbentry->snapshot_functions = NULL; /* * In the collector, disregard the timestamp we read from the @@ -5098,54 +4909,26 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) * stats file immediately upon the first request from any * backend. */ - if (pgStatRunningInCollector) - dbentry->stats_timestamp = 0; - - /* - * Don't create tables/functions hashtables for uninteresting - * databases. - */ - if (onlydb != InvalidOid) - { - if (dbbuf.databaseid != onlydb && - dbbuf.databaseid != InvalidOid) - break; - } - - memset(&hash_ctl, 0, sizeof(hash_ctl)); - hash_ctl.keysize = sizeof(Oid); - hash_ctl.entrysize = sizeof(PgStat_StatTabEntry); - hash_ctl.hcxt = pgStatLocalContext; - dbentry->tables = hash_create("Per-database table", - PGSTAT_TAB_HASH_SIZE, - &hash_ctl, - HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); - - hash_ctl.keysize = sizeof(Oid); - hash_ctl.entrysize = sizeof(PgStat_StatFuncEntry); - hash_ctl.hcxt = pgStatLocalContext; - dbentry->functions = hash_create("Per-database function", - PGSTAT_FUNCTION_HASH_SIZE, - &hash_ctl, - HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); + dbentry->stats_timestamp = 0; /* * If requested, read the data from the database-specific * file. Otherwise we just leave the hashtables empty. */ - if (deep) - pgstat_read_db_statsfile(dbentry->databaseid, - dbentry->tables, - dbentry->functions, - permanent); - + tblstats = dshash_create(area, &dsh_tblparams, 0); + dbentry->tables = dshash_get_hash_table_handle(tblstats); + /* we don't create function hash at the present */ + dshash_release_lock(db_stats, dbentry); + pgstat_read_db_statsfile(dbentry->databaseid, + tblstats, funcstats); + dshash_detach(tblstats); break; case 'E': goto done; default: - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); goto done; @@ -5153,36 +4936,62 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep) } done: + LWLockRelease(StatsLock); FreeFile(fpin); - /* If requested to read the permanent file, also get rid of it. */ - if (permanent) - { - elog(DEBUG2, "removing permanent stats file \"%s\"", statfile); - unlink(statfile); - } + elog(DEBUG2, "removing permanent stats file \"%s\"", statfile); + unlink(statfile); - return dbhash; + return; } +Size +StatsShmemSize(void) +{ + return sizeof(StatsShmemStruct); +} + +void +StatsShmemInit(void) +{ + bool found; + + StatsShmem = (StatsShmemStruct *) + ShmemInitStruct("Stats area", StatsShmemSize(), + &found); + if (!IsUnderPostmaster) + { + Assert(!found); + + StatsShmem->stats_dsa_handle = DSM_HANDLE_INVALID; + + /* Load saved data if any */ + pgstat_read_statsfiles(); + + /* need to be called before dsm shutodwn */ + before_shmem_exit(pgstat_postmaster_shutdown, (Datum) 0); + } +} + +static void +pgstat_postmaster_shutdown(int code, Datum arg) +{ + /* we trash the stats on crash */ + if (code == 0) + pgstat_write_statsfiles(); +} + /* ---------- * pgstat_read_db_statsfile() - * - * Reads in the existing statistics collector file for the given database, - * filling the passed-in tables and functions hash tables. - * - * As in pgstat_read_statsfiles, if the permanent file is requested, it is - * removed after reading. - * - * Note: this code has the ability to skip storing per-table or per-function - * data, if NULL is passed for the corresponding hashtable. That's not used - * at the moment though. + * Reads in the permanent statistics collector file and create shared + * statistics tables. The file is removed afer reading. * ---------- */ static void -pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, - bool permanent) +pgstat_read_db_statsfile(Oid databaseid, + dshash_table *tabhash, dshash_table *funchash) { PgStat_StatTabEntry *tabentry; PgStat_StatTabEntry tabbuf; @@ -5193,7 +5002,10 @@ pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, bool found; char statfile[MAXPGPATH]; - get_dbstat_filename(permanent, false, databaseid, statfile, MAXPGPATH); + /* should be called from postmaster */ + Assert(!IsUnderPostmaster); + + get_dbstat_filename(false, databaseid, statfile, MAXPGPATH); /* * Try to open the stats file. If it doesn't exist, the backends simply @@ -5207,7 +5019,7 @@ pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, if ((fpin = AllocateFile(statfile, PG_BINARY_R)) == NULL) { if (errno != ENOENT) - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errcode_for_file_access(), errmsg("could not open statistics file \"%s\": %m", statfile))); @@ -5220,7 +5032,7 @@ pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, if (fread(&format_id, 1, sizeof(format_id), fpin) != sizeof(format_id) || format_id != PGSTAT_FILE_FORMAT_ID) { - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); goto done; } @@ -5240,7 +5052,7 @@ pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, if (fread(&tabbuf, 1, sizeof(PgStat_StatTabEntry), fpin) != sizeof(PgStat_StatTabEntry)) { - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); goto done; @@ -5252,19 +5064,21 @@ pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, if (tabhash == NULL) break; - tabentry = (PgStat_StatTabEntry *) hash_search(tabhash, - (void *) &tabbuf.tableid, - HASH_ENTER, &found); + tabentry = (PgStat_StatTabEntry *) + dshash_find_or_insert(tabhash, + (void *) &tabbuf.tableid, &found); if (found) { - ereport(pgStatRunningInCollector ? LOG : WARNING, + dshash_release_lock(tabhash, tabentry); + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); goto done; } memcpy(tabentry, &tabbuf, sizeof(tabbuf)); + dshash_release_lock(tabhash, tabentry); break; /* @@ -5274,7 +5088,7 @@ pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, if (fread(&funcbuf, 1, sizeof(PgStat_StatFuncEntry), fpin) != sizeof(PgStat_StatFuncEntry)) { - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); goto done; @@ -5286,19 +5100,20 @@ pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, if (funchash == NULL) break; - funcentry = (PgStat_StatFuncEntry *) hash_search(funchash, - (void *) &funcbuf.functionid, - HASH_ENTER, &found); + funcentry = (PgStat_StatFuncEntry *) + dshash_find_or_insert(funchash, + (void *) &funcbuf.functionid, &found); if (found) { - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); goto done; } memcpy(funcentry, &funcbuf, sizeof(funcbuf)); + dshash_release_lock(funchash, funcentry); break; /* @@ -5308,7 +5123,7 @@ pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, goto done; default: - ereport(pgStatRunningInCollector ? LOG : WARNING, + ereport(LOG, (errmsg("corrupted statistics file \"%s\"", statfile))); goto done; @@ -5318,276 +5133,290 @@ pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, done: FreeFile(fpin); - if (permanent) - { - elog(DEBUG2, "removing permanent stats file \"%s\"", statfile); - unlink(statfile); - } + elog(DEBUG2, "removing permanent stats file \"%s\"", statfile); + unlink(statfile); } /* ---------- - * pgstat_read_db_statsfile_timestamp() - + * backend_clean_snapshot_callback() - * - * Attempt to determine the timestamp of the last db statfile write. - * Returns true if successful; the timestamp is stored in *ts. - * - * This needs to be careful about handling databases for which no stats file - * exists, such as databases without a stat entry or those not yet written: - * - * - if there's a database entry in the global file, return the corresponding - * stats_timestamp value. - * - * - if there's no db stat entry (e.g. for a new or inactive database), - * there's no stats_timestamp value, but also nothing to write so we return - * the timestamp of the global statfile. + * This is usually called with arg = NULL when the memory context where the + * current snapshot has been taken. Don't bother releasing memory in the + * case. * ---------- */ -static bool -pgstat_read_db_statsfile_timestamp(Oid databaseid, bool permanent, - TimestampTz *ts) +static void +backend_clean_snapshot_callback(void *arg) { - 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; - - /* - * Try to open the stats file. As above, anything but ENOENT is worthy of - * complaining about. - */ - if ((fpin = AllocateFile(statfile, PG_BINARY_R)) == NULL) + if (arg != NULL) { - if (errno != ENOENT) - ereport(pgStatRunningInCollector ? LOG : WARNING, - (errcode_for_file_access(), - errmsg("could not open statistics file \"%s\": %m", - statfile))); - return false; - } + /* explicitly called, so explicitly free resources */ + if (snapshot_globalStats) + pfree(snapshot_globalStats); - /* - * Verify it's of the expected format. - */ - if (fread(&format_id, 1, sizeof(format_id), fpin) != sizeof(format_id) || - format_id != PGSTAT_FILE_FORMAT_ID) - { - ereport(pgStatRunningInCollector ? LOG : WARNING, - (errmsg("corrupted statistics file \"%s\"", statfile))); - FreeFile(fpin); - return false; - } + if (snapshot_archiverStats) + pfree(snapshot_archiverStats); - /* - * Read global stats struct - */ - if (fread(&myGlobalStats, 1, sizeof(myGlobalStats), - fpin) != sizeof(myGlobalStats)) - { - ereport(pgStatRunningInCollector ? LOG : WARNING, - (errmsg("corrupted statistics file \"%s\"", statfile))); - FreeFile(fpin); - 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; - - /* - * We found an existing collector stats file. Read it and look for a - * record for the requested database. If found, use its timestamp. - */ - for (;;) - { - switch (fgetc(fpin)) + if (snapshot_db_stats) { - /* - * 'D' A PgStat_StatDBEntry struct describing a database - * follows. - */ - case 'D': - if (fread(&dbentry, 1, offsetof(PgStat_StatDBEntry, tables), - fpin) != offsetof(PgStat_StatDBEntry, tables)) - { - ereport(pgStatRunningInCollector ? LOG : WARNING, - (errmsg("corrupted statistics file \"%s\"", - statfile))); - goto done; - } + HASH_SEQ_STATUS seq; + PgStat_StatDBEntry *dbent; - /* - * If this is the DB we're looking for, save its timestamp and - * we're done. - */ - if (dbentry.databaseid == databaseid) - { - *ts = dbentry.stats_timestamp; - goto done; - } - - break; - - case 'E': - goto done; - - default: - ereport(pgStatRunningInCollector ? LOG : WARNING, - (errmsg("corrupted statistics file \"%s\"", - statfile))); - goto done; + hash_seq_init(&seq, snapshot_db_stats); + while ((dbent = hash_seq_search(&seq)) != NULL) + { + if (dbent->snapshot_tables) + hash_destroy(dbent->snapshot_tables); + if (dbent->snapshot_functions) + hash_destroy(dbent->snapshot_functions); + } + hash_destroy(snapshot_db_stats); } } -done: - FreeFile(fpin); - return true; + /* mark as the resource are not allocated */ + snapshot_globalStats = NULL; + snapshot_archiverStats = NULL; + snapshot_db_stats = NULL; } /* - * If not already done, read the statistics collector stats file into - * some hash tables. The results will be kept until pgstat_clear_snapshot() - * is called (typically, at end of transaction). + * create_local_stats_hash() - + * + * Creates a dynahash used for table/function stats cache. */ -static void -backend_read_statsfile(void) +static HTAB * +create_local_stats_hash(const char *name, size_t keysize, size_t entrysize, + int nentries) { - TimestampTz min_ts = 0; - TimestampTz ref_ts = 0; - Oid inquiry_db; - int count; + HTAB *result; + HASHCTL ctl; - /* already read it? */ - if (pgStatDBHash) - return; - Assert(!pgStatRunningInCollector); - - /* - * In a normal backend, we check staleness of the data for our own DB, and - * so we send MyDatabaseId in inquiry messages. In the autovac launcher, - * check staleness of the shared-catalog data, and send InvalidOid in - * inquiry messages so as not to force writing unnecessary data. - */ - if (IsAutoVacuumLauncherProcess()) - inquiry_db = InvalidOid; - else - inquiry_db = MyDatabaseId; - - /* - * Loop until fresh enough stats file is available or we ran out of time. - * The stats inquiry message is sent repeatedly in case collector drops - * it; but not every single time, as that just swamps the collector. - */ - for (count = 0; count < PGSTAT_POLL_LOOP_COUNT; count++) - { - bool ok; - TimestampTz file_ts = 0; - TimestampTz cur_ts; - - CHECK_FOR_INTERRUPTS(); - - ok = pgstat_read_db_statsfile_timestamp(inquiry_db, false, &file_ts); - - cur_ts = GetCurrentTimestamp(); - /* Calculate min acceptable timestamp, if we didn't already */ - if (count == 0 || cur_ts < ref_ts) - { - /* - * We set the minimum acceptable timestamp to PGSTAT_STAT_INTERVAL - * msec before now. This indirectly ensures that the collector - * needn't write the file more often than PGSTAT_STAT_INTERVAL. In - * an autovacuum worker, however, we want a lower delay to avoid - * using stale data, so we use PGSTAT_RETRY_DELAY (since the - * number of workers is low, this shouldn't be a problem). - * - * We don't recompute min_ts after sleeping, except in the - * unlikely case that cur_ts went backwards. So we might end up - * accepting a file a bit older than PGSTAT_STAT_INTERVAL. In - * practice that shouldn't happen, though, as long as the sleep - * time is less than PGSTAT_STAT_INTERVAL; and we don't want to - * tell the collector that our cutoff time is less than what we'd - * actually accept. - */ - ref_ts = cur_ts; - if (IsAutoVacuumWorkerProcess()) - min_ts = TimestampTzPlusMilliseconds(ref_ts, - -PGSTAT_RETRY_DELAY); - else - min_ts = TimestampTzPlusMilliseconds(ref_ts, - -PGSTAT_STAT_INTERVAL); - } - - /* - * If the file timestamp is actually newer than cur_ts, we must have - * had a clock glitch (system time went backwards) or there is clock - * skew between our processor and the stats collector's processor. - * Accept the file, but send an inquiry message anyway to make - * pgstat_recv_inquiry do a sanity check on the collector's time. - */ - if (ok && file_ts > cur_ts) - { - /* - * A small amount of clock skew between processors isn't terribly - * surprising, but a large difference is worth logging. We - * arbitrarily define "large" as 1000 msec. - */ - if (file_ts >= TimestampTzPlusMilliseconds(cur_ts, 1000)) - { - char *filetime; - char *mytime; - - /* Copy because timestamptz_to_str returns a static buffer */ - filetime = pstrdup(timestamptz_to_str(file_ts)); - mytime = pstrdup(timestamptz_to_str(cur_ts)); - elog(LOG, "stats collector's time %s is later than backend local time %s", - filetime, mytime); - pfree(filetime); - pfree(mytime); - } - - pgstat_send_inquiry(cur_ts, min_ts, inquiry_db); - break; - } - - /* Normal acceptance case: file is not older than cutoff time */ - if (ok && file_ts >= min_ts) - break; - - /* Not there or too old, so kick the collector and wait a bit */ - if ((count % PGSTAT_INQ_LOOP_COUNT) == 0) - pgstat_send_inquiry(cur_ts, min_ts, inquiry_db); - - pg_usleep(PGSTAT_RETRY_DELAY * 1000L); - } - - if (count >= PGSTAT_POLL_LOOP_COUNT) - ereport(LOG, - (errmsg("using stale statistics instead of current ones " - "because stats collector is not responding"))); - - /* - * Autovacuum launcher wants stats about all databases, but a shallow read - * is sufficient. Regular backends want a deep read for just the tables - * they can see (MyDatabaseId + shared catalogs). - */ - if (IsAutoVacuumLauncherProcess()) - pgStatDBHash = pgstat_read_statsfiles(InvalidOid, false, false); - else - pgStatDBHash = pgstat_read_statsfiles(MyDatabaseId, false, true); + /* Create the hash in the stats context */ + ctl.keysize = keysize; + ctl.entrysize = entrysize; + ctl.hcxt = stats_cxt; + result = hash_create(name, nentries, &ctl, + HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); + return result; } +/* + * snapshot_statentry() - Find an entriy from source dshash. + * + * Returns the entry for key or NULL if not found. If dest is not null, uses + * *dest as local cache, which is created in the same shape with the given + * dshash when *dest is NULL. In both cases the result is cached in the hash + * and the same entry is returned to subsequent calls for the same key. + * + * Otherwise returned entry is a copy that is palloc'ed in the current memory + * context. Its content may differ for every request. + * + * If dshash is NULL, temporaralily attaches dsh_handle instead. + */ +static void * +snapshot_statentry(HTAB **dest, const char *hashname, + dshash_table *dshash, dshash_table_handle dsh_handle, + const dshash_parameters *dsh_params, Oid key) +{ + void *lentry = NULL; + size_t keysize = dsh_params->key_size; + size_t entrysize = dsh_params->entry_size; + + if (dest) + { + /* caches the result entry */ + bool found; + + /* + * Create new hash with arbitrary initial entries since we don't know + * how this hash will grow. + */ + if (!*dest) + { + Assert(hashname); + *dest = create_local_stats_hash(hashname, keysize, entrysize, 32); + } + + lentry = hash_search(*dest, &key, HASH_ENTER, &found); + if (!found) + { + dshash_table *t = dshash; + void *sentry; + + if (!t) + t = dshash_attach(area, dsh_params, dsh_handle, NULL); + + sentry = dshash_find(t, &key, false); + + /* + * We expect that the stats for specified database exists in most + * cases. + */ + if (!sentry) + { + hash_search(*dest, &key, HASH_REMOVE, NULL); + if (!dshash) + dshash_detach(t); + return NULL; + } + memcpy(lentry, sentry, entrysize); + dshash_release_lock(t, sentry); + + if (!dshash) + dshash_detach(t); + } + } + else + { + /* + * The caller don't want caching. Just make a copy of the entry then + * return. + */ + dshash_table *t = dshash; + void *sentry; + + if (!t) + t = dshash_attach(area, dsh_params, dsh_handle, NULL); + + sentry = dshash_find(t, &key, false); + if (sentry) + { + lentry = palloc(entrysize); + memcpy(lentry, sentry, entrysize); + dshash_release_lock(t, sentry); + } + + if (!dshash) + dshash_detach(t); + } + + return lentry; +} + +/* + * backend_snapshot_global_stats() - + * + * Makes a local copy of global stats if not already done. They will be kept + * until pgstat_clear_snapshot() is called or the end of the current memory + * context (typically TopTransactionContext). Returns false if the shared + * stats is not created yet. + */ +static bool +backend_snapshot_global_stats(void) +{ + MemoryContext oldcontext = CurrentMemoryContext; + MemoryContextCallback *mcxt_cb; + + /* Nothing to do if already done */ + if (snapshot_globalStats) + return true; + + Assert(snapshot_archiverStats == NULL); + + /* + * The snapshot lives within the current top transaction if any, or the + * current memory context liftime otherwise. + */ + if (IsTransactionState()) + oldcontext = MemoryContextSwitchTo(TopTransactionContext); + + /* Remember for stats memory allocation later */ + stats_cxt = CurrentMemoryContext; + + /* global stats can be just copied */ + snapshot_globalStats = palloc(sizeof(PgStat_GlobalStats)); + memcpy(snapshot_globalStats, shared_globalStats, + sizeof(PgStat_GlobalStats)); + + snapshot_archiverStats = palloc(sizeof(PgStat_ArchiverStats)); + memcpy(snapshot_archiverStats, shared_archiverStats, + sizeof(PgStat_ArchiverStats)); + + /* set the timestamp of this snapshot */ + snapshot_globalStats->stats_timestamp = GetCurrentTimestamp(); + + /* register callback to clear snapshot */ + mcxt_cb = (MemoryContextCallback *)palloc(sizeof(MemoryContextCallback)); + mcxt_cb->func = backend_clean_snapshot_callback; + mcxt_cb->arg = NULL; + MemoryContextRegisterResetCallback(CurrentMemoryContext, mcxt_cb); + MemoryContextSwitchTo(oldcontext); + + return true; +} + +/* ---------- + * pgstat_fetch_stat_dbentry() - + * + * Find database stats entry on backends. The returned entries are cached + * until transaction end. If onshot is true, they are not cached and returned + * in a palloc'ed memory. + */ +PgStat_StatDBEntry * +pgstat_fetch_stat_dbentry(Oid dbid, bool oneshot) +{ + /* take a local snapshot if we don't have one */ + char *hashname = "local database stats hash"; + PgStat_StatDBEntry *dbentry; + + /* should be called from backends */ + Assert(IsUnderPostmaster); + + /* If not done for this transaction, take a snapshot of global stats */ + if (!backend_snapshot_global_stats()) + return NULL; + + dbentry = snapshot_statentry(oneshot ? NULL : &snapshot_db_stats, + hashname, db_stats, 0, &dsh_dbparams, + dbid); + + return dbentry; +} + +/* ---------- + * backend_get_tab_entry() - + * + * Find table stats entry on backends. The returned entries are cached until + * transaction end. If onshot is true, they are not cached and returned in a + * palloc'ed memory. + */ +PgStat_StatTabEntry * +backend_get_tab_entry(PgStat_StatDBEntry *dbent, Oid reloid, bool oneshot) +{ + /* take a local snapshot if we don't have one */ + char *hashname = "local table stats hash"; + + /* should be called from backends */ + Assert(IsUnderPostmaster); + + return snapshot_statentry(oneshot ? NULL : &dbent->snapshot_tables, + hashname, NULL, dbent->tables, &dsh_tblparams, + reloid); +} + +/* ---------- + * backend_get_func_entry() - + * + * Find function stats entry on backends. The returned entries are cached + * until transaction end. If onshot is true, they are not cached and returned + * in a palloc'ed memory. + */ +static PgStat_StatFuncEntry * +backend_get_func_etnry(PgStat_StatDBEntry *dbent, Oid funcid, bool oneshot) +{ + char *hashname = "local table stats hash"; + + /* should be called from backends */ + Assert(IsUnderPostmaster); + + if (dbent->functions == DSM_HANDLE_INVALID) + return NULL; + + return snapshot_statentry(oneshot ? NULL : &dbent->snapshot_tables, + hashname, NULL, dbent->functions, &dsh_funcparams, + funcid); +} /* ---------- * pgstat_setup_memcxt() - @@ -5618,6 +5447,8 @@ pgstat_setup_memcxt(void) void pgstat_clear_snapshot(void) { + int param = 0; /* only the address is significant */ + /* Release memory, if any was allocated */ if (pgStatLocalContext) MemoryContextDelete(pgStatLocalContext); @@ -5627,717 +5458,112 @@ pgstat_clear_snapshot(void) pgStatDBHash = NULL; localBackendStatusTable = NULL; localNumBackends = 0; + + /* + * the parameter inform the function that it is not called from + * MemoryContextCallback + */ + backend_clean_snapshot_callback(¶m); } -/* ---------- - * pgstat_recv_inquiry() - - * - * Process stat inquiry requests. - * ---------- - */ -static void -pgstat_recv_inquiry(PgStat_MsgInquiry *msg, int len) +static bool +pgstat_update_tabentry(dshash_table *tabhash, PgStat_TableStatus *stat, + bool nowait) { - PgStat_StatDBEntry *dbentry; + PgStat_StatTabEntry *tabentry; + bool found; - elog(DEBUG2, "received inquiry for database %u", msg->databaseid); + if (tabhash == NULL) + return false; - /* - * If there's already a write request for this DB, there's nothing to do. - * - * Note that if a request is found, we return early and skip the below - * check for clock skew. This is okay, since the only way for a DB - * request to be present in the list is that we have been here since the - * last write round. It seems sufficient to check for clock skew once per - * write round. - */ - if (list_member_oid(pending_write_requests, msg->databaseid)) - return; + tabentry = (PgStat_StatTabEntry *) + dshash_find_or_insert_extended(tabhash, (void *) &(stat->t_id), + &found, nowait); - /* - * Check to see if we last wrote this database at a time >= the requested - * cutoff time. If so, this is a stale request that was generated before - * we updated the DB file, and we don't need to do so again. - * - * If the requestor's local clock time is older than stats_timestamp, we - * should suspect a clock glitch, ie system time going backwards; though - * the more likely explanation is just delayed message receipt. It is - * worth expending a GetCurrentTimestamp call to be sure, since a large - * retreat in the system clock reading could otherwise cause us to neglect - * to update the stats file for a long time. - */ - dbentry = pgstat_get_db_entry(msg->databaseid, false); - if (dbentry == NULL) + /* failed to acquire lock */ + if (tabentry == NULL) + return false; + + if (!found) { /* - * We have no data for this DB. Enter a write request anyway so that - * the global stats will get updated. This is needed to prevent - * backend_read_statsfile from waiting for data that we cannot supply, - * in the case of a new DB that nobody has yet reported any stats for. - * See the behavior of pgstat_read_db_statsfile_timestamp. + * If it's a new table entry, initialize counters to the values we + * just got. */ + tabentry->numscans = stat->t_counts.t_numscans; + tabentry->tuples_returned = stat->t_counts.t_tuples_returned; + tabentry->tuples_fetched = stat->t_counts.t_tuples_fetched; + tabentry->tuples_inserted = stat->t_counts.t_tuples_inserted; + tabentry->tuples_updated = stat->t_counts.t_tuples_updated; + tabentry->tuples_deleted = stat->t_counts.t_tuples_deleted; + tabentry->tuples_hot_updated = stat->t_counts.t_tuples_hot_updated; + tabentry->n_live_tuples = stat->t_counts.t_delta_live_tuples; + tabentry->n_dead_tuples = stat->t_counts.t_delta_dead_tuples; + tabentry->changes_since_analyze = stat->t_counts.t_changed_tuples; + tabentry->blocks_fetched = stat->t_counts.t_blocks_fetched; + tabentry->blocks_hit = stat->t_counts.t_blocks_hit; + + tabentry->vacuum_timestamp = 0; + tabentry->vacuum_count = 0; + tabentry->autovac_vacuum_timestamp = 0; + tabentry->autovac_vacuum_count = 0; + tabentry->analyze_timestamp = 0; + tabentry->analyze_count = 0; + tabentry->autovac_analyze_timestamp = 0; + tabentry->autovac_analyze_count = 0; } - else if (msg->clock_time < dbentry->stats_timestamp) + else { - TimestampTz cur_ts = GetCurrentTimestamp(); - - if (cur_ts < dbentry->stats_timestamp) - { - /* - * Sure enough, time went backwards. Force a new stats file write - * to get back in sync; but first, log a complaint. - */ - char *writetime; - char *mytime; - - /* Copy because timestamptz_to_str returns a static buffer */ - writetime = pstrdup(timestamptz_to_str(dbentry->stats_timestamp)); - mytime = pstrdup(timestamptz_to_str(cur_ts)); - elog(LOG, - "stats_timestamp %s is later than collector's time %s for database %u", - writetime, mytime, dbentry->databaseid); - pfree(writetime); - pfree(mytime); - } - else - { - /* - * Nope, it's just an old request. Assuming msg's clock_time is - * >= its cutoff_time, it must be stale, so we can ignore it. - */ - return; - } - } - else if (msg->cutoff_time <= dbentry->stats_timestamp) - { - /* Stale request, ignore it */ - return; - } - - /* - * We need to write this DB, so create a request. - */ - pending_write_requests = lappend_oid(pending_write_requests, - msg->databaseid); -} - - -/* ---------- - * pgstat_recv_tabstat() - - * - * Count what the backend has done. - * ---------- - */ -static void -pgstat_recv_tabstat(PgStat_MsgTabstat *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - PgStat_StatTabEntry *tabentry; - int i; - bool found; - - dbentry = pgstat_get_db_entry(msg->m_databaseid, true); - - /* - * Update database-wide stats. - */ - dbentry->n_xact_commit += (PgStat_Counter) (msg->m_xact_commit); - dbentry->n_xact_rollback += (PgStat_Counter) (msg->m_xact_rollback); - dbentry->n_block_read_time += msg->m_block_read_time; - dbentry->n_block_write_time += msg->m_block_write_time; - - /* - * Process all table entries in the message. - */ - for (i = 0; i < msg->m_nentries; i++) - { - PgStat_TableEntry *tabmsg = &(msg->m_entry[i]); - - tabentry = (PgStat_StatTabEntry *) hash_search(dbentry->tables, - (void *) &(tabmsg->t_id), - HASH_ENTER, &found); - - if (!found) - { - /* - * If it's a new table entry, initialize counters to the values we - * just got. - */ - tabentry->numscans = tabmsg->t_counts.t_numscans; - tabentry->tuples_returned = tabmsg->t_counts.t_tuples_returned; - tabentry->tuples_fetched = tabmsg->t_counts.t_tuples_fetched; - tabentry->tuples_inserted = tabmsg->t_counts.t_tuples_inserted; - tabentry->tuples_updated = tabmsg->t_counts.t_tuples_updated; - tabentry->tuples_deleted = tabmsg->t_counts.t_tuples_deleted; - tabentry->tuples_hot_updated = tabmsg->t_counts.t_tuples_hot_updated; - tabentry->n_live_tuples = tabmsg->t_counts.t_delta_live_tuples; - tabentry->n_dead_tuples = tabmsg->t_counts.t_delta_dead_tuples; - tabentry->changes_since_analyze = tabmsg->t_counts.t_changed_tuples; - tabentry->blocks_fetched = tabmsg->t_counts.t_blocks_fetched; - tabentry->blocks_hit = tabmsg->t_counts.t_blocks_hit; - - tabentry->vacuum_timestamp = 0; - tabentry->vacuum_count = 0; - tabentry->autovac_vacuum_timestamp = 0; - tabentry->autovac_vacuum_count = 0; - tabentry->analyze_timestamp = 0; - tabentry->analyze_count = 0; - tabentry->autovac_analyze_timestamp = 0; - tabentry->autovac_analyze_count = 0; - } - else - { - /* - * Otherwise add the values to the existing entry. - */ - tabentry->numscans += tabmsg->t_counts.t_numscans; - tabentry->tuples_returned += tabmsg->t_counts.t_tuples_returned; - tabentry->tuples_fetched += tabmsg->t_counts.t_tuples_fetched; - tabentry->tuples_inserted += tabmsg->t_counts.t_tuples_inserted; - tabentry->tuples_updated += tabmsg->t_counts.t_tuples_updated; - tabentry->tuples_deleted += tabmsg->t_counts.t_tuples_deleted; - tabentry->tuples_hot_updated += tabmsg->t_counts.t_tuples_hot_updated; - /* If table was truncated, first reset the live/dead counters */ - if (tabmsg->t_counts.t_truncated) - { - tabentry->n_live_tuples = 0; - tabentry->n_dead_tuples = 0; - } - tabentry->n_live_tuples += tabmsg->t_counts.t_delta_live_tuples; - tabentry->n_dead_tuples += tabmsg->t_counts.t_delta_dead_tuples; - tabentry->changes_since_analyze += tabmsg->t_counts.t_changed_tuples; - tabentry->blocks_fetched += tabmsg->t_counts.t_blocks_fetched; - tabentry->blocks_hit += tabmsg->t_counts.t_blocks_hit; - } - - /* Clamp n_live_tuples in case of negative delta_live_tuples */ - tabentry->n_live_tuples = Max(tabentry->n_live_tuples, 0); - /* Likewise for n_dead_tuples */ - tabentry->n_dead_tuples = Max(tabentry->n_dead_tuples, 0); - /* - * Add per-table stats to the per-database entry, too. + * Otherwise add the values to the existing entry. */ - dbentry->n_tuples_returned += tabmsg->t_counts.t_tuples_returned; - dbentry->n_tuples_fetched += tabmsg->t_counts.t_tuples_fetched; - dbentry->n_tuples_inserted += tabmsg->t_counts.t_tuples_inserted; - dbentry->n_tuples_updated += tabmsg->t_counts.t_tuples_updated; - dbentry->n_tuples_deleted += tabmsg->t_counts.t_tuples_deleted; - dbentry->n_blocks_fetched += tabmsg->t_counts.t_blocks_fetched; - dbentry->n_blocks_hit += tabmsg->t_counts.t_blocks_hit; - } -} - - -/* ---------- - * pgstat_recv_tabpurge() - - * - * Arrange for dead table removal. - * ---------- - */ -static void -pgstat_recv_tabpurge(PgStat_MsgTabpurge *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - int i; - - dbentry = pgstat_get_db_entry(msg->m_databaseid, false); - - /* - * No need to purge if we don't even know the database. - */ - if (!dbentry || !dbentry->tables) - return; - - /* - * Process all table entries in the message. - */ - for (i = 0; i < msg->m_nentries; i++) - { - /* Remove from hashtable if present; we don't care if it's not. */ - (void) hash_search(dbentry->tables, - (void *) &(msg->m_tableid[i]), - HASH_REMOVE, NULL); - } -} - - -/* ---------- - * pgstat_recv_dropdb() - - * - * Arrange for dead database removal - * ---------- - */ -static void -pgstat_recv_dropdb(PgStat_MsgDropdb *msg, int len) -{ - Oid dbid = msg->m_databaseid; - PgStat_StatDBEntry *dbentry; - - /* - * Lookup the database in the hashtable. - */ - dbentry = pgstat_get_db_entry(dbid, false); - - /* - * If found, remove it (along with the db statfile). - */ - if (dbentry) - { - char statfile[MAXPGPATH]; - - get_dbstat_filename(false, false, dbid, statfile, MAXPGPATH); - - elog(DEBUG2, "removing stats file \"%s\"", statfile); - unlink(statfile); - - if (dbentry->tables != NULL) - hash_destroy(dbentry->tables); - if (dbentry->functions != NULL) - hash_destroy(dbentry->functions); - - if (hash_search(pgStatDBHash, - (void *) &dbid, - HASH_REMOVE, NULL) == NULL) - ereport(ERROR, - (errmsg("database hash table corrupted during cleanup --- abort"))); - } -} - - -/* ---------- - * pgstat_recv_resetcounter() - - * - * Reset the statistics for the specified database. - * ---------- - */ -static void -pgstat_recv_resetcounter(PgStat_MsgResetcounter *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - - /* - * Lookup the database in the hashtable. Nothing to do if not there. - */ - dbentry = pgstat_get_db_entry(msg->m_databaseid, false); - - if (!dbentry) - return; - - /* - * We simply throw away all the database's table entries by recreating a - * new hash table for them. - */ - if (dbentry->tables != NULL) - hash_destroy(dbentry->tables); - if (dbentry->functions != NULL) - hash_destroy(dbentry->functions); - - dbentry->tables = NULL; - dbentry->functions = NULL; - - /* - * Reset database-level stats, too. This creates empty hash tables for - * tables and functions. - */ - reset_dbentry_counters(dbentry); -} - -/* ---------- - * pgstat_recv_resetshared() - - * - * Reset some shared statistics of the cluster. - * ---------- - */ -static void -pgstat_recv_resetsharedcounter(PgStat_MsgResetsharedcounter *msg, int len) -{ - if (msg->m_resettarget == RESET_BGWRITER) - { - /* Reset the global background writer statistics for the cluster. */ - 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 - * complain here if it's not valid - */ -} - -/* ---------- - * pgstat_recv_resetsinglecounter() - - * - * Reset a statistics for a single object - * ---------- - */ -static void -pgstat_recv_resetsinglecounter(PgStat_MsgResetsinglecounter *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - - dbentry = pgstat_get_db_entry(msg->m_databaseid, false); - - if (!dbentry) - return; - - /* Set the reset timestamp for the whole database */ - dbentry->stat_reset_timestamp = GetCurrentTimestamp(); - - /* Remove object if it exists, ignore it if not */ - if (msg->m_resettype == RESET_TABLE) - (void) hash_search(dbentry->tables, (void *) &(msg->m_objectid), - HASH_REMOVE, NULL); - else if (msg->m_resettype == RESET_FUNCTION) - (void) hash_search(dbentry->functions, (void *) &(msg->m_objectid), - HASH_REMOVE, NULL); -} - -/* ---------- - * pgstat_recv_autovac() - - * - * Process an autovacuum signalling message. - * ---------- - */ -static void -pgstat_recv_autovac(PgStat_MsgAutovacStart *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - - /* - * Store the last autovacuum time in the database's hashtable entry. - */ - dbentry = pgstat_get_db_entry(msg->m_databaseid, true); - - dbentry->last_autovac_time = msg->m_start_time; -} - -/* ---------- - * pgstat_recv_vacuum() - - * - * Process a VACUUM message. - * ---------- - */ -static void -pgstat_recv_vacuum(PgStat_MsgVacuum *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - PgStat_StatTabEntry *tabentry; - - /* - * Store the data in the table's hashtable entry. - */ - dbentry = pgstat_get_db_entry(msg->m_databaseid, true); - - tabentry = pgstat_get_tab_entry(dbentry, msg->m_tableoid, true); - - tabentry->n_live_tuples = msg->m_live_tuples; - tabentry->n_dead_tuples = msg->m_dead_tuples; - - if (msg->m_autovacuum) - { - tabentry->autovac_vacuum_timestamp = msg->m_vacuumtime; - tabentry->autovac_vacuum_count++; - } - else - { - tabentry->vacuum_timestamp = msg->m_vacuumtime; - tabentry->vacuum_count++; - } -} - -/* ---------- - * pgstat_recv_analyze() - - * - * Process an ANALYZE message. - * ---------- - */ -static void -pgstat_recv_analyze(PgStat_MsgAnalyze *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - PgStat_StatTabEntry *tabentry; - - /* - * Store the data in the table's hashtable entry. - */ - dbentry = pgstat_get_db_entry(msg->m_databaseid, true); - - tabentry = pgstat_get_tab_entry(dbentry, msg->m_tableoid, true); - - tabentry->n_live_tuples = msg->m_live_tuples; - tabentry->n_dead_tuples = msg->m_dead_tuples; - - /* - * If commanded, reset changes_since_analyze to zero. This forgets any - * changes that were committed while the ANALYZE was in progress, but we - * have no good way to estimate how many of those there were. - */ - if (msg->m_resetcounter) - tabentry->changes_since_analyze = 0; - - if (msg->m_autovacuum) - { - tabentry->autovac_analyze_timestamp = msg->m_analyzetime; - tabentry->autovac_analyze_count++; - } - else - { - tabentry->analyze_timestamp = msg->m_analyzetime; - tabentry->analyze_count++; - } -} - - -/* ---------- - * 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() - - * - * Process a BGWRITER message. - * ---------- - */ -static void -pgstat_recv_bgwriter(PgStat_MsgBgWriter *msg, int len) -{ - globalStats.timed_checkpoints += msg->m_timed_checkpoints; - globalStats.requested_checkpoints += msg->m_requested_checkpoints; - globalStats.checkpoint_write_time += msg->m_checkpoint_write_time; - globalStats.checkpoint_sync_time += msg->m_checkpoint_sync_time; - globalStats.buf_written_checkpoints += msg->m_buf_written_checkpoints; - globalStats.buf_written_clean += msg->m_buf_written_clean; - globalStats.maxwritten_clean += msg->m_maxwritten_clean; - globalStats.buf_written_backend += msg->m_buf_written_backend; - globalStats.buf_fsync_backend += msg->m_buf_fsync_backend; - globalStats.buf_alloc += msg->m_buf_alloc; -} - -/* ---------- - * pgstat_recv_recoveryconflict() - - * - * Process a RECOVERYCONFLICT message. - * ---------- - */ -static void -pgstat_recv_recoveryconflict(PgStat_MsgRecoveryConflict *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - - dbentry = pgstat_get_db_entry(msg->m_databaseid, true); - - switch (msg->m_reason) - { - case PROCSIG_RECOVERY_CONFLICT_DATABASE: - - /* - * Since we drop the information about the database as soon as it - * replicates, there is no point in counting these conflicts. - */ - break; - case PROCSIG_RECOVERY_CONFLICT_TABLESPACE: - dbentry->n_conflict_tablespace++; - break; - case PROCSIG_RECOVERY_CONFLICT_LOCK: - dbentry->n_conflict_lock++; - break; - case PROCSIG_RECOVERY_CONFLICT_SNAPSHOT: - dbentry->n_conflict_snapshot++; - break; - case PROCSIG_RECOVERY_CONFLICT_BUFFERPIN: - dbentry->n_conflict_bufferpin++; - break; - case PROCSIG_RECOVERY_CONFLICT_STARTUP_DEADLOCK: - dbentry->n_conflict_startup_deadlock++; - break; - } -} - -/* ---------- - * pgstat_recv_deadlock() - - * - * Process a DEADLOCK message. - * ---------- - */ -static void -pgstat_recv_deadlock(PgStat_MsgDeadlock *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - - dbentry = pgstat_get_db_entry(msg->m_databaseid, true); - - dbentry->n_deadlocks++; -} - -/* ---------- - * pgstat_recv_tempfile() - - * - * Process a TEMPFILE message. - * ---------- - */ -static void -pgstat_recv_tempfile(PgStat_MsgTempFile *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - - dbentry = pgstat_get_db_entry(msg->m_databaseid, true); - - dbentry->n_temp_bytes += msg->m_filesize; - dbentry->n_temp_files += 1; -} - -/* ---------- - * pgstat_recv_funcstat() - - * - * Count what the backend has done. - * ---------- - */ -static void -pgstat_recv_funcstat(PgStat_MsgFuncstat *msg, int len) -{ - PgStat_FunctionEntry *funcmsg = &(msg->m_entry[0]); - PgStat_StatDBEntry *dbentry; - PgStat_StatFuncEntry *funcentry; - int i; - bool found; - - dbentry = pgstat_get_db_entry(msg->m_databaseid, true); - - /* - * Process all function entries in the message. - */ - for (i = 0; i < msg->m_nentries; i++, funcmsg++) - { - funcentry = (PgStat_StatFuncEntry *) hash_search(dbentry->functions, - (void *) &(funcmsg->f_id), - HASH_ENTER, &found); - - if (!found) + tabentry->numscans += stat->t_counts.t_numscans; + tabentry->tuples_returned += stat->t_counts.t_tuples_returned; + tabentry->tuples_fetched += stat->t_counts.t_tuples_fetched; + tabentry->tuples_inserted += stat->t_counts.t_tuples_inserted; + tabentry->tuples_updated += stat->t_counts.t_tuples_updated; + tabentry->tuples_deleted += stat->t_counts.t_tuples_deleted; + tabentry->tuples_hot_updated += stat->t_counts.t_tuples_hot_updated; + /* If table was truncated, first reset the live/dead counters */ + if (stat->t_counts.t_truncated) { - /* - * If it's a new function entry, initialize counters to the values - * we just got. - */ - funcentry->f_numcalls = funcmsg->f_numcalls; - funcentry->f_total_time = funcmsg->f_total_time; - funcentry->f_self_time = funcmsg->f_self_time; - } - else - { - /* - * Otherwise add the values to the existing entry. - */ - funcentry->f_numcalls += funcmsg->f_numcalls; - funcentry->f_total_time += funcmsg->f_total_time; - funcentry->f_self_time += funcmsg->f_self_time; + tabentry->n_live_tuples = 0; + tabentry->n_dead_tuples = 0; } + tabentry->n_live_tuples += stat->t_counts.t_delta_live_tuples; + tabentry->n_dead_tuples += stat->t_counts.t_delta_dead_tuples; + tabentry->changes_since_analyze += stat->t_counts.t_changed_tuples; + tabentry->blocks_fetched += stat->t_counts.t_blocks_fetched; + tabentry->blocks_hit += stat->t_counts.t_blocks_hit; } + + /* Clamp n_live_tuples in case of negative delta_live_tuples */ + tabentry->n_live_tuples = Max(tabentry->n_live_tuples, 0); + /* Likewise for n_dead_tuples */ + tabentry->n_dead_tuples = Max(tabentry->n_dead_tuples, 0); + + dshash_release_lock(tabhash, tabentry); + + return true; } -/* ---------- - * pgstat_recv_funcpurge() - - * - * Arrange for dead function removal. - * ---------- - */ static void -pgstat_recv_funcpurge(PgStat_MsgFuncpurge *msg, int len) -{ - PgStat_StatDBEntry *dbentry; - int i; - - dbentry = pgstat_get_db_entry(msg->m_databaseid, false); - - /* - * No need to purge if we don't even know the database. - */ - if (!dbentry || !dbentry->functions) - return; - - /* - * Process all function entries in the message. - */ - for (i = 0; i < msg->m_nentries; i++) - { - /* Remove from hashtable if present; we don't care if it's not. */ - (void) hash_search(dbentry->functions, - (void *) &(msg->m_functionid[i]), - HASH_REMOVE, NULL); - } -} - -/* ---------- - * pgstat_write_statsfile_needed() - - * - * Do we need to write out any stats files? - * ---------- - */ -static bool -pgstat_write_statsfile_needed(void) -{ - if (pending_write_requests != NIL) - return true; - - /* Everything was written recently */ - return false; -} - -/* ---------- - * pgstat_db_requested() - - * - * Checks whether stats for a particular DB need to be written to a file. - * ---------- - */ -static bool -pgstat_db_requested(Oid databaseid) +pgstat_update_dbentry(PgStat_StatDBEntry *dbentry, PgStat_TableStatus *stat) { /* - * If any requests are outstanding at all, we should write the stats for - * shared catalogs (the "database" with OID 0). This ensures that - * backends will see up-to-date stats for shared catalogs, even though - * they send inquiry messages mentioning only their own DB. + * Add per-table stats to the per-database entry, too. */ - if (databaseid == InvalidOid && pending_write_requests != NIL) - return true; - - /* Search to see if there's an open request to write this database. */ - if (list_member_oid(pending_write_requests, databaseid)) - return true; - - return false; + dbentry->n_tuples_returned += stat->t_counts.t_tuples_returned; + dbentry->n_tuples_fetched += stat->t_counts.t_tuples_fetched; + dbentry->n_tuples_inserted += stat->t_counts.t_tuples_inserted; + dbentry->n_tuples_updated += stat->t_counts.t_tuples_updated; + dbentry->n_tuples_deleted += stat->t_counts.t_tuples_deleted; + dbentry->n_blocks_fetched += stat->t_counts.t_blocks_fetched; + dbentry->n_blocks_hit += stat->t_counts.t_blocks_hit; } + /* * Convert a potentially unsafely truncated activity string (see * PgBackendStatus.st_activity_raw's documentation) into a correctly truncated diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 8336f136c7..559aeedb6e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -255,7 +255,6 @@ static pid_t StartupPID = 0, WalReceiverPID = 0, AutoVacPID = 0, PgArchPID = 0, - PgStatPID = 0, SysLoggerPID = 0; /* Startup process's status */ @@ -1295,12 +1294,6 @@ PostmasterMain(int argc, char *argv[]) whereToSendOutput = DestNone; - /* - * Initialize stats collection subsystem (this does NOT start the - * collector process!) - */ - pgstat_init(); - /* * Initialize the autovacuum subsystem (again, no process start yet) */ @@ -1753,11 +1746,6 @@ ServerLoop(void) start_autovac_launcher = false; /* signal processed */ } - /* If we have lost the stats collector, try to start a new one */ - if (PgStatPID == 0 && - (pmState == PM_RUN || pmState == PM_HOT_STANDBY)) - PgStatPID = pgstat_start(); - /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) PgArchPID = StartArchiver(); @@ -2582,8 +2570,6 @@ SIGHUP_handler(SIGNAL_ARGS) signal_child(PgArchPID, SIGHUP); if (SysLoggerPID != 0) signal_child(SysLoggerPID, SIGHUP); - if (PgStatPID != 0) - signal_child(PgStatPID, SIGHUP); /* Reload authentication config files too */ if (!load_hba()) @@ -2914,8 +2900,6 @@ reaper(SIGNAL_ARGS) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) PgArchPID = StartArchiver(); - if (PgStatPID == 0) - PgStatPID = pgstat_start(); /* workers may be scheduled to start now */ maybe_start_bgworkers(); @@ -2982,13 +2966,6 @@ reaper(SIGNAL_ARGS) SignalChildren(SIGUSR2); pmState = PM_SHUTDOWN_2; - - /* - * We can also shut down the stats collector now; there's - * nothing left for it to do. - */ - if (PgStatPID != 0) - signal_child(PgStatPID, SIGQUIT); } else { @@ -3063,22 +3040,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the statistics collector? If so, just try to start a new - * one; no need to force reset of the rest of the system. (If fail, - * we'll try again in future cycles of the main loop.) - */ - if (pid == PgStatPID) - { - PgStatPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("statistics collector process"), - pid, exitstatus); - if (pmState == PM_RUN || pmState == PM_HOT_STANDBY) - PgStatPID = pgstat_start(); - continue; - } - /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3537,22 +3498,6 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(PgArchPID, SIGQUIT); } - /* - * Force a power-cycle of the pgstat process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgStatPID != 0 && take_action) - { - ereport(DEBUG2, - (errmsg_internal("sending %s to process %d", - "SIGQUIT", - (int) PgStatPID))); - signal_child(PgStatPID, SIGQUIT); - allow_immediate_pgstat_restart(); - } - /* We do NOT restart the syslogger */ if (Shutdown != ImmediateShutdown) @@ -3756,8 +3701,6 @@ PostmasterStateMachine(void) SignalChildren(SIGQUIT); if (PgArchPID != 0) signal_child(PgArchPID, SIGQUIT); - if (PgStatPID != 0) - signal_child(PgStatPID, SIGQUIT); } } } @@ -3796,8 +3739,7 @@ PostmasterStateMachine(void) * normal state transition leading up to PM_WAIT_DEAD_END, or during * FatalError processing. */ - if (dlist_is_empty(&BackendList) && - PgArchPID == 0 && PgStatPID == 0) + if (dlist_is_empty(&BackendList) && PgArchPID == 0) { /* These other guys should be dead already */ Assert(StartupPID == 0); @@ -3998,8 +3940,6 @@ TerminateChildren(int signal) signal_child(AutoVacPID, signal); if (PgArchPID != 0) signal_child(PgArchPID, signal); - if (PgStatPID != 0) - signal_child(PgStatPID, signal); } /* @@ -4972,18 +4912,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } - if (strcmp(argv[1], "--forkcol") == 0) - { - /* Do not want to attach to shared memory */ - - PgstatCollectorMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forklog") == 0) { /* Do not want to attach to shared memory */ @@ -5096,12 +5024,6 @@ sigusr1_handler(SIGNAL_ARGS) if (CheckPostmasterSignal(PMSIGNAL_BEGIN_HOT_STANDBY) && pmState == PM_RECOVERY && Shutdown == NoShutdown) { - /* - * Likewise, start other special children as needed. - */ - Assert(PgStatPID == 0); - PgStatPID = pgstat_start(); - ereport(LOG, (errmsg("database system is ready to accept read only connections"))); diff --git a/src/backend/replication/logical/tablesync.c b/src/backend/replication/logical/tablesync.c index 6e420d893c..862582da23 100644 --- a/src/backend/replication/logical/tablesync.c +++ b/src/backend/replication/logical/tablesync.c @@ -127,7 +127,7 @@ finish_sync_worker(void) if (IsTransactionState()) { CommitTransactionCommand(); - pgstat_report_stat(false); + pgstat_update_stat(true); } /* And flush all writes. */ @@ -143,6 +143,9 @@ finish_sync_worker(void) /* Find the main apply worker and signal it. */ logicalrep_worker_wakeup(MyLogicalRepWorker->subid, InvalidOid); + /* clean up retained statistics */ + pgstat_update_stat(true); + /* Stop gracefully */ proc_exit(0); } @@ -533,7 +536,7 @@ process_syncing_tables_for_apply(XLogRecPtr current_lsn) if (started_tx) { CommitTransactionCommand(); - pgstat_report_stat(false); + pgstat_update_stat(false); } } @@ -876,7 +879,7 @@ LogicalRepSyncTableStart(XLogRecPtr *origin_startpos) MyLogicalRepWorker->relstate, MyLogicalRepWorker->relstate_lsn); CommitTransactionCommand(); - pgstat_report_stat(false); + pgstat_update_stat(false); /* * We want to do the table data sync in a single transaction. diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index 277da69fa6..087850d089 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -491,7 +491,7 @@ apply_handle_commit(StringInfo s) replorigin_session_origin_timestamp = commit_data.committime; CommitTransactionCommand(); - pgstat_report_stat(false); + pgstat_update_stat(false); store_flush_position(commit_data.end_lsn); } @@ -1324,6 +1324,8 @@ LogicalRepApplyLoop(XLogRecPtr last_received) } send_feedback(last_received, requestReply, requestReply); + + pgstat_update_stat(false); } } } diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c index 01eabe5706..e794a81c4c 100644 --- a/src/backend/storage/buffer/bufmgr.c +++ b/src/backend/storage/buffer/bufmgr.c @@ -1984,7 +1984,7 @@ BufferSync(int flags) if (SyncOneBuffer(buf_id, false, &wb_context) & BUF_WRITTEN) { TRACE_POSTGRESQL_BUFFER_SYNC_WRITTEN(buf_id); - BgWriterStats.m_buf_written_checkpoints++; + BgWriterStats.buf_written_checkpoints++; num_written++; } } @@ -2092,7 +2092,7 @@ BgBufferSync(WritebackContext *wb_context) strategy_buf_id = StrategySyncStart(&strategy_passes, &recent_alloc); /* Report buffer alloc counts to pgstat */ - BgWriterStats.m_buf_alloc += recent_alloc; + BgWriterStats.buf_alloc += recent_alloc; /* * If we're not running the LRU scan, just stop after doing the stats @@ -2282,7 +2282,7 @@ BgBufferSync(WritebackContext *wb_context) reusable_buffers++; if (++num_written >= bgwriter_lru_maxpages) { - BgWriterStats.m_maxwritten_clean++; + BgWriterStats.maxwritten_clean++; break; } } @@ -2290,7 +2290,7 @@ BgBufferSync(WritebackContext *wb_context) reusable_buffers++; } - BgWriterStats.m_buf_written_clean += num_written; + BgWriterStats.buf_written_clean += num_written; #ifdef BGW_DEBUG elog(DEBUG1, "bgwriter: recent_alloc=%u smoothed=%.2f delta=%ld ahead=%d density=%.2f reusable_est=%d upcoming_est=%d scanned=%d wrote=%d reusable=%d", diff --git a/src/backend/storage/ipc/dsm.c b/src/backend/storage/ipc/dsm.c index edee89c116..18e73b0288 100644 --- a/src/backend/storage/ipc/dsm.c +++ b/src/backend/storage/ipc/dsm.c @@ -197,6 +197,15 @@ dsm_postmaster_startup(PGShmemHeader *shim) dsm_control->maxitems = maxitems; } +/* + * clear dsm_init state on child start. + */ +void +dsm_child_init(void) +{ + dsm_init_done = false; +} + /* * Determine whether the control segment from the previous postmaster * invocation still exists. If so, remove the dynamic shared memory @@ -423,6 +432,15 @@ dsm_set_control_handle(dsm_handle h) } #endif +/* + * Return if dsm feature is available on this process. + */ +bool +dsm_is_available(void) +{ + return dsm_control != NULL; +} + /* * Create a new dynamic shared memory segment. * @@ -440,8 +458,7 @@ dsm_create(Size size, int flags) uint32 i; uint32 nitems; - /* Unsafe in postmaster (and pointless in a stand-alone backend). */ - Assert(IsUnderPostmaster); + Assert(dsm_is_available()); if (!dsm_init_done) dsm_backend_startup(); @@ -537,8 +554,7 @@ dsm_attach(dsm_handle h) uint32 i; uint32 nitems; - /* Unsafe in postmaster (and pointless in a stand-alone backend). */ - Assert(IsUnderPostmaster); + Assert(dsm_is_available()); if (!dsm_init_done) dsm_backend_startup(); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 0c86a581c0..cce6d3ffa2 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -150,6 +150,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port) size = add_size(size, SyncScanShmemSize()); size = add_size(size, AsyncShmemSize()); size = add_size(size, BackendRandomShmemSize()); + size = add_size(size, StatsShmemSize()); #ifdef EXEC_BACKEND size = add_size(size, ShmemBackendArraySize()); #endif @@ -282,8 +283,13 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port) /* Initialize dynamic shared memory facilities. */ if (!IsUnderPostmaster) + { dsm_postmaster_startup(shim); + /* Stats collector uses dynamic shared memory */ + StatsShmemInit(); + } + /* * Now give loadable modules a chance to set up their shmem allocations */ diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index a6fda81feb..c46bb8d057 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -521,6 +521,9 @@ RegisterLWLockTranches(void) LWLockRegisterTranche(LWTRANCHE_TBM, "tbm"); LWLockRegisterTranche(LWTRANCHE_PARALLEL_APPEND, "parallel_append"); LWLockRegisterTranche(LWTRANCHE_PARALLEL_HASH_JOIN, "parallel_hash_join"); + LWLockRegisterTranche(LWTRANCHE_STATS_DSA, "stats table dsa"); + LWLockRegisterTranche(LWTRANCHE_STATS_DB, "db stats"); + LWLockRegisterTranche(LWTRANCHE_STATS_FUNC_TABLE, "table/func stats"); /* Register named tranches. */ for (i = 0; i < NamedLWLockTrancheRequests; i++) diff --git a/src/backend/storage/lmgr/lwlocknames.txt b/src/backend/storage/lmgr/lwlocknames.txt index e6025ecedb..798af9f168 100644 --- a/src/backend/storage/lmgr/lwlocknames.txt +++ b/src/backend/storage/lmgr/lwlocknames.txt @@ -50,3 +50,4 @@ OldSnapshotTimeMapLock 42 BackendRandomLock 43 LogicalRepWorkerLock 44 CLogTruncationLock 45 +StatsLock 46 diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c index a3b9757565..ee4e43331b 100644 --- a/src/backend/tcop/postgres.c +++ b/src/backend/tcop/postgres.c @@ -3146,6 +3146,12 @@ ProcessInterrupts(void) if (ParallelMessagePending) HandleParallelMessages(); + + if (IdleStatsUpdateTimeoutPending) + { + IdleStatsUpdateTimeoutPending = false; + pgstat_update_stat(true); + } } @@ -3720,6 +3726,7 @@ 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_stats_update_timeout = false; /* Initialize startup process environment if necessary. */ if (!IsUnderPostmaster) @@ -4160,9 +4167,17 @@ PostgresMain(int argc, char *argv[], } else { - ProcessCompletedNotifies(); - pgstat_report_stat(false); + long stats_timeout; + ProcessCompletedNotifies(); + + stats_timeout = pgstat_update_stat(false); + if (stats_timeout > 0) + { + disable_idle_stats_update_timeout = true; + enable_timeout_after(IDLE_STATS_UPDATE_TIMEOUT, + stats_timeout); + } set_ps_display("idle", false); pgstat_report_activity(STATE_IDLE, NULL); } @@ -4197,7 +4212,7 @@ PostgresMain(int argc, char *argv[], DoingCommandRead = false; /* - * (5) turn off the idle-in-transaction timeout + * (5) turn off the idle-in-transaction timeout and stats update timeout */ if (disable_idle_in_transaction_timeout) { @@ -4205,6 +4220,12 @@ PostgresMain(int argc, char *argv[], disable_idle_in_transaction_timeout = false; } + if (disable_idle_stats_update_timeout) + { + disable_timeout(IDLE_STATS_UPDATE_TIMEOUT, false); + disable_idle_stats_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 e95e347184..eca801eeed 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -33,7 +33,7 @@ #define UINT32_ACCESS_ONCE(var) ((uint32)(*((volatile uint32 *)&(var)))) /* Global bgwriter statistics, from bgwriter.c */ -extern PgStat_MsgBgWriter bgwriterStats; +extern PgStat_BgWriter bgwriterStats; Datum pg_stat_get_numscans(PG_FUNCTION_ARGS) @@ -1176,7 +1176,7 @@ pg_stat_get_db_xact_commit(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_xact_commit); @@ -1192,7 +1192,7 @@ pg_stat_get_db_xact_rollback(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_xact_rollback); @@ -1208,7 +1208,7 @@ pg_stat_get_db_blocks_fetched(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_blocks_fetched); @@ -1224,7 +1224,7 @@ pg_stat_get_db_blocks_hit(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_blocks_hit); @@ -1240,7 +1240,7 @@ pg_stat_get_db_tuples_returned(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_tuples_returned); @@ -1256,7 +1256,7 @@ pg_stat_get_db_tuples_fetched(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_tuples_fetched); @@ -1272,7 +1272,7 @@ pg_stat_get_db_tuples_inserted(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_tuples_inserted); @@ -1288,7 +1288,7 @@ pg_stat_get_db_tuples_updated(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_tuples_updated); @@ -1304,7 +1304,7 @@ pg_stat_get_db_tuples_deleted(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_tuples_deleted); @@ -1319,7 +1319,7 @@ pg_stat_get_db_stat_reset_time(PG_FUNCTION_ARGS) TimestampTz result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = dbentry->stat_reset_timestamp; @@ -1337,7 +1337,7 @@ pg_stat_get_db_temp_files(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = dbentry->n_temp_files; @@ -1353,7 +1353,7 @@ pg_stat_get_db_temp_bytes(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = dbentry->n_temp_bytes; @@ -1368,7 +1368,7 @@ pg_stat_get_db_conflict_tablespace(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_conflict_tablespace); @@ -1383,7 +1383,7 @@ pg_stat_get_db_conflict_lock(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_conflict_lock); @@ -1398,7 +1398,7 @@ pg_stat_get_db_conflict_snapshot(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_conflict_snapshot); @@ -1413,7 +1413,7 @@ pg_stat_get_db_conflict_bufferpin(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_conflict_bufferpin); @@ -1428,7 +1428,7 @@ pg_stat_get_db_conflict_startup_deadlock(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_conflict_startup_deadlock); @@ -1443,7 +1443,7 @@ pg_stat_get_db_conflict_all(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) ( @@ -1463,7 +1463,7 @@ pg_stat_get_db_deadlocks(PG_FUNCTION_ARGS) int64 result; PgStat_StatDBEntry *dbentry; - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = (int64) (dbentry->n_deadlocks); @@ -1479,7 +1479,7 @@ pg_stat_get_db_blk_read_time(PG_FUNCTION_ARGS) PgStat_StatDBEntry *dbentry; /* convert counter from microsec to millisec for display */ - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = ((double) dbentry->n_block_read_time) / 1000.0; @@ -1495,7 +1495,7 @@ pg_stat_get_db_blk_write_time(PG_FUNCTION_ARGS) PgStat_StatDBEntry *dbentry; /* convert counter from microsec to millisec for display */ - if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL) + if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL) result = 0; else result = ((double) dbentry->n_block_write_time) / 1000.0; @@ -1850,6 +1850,9 @@ pg_stat_get_archiver(PG_FUNCTION_ARGS) /* Get statistics about the archiver process */ archiver_stats = pgstat_fetch_stat_archiver(); + if (archiver_stats == NULL) + PG_RETURN_NULL(); + /* Fill values and NULLs */ values[0] = Int64GetDatum(archiver_stats->archived_count); if (*(archiver_stats->last_archived_wal) == '\0') @@ -1879,6 +1882,5 @@ pg_stat_get_archiver(PG_FUNCTION_ARGS) values[6] = TimestampTzGetDatum(archiver_stats->stat_reset_timestamp); /* Returns the record as Datum */ - PG_RETURN_DATUM(HeapTupleGetDatum( - heap_form_tuple(tupdesc, values, nulls))); + PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls))); } diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c index c6939779b9..1377bbbbdb 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 IdleStatsUpdateTimeoutPending = 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 4f1d2a0d28..1e4fa89135 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 IdleStatsUpdateTimeoutHandler(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_STATS_UPDATE_TIMEOUT, + IdleStatsUpdateTimeoutHandler); } /* @@ -1239,6 +1242,14 @@ IdleInTransactionSessionTimeoutHandler(void) SetLatch(MyLatch); } +static void +IdleStatsUpdateTimeoutHandler(void) +{ + IdleStatsUpdateTimeoutPending = 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 0327b295da..cfdffbca2b 100644 --- a/src/backend/utils/misc/guc.c +++ b/src/backend/utils/misc/guc.c @@ -188,7 +188,6 @@ static bool check_autovacuum_max_workers(int *newval, void **extra, GucSource so static bool check_autovacuum_work_mem(int *newval, void **extra, GucSource source); static bool check_effective_io_concurrency(int *newval, void **extra, GucSource source); static void assign_effective_io_concurrency(int newval, void *extra); -static void assign_pgstat_temp_directory(const char *newval, void *extra); static bool check_application_name(char **newval, void **extra, GucSource source); static void assign_application_name(const char *newval, void *extra); static bool check_cluster_name(char **newval, void **extra, GucSource source); @@ -3766,17 +3765,6 @@ static struct config_string ConfigureNamesString[] = NULL, NULL, NULL }, - { - {"stats_temp_directory", PGC_SIGHUP, STATS_COLLECTOR, - gettext_noop("Writes temporary statistics files to the specified directory."), - NULL, - GUC_SUPERUSER_ONLY - }, - &pgstat_temp_directory, - PG_STAT_TMP_DIR, - check_canonical_path, assign_pgstat_temp_directory, NULL - }, - { {"synchronous_standby_names", PGC_SIGHUP, REPLICATION_MASTER, gettext_noop("Number of synchronous standbys and list of names of potential synchronous ones."), @@ -10725,35 +10713,6 @@ assign_effective_io_concurrency(int newval, void *extra) #endif /* USE_PREFETCH */ } -static void -assign_pgstat_temp_directory(const char *newval, void *extra) -{ - /* check_canonical_path already canonicalized newval for us */ - char *dname; - char *tname; - char *fname; - - /* directory */ - dname = guc_malloc(ERROR, strlen(newval) + 1); /* runtime dir */ - sprintf(dname, "%s", newval); - - /* global stats */ - tname = guc_malloc(ERROR, strlen(newval) + 12); /* /global.tmp */ - sprintf(tname, "%s/global.tmp", newval); - fname = guc_malloc(ERROR, strlen(newval) + 13); /* /global.stat */ - sprintf(fname, "%s/global.stat", newval); - - if (pgstat_stat_directory) - free(pgstat_stat_directory); - pgstat_stat_directory = dname; - if (pgstat_stat_tmpname) - free(pgstat_stat_tmpname); - pgstat_stat_tmpname = tname; - if (pgstat_stat_filename) - free(pgstat_stat_filename); - pgstat_stat_filename = fname; -} - static bool check_application_name(char **newval, void **extra, GucSource source) { diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 3fe257c53f..58cb38e00d 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -501,7 +501,6 @@ #track_io_timing = off #track_functions = none # none, pl, all #track_activity_query_size = 1024 # (change requires restart) -#stats_temp_directory = 'pg_stat_tmp' # - Monitoring - diff --git a/src/bin/pg_basebackup/t/010_pg_basebackup.pl b/src/bin/pg_basebackup/t/010_pg_basebackup.pl index 2211d90c6f..e6f4d30658 100644 --- a/src/bin/pg_basebackup/t/010_pg_basebackup.pl +++ b/src/bin/pg_basebackup/t/010_pg_basebackup.pl @@ -123,7 +123,7 @@ is_deeply( # Contents of these directories should not be copied. foreach my $dirname ( - qw(pg_dynshmem pg_notify pg_replslot pg_serial pg_snapshots pg_stat_tmp pg_subtrans) + qw(pg_dynshmem pg_notify pg_replslot pg_serial pg_snapshots pg_subtrans) ) { is_deeply( diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 3026f95728..91c3fb1a0a 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 IdleStatsUpdateTimeoutPending; extern PGDLLIMPORT volatile sig_atomic_t ConfigReloadPending; extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost; @@ -403,7 +404,6 @@ typedef enum CheckpointerProcess, WalWriterProcess, WalReceiverProcess, - NUM_AUXPROCTYPES /* Must be last! */ } AuxProcType; diff --git a/src/include/pgstat.h b/src/include/pgstat.h index 33c7372f00..8ed01499e5 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -13,6 +13,7 @@ #include "datatype/timestamp.h" #include "fmgr.h" +#include "lib/dshash.h" #include "libpq/pqcomm.h" #include "port/atomics.h" #include "portability/instr_time.h" @@ -41,32 +42,6 @@ typedef enum TrackFunctionsLevel TRACK_FUNC_ALL } TrackFunctionsLevel; -/* ---------- - * The types of backend -> collector messages - * ---------- - */ -typedef enum StatMsgType -{ - PGSTAT_MTYPE_DUMMY, - PGSTAT_MTYPE_INQUIRY, - PGSTAT_MTYPE_TABSTAT, - PGSTAT_MTYPE_TABPURGE, - PGSTAT_MTYPE_DROPDB, - PGSTAT_MTYPE_RESETCOUNTER, - PGSTAT_MTYPE_RESETSHAREDCOUNTER, - PGSTAT_MTYPE_RESETSINGLECOUNTER, - PGSTAT_MTYPE_AUTOVAC_START, - PGSTAT_MTYPE_VACUUM, - PGSTAT_MTYPE_ANALYZE, - PGSTAT_MTYPE_ARCHIVER, - PGSTAT_MTYPE_BGWRITER, - PGSTAT_MTYPE_FUNCSTAT, - PGSTAT_MTYPE_FUNCPURGE, - PGSTAT_MTYPE_RECOVERYCONFLICT, - PGSTAT_MTYPE_TEMPFILE, - PGSTAT_MTYPE_DEADLOCK -} StatMsgType; - /* ---------- * The data type used for counters. * ---------- @@ -115,13 +90,6 @@ typedef struct PgStat_TableCounts PgStat_Counter t_blocks_hit; } PgStat_TableCounts; -/* Possible targets for resetting cluster-wide shared values */ -typedef enum PgStat_Shared_Reset_Target -{ - RESET_ARCHIVER, - RESET_BGWRITER -} PgStat_Shared_Reset_Target; - /* Possible object types for resetting single counters */ typedef enum PgStat_Single_Reset_Type { @@ -180,271 +148,23 @@ typedef struct PgStat_TableXactStatus } PgStat_TableXactStatus; -/* ------------------------------------------------------------ - * Message formats follow - * ------------------------------------------------------------ - */ - - /* ---------- - * PgStat_MsgHdr The common message header + * PgStat_BgWriter bgwriter statistics * ---------- */ -typedef struct PgStat_MsgHdr +typedef struct PgStat_BgWriter { - StatMsgType m_type; - int m_size; -} PgStat_MsgHdr; - -/* ---------- - * Space available in a message. This will keep the UDP packets below 1K, - * which should fit unfragmented into the MTU of the loopback interface. - * (Larger values of PGSTAT_MAX_MSG_SIZE would work for that on most - * platforms, but we're being conservative here.) - * ---------- - */ -#define PGSTAT_MAX_MSG_SIZE 1000 -#define PGSTAT_MSG_PAYLOAD (PGSTAT_MAX_MSG_SIZE - sizeof(PgStat_MsgHdr)) - - -/* ---------- - * PgStat_MsgDummy A dummy message, ignored by the collector - * ---------- - */ -typedef struct PgStat_MsgDummy -{ - PgStat_MsgHdr m_hdr; -} PgStat_MsgDummy; - - -/* ---------- - * PgStat_MsgInquiry Sent by a backend to ask the collector - * to write the stats file(s). - * - * Ordinarily, an inquiry message prompts writing of the global stats file, - * the stats file for shared catalogs, and the stats file for the specified - * database. If databaseid is InvalidOid, only the first two are written. - * - * New file(s) will be written only if the existing file has a timestamp - * older than the specified cutoff_time; this prevents duplicated effort - * when multiple requests arrive at nearly the same time, assuming that - * backends send requests with cutoff_times a little bit in the past. - * - * clock_time should be the requestor's current local time; the collector - * uses this to check for the system clock going backward, but it has no - * effect unless that occurs. We assume clock_time >= cutoff_time, though. - * ---------- - */ - -typedef struct PgStat_MsgInquiry -{ - PgStat_MsgHdr m_hdr; - TimestampTz clock_time; /* observed local clock time */ - TimestampTz cutoff_time; /* minimum acceptable file timestamp */ - Oid databaseid; /* requested DB (InvalidOid => shared only) */ -} PgStat_MsgInquiry; - - -/* ---------- - * PgStat_TableEntry Per-table info in a MsgTabstat - * ---------- - */ -typedef struct PgStat_TableEntry -{ - Oid t_id; - PgStat_TableCounts t_counts; -} PgStat_TableEntry; - -/* ---------- - * PgStat_MsgTabstat Sent by the backend to report table - * and buffer access statistics. - * ---------- - */ -#define PGSTAT_NUM_TABENTRIES \ - ((PGSTAT_MSG_PAYLOAD - sizeof(Oid) - 3 * sizeof(int) - 2 * sizeof(PgStat_Counter)) \ - / sizeof(PgStat_TableEntry)) - -typedef struct PgStat_MsgTabstat -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; - int m_nentries; - int m_xact_commit; - int m_xact_rollback; - PgStat_Counter m_block_read_time; /* times in microseconds */ - PgStat_Counter m_block_write_time; - PgStat_TableEntry m_entry[PGSTAT_NUM_TABENTRIES]; -} PgStat_MsgTabstat; - - -/* ---------- - * PgStat_MsgTabpurge Sent by the backend to tell the collector - * about dead tables. - * ---------- - */ -#define PGSTAT_NUM_TABPURGE \ - ((PGSTAT_MSG_PAYLOAD - sizeof(Oid) - sizeof(int)) \ - / sizeof(Oid)) - -typedef struct PgStat_MsgTabpurge -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; - int m_nentries; - Oid m_tableid[PGSTAT_NUM_TABPURGE]; -} PgStat_MsgTabpurge; - - -/* ---------- - * PgStat_MsgDropdb Sent by the backend to tell the collector - * about a dropped database - * ---------- - */ -typedef struct PgStat_MsgDropdb -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; -} PgStat_MsgDropdb; - - -/* ---------- - * PgStat_MsgResetcounter Sent by the backend to tell the collector - * to reset counters - * ---------- - */ -typedef struct PgStat_MsgResetcounter -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; -} PgStat_MsgResetcounter; - -/* ---------- - * PgStat_MsgResetsharedcounter Sent by the backend to tell the collector - * to reset a shared counter - * ---------- - */ -typedef struct PgStat_MsgResetsharedcounter -{ - PgStat_MsgHdr m_hdr; - PgStat_Shared_Reset_Target m_resettarget; -} PgStat_MsgResetsharedcounter; - -/* ---------- - * PgStat_MsgResetsinglecounter Sent by the backend to tell the collector - * to reset a single counter - * ---------- - */ -typedef struct PgStat_MsgResetsinglecounter -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; - PgStat_Single_Reset_Type m_resettype; - Oid m_objectid; -} PgStat_MsgResetsinglecounter; - -/* ---------- - * PgStat_MsgAutovacStart Sent by the autovacuum daemon to signal - * that a database is going to be processed - * ---------- - */ -typedef struct PgStat_MsgAutovacStart -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; - TimestampTz m_start_time; -} PgStat_MsgAutovacStart; - - -/* ---------- - * PgStat_MsgVacuum Sent by the backend or autovacuum daemon - * after VACUUM - * ---------- - */ -typedef struct PgStat_MsgVacuum -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; - Oid m_tableoid; - bool m_autovacuum; - TimestampTz m_vacuumtime; - PgStat_Counter m_live_tuples; - PgStat_Counter m_dead_tuples; -} PgStat_MsgVacuum; - - -/* ---------- - * PgStat_MsgAnalyze Sent by the backend or autovacuum daemon - * after ANALYZE - * ---------- - */ -typedef struct PgStat_MsgAnalyze -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; - Oid m_tableoid; - bool m_autovacuum; - bool m_resetcounter; - TimestampTz m_analyzetime; - PgStat_Counter m_live_tuples; - PgStat_Counter m_dead_tuples; -} 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. - * ---------- - */ -typedef struct PgStat_MsgBgWriter -{ - PgStat_MsgHdr m_hdr; - - PgStat_Counter m_timed_checkpoints; - PgStat_Counter m_requested_checkpoints; - PgStat_Counter m_buf_written_checkpoints; - PgStat_Counter m_buf_written_clean; - PgStat_Counter m_maxwritten_clean; - PgStat_Counter m_buf_written_backend; - PgStat_Counter m_buf_fsync_backend; - PgStat_Counter m_buf_alloc; - PgStat_Counter m_checkpoint_write_time; /* times in milliseconds */ - PgStat_Counter m_checkpoint_sync_time; -} PgStat_MsgBgWriter; - -/* ---------- - * PgStat_MsgRecoveryConflict Sent by the backend upon recovery conflict - * ---------- - */ -typedef struct PgStat_MsgRecoveryConflict -{ - PgStat_MsgHdr m_hdr; - - Oid m_databaseid; - int m_reason; -} PgStat_MsgRecoveryConflict; - -/* ---------- - * PgStat_MsgTempFile Sent by the backend upon creating a temp file - * ---------- - */ -typedef struct PgStat_MsgTempFile -{ - PgStat_MsgHdr m_hdr; - - Oid m_databaseid; - size_t m_filesize; -} PgStat_MsgTempFile; + PgStat_Counter timed_checkpoints; + PgStat_Counter requested_checkpoints; + PgStat_Counter buf_written_checkpoints; + PgStat_Counter buf_written_clean; + PgStat_Counter maxwritten_clean; + PgStat_Counter buf_written_backend; + PgStat_Counter buf_fsync_backend; + PgStat_Counter buf_alloc; + PgStat_Counter checkpoint_write_time; /* times in milliseconds */ + PgStat_Counter checkpoint_sync_time; +} PgStat_BgWriter; /* ---------- * PgStat_FunctionCounts The actual per-function counts kept by a backend @@ -485,79 +205,6 @@ typedef struct PgStat_FunctionEntry PgStat_Counter f_self_time; } PgStat_FunctionEntry; -/* ---------- - * PgStat_MsgFuncstat Sent by the backend to report function - * usage statistics. - * ---------- - */ -#define PGSTAT_NUM_FUNCENTRIES \ - ((PGSTAT_MSG_PAYLOAD - sizeof(Oid) - sizeof(int)) \ - / sizeof(PgStat_FunctionEntry)) - -typedef struct PgStat_MsgFuncstat -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; - int m_nentries; - PgStat_FunctionEntry m_entry[PGSTAT_NUM_FUNCENTRIES]; -} PgStat_MsgFuncstat; - -/* ---------- - * PgStat_MsgFuncpurge Sent by the backend to tell the collector - * about dead functions. - * ---------- - */ -#define PGSTAT_NUM_FUNCPURGE \ - ((PGSTAT_MSG_PAYLOAD - sizeof(Oid) - sizeof(int)) \ - / sizeof(Oid)) - -typedef struct PgStat_MsgFuncpurge -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; - int m_nentries; - Oid m_functionid[PGSTAT_NUM_FUNCPURGE]; -} PgStat_MsgFuncpurge; - -/* ---------- - * PgStat_MsgDeadlock Sent by the backend to tell the collector - * about a deadlock that occurred. - * ---------- - */ -typedef struct PgStat_MsgDeadlock -{ - PgStat_MsgHdr m_hdr; - Oid m_databaseid; -} PgStat_MsgDeadlock; - - -/* ---------- - * PgStat_Msg Union over all possible messages. - * ---------- - */ -typedef union PgStat_Msg -{ - PgStat_MsgHdr msg_hdr; - PgStat_MsgDummy msg_dummy; - PgStat_MsgInquiry msg_inquiry; - PgStat_MsgTabstat msg_tabstat; - PgStat_MsgTabpurge msg_tabpurge; - PgStat_MsgDropdb msg_dropdb; - PgStat_MsgResetcounter msg_resetcounter; - PgStat_MsgResetsharedcounter msg_resetsharedcounter; - PgStat_MsgResetsinglecounter msg_resetsinglecounter; - 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; - PgStat_MsgRecoveryConflict msg_recoveryconflict; - PgStat_MsgDeadlock msg_deadlock; -} PgStat_Msg; - - /* ------------------------------------------------------------ * Statistic collector data structures follow * @@ -601,10 +248,13 @@ typedef struct PgStat_StatDBEntry /* * tables and functions must be last in the struct, because we don't write - * the pointers out to the stats file. + * the handles and pointers out to the stats file. */ - HTAB *tables; - HTAB *functions; + dshash_table_handle tables; + dshash_table_handle functions; + /* for snapshot tables */ + HTAB *snapshot_tables; + HTAB *snapshot_functions; } PgStat_StatDBEntry; @@ -1136,13 +786,11 @@ extern bool pgstat_track_counts; extern int pgstat_track_functions; extern PGDLLIMPORT int pgstat_track_activity_query_size; extern char *pgstat_stat_directory; -extern char *pgstat_stat_tmpname; -extern char *pgstat_stat_filename; /* * BgWriter statistics counters are updated directly by bgwriter and bufmgr */ -extern PgStat_MsgBgWriter BgWriterStats; +extern PgStat_BgWriter BgWriterStats; /* * Updated by pgstat_count_buffer_*_time macros @@ -1154,34 +802,20 @@ extern PgStat_Counter pgStatBlockWriteTime; * Functions called from postmaster * ---------- */ -extern Size BackendStatusShmemSize(void); -extern void CreateSharedBackendStatus(void); - -extern void pgstat_init(void); -extern int pgstat_start(void); extern void pgstat_reset_all(void); -extern void allow_immediate_pgstat_restart(void); - -#ifdef EXEC_BACKEND -extern void PgstatCollectorMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif - /* ---------- * Functions called from backends * ---------- */ -extern void pgstat_ping(void); - -extern void pgstat_report_stat(bool force); +extern long pgstat_update_stat(bool force); extern void pgstat_vacuum_stat(void); extern void pgstat_drop_database(Oid databaseid); -extern void pgstat_clear_snapshot(void); extern void pgstat_reset_counters(void); -extern void pgstat_reset_shared_counters(const char *); -extern void pgstat_reset_single_counter(Oid objectid, PgStat_Single_Reset_Type type); - +extern void pgstat_reset_shared_counters(const char *target); +extern void pgstat_reset_single_counter(Oid objectid, + PgStat_Single_Reset_Type type); extern void pgstat_report_autovac(Oid dboid); extern void pgstat_report_vacuum(Oid tableoid, bool shared, PgStat_Counter livetuples, PgStat_Counter deadtuples); @@ -1192,6 +826,8 @@ extern void pgstat_report_analyze(Relation rel, extern void pgstat_report_recovery_conflict(int reason); extern void pgstat_report_deadlock(void); +extern void pgstat_clear_snapshot(void); + extern void pgstat_initialize(void); extern void pgstat_bestart(void); @@ -1219,6 +855,9 @@ 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 PgStat_StatDBEntry *backend_get_db_entry(Oid dbid, bool oneshot); +extern HTAB *backend_snapshot_all_db_entries(void); +extern PgStat_StatTabEntry *backend_get_tab_entry(PgStat_StatDBEntry *dbent, Oid relid, bool oneshot); /* ---------- * pgstat_report_wait_start() - @@ -1338,15 +977,15 @@ 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); +extern void pgstat_update_archiver(const char *xlog, bool failed); +extern void pgstat_update_bgwriter(void); /* ---------- * Support functions for the SQL-callable functions to * generate the pgstat* views. * ---------- */ -extern PgStat_StatDBEntry *pgstat_fetch_stat_dbentry(Oid dbid); +extern PgStat_StatDBEntry *pgstat_fetch_stat_dbentry(Oid relid, bool oneshot); extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid); extern PgBackendStatus *pgstat_fetch_stat_beentry(int beid); extern LocalPgBackendStatus *pgstat_fetch_stat_local_beentry(int beid); @@ -1355,4 +994,14 @@ extern int pgstat_fetch_stat_numbackends(void); extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void); extern PgStat_GlobalStats *pgstat_fetch_global(void); +/* File input/output functions */ +extern void pgstat_read_statsfiles(void); +extern void pgstat_write_statsfiles(void); + +/* For shared memory allocation/initialize */ +extern Size BackendStatusShmemSize(void); +extern void CreateSharedBackendStatus(void); +extern Size StatsShmemSize(void); +extern void StatsShmemInit(void); + #endif /* PGSTAT_H */ diff --git a/src/include/storage/dsm.h b/src/include/storage/dsm.h index b4654cb5ca..379f0bc5c0 100644 --- a/src/include/storage/dsm.h +++ b/src/include/storage/dsm.h @@ -26,6 +26,7 @@ typedef struct dsm_segment dsm_segment; struct PGShmemHeader; /* avoid including pg_shmem.h */ extern void dsm_cleanup_using_control_segment(dsm_handle old_control_handle); extern void dsm_postmaster_startup(struct PGShmemHeader *); +extern void dsm_child_init(void); extern void dsm_backend_shutdown(void); extern void dsm_detach_all(void); @@ -33,6 +34,8 @@ extern void dsm_detach_all(void); extern void dsm_set_control_handle(dsm_handle h); #endif +extern bool dsm_is_available(void); + /* Functions that create or remove mappings. */ extern dsm_segment *dsm_create(Size size, int flags); extern dsm_segment *dsm_attach(dsm_handle h); diff --git a/src/include/storage/lwlock.h b/src/include/storage/lwlock.h index b2dcb73287..4cb628b15f 100644 --- a/src/include/storage/lwlock.h +++ b/src/include/storage/lwlock.h @@ -219,6 +219,9 @@ typedef enum BuiltinTrancheIds LWTRANCHE_SHARED_TUPLESTORE, LWTRANCHE_TBM, LWTRANCHE_PARALLEL_APPEND, + LWTRANCHE_STATS_DSA, + LWTRANCHE_STATS_DB, + LWTRANCHE_STATS_FUNC_TABLE, LWTRANCHE_FIRST_USER_DEFINED } BuiltinTrancheIds; diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h index dcc7307c16..b8a56645b6 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_STATS_UPDATE_TIMEOUT, /* First user-definable timeout reason */ USER_TIMEOUT, /* Maximum number of timeout reasons */ diff --git a/src/test/modules/worker_spi/worker_spi.c b/src/test/modules/worker_spi/worker_spi.c index 0d705a3f2e..da488ebfd4 100644 --- a/src/test/modules/worker_spi/worker_spi.c +++ b/src/test/modules/worker_spi/worker_spi.c @@ -295,7 +295,7 @@ worker_spi_main(Datum main_arg) SPI_finish(); PopActiveSnapshot(); CommitTransactionCommand(); - pgstat_report_stat(false); + pgstat_update_stat(false); pgstat_report_activity(STATE_IDLE, NULL); } -- 2.16.3