stats-temp-files-v3.diff

text/plain

Filename: stats-temp-files-v3.diff
Type: text/plain
Part: 0
Message: Re: PATCH: tracking temp files in pg_stat_database

Patch

Same data as JSON: GET /api/v1/attachments/:id/patch the parsed metadata as JSON — format, series position, per-file stats; never the diff bytes. API reference →
Format: unified
Series: patch v3
File+
doc/src/sgml/monitoring.sgml 20 0
src/backend/catalog/system_views.sql 2 0
src/backend/postmaster/pgstat.c 50 1
src/backend/storage/file/fd.c 18 20
src/backend/utils/adt/pgstatfuncs.c 33 0
src/include/catalog/pg_proc.h 4 0
src/include/pgstat.h 18 2
src/test/regress/expected/rules.out 1 1
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index a12a9a2..3635c3f 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -691,6 +691,26 @@ postgres: <replaceable>user</> <replaceable>database</> <replaceable>host</> <re
      </row>
 
      <row>
+      <entry><literal><function>pg_stat_get_db_temp_files</function>(<type>oid</type>)</literal></entry>
+      <entry><type>bigint</type></entry>
+      <entry>
+       Nuber of temporary files written for the database. All temporary files are
+       counted, regardless of why the temporary file was created (sorting or hash
+       join) or file size (log_temp_file does not affect this).
+      </entry>
+     </row>
+
+     <row>
+      <entry><literal><function>pg_stat_get_db_temp_bytes</function>(<type>oid</type>)</literal></entry>
+      <entry><type>bigint</type></entry>
+      <entry>
+       Amount of data written to temporary files for the database. All temporary
+       files are counted, regardless of why the temporary file was created (sorting
+       or hash join) or file size (log_temp_file does not affect this).
+      </entry>
+     </row>
+
+     <row>
       <entry><literal><function>pg_stat_get_numscans</function>(<type>oid</type>)</literal></entry>
       <entry><type>bigint</type></entry>
       <entry>
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 50ba20c..3a0dca3 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -574,6 +574,8 @@ CREATE VIEW pg_stat_database AS
             pg_stat_get_db_tuples_updated(D.oid) AS tup_updated,
             pg_stat_get_db_tuples_deleted(D.oid) AS tup_deleted,
             pg_stat_get_db_conflict_all(D.oid) AS conflicts,
+            pg_stat_get_db_temp_files(D.oid) AS temp_files,
+            pg_stat_get_db_temp_bytes(D.oid) AS temp_bytes,
             pg_stat_get_db_stat_reset_time(D.oid) AS stats_reset
     FROM pg_database D;
 
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index 323d42b..6a2ff1d 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -286,7 +286,7 @@ 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_tempfile(PgStat_MsgTempFile *msg, int len);
 
 /* ------------------------------------------------------------
  * Public functions called from postmaster follow
@@ -1339,6 +1339,29 @@ pgstat_report_recovery_conflict(int reason)
 	pgstat_send(&msg, sizeof(msg));
 }
 
+
+/* --------
+ * pgstat_report_tempfile() -
+ *
+ *	Tell the collector about a temporary file.
+ * --------
+ */
+void
+pgstat_report_tempfile(size_t filesize)
+{
+	PgStat_MsgTempFile msg;
+
+	if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts)
+		return;
+
+	pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TEMPFILE);
+	msg.m_databaseid = MyDatabaseId;
+	msg.m_filesize = filesize;
+	pgstat_send(&msg, sizeof(msg));
+}
+
+;
+
 /* ----------
  * pgstat_ping() -
  *
@@ -3185,6 +3208,10 @@ PgstatCollectorMain(int argc, char *argv[])
 					pgstat_recv_recoveryconflict((PgStat_MsgRecoveryConflict *) &msg, len);
 					break;
 
+				case PGSTAT_MTYPE_TEMPFILE:
+					pgstat_recv_tempfile((PgStat_MsgTempFile *) &msg, len);
+					break;
+
 				default:
 					break;
 			}
@@ -3266,6 +3293,8 @@ pgstat_get_db_entry(Oid databaseid, bool create)
 		result->n_conflict_snapshot = 0;
 		result->n_conflict_bufferpin = 0;
 		result->n_conflict_startup_deadlock = 0;
+		result->n_temp_files = 0;
+		result->n_temp_bytes = 0;
 
 		result->stat_reset_timestamp = GetCurrentTimestamp();
 
@@ -4177,6 +4206,8 @@ pgstat_recv_resetcounter(PgStat_MsgResetcounter *msg, int len)
 	dbentry->n_tuples_updated = 0;
 	dbentry->n_tuples_deleted = 0;
 	dbentry->last_autovac_time = 0;
+	dbentry->n_temp_bytes = 0;
+	dbentry->n_temp_files = 0;
 
 	dbentry->stat_reset_timestamp = GetCurrentTimestamp();
 
@@ -4403,6 +4434,24 @@ pgstat_recv_recoveryconflict(PgStat_MsgRecoveryConflict *msg, int len)
 }
 
 /* ----------
+ * pgstat_recv_tempfile() -
+ *
+ *	Process as PGSTAT_MTYPE_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.
diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c
index 43bc43a..7a47ae7 100644
--- a/src/backend/storage/file/fd.c
+++ b/src/backend/storage/file/fd.c
@@ -1088,6 +1088,10 @@ FileClose(File file)
 	 */
 	if (vfdP->fdstate & FD_TEMPORARY)
 	{
+		
+		struct stat filestats;
+		int			stat_errno;
+		
 		/*
 		 * If we get an error, as could happen within the ereport/elog calls,
 		 * we'll come right back here during transaction abort.  Reset the
@@ -1101,23 +1105,23 @@ FileClose(File file)
 		temporary_files_size -= vfdP->fileSize;
 		vfdP->fileSize = 0;
 
-		if (log_temp_files >= 0)
-		{
-			struct stat filestats;
-			int			stat_errno;
+		/* first try the stat() */
+		if (stat(vfdP->fileName, &filestats))
+			stat_errno = errno;
+		else
+			stat_errno = 0;
 
-			/* first try the stat() */
-			if (stat(vfdP->fileName, &filestats))
-				stat_errno = errno;
-			else
-				stat_errno = 0;
+		/* in any case do the unlink */
+		if (unlink(vfdP->fileName))
+			elog(LOG, "could not unlink file \"%s\": %m", vfdP->fileName);
 
-			/* in any case do the unlink */
-			if (unlink(vfdP->fileName))
-				elog(LOG, "could not unlink file \"%s\": %m", vfdP->fileName);
+		/* and last report the stat results */
+		if (stat_errno == 0)
+		{
 
-			/* and last report the stat results */
-			if (stat_errno == 0)
+			pgstat_report_tempfile(filestats.st_size);
+			
+			if (log_temp_files >= 0)
 			{
 				if ((filestats.st_size / 1024) >= log_temp_files)
 					ereport(LOG,
@@ -1131,12 +1135,6 @@ FileClose(File file)
 				elog(LOG, "could not stat file \"%s\": %m", vfdP->fileName);
 			}
 		}
-		else
-		{
-			/* easy case, just do the unlink */
-			if (unlink(vfdP->fileName))
-				elog(LOG, "could not unlink file \"%s\": %m", vfdP->fileName);
-		}
 	}
 
 	/* Unregister it from the resource owner */
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index b4986d8..2804af7 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -79,6 +79,8 @@ extern Datum pg_stat_get_db_conflict_bufferpin(PG_FUNCTION_ARGS);
 extern Datum pg_stat_get_db_conflict_startup_deadlock(PG_FUNCTION_ARGS);
 extern Datum pg_stat_get_db_conflict_all(PG_FUNCTION_ARGS);
 extern Datum pg_stat_get_db_stat_reset_time(PG_FUNCTION_ARGS);
+extern Datum pg_stat_get_db_temp_files(PG_FUNCTION_ARGS);
+extern Datum pg_stat_get_db_temp_bytes(PG_FUNCTION_ARGS);
 
 extern Datum pg_stat_get_bgwriter_timed_checkpoints(PG_FUNCTION_ARGS);
 extern Datum pg_stat_get_bgwriter_requested_checkpoints(PG_FUNCTION_ARGS);
@@ -1180,6 +1182,37 @@ pg_stat_get_db_stat_reset_time(PG_FUNCTION_ARGS)
 }
 
 Datum
+pg_stat_get_db_temp_files(PG_FUNCTION_ARGS)
+{
+	Oid		dbid = PG_GETARG_OID(0);
+	int64	result;
+	PgStat_StatDBEntry *dbentry;
+
+	if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+		result = 0;
+	else
+		result = dbentry->n_temp_files;
+
+	PG_RETURN_INT64(result);
+}
+
+
+Datum
+pg_stat_get_db_temp_bytes(PG_FUNCTION_ARGS)
+{
+	Oid		dbid = PG_GETARG_OID(0);
+	int64	result;
+	PgStat_StatDBEntry *dbentry;
+
+	if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+		result = 0;
+	else
+		result = dbentry->n_temp_bytes;
+
+	PG_RETURN_INT64(result);
+}
+
+Datum
 pg_stat_get_db_conflict_tablespace(PG_FUNCTION_ARGS)
 {
 	Oid			dbid = PG_GETARG_OID(0);
diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h
index 355c61a..df68a8d 100644
--- a/src/include/catalog/pg_proc.h
+++ b/src/include/catalog/pg_proc.h
@@ -2633,6 +2633,10 @@ DATA(insert OID = 3070 (  pg_stat_get_db_conflict_all PGNSP PGUID 12 1 0 0 0 f f
 DESCR("statistics: recovery conflicts in database");
 DATA(insert OID = 3074 (  pg_stat_get_db_stat_reset_time PGNSP PGUID 12 1 0 0 0 f f f t f s 1 0 1184 "26" _null_ _null_ _null_ _null_ pg_stat_get_db_stat_reset_time _null_ _null_ _null_ ));
 DESCR("statistics: last reset for a database");
+DATA(insert OID = 3079 (  pg_stat_get_db_temp_files PGNSP PGUID 12 1 0 0 0 f f f t f s 1 0 20 "26" _null_ _null_ _null_ _null_ pg_stat_get_db_temp_files _null_ _null_ _null_ ));
+DESCR("statistics: number of temporary files written");
+DATA(insert OID = 3080 (  pg_stat_get_db_temp_bytes PGNSP PGUID 12 1 0 0 0 f f f t f s 1 0 20 "26" _null_ _null_ _null_ _null_ pg_stat_get_db_temp_bytes _null_ _null_ _null_ ));
+DESCR("statistics: number of bytes in temporary files written");
 DATA(insert OID = 2769 ( pg_stat_get_bgwriter_timed_checkpoints PGNSP PGUID 12 1 0 0 0 f f f t f s 0 0 20 "" _null_ _null_ _null_ _null_ pg_stat_get_bgwriter_timed_checkpoints _null_ _null_ _null_ ));
 DESCR("statistics: number of timed checkpoints started by the bgwriter");
 DATA(insert OID = 2770 ( pg_stat_get_bgwriter_requested_checkpoints PGNSP PGUID 12 1 0 0 0 f f f t f s 0 0 20 "" _null_ _null_ _null_ _null_ pg_stat_get_bgwriter_requested_checkpoints _null_ _null_ _null_ ));
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index b8c6d82..df27d80 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -47,7 +47,8 @@ typedef enum StatMsgType
 	PGSTAT_MTYPE_BGWRITER,
 	PGSTAT_MTYPE_FUNCSTAT,
 	PGSTAT_MTYPE_FUNCPURGE,
-	PGSTAT_MTYPE_RECOVERYCONFLICT
+	PGSTAT_MTYPE_RECOVERYCONFLICT,
+	PGSTAT_MTYPE_TEMPFILE
 } StatMsgType;
 
 /* ----------
@@ -377,6 +378,18 @@ typedef struct PgStat_MsgRecoveryConflict
 } 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_FunctionCounts	The actual per-function counts kept by a backend
  *
  * This struct should contain only actual event counters, because we memcmp
@@ -507,9 +520,11 @@ typedef struct PgStat_StatDBEntry
 	PgStat_Counter n_conflict_snapshot;
 	PgStat_Counter n_conflict_bufferpin;
 	PgStat_Counter n_conflict_startup_deadlock;
+	PgStat_Counter n_temp_files;
+	PgStat_Counter n_temp_bytes;
+	
 	TimestampTz stat_reset_timestamp;
 
-
 	/*
 	 * tables and functions must be last in the struct, because we don't write
 	 * the pointers out to the stats file.
@@ -716,6 +731,7 @@ extern void pgstat_initialize(void);
 extern void pgstat_bestart(void);
 
 extern void pgstat_report_activity(const char *cmd_str);
+extern void pgstat_report_tempfile(size_t filesize);
 extern void pgstat_report_appname(const char *appname);
 extern void pgstat_report_xact_timestamp(TimestampTz tstamp);
 extern void pgstat_report_waiting(bool waiting);
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index 454e1f9..c558066 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1296,7 +1296,7 @@ SELECT viewname, definition FROM pg_views WHERE schemaname <> 'information_schem
  pg_stat_all_indexes             | SELECT c.oid AS relid, i.oid AS indexrelid, n.nspname AS schemaname, c.relname, i.relname AS indexrelname, pg_stat_get_numscans(i.oid) AS idx_scan, pg_stat_get_tuples_returned(i.oid) AS idx_tup_read, pg_stat_get_tuples_fetched(i.oid) AS idx_tup_fetch FROM (((pg_class c JOIN pg_index x ON ((c.oid = x.indrelid))) JOIN pg_class i ON ((i.oid = x.indexrelid))) LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace))) WHERE (c.relkind = ANY (ARRAY['r'::"char", 't'::"char"]));
  pg_stat_all_tables              | SELECT c.oid AS relid, n.nspname AS schemaname, c.relname, pg_stat_get_numscans(c.oid) AS seq_scan, pg_stat_get_tuples_returned(c.oid) AS seq_tup_read, (sum(pg_stat_get_numscans(i.indexrelid)))::bigint AS idx_scan, ((sum(pg_stat_get_tuples_fetched(i.indexrelid)))::bigint + pg_stat_get_tuples_fetched(c.oid)) AS idx_tup_fetch, pg_stat_get_tuples_inserted(c.oid) AS n_tup_ins, pg_stat_get_tuples_updated(c.oid) AS n_tup_upd, pg_stat_get_tuples_deleted(c.oid) AS n_tup_del, pg_stat_get_tuples_hot_updated(c.oid) AS n_tup_hot_upd, pg_stat_get_live_tuples(c.oid) AS n_live_tup, pg_stat_get_dead_tuples(c.oid) AS n_dead_tup, pg_stat_get_last_vacuum_time(c.oid) AS last_vacuum, pg_stat_get_last_autovacuum_time(c.oid) AS last_autovacuum, pg_stat_get_last_analyze_time(c.oid) AS last_analyze, pg_stat_get_last_autoanalyze_time(c.oid) AS last_autoanalyze, pg_stat_get_vacuum_count(c.oid) AS vacuum_count, pg_stat_get_autovacuum_count(c.oid) AS autovacuum_count, pg_stat_get_analyze_count(c.oid) AS analyze_count, pg_stat_get_autoanalyze_count(c.oid) AS autoanalyze_count FROM ((pg_class c LEFT JOIN pg_index i ON ((c.oid = i.indrelid))) LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace))) WHERE (c.relkind = ANY (ARRAY['r'::"char", 't'::"char"])) GROUP BY c.oid, n.nspname, c.relname;
  pg_stat_bgwriter                | SELECT pg_stat_get_bgwriter_timed_checkpoints() AS checkpoints_timed, pg_stat_get_bgwriter_requested_checkpoints() AS checkpoints_req, pg_stat_get_bgwriter_buf_written_checkpoints() AS buffers_checkpoint, pg_stat_get_bgwriter_buf_written_clean() AS buffers_clean, pg_stat_get_bgwriter_maxwritten_clean() AS maxwritten_clean, pg_stat_get_buf_written_backend() AS buffers_backend, pg_stat_get_buf_fsync_backend() AS buffers_backend_fsync, pg_stat_get_buf_alloc() AS buffers_alloc, pg_stat_get_bgwriter_stat_reset_time() AS stats_reset;
- pg_stat_database                | SELECT d.oid AS datid, d.datname, pg_stat_get_db_numbackends(d.oid) AS numbackends, pg_stat_get_db_xact_commit(d.oid) AS xact_commit, pg_stat_get_db_xact_rollback(d.oid) AS xact_rollback, (pg_stat_get_db_blocks_fetched(d.oid) - pg_stat_get_db_blocks_hit(d.oid)) AS blks_read, pg_stat_get_db_blocks_hit(d.oid) AS blks_hit, pg_stat_get_db_tuples_returned(d.oid) AS tup_returned, pg_stat_get_db_tuples_fetched(d.oid) AS tup_fetched, pg_stat_get_db_tuples_inserted(d.oid) AS tup_inserted, pg_stat_get_db_tuples_updated(d.oid) AS tup_updated, pg_stat_get_db_tuples_deleted(d.oid) AS tup_deleted, pg_stat_get_db_conflict_all(d.oid) AS conflicts, pg_stat_get_db_stat_reset_time(d.oid) AS stats_reset FROM pg_database d;
+ pg_stat_database                | SELECT d.oid AS datid, d.datname, pg_stat_get_db_numbackends(d.oid) AS numbackends, pg_stat_get_db_xact_commit(d.oid) AS xact_commit, pg_stat_get_db_xact_rollback(d.oid) AS xact_rollback, (pg_stat_get_db_blocks_fetched(d.oid) - pg_stat_get_db_blocks_hit(d.oid)) AS blks_read, pg_stat_get_db_blocks_hit(d.oid) AS blks_hit, pg_stat_get_db_tuples_returned(d.oid) AS tup_returned, pg_stat_get_db_tuples_fetched(d.oid) AS tup_fetched, pg_stat_get_db_tuples_inserted(d.oid) AS tup_inserted, pg_stat_get_db_tuples_updated(d.oid) AS tup_updated, pg_stat_get_db_tuples_deleted(d.oid) AS tup_deleted, pg_stat_get_db_conflict_all(d.oid) AS conflicts, pg_stat_get_db_temp_files(d.oid) AS temp_files, pg_stat_get_db_temp_bytes(d.oid) AS temp_bytes, pg_stat_get_db_stat_reset_time(d.oid) AS stats_reset FROM pg_database d;
  pg_stat_database_conflicts      | SELECT d.oid AS datid, d.datname, pg_stat_get_db_conflict_tablespace(d.oid) AS confl_tablespace, pg_stat_get_db_conflict_lock(d.oid) AS confl_lock, pg_stat_get_db_conflict_snapshot(d.oid) AS confl_snapshot, pg_stat_get_db_conflict_bufferpin(d.oid) AS confl_bufferpin, pg_stat_get_db_conflict_startup_deadlock(d.oid) AS confl_deadlock FROM pg_database d;
  pg_stat_replication             | SELECT s.procpid, s.usesysid, u.rolname AS usename, s.application_name, s.client_addr, s.client_hostname, s.client_port, s.backend_start, w.state, w.sent_location, w.write_location, w.flush_location, w.replay_location, w.sync_priority, w.sync_state FROM pg_stat_get_activity(NULL::integer) s(datid, procpid, usesysid, application_name, current_query, waiting, xact_start, query_start, backend_start, client_addr, client_hostname, client_port), pg_authid u, pg_stat_get_wal_senders() w(procpid, state, sent_location, write_location, flush_location, replay_location, sync_priority, sync_state) WHERE ((s.usesysid = u.oid) AND (s.procpid = w.procpid));
  pg_stat_sys_indexes             | SELECT pg_stat_all_indexes.relid, pg_stat_all_indexes.indexrelid, pg_stat_all_indexes.schemaname, pg_stat_all_indexes.relname, pg_stat_all_indexes.indexrelname, pg_stat_all_indexes.idx_scan, pg_stat_all_indexes.idx_tup_read, pg_stat_all_indexes.idx_tup_fetch FROM pg_stat_all_indexes WHERE ((pg_stat_all_indexes.schemaname = ANY (ARRAY['pg_catalog'::name, 'information_schema'::name])) OR (pg_stat_all_indexes.schemaname ~ '^pg_toast'::text));