pgstat: stats collector references in comments.

Soon the stats collector will be no more, with statistics instead getting
stored in shared memory. There are a lot of references to the stats collector
in comments. This commit replaces most of these references with "cumulative
statistics system", with the remaining ones getting replaced as part of
subsequent commits.

This is done separately from the - quite large - shared memory statistics
patch to make review easier.

Author: Andres Freund <andres@anarazel.de>
Reviewed-By: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-By: Thomas Munro <thomas.munro@gmail.com>
Reviewed-By: Kyotaro Horiguchi <horikyota.ntt@gmail.com>
Discussion: https://postgr.es/m/20220303021600.hs34ghqcw6zcokdh@alap3.anarazel.de
Discussion: https://postgr.es/m/20220308205351.2xcn6k4x5yivcxyd@alap3.anarazel.de

Author: anarazel

contrib/test_decoding/t/001_repl_stats.pl

@@ -88,8 +88,7 @@ sub test_slot_stats
 # Test to remove one of the replication slots and adjust
 # max_replication_slots accordingly to the number of slots. This leads
 # to a mismatch between the number of slots present in the stats file and the
-# number of stats present in the shared memory, simulating the scenario for
-# drop slot message lost by the statistics collector process. We verify
+# number of stats present in shared memory. We verify
 # replication statistics data is fine after restart.
 
 $node->stop;

src/backend/access/heap/heapam_handler.c

@@ -1089,8 +1089,8 @@ heapam_scan_analyze_next_tuple(TableScanDesc scan, TransactionId OldestXmin,
 				 * our own.  In this case we should count and sample the row,
 				 * to accommodate users who load a table and analyze it in one
 				 * transaction.  (pgstat_report_analyze has to adjust the
-				 * numbers we send to the stats collector to make this come
-				 * out right.)
+				 * numbers we report to the cumulative stats system to make
+				 * this come out right.)
 				 */
 				if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(targtuple->t_data)))
 				{

src/backend/access/heap/vacuumlazy.c

@@ -609,9 +609,9 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
 						&frozenxid_updated, &minmulti_updated, false);
 
 	/*
-	 * Report results to the stats collector, too.
+	 * Report results to the cumulative stats system, too.
 	 *
-	 * Deliberately avoid telling the stats collector about LP_DEAD items that
+	 * Deliberately avoid telling the stats system about LP_DEAD items that
 	 * remain in the table due to VACUUM bypassing index and heap vacuuming.
 	 * ANALYZE will consider the remaining LP_DEAD items to be dead "tuples".
 	 * It seems like a good idea to err on the side of not vacuuming again too
@@ -2228,10 +2228,10 @@ lazy_vacuum(LVRelState *vacrel)
 		 * dead_items space is not CPU cache resident.
 		 *
 		 * We don't take any special steps to remember the LP_DEAD items (such
-		 * as counting them in our final report to the stats collector) when
+		 * as counting them in our final update to the stats system) when
 		 * the optimization is applied.  Though the accounting used in
 		 * analyze.c's acquire_sample_rows() will recognize the same LP_DEAD
-		 * items as dead rows in its own stats collector report, that's okay.
+		 * items as dead rows in its own stats report, that's okay.
 		 * The discrepancy should be negligible.  If this optimization is ever
 		 * expanded to cover more cases then this may need to be reconsidered.
 		 */

src/backend/commands/analyze.c

@@ -680,7 +680,7 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 	}
 
 	/*
-	 * Now report ANALYZE to the stats collector.  For regular tables, we do
+	 * Now report ANALYZE to the cumulative stats system.  For regular tables, we do
 	 * it only if not doing inherited stats.  For partitioned tables, we only
 	 * do it for inherited stats. (We're never called for not-inherited stats
 	 * on partitioned tables anyway.)

src/backend/commands/dbcommands.c

@@ -1665,7 +1665,7 @@ dropdb(const char *dbname, bool missing_ok, bool force)
 	DropDatabaseBuffers(db_id);
 
 	/*
-	 * Tell the stats collector to forget it immediately, too.
+	 * Tell the cumulative stats system to forget it immediately, too.
 	 */
 	pgstat_drop_database(db_id);
 

src/backend/commands/matview.c

@@ -338,10 +338,10 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		refresh_by_heap_swap(matviewOid, OIDNewHeap, relpersistence);
 
 		/*
-		 * Inform stats collector about our activity: basically, we truncated
-		 * the matview and inserted some new data.  (The concurrent code path
-		 * above doesn't need to worry about this because the inserts and
-		 * deletes it issues get counted by lower-level code.)
+		 * Inform cumulative stats system about our activity: basically, we
+		 * truncated the matview and inserted some new data.  (The concurrent
+		 * code path above doesn't need to worry about this because the inserts
+		 * and deletes it issues get counted by lower-level code.)
 		 */
 		pgstat_count_truncate(matviewRel);
 		if (!stmt->skipData)

src/backend/commands/subscriptioncmds.c

@@ -1409,7 +1409,7 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	 * slot stays dropped even if the transaction rolls back.  So we cannot
 	 * run DROP SUBSCRIPTION inside a transaction block if dropping the
 	 * replication slot.  Also, in this case, we report a message for dropping
-	 * the subscription to the stats collector.
+	 * the subscription to the cumulative stats system.
 	 *
 	 * XXX The command name should really be something like "DROP SUBSCRIPTION
 	 * of a subscription that is associated with a replication slot", but we
@@ -1583,7 +1583,7 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	PG_END_TRY();
 
 	/*
-	 * Send a message for dropping this subscription to the stats collector.
+	 * Tell the cumulative stats system that the subscription is getting dropped.
 	 * We can safely report dropping the subscription statistics here if the
 	 * subscription is associated with a replication slot since we cannot run
 	 * DROP SUBSCRIPTION inside a transaction block.  Subscription statistics

src/backend/commands/vacuum.c

@@ -352,8 +352,8 @@ vacuum(List *relations, VacuumParams *params,
 				 errmsg("PROCESS_TOAST required with VACUUM FULL")));
 
 	/*
-	 * Send info about dead objects to the statistics collector, unless we are
-	 * in autovacuum --- autovacuum.c does this for itself.
+	 * Send info about dead objects to the cumulative stats system, unless
+	 * we are in autovacuum --- autovacuum.c does this for itself.
 	 */
 	if ((params->options & VACOPT_VACUUM) && !IsAutoVacuumWorkerProcess())
 		pgstat_vacuum_stat();

src/backend/postmaster/autovacuum.c

@@ -1689,7 +1689,7 @@ AutoVacWorkerMain(int argc, char *argv[])
 		char		dbname[NAMEDATALEN];
 
 		/*
-		 * Report autovac startup to the stats collector.  We deliberately do
+		 * Report autovac startup to the cumulative stats system.  We deliberately do
 		 * this before InitPostgres, so that the last_autovac_time will get
 		 * updated even if the connection attempt fails.  This is to prevent
 		 * autovac from getting "stuck" repeatedly selecting an unopenable
@@ -1996,9 +1996,9 @@ do_autovacuum(void)
 	StartTransactionCommand();
 
 	/*
-	 * Clean up any dead statistics collector entries for this DB. We always
-	 * want to do this exactly once per DB-processing cycle, even if we find
-	 * nothing worth vacuuming in the database.
+	 * Clean up any dead statistics entries for this DB. We always want to do
+	 * this exactly once per DB-processing cycle, even if we find nothing
+	 * worth vacuuming in the database.
 	 */
 	pgstat_vacuum_stat();
 
@@ -3041,7 +3041,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
  *
  * For analyze, the analysis done is that the number of tuples inserted,
  * deleted and updated since the last analyze exceeds a threshold calculated
- * in the same fashion as above.  Note that the collector actually stores
+ * in the same fashion as above.  Note that the cumulative stats system stores
  * the number of tuples (both live and dead) that there were as of the last
  * analyze.  This is asymmetric to the VACUUM case.
  *
@@ -3051,8 +3051,8 @@ recheck_relation_needs_vacanalyze(Oid relid,
  *
  * A table whose autovacuum_enabled option is false is
  * automatically skipped (unless we have to vacuum it due to freeze_max_age).
- * Thus autovacuum can be disabled for specific tables. Also, when the stats
- * collector does not have data about a table, it will be skipped.
+ * Thus autovacuum can be disabled for specific tables. Also, when the cumulative
+ * stats system does not have data about a table, it will be skipped.
  *
  * A table whose vac_base_thresh value is < 0 takes the base value from the
  * autovacuum_vacuum_threshold GUC variable.  Similarly, a vac_scale_factor

src/backend/postmaster/bgwriter.c

@@ -240,9 +240,7 @@ BackgroundWriterMain(void)
 		 */
 		can_hibernate = BgBufferSync(&wb_context);
 
-		/*
-		 * Send off activity statistics to the stats collector
-		 */
+		/* Report pending statistics to the cumulative stats system */
 		pgstat_send_bgwriter();
 
 		if (FirstCallSinceLastCheckpoint())

src/backend/postmaster/checkpointer.c

@@ -492,12 +492,8 @@ CheckpointerMain(void)
 		/* Check for archive_timeout and switch xlog files if necessary. */
 		CheckArchiveTimeout();
 
-		/*
-		 * Send off activity statistics to the stats collector.
-		 */
+		/* Report pending statistics to the cumulative stats system */
 		pgstat_send_checkpointer();
-
-		/* Send WAL statistics to the stats collector. */
 		pgstat_send_wal(true);
 
 		/*
@@ -570,8 +566,8 @@ HandleCheckpointerInterrupts(void)
 		 * Close down the database.
 		 *
 		 * Since ShutdownXLOG() creates restartpoint or checkpoint, and
-		 * updates the statistics, increment the checkpoint request and send
-		 * the statistics to the stats collector.
+		 * updates the statistics, increment the checkpoint request and flush
+		 * out pending statistic.
 		 */
 		PendingCheckpointerStats.m_requested_checkpoints++;
 		ShutdownXLOG(0, 0);
@@ -718,9 +714,7 @@ CheckpointWriteDelay(int flags, double progress)
 
 		CheckArchiveTimeout();
 
-		/*
-		 * Report interim activity statistics.
-		 */
+		/* Report interim statistics to the cumulative stats system */
 		pgstat_send_checkpointer();
 
 		/*

src/backend/postmaster/pgarch.c

@@ -477,8 +477,8 @@ pgarch_ArchiverCopyLoop(void)
 				pgarch_archiveDone(xlog);
 
 				/*
-				 * Tell the collector about the WAL file that we successfully
-				 * archived
+				 * Tell the cumulative stats system about the WAL file that we
+				 * successfully archived
 				 */
 				pgstat_send_archiver(xlog, false);
 
@@ -487,8 +487,8 @@ pgarch_ArchiverCopyLoop(void)
 			else
 			{
 				/*
-				 * Tell the collector about the WAL file that we failed to
-				 * archive
+				 * Tell the cumulative stats system about the WAL file that we
+				 * failed to archive
 				 */
 				pgstat_send_archiver(xlog, true);
 

src/backend/postmaster/pgstat.c

@@ -693,20 +693,20 @@ allow_immediate_pgstat_restart(void)
 /*
  * Shut down a single backend's statistics reporting at process exit.
  *
- * Flush any remaining statistics counts out to the collector.
- * Without this, operations triggered during backend exit (such as
- * temp table deletions) won't be counted.
+ * Flush out any remaining statistics counts.  Without this, operations
+ * triggered during backend exit (such as temp table deletions) won't be
+ * counted.
  */
 static void
 pgstat_shutdown_hook(int code, Datum arg)
 {
 	Assert(!pgstat_is_shutdown);
 
 	/*
-	 * If we got as far as discovering our own database ID, we can report what
-	 * we did to the collector.  Otherwise, we'd be sending an invalid
-	 * database ID, so forget it.  (This means that accesses to pg_database
-	 * during failed backend starts might never get counted.)
+	 * If we got as far as discovering our own database ID, we can flush out
+	 * what we did so far.  Otherwise, we'd be reporting an invalid database
+	 * ID, so forget it.  (This means that accesses to pg_database during
+	 * failed backend starts might never get counted.)
 	 */
 	if (OidIsValid(MyDatabaseId))
 		pgstat_report_stat(true);
@@ -1065,7 +1065,7 @@ pgstat_collect_oids(Oid catalogid, AttrNumber anum_oid)
 }
 
 /*
- * 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.
@@ -1084,7 +1084,7 @@ pgstat_reset_counters(void)
 }
 
 /*
- * 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.
@@ -1106,7 +1106,7 @@ pgstat_reset_single_counter(Oid objoid, PgStat_Single_Reset_Type type)
 }
 
 /*
- * 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.
@@ -1198,8 +1198,8 @@ pgstat_clear_snapshot(void)
 /*
  * 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.
+ * that the database doesn't exist, just that there are no statistics, so the
+ * caller is better off to report ZERO instead.
  */
 PgStat_StatDBEntry *
 pgstat_fetch_stat_dbentry(Oid dbid)
@@ -1233,8 +1233,8 @@ pgstat_fetch_global(void)
 /*
  * Support function for the SQL-callable pgstat* functions. Returns
  * the collected statistics for one table or NULL. NULL doesn't mean
- * that the table doesn't exist, it is just not yet known by the
- * collector, so the caller is better off to report ZERO instead.
+ * that the table doesn't exist, just that there are no statistics, so the
+ * caller is better off to report ZERO instead.
  */
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)

src/backend/postmaster/walwriter.c

@@ -257,7 +257,7 @@ WalWriterMain(void)
 		else if (left_till_hibernate > 0)
 			left_till_hibernate--;
 
-		/* Send WAL statistics to the stats collector */
+		/* report pending statistics to the cumulative stats system */
 		pgstat_send_wal(false);
 
 		/*
@@ -295,12 +295,11 @@ HandleWalWriterInterrupts(void)
 	if (ShutdownRequestPending)
 	{
 		/*
-		 * Force to send remaining WAL statistics to the stats collector at
-		 * process exit.
+		 * Force reporting remaining WAL statistics at process exit.
 		 *
 		 * Since pgstat_send_wal is invoked with 'force' is false in main loop
-		 * to avoid overloading to the stats collector, there may exist unsent
-		 * stats counters for the WAL writer.
+		 * to avoid overloading the cumulative stats system, there may exist
+		 * unreported stats counters for the WAL writer.
 		 */
 		pgstat_send_wal(true);
 

src/backend/replication/basebackup.c

@@ -1505,8 +1505,8 @@ is_checksummed_file(const char *fullpath, const char *filename)
  *
  * If 'missing_ok' is true, will not throw an error if the file is not found.
  *
- * If dboid is anything other than InvalidOid then any checksum failures detected
- * will get reported to the stats collector.
+ * If dboid is anything other than InvalidOid then any checksum failures
+ * detected will get reported to the cumulative stats system.
  *
  * Returns true if the file was successfully sent, false if 'missing_ok',
  * and the file did not exist.

src/backend/tcop/postgres.c

@@ -2937,7 +2937,7 @@ die(SIGNAL_ARGS)
 		ProcDiePending = true;
 	}
 
-	/* for the statistics collector */
+	/* for the cumulative stats system */
 	pgStatSessionEndCause = DISCONNECT_KILLED;
 
 	/* If we're still here, waken anything waiting on the process latch */
@@ -4368,8 +4368,8 @@ PostgresMain(const char *dbname, const char *username)
 		 *
 		 * Note: this includes fflush()'ing the last of the prior output.
 		 *
-		 * This is also a good time to send collected statistics to the
-		 * collector, and to update the PS stats display.  We avoid doing
+		 * This is also a good time to flush out collected statistics to the
+		 * cumulative stats system, and to update the PS stats display.  We avoid doing
 		 * those every time through the message loop because it'd slow down
 		 * processing of batched messages, and because we don't want to report
 		 * uncommitted updates (that confuses autovacuum).  The notification
@@ -4710,7 +4710,7 @@ PostgresMain(const char *dbname, const char *username)
 				 */
 			case EOF:
 
-				/* for the statistics collector */
+				/* for the cumulative statistics system */
 				pgStatSessionEndCause = DISCONNECT_CLIENT_EOF;
 
 				/* FALLTHROUGH */

src/backend/utils/activity/pgstat_archiver.c

@@ -22,8 +22,7 @@
 
 
 /*
- * Tell the collector about the WAL file that we successfully
- * archived or failed to archive.
+ * Report archiver statistics
  */
 void
 pgstat_send_archiver(const char *xlog, bool failed)

src/backend/utils/activity/pgstat_bgwriter.c

@@ -29,7 +29,7 @@ PgStat_MsgBgWriter PendingBgWriterStats;
 
 
 /*
- * Send bgwriter statistics to the collector
+ * Report bgwriter statistics
  */
 void
 pgstat_send_bgwriter(void)

src/backend/utils/activity/pgstat_checkpointer.c

@@ -29,7 +29,7 @@ PgStat_MsgCheckpointer PendingCheckpointerStats;
 
 
 /*
- * Send checkpointer statistics to the collector
+ * Report checkpointer statistics
  */
 void
 pgstat_send_checkpointer(void)