pg_stat_statements: Add columns to track parallel worker activity

michaelpq · michaelpq · commit cf54a2c00254 · 2024-10-09T08:30:45.000+09:00
The view pg_stat_statements gains two columns: - parallel_workers_to_launch, the number of parallel workers planned to be launched. - parallel_workers_launched, the number of parallel workers actually launched. The ratio of both columns offers hints that parallel workers are lacking on a per-statement basis, requiring some tuning, in coordination with "calls", the number of times a query is executed. As of now, these numbers are tracked within Gather and GatherMerge nodes. They could be extended to utilities that make use of parallel workers (parallel btree and brin, VACUUM). The module is bumped to 1.12. Author: Guillaume Lelarge Discussion: https://postgr.es/m/CAECtzeWtTGOK0UgKXdDGpfTVSa5bd_VbUt6K6xn8P7X+_dZqKw@mail.gmail.com
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
@@ -7,7 +7,7 @@ OBJS = \
 
 EXTENSION = pg_stat_statements
 DATA = pg_stat_statements--1.4.sql \
-	pg_stat_statements--1.10--1.11.sql \
+	pg_stat_statements--1.11--1.12.sql pg_stat_statements--1.10--1.11.sql \
 	pg_stat_statements--1.9--1.10.sql pg_stat_statements--1.8--1.9.sql \
 	pg_stat_statements--1.7--1.8.sql pg_stat_statements--1.6--1.7.sql \
 	pg_stat_statements--1.5--1.6.sql pg_stat_statements--1.4--1.5.sql \
@@ -19,8 +19,8 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
-	user_activity wal entry_timestamp privileges extended cleanup \
-	oldextversions
+	user_activity wal entry_timestamp privileges extended \
+	parallel cleanup oldextversions
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/oldextversions.out b/contrib/pg_stat_statements/expected/oldextversions.out
@@ -342,4 +342,68 @@ SELECT pg_stat_statements_reset() IS NOT NULL AS t;
  t
 (1 row)
 
+-- New functions and views for pg_stat_statements in 1.12
+AlTER EXTENSION pg_stat_statements UPDATE TO '1.12';
+\d pg_stat_statements
+                            View "public.pg_stat_statements"
+           Column           |           Type           | Collation | Nullable | Default 
+----------------------------+--------------------------+-----------+----------+---------
+ userid                     | oid                      |           |          | 
+ dbid                       | oid                      |           |          | 
+ toplevel                   | boolean                  |           |          | 
+ queryid                    | bigint                   |           |          | 
+ query                      | text                     |           |          | 
+ plans                      | bigint                   |           |          | 
+ total_plan_time            | double precision         |           |          | 
+ min_plan_time              | double precision         |           |          | 
+ max_plan_time              | double precision         |           |          | 
+ mean_plan_time             | double precision         |           |          | 
+ stddev_plan_time           | double precision         |           |          | 
+ calls                      | bigint                   |           |          | 
+ total_exec_time            | double precision         |           |          | 
+ min_exec_time              | double precision         |           |          | 
+ max_exec_time              | double precision         |           |          | 
+ mean_exec_time             | double precision         |           |          | 
+ stddev_exec_time           | double precision         |           |          | 
+ rows                       | bigint                   |           |          | 
+ shared_blks_hit            | bigint                   |           |          | 
+ shared_blks_read           | bigint                   |           |          | 
+ shared_blks_dirtied        | bigint                   |           |          | 
+ shared_blks_written        | bigint                   |           |          | 
+ local_blks_hit             | bigint                   |           |          | 
+ local_blks_read            | bigint                   |           |          | 
+ local_blks_dirtied         | bigint                   |           |          | 
+ local_blks_written         | bigint                   |           |          | 
+ temp_blks_read             | bigint                   |           |          | 
+ temp_blks_written          | bigint                   |           |          | 
+ shared_blk_read_time       | double precision         |           |          | 
+ shared_blk_write_time      | double precision         |           |          | 
+ local_blk_read_time        | double precision         |           |          | 
+ local_blk_write_time       | double precision         |           |          | 
+ temp_blk_read_time         | double precision         |           |          | 
+ temp_blk_write_time        | double precision         |           |          | 
+ wal_records                | bigint                   |           |          | 
+ wal_fpi                    | bigint                   |           |          | 
+ wal_bytes                  | numeric                  |           |          | 
+ jit_functions              | bigint                   |           |          | 
+ jit_generation_time        | double precision         |           |          | 
+ jit_inlining_count         | bigint                   |           |          | 
+ jit_inlining_time          | double precision         |           |          | 
+ jit_optimization_count     | bigint                   |           |          | 
+ jit_optimization_time      | double precision         |           |          | 
+ jit_emission_count         | bigint                   |           |          | 
+ jit_emission_time          | double precision         |           |          | 
+ jit_deform_count           | bigint                   |           |          | 
+ jit_deform_time            | double precision         |           |          | 
+ parallel_workers_to_launch | bigint                   |           |          | 
+ parallel_workers_launched  | bigint                   |           |          | 
+ stats_since                | timestamp with time zone |           |          | 
+ minmax_stats_since         | timestamp with time zone |           |          | 
+
+SELECT count(*) > 0 AS has_data FROM pg_stat_statements;
+ has_data 
+----------
+ t
+(1 row)
+
 DROP EXTENSION pg_stat_statements;
diff --git a/contrib/pg_stat_statements/expected/parallel.out b/contrib/pg_stat_statements/expected/parallel.out
@@ -0,0 +1,34 @@
+--
+-- Tests for parallel statistics
+--
+SET pg_stat_statements.track_utility = FALSE;
+-- encourage use of parallel plans
+SET parallel_setup_cost = 0;
+SET parallel_tuple_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET max_parallel_workers_per_gather = 2;
+CREATE TABLE pgss_parallel_tab (a int);
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT count(*) FROM pgss_parallel_tab;
+ count 
+-------
+     0
+(1 row)
+
+SELECT query,
+  parallel_workers_to_launch > 0 AS has_workers_to_launch,
+  parallel_workers_launched > 0 AS has_workers_launched
+  FROM pg_stat_statements
+  WHERE query ~ 'SELECT count'
+  ORDER BY query COLLATE "C";
+                 query                  | has_workers_to_launch | has_workers_launched 
+----------------------------------------+-----------------------+----------------------
+ SELECT count(*) FROM pgss_parallel_tab | t                     | t
+(1 row)
+
+DROP TABLE pgss_parallel_tab;
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
@@ -21,6 +21,7 @@ contrib_targets += pg_stat_statements
 install_data(
   'pg_stat_statements.control',
   'pg_stat_statements--1.4.sql',
+  'pg_stat_statements--1.11--1.12.sql',
   'pg_stat_statements--1.10--1.11.sql',
   'pg_stat_statements--1.9--1.10.sql',
   'pg_stat_statements--1.8--1.9.sql',
@@ -52,6 +53,7 @@ tests += {
       'entry_timestamp',
       'privileges',
       'extended',
+      'parallel',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/pg_stat_statements--1.11--1.12.sql b/contrib/pg_stat_statements/pg_stat_statements--1.11--1.12.sql
@@ -0,0 +1,75 @@
+/* contrib/pg_stat_statements/pg_stat_statements--1.11--1.12.sql */
+
+-- complain if script is sourced in psql, rather than via ALTER EXTENSION
+\echo Use "ALTER EXTENSION pg_stat_statements UPDATE TO '1.12'" to load this file. \quit
+
+/* First we have to remove them from the extension */
+ALTER EXTENSION pg_stat_statements DROP VIEW pg_stat_statements;
+ALTER EXTENSION pg_stat_statements DROP FUNCTION pg_stat_statements(boolean);
+
+/* Then we can drop them */
+DROP VIEW pg_stat_statements;
+DROP FUNCTION pg_stat_statements(boolean);
+
+/* Now redefine */
+CREATE FUNCTION pg_stat_statements(IN showtext boolean,
+    OUT userid oid,
+    OUT dbid oid,
+    OUT toplevel bool,
+    OUT queryid bigint,
+    OUT query text,
+    OUT plans int8,
+    OUT total_plan_time float8,
+    OUT min_plan_time float8,
+    OUT max_plan_time float8,
+    OUT mean_plan_time float8,
+    OUT stddev_plan_time float8,
+    OUT calls int8,
+    OUT total_exec_time float8,
+    OUT min_exec_time float8,
+    OUT max_exec_time float8,
+    OUT mean_exec_time float8,
+    OUT stddev_exec_time float8,
+    OUT rows int8,
+    OUT shared_blks_hit int8,
+    OUT shared_blks_read int8,
+    OUT shared_blks_dirtied int8,
+    OUT shared_blks_written int8,
+    OUT local_blks_hit int8,
+    OUT local_blks_read int8,
+    OUT local_blks_dirtied int8,
+    OUT local_blks_written int8,
+    OUT temp_blks_read int8,
+    OUT temp_blks_written int8,
+    OUT shared_blk_read_time float8,
+    OUT shared_blk_write_time float8,
+    OUT local_blk_read_time float8,
+    OUT local_blk_write_time float8,
+    OUT temp_blk_read_time float8,
+    OUT temp_blk_write_time float8,
+    OUT wal_records int8,
+    OUT wal_fpi int8,
+    OUT wal_bytes numeric,
+    OUT jit_functions int8,
+    OUT jit_generation_time float8,
+    OUT jit_inlining_count int8,
+    OUT jit_inlining_time float8,
+    OUT jit_optimization_count int8,
+    OUT jit_optimization_time float8,
+    OUT jit_emission_count int8,
+    OUT jit_emission_time float8,
+    OUT jit_deform_count int8,
+    OUT jit_deform_time float8,
+    OUT parallel_workers_to_launch int8,
+    OUT parallel_workers_launched int8,
+    OUT stats_since timestamp with time zone,
+    OUT minmax_stats_since timestamp with time zone
+)
+RETURNS SETOF record
+AS 'MODULE_PATHNAME', 'pg_stat_statements_1_12'
+LANGUAGE C STRICT VOLATILE PARALLEL SAFE;
+
+CREATE VIEW pg_stat_statements AS
+  SELECT * FROM pg_stat_statements(true);
+
+GRANT SELECT ON pg_stat_statements TO PUBLIC;
diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c
@@ -113,6 +113,7 @@ typedef enum pgssVersion
 	PGSS_V1_9,
 	PGSS_V1_10,
 	PGSS_V1_11,
+	PGSS_V1_12,
 } pgssVersion;
 
 typedef enum pgssStoreKind
@@ -204,6 +205,10 @@ typedef struct Counters
 	int64		jit_emission_count; /* number of times emission time has been
 									 * > 0 */
 	double		jit_emission_time;	/* total time to emit jit code */
+	int64		parallel_workers_to_launch; /* # of parallel workers planned
+											 * to be launched */
+	int64		parallel_workers_launched;	/* # of parallel workers actually
+											 * launched */
 } Counters;
 
 /*
@@ -317,6 +322,7 @@ PG_FUNCTION_INFO_V1(pg_stat_statements_1_8);
 PG_FUNCTION_INFO_V1(pg_stat_statements_1_9);
 PG_FUNCTION_INFO_V1(pg_stat_statements_1_10);
 PG_FUNCTION_INFO_V1(pg_stat_statements_1_11);
+PG_FUNCTION_INFO_V1(pg_stat_statements_1_12);
 PG_FUNCTION_INFO_V1(pg_stat_statements);
 PG_FUNCTION_INFO_V1(pg_stat_statements_info);
 
@@ -347,7 +353,9 @@ static void pgss_store(const char *query, uint64 queryId,
 					   const BufferUsage *bufusage,
 					   const WalUsage *walusage,
 					   const struct JitInstrumentation *jitusage,
-					   JumbleState *jstate);
+					   JumbleState *jstate,
+					   int parallel_workers_to_launch,
+					   int parallel_workers_launched);
 static void pg_stat_statements_internal(FunctionCallInfo fcinfo,
 										pgssVersion api_version,
 										bool showtext);
@@ -867,7 +875,9 @@ pgss_post_parse_analyze(ParseState *pstate, Query *query, JumbleState *jstate)
 				   NULL,
 				   NULL,
 				   NULL,
-				   jstate);
+				   jstate,
+				   0,
+				   0);
 }
 
 /*
@@ -945,7 +955,9 @@ pgss_planner(Query *parse,
 				   &bufusage,
 				   &walusage,
 				   NULL,
-				   NULL);
+				   NULL,
+				   0,
+				   0);
 	}
 	else
 	{
@@ -1078,7 +1090,9 @@ pgss_ExecutorEnd(QueryDesc *queryDesc)
 				   &queryDesc->totaltime->bufusage,
 				   &queryDesc->totaltime->walusage,
 				   queryDesc->estate->es_jit ? &queryDesc->estate->es_jit->instr : NULL,
-				   NULL);
+				   NULL,
+				   queryDesc->estate->es_parallel_workers_to_launch,
+				   queryDesc->estate->es_parallel_workers_launched);
 	}
 
 	if (prev_ExecutorEnd)
@@ -1209,7 +1223,9 @@ pgss_ProcessUtility(PlannedStmt *pstmt, const char *queryString,
 				   &bufusage,
 				   &walusage,
 				   NULL,
-				   NULL);
+				   NULL,
+				   0,
+				   0);
 	}
 	else
 	{
@@ -1270,7 +1286,9 @@ pgss_store(const char *query, uint64 queryId,
 		   const BufferUsage *bufusage,
 		   const WalUsage *walusage,
 		   const struct JitInstrumentation *jitusage,
-		   JumbleState *jstate)
+		   JumbleState *jstate,
+		   int parallel_workers_to_launch,
+		   int parallel_workers_launched)
 {
 	pgssHashKey key;
 	pgssEntry  *entry;
@@ -1473,6 +1491,10 @@ pgss_store(const char *query, uint64 queryId,
 			entry->counters.jit_emission_time += INSTR_TIME_GET_MILLISEC(jitusage->emission_counter);
 		}
 
+		/* parallel worker counters */
+		entry->counters.parallel_workers_to_launch += parallel_workers_to_launch;
+		entry->counters.parallel_workers_launched += parallel_workers_launched;
+
 		SpinLockRelease(&entry->mutex);
 	}
 
@@ -1539,7 +1561,8 @@ pg_stat_statements_reset(PG_FUNCTION_ARGS)
 #define PG_STAT_STATEMENTS_COLS_V1_9	33
 #define PG_STAT_STATEMENTS_COLS_V1_10	43
 #define PG_STAT_STATEMENTS_COLS_V1_11	49
-#define PG_STAT_STATEMENTS_COLS			49	/* maximum of above */
+#define PG_STAT_STATEMENTS_COLS_V1_12	51
+#define PG_STAT_STATEMENTS_COLS			51	/* maximum of above */
 
 /*
  * Retrieve statement statistics.
@@ -1551,6 +1574,16 @@ pg_stat_statements_reset(PG_FUNCTION_ARGS)
  * expected API version is identified by embedding it in the C name of the
  * function.  Unfortunately we weren't bright enough to do that for 1.1.
  */
+Datum
+pg_stat_statements_1_12(PG_FUNCTION_ARGS)
+{
+	bool		showtext = PG_GETARG_BOOL(0);
+
+	pg_stat_statements_internal(fcinfo, PGSS_V1_12, showtext);
+
+	return (Datum) 0;
+}
+
 Datum
 pg_stat_statements_1_11(PG_FUNCTION_ARGS)
 {
@@ -1695,6 +1728,10 @@ pg_stat_statements_internal(FunctionCallInfo fcinfo,
 			if (api_version != PGSS_V1_11)
 				elog(ERROR, "incorrect number of output arguments");
 			break;
+		case PG_STAT_STATEMENTS_COLS_V1_12:
+			if (api_version != PGSS_V1_12)
+				elog(ERROR, "incorrect number of output arguments");
+			break;
 		default:
 			elog(ERROR, "incorrect number of output arguments");
 	}
@@ -1932,6 +1969,14 @@ pg_stat_statements_internal(FunctionCallInfo fcinfo,
 		{
 			values[i++] = Int64GetDatumFast(tmp.jit_deform_count);
 			values[i++] = Float8GetDatumFast(tmp.jit_deform_time);
+		}
+		if (api_version >= PGSS_V1_12)
+		{
+			values[i++] = Int64GetDatumFast(tmp.parallel_workers_to_launch);
+			values[i++] = Int64GetDatumFast(tmp.parallel_workers_launched);
+		}
+		if (api_version >= PGSS_V1_11)
+		{
 			values[i++] = TimestampTzGetDatum(stats_since);
 			values[i++] = TimestampTzGetDatum(minmax_stats_since);
 		}
@@ -1944,6 +1989,7 @@ pg_stat_statements_internal(FunctionCallInfo fcinfo,
 					 api_version == PGSS_V1_9 ? PG_STAT_STATEMENTS_COLS_V1_9 :
 					 api_version == PGSS_V1_10 ? PG_STAT_STATEMENTS_COLS_V1_10 :
 					 api_version == PGSS_V1_11 ? PG_STAT_STATEMENTS_COLS_V1_11 :
+					 api_version == PGSS_V1_12 ? PG_STAT_STATEMENTS_COLS_V1_12 :
 					 -1 /* fail if you forget to update this assert */ ));
 
 		tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
diff --git a/contrib/pg_stat_statements/pg_stat_statements.control b/contrib/pg_stat_statements/pg_stat_statements.control
@@ -1,5 +1,5 @@
 # pg_stat_statements extension
 comment = 'track planning and execution statistics of all SQL statements executed'
-default_version = '1.11'
+default_version = '1.12'
 module_pathname = '$libdir/pg_stat_statements'
 relocatable = true
diff --git a/contrib/pg_stat_statements/sql/oldextversions.sql b/contrib/pg_stat_statements/sql/oldextversions.sql
@@ -58,4 +58,9 @@ SELECT count(*) > 0 AS has_data FROM pg_stat_statements;
 SELECT pg_get_functiondef('pg_stat_statements_reset'::regproc);
 SELECT pg_stat_statements_reset() IS NOT NULL AS t;
 
+-- New functions and views for pg_stat_statements in 1.12
+AlTER EXTENSION pg_stat_statements UPDATE TO '1.12';
+\d pg_stat_statements
+SELECT count(*) > 0 AS has_data FROM pg_stat_statements;
+
 DROP EXTENSION pg_stat_statements;
diff --git a/contrib/pg_stat_statements/sql/parallel.sql b/contrib/pg_stat_statements/sql/parallel.sql
diff --git a/doc/src/sgml/pgstatstatements.sgml b/doc/src/sgml/pgstatstatements.sgml
