Instrument usage stack v7

contrib/auto_explain/auto_explain.c

@@ -305,19 +305,9 @@ explain_ExecutorStart(QueryDesc *queryDesc, int eflags)
 
 	if (auto_explain_enabled())
 	{
-		/*
-		 * Set up to track total elapsed time in ExecutorRun.  Make sure the
-		 * space is allocated in the per-query context so it will go away at
-		 * ExecutorEnd.
-		 */
+		/* Set up to track total elapsed time in ExecutorRun. */
 		if (queryDesc->totaltime == NULL)
-		{
-			MemoryContext oldcxt;
-
-			oldcxt = MemoryContextSwitchTo(queryDesc->estate->es_query_cxt);
-			queryDesc->totaltime = InstrAlloc(1, INSTRUMENT_ALL, false);
-			MemoryContextSwitchTo(oldcxt);
-		}
+			queryDesc->totaltime = InstrAlloc(INSTRUMENT_ALL);
 	}
 }
 
@@ -381,12 +371,6 @@ explain_ExecutorEnd(QueryDesc *queryDesc)
 		 */
 		oldcxt = MemoryContextSwitchTo(queryDesc->estate->es_query_cxt);
 
-		/*
-		 * Make sure stats accumulation is done.  (Note: it's okay if several
-		 * levels of hook all do this.)
-		 */
-		InstrEndLoop(queryDesc->totaltime);
-
 		/* Log plan if duration is exceeded. */
 		msec = INSTR_TIME_GET_MILLISEC(queryDesc->totaltime->total);
 		if (msec >= auto_explain_log_min_duration)

contrib/meson.build

@@ -50,6 +50,7 @@ subdir('pg_logicalinspect')
 subdir('pg_overexplain')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
+subdir('pg_session_buffer_usage')
 subdir('pg_stat_statements')
 subdir('pgstattuple')
 subdir('pg_surgery')

contrib/pg_session_buffer_usage/Makefile

@@ -0,0 +1,23 @@
+# contrib/pg_session_buffer_usage/Makefile
+
+MODULE_big = pg_session_buffer_usage
+OBJS = \
+	$(WIN32RES) \
+	pg_session_buffer_usage.o
+
+EXTENSION = pg_session_buffer_usage
+DATA = pg_session_buffer_usage--1.0.sql
+PGFILEDESC = "pg_session_buffer_usage - show buffer usage statistics for the current session"
+
+REGRESS = pg_session_buffer_usage
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_session_buffer_usage
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif

contrib/pg_session_buffer_usage/expected/pg_session_buffer_usage.out

@@ -0,0 +1,283 @@
+LOAD 'pg_session_buffer_usage';
+CREATE EXTENSION pg_session_buffer_usage;
+-- Verify all columns are non-negative
+SELECT count(*) = 1 AS ok FROM pg_session_buffer_usage()
+WHERE shared_blks_hit >= 0 AND shared_blks_read >= 0
+  AND shared_blks_dirtied >= 0 AND shared_blks_written >= 0
+  AND local_blks_hit >= 0 AND local_blks_read >= 0
+  AND local_blks_dirtied >= 0 AND local_blks_written >= 0
+  AND temp_blks_read >= 0 AND temp_blks_written >= 0
+  AND shared_blk_read_time >= 0 AND shared_blk_write_time >= 0
+  AND local_blk_read_time >= 0 AND local_blk_write_time >= 0
+  AND temp_blk_read_time >= 0 AND temp_blk_write_time >= 0;
+ ok 
+----
+ t
+(1 row)
+
+-- Verify counters increase after buffer activity
+SELECT pg_session_buffer_usage_reset();
+ pg_session_buffer_usage_reset 
+-------------------------------
+
+(1 row)
+
+CREATE TEMP TABLE test_buf_activity (id int, data text);
+INSERT INTO test_buf_activity SELECT i, repeat('x', 100) FROM generate_series(1, 1000) AS i;
+SELECT count(*) FROM test_buf_activity;
+ count 
+-------
+  1000
+(1 row)
+
+SELECT local_blks_hit + local_blks_read > 0 AS blocks_increased
+FROM pg_session_buffer_usage();
+ blocks_increased 
+------------------
+ t
+(1 row)
+
+DROP TABLE test_buf_activity;
+-- Parallel query test
+CREATE TABLE par_dc_tab (a int, b char(200));
+INSERT INTO par_dc_tab SELECT i, repeat('x', 200) FROM generate_series(1, 5000) AS i;
+SELECT count(*) FROM par_dc_tab;
+ count 
+-------
+  5000
+(1 row)
+
+-- Measure serial scan delta (leader does all the work)
+SET max_parallel_workers_per_gather = 0;
+SELECT pg_session_buffer_usage_reset();
+ pg_session_buffer_usage_reset 
+-------------------------------
+
+(1 row)
+
+SELECT count(*) FROM par_dc_tab;
+ count 
+-------
+  5000
+(1 row)
+
+CREATE TEMP TABLE dc_serial_result AS
+SELECT shared_blks_hit AS serial_delta FROM pg_session_buffer_usage();
+-- Measure parallel scan delta with leader NOT participating in scanning.
+-- Workers do all table scanning; leader only runs the Gather node.
+SET parallel_setup_cost = 0;
+SET parallel_tuple_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET max_parallel_workers_per_gather = 2;
+SET parallel_leader_participation = off;
+SELECT pg_session_buffer_usage_reset();
+ pg_session_buffer_usage_reset 
+-------------------------------
+
+(1 row)
+
+SELECT count(*) FROM par_dc_tab;
+ count 
+-------
+  5000
+(1 row)
+
+-- Confirm we got a similar hit counter through parallel worker accumulation
+SELECT shared_blks_hit > s.serial_delta / 2 AND shared_blks_hit < s.serial_delta * 2
+       AS leader_buffers_match
+FROM pg_session_buffer_usage(), dc_serial_result s;
+ leader_buffers_match 
+----------------------
+ t
+(1 row)
+
+RESET parallel_setup_cost;
+RESET parallel_tuple_cost;
+RESET min_parallel_table_scan_size;
+RESET max_parallel_workers_per_gather;
+RESET parallel_leader_participation;
+DROP TABLE par_dc_tab, dc_serial_result;
+--
+-- Abort/exception tests: verify buffer usage survives various error paths.
+--
+-- Rolled-back divide-by-zero under EXPLAIN ANALYZE
+CREATE TEMP TABLE exc_tab (a int, b char(20));
+SELECT pg_session_buffer_usage_reset();
+ pg_session_buffer_usage_reset 
+-------------------------------
+
+(1 row)
+
+EXPLAIN (ANALYZE, BUFFERS, COSTS OFF)
+        WITH ins AS (INSERT INTO exc_tab VALUES (1, 'aaa') RETURNING a)
+        SELECT a / 0 FROM ins;
+ERROR:  division by zero
+SELECT local_blks_dirtied > 0 AS exception_buffers_visible
+FROM pg_session_buffer_usage();
+ exception_buffers_visible 
+---------------------------
+ t
+(1 row)
+
+DROP TABLE exc_tab;
+-- Unique constraint violation in regular query
+CREATE TEMP TABLE unique_tab (a int UNIQUE, b char(20));
+INSERT INTO unique_tab VALUES (1, 'first');
+SELECT pg_session_buffer_usage_reset();
+ pg_session_buffer_usage_reset 
+-------------------------------
+
+(1 row)
+
+INSERT INTO unique_tab VALUES (1, 'duplicate');
+ERROR:  duplicate key value violates unique constraint "unique_tab_a_key"
+DETAIL:  Key (a)=(1) already exists.
+SELECT local_blks_hit > 0 AS unique_violation_buffers_visible
+FROM pg_session_buffer_usage();
+ unique_violation_buffers_visible 
+----------------------------------
+ t
+(1 row)
+
+DROP TABLE unique_tab;
+-- Caught exception in PL/pgSQL subtransaction (BEGIN...EXCEPTION)
+CREATE TEMP TABLE subxact_tab (a int, b char(20));
+CREATE FUNCTION subxact_exc_func() RETURNS text AS $$
+BEGIN
+    BEGIN
+        EXECUTE 'EXPLAIN (ANALYZE, BUFFERS, COSTS OFF)
+            WITH ins AS (INSERT INTO subxact_tab VALUES (1, ''aaa'') RETURNING a)
+            SELECT a / 0 FROM ins';
+    EXCEPTION WHEN division_by_zero THEN
+        RETURN 'caught';
+    END;
+    RETURN 'not reached';
+END;
+$$ LANGUAGE plpgsql;
+SELECT pg_session_buffer_usage_reset();
+ pg_session_buffer_usage_reset 
+-------------------------------
+
+(1 row)
+
+SELECT subxact_exc_func();
+ subxact_exc_func 
+------------------
+ caught
+(1 row)
+
+SELECT local_blks_dirtied > 0 AS subxact_buffers_visible
+FROM pg_session_buffer_usage();
+ subxact_buffers_visible 
+-------------------------
+ t
+(1 row)
+
+DROP FUNCTION subxact_exc_func;
+DROP TABLE subxact_tab;
+-- Cursor (FOR loop) in aborted subtransaction; verify post-exception tracking
+CREATE TEMP TABLE cursor_tab (a int, b char(200));
+INSERT INTO cursor_tab SELECT i, repeat('x', 200) FROM generate_series(1, 500) AS i;
+CREATE FUNCTION cursor_exc_func() RETURNS text AS $$
+DECLARE
+    rec record;
+    cnt int := 0;
+BEGIN
+    BEGIN
+        FOR rec IN SELECT * FROM cursor_tab LOOP
+            cnt := cnt + 1;
+            IF cnt = 250 THEN
+                PERFORM 1 / 0;
+            END IF;
+        END LOOP;
+    EXCEPTION WHEN division_by_zero THEN
+        RETURN 'caught after ' || cnt || ' rows';
+    END;
+    RETURN 'not reached';
+END;
+$$ LANGUAGE plpgsql;
+SELECT pg_session_buffer_usage_reset();
+ pg_session_buffer_usage_reset 
+-------------------------------
+
+(1 row)
+
+SELECT cursor_exc_func();
+    cursor_exc_func    
+-----------------------
+ caught after 250 rows
+(1 row)
+
+SELECT local_blks_hit + local_blks_read > 0
+       AS cursor_subxact_buffers_visible
+FROM pg_session_buffer_usage();
+ cursor_subxact_buffers_visible 
+--------------------------------
+ t
+(1 row)
+
+DROP FUNCTION cursor_exc_func;
+DROP TABLE cursor_tab;
+-- Parallel worker abort: worker buffer activity is currently NOT propagated on abort.
+--
+-- When a parallel worker aborts, InstrEndParallelQuery and
+-- ExecParallelReportInstrumentation never run, so the worker's buffer
+-- activity is never written to shared memory, despite the information having been
+-- captured by the res owner release instrumentation handling.
+CREATE TABLE par_abort_tab (a int, b char(200));
+INSERT INTO par_abort_tab SELECT i, repeat('x', 200) FROM generate_series(1, 5000) AS i;
+-- Warm shared buffers so all reads become hits
+SELECT count(*) FROM par_abort_tab;
+ count 
+-------
+  5000
+(1 row)
+
+-- Measure serial scan delta as a reference (leader reads all blocks)
+SET max_parallel_workers_per_gather = 0;
+SELECT pg_session_buffer_usage_reset();
+ pg_session_buffer_usage_reset 
+-------------------------------
+
+(1 row)
+
+SELECT b::int2 FROM par_abort_tab WHERE a > 1000;
+ERROR:  invalid input syntax for type smallint: "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
+CREATE TABLE par_abort_serial_result AS
+SELECT shared_blks_hit AS serial_delta FROM pg_session_buffer_usage();
+-- Now force parallel with leader NOT participating in scanning
+SET parallel_setup_cost = 0;
+SET parallel_tuple_cost = 0;
+SET min_parallel_table_scan_size = 0;
+SET max_parallel_workers_per_gather = 2;
+SET parallel_leader_participation = off;
+SET debug_parallel_query = on; -- Ensure we get CONTEXT line consistently
+SELECT pg_session_buffer_usage_reset();
+ pg_session_buffer_usage_reset 
+-------------------------------
+
+(1 row)
+
+SELECT b::int2 FROM par_abort_tab WHERE a > 1000;
+ERROR:  invalid input syntax for type smallint: "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
+CONTEXT:  parallel worker
+RESET debug_parallel_query;
+-- Workers scanned the table but aborted before reporting stats back.
+-- The leader's delta should be much less than a serial scan, documenting
+-- that worker buffer activity is lost on abort.
+SELECT shared_blks_hit < s.serial_delta / 2
+       AS worker_abort_buffers_not_propagated
+FROM pg_session_buffer_usage(), par_abort_serial_result s;
+ worker_abort_buffers_not_propagated 
+-------------------------------------
+ t
+(1 row)
+
+RESET parallel_setup_cost;
+RESET parallel_tuple_cost;
+RESET min_parallel_table_scan_size;
+RESET max_parallel_workers_per_gather;
+RESET parallel_leader_participation;
+DROP TABLE par_abort_tab, par_abort_serial_result;
+-- Cleanup
+DROP EXTENSION pg_session_buffer_usage;

contrib/pg_session_buffer_usage/meson.build

@@ -0,0 +1,34 @@
+# Copyright (c) 2026, PostgreSQL Global Development Group
+
+pg_session_buffer_usage_sources = files(
+  'pg_session_buffer_usage.c',
+)
+
+if host_system == 'windows'
+  pg_session_buffer_usage_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_session_buffer_usage',
+    '--FILEDESC', 'pg_session_buffer_usage - show buffer usage statistics for the current session',])
+endif
+
+pg_session_buffer_usage = shared_module('pg_session_buffer_usage',
+  pg_session_buffer_usage_sources,
+  kwargs: contrib_mod_args,
+)
+contrib_targets += pg_session_buffer_usage
+
+install_data(
+  'pg_session_buffer_usage--1.0.sql',
+  'pg_session_buffer_usage.control',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_session_buffer_usage',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'regress': {
+    'sql': [
+      'pg_session_buffer_usage',
+    ],
+  },
+}