Attached is a patch that adds a few injection points for hash
aggregation.
A couple questions on the injection points framework:
* The patch allows forcing the partition fan-out to one. I could
imagine forcing it to a specific value, is there a way to do that?
* The injection_points extension offers the concept of a "local"
injection point. While that makes sense for the callback function, it
doesn't make sense when using the "local_var = 123" style, because that
will happen regardless of the condition, right?
* Callbacks are given very little context from the injection point
itself, so it's hard for me to imagine what a callback might do other
than logging the name of the injection point or waiting (as the
extension implements). What else would callbacks be good for?
--
Jeff Davis
PostgreSQL Contributor Team - AWS
From f98ee96920de46a5bba4da4079395d5e959472a4 Mon Sep 17 00:00:00 2001
From: Jeff Davis <j...@j-davis.com>
Date: Sun, 2 Feb 2025 05:26:58 -0800
Subject: [PATCH v1] Add injection points for hash aggregation.
---
src/backend/executor/nodeAgg.c | 20 ++++++
src/test/modules/injection_points/Makefile | 2 +-
.../injection_points/expected/hashagg.out | 68 +++++++++++++++++++
src/test/modules/injection_points/meson.build | 1 +
.../modules/injection_points/sql/hashagg.sql | 22 ++++++
5 files changed, 112 insertions(+), 1 deletion(-)
create mode 100644 src/test/modules/injection_points/expected/hashagg.out
create mode 100644 src/test/modules/injection_points/sql/hashagg.sql
diff --git a/src/backend/executor/nodeAgg.c b/src/backend/executor/nodeAgg.c
index 3005b5c0e3b..267a3229145 100644
--- a/src/backend/executor/nodeAgg.c
+++ b/src/backend/executor/nodeAgg.c
@@ -269,6 +269,7 @@
#include "utils/datum.h"
#include "utils/dynahash.h"
#include "utils/expandeddatum.h"
+#include "utils/injection_point.h"
#include "utils/logtape.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
@@ -1489,6 +1490,14 @@ build_hash_tables(AggState *aggstate)
perhash->aggnode->numGroups,
memory);
+#ifdef USE_INJECTION_POINTS
+ if (IS_INJECTION_POINT_ATTACHED("hash-aggregate-oversize-table"))
+ {
+ nbuckets = memory / sizeof(TupleHashEntryData);
+ INJECTION_POINT_CACHED("hash-aggregate-oversize-table");
+ }
+#endif
+
build_hash_table(aggstate, setno, nbuckets);
}
@@ -1881,6 +1890,7 @@ hash_agg_check_limits(AggState *aggstate)
static void
hash_agg_enter_spill_mode(AggState *aggstate)
{
+ INJECTION_POINT("hash-aggregate-enter-spill-mode");
aggstate->hash_spill_mode = true;
hashagg_recompile_expressions(aggstate, aggstate->table_filled, true);
@@ -2652,6 +2662,7 @@ agg_refill_hash_table(AggState *aggstate)
*/
hashagg_recompile_expressions(aggstate, true, true);
+ INJECTION_POINT("hash-aggregate-process-batch");
for (;;)
{
TupleTableSlot *spillslot = aggstate->hash_spill_rslot;
@@ -2900,6 +2911,15 @@ hashagg_spill_init(HashAggSpill *spill, LogicalTapeSet *tapeset, int used_bits,
npartitions = hash_choose_num_partitions(input_groups, hashentrysize,
used_bits, &partition_bits);
+#ifdef USE_INJECTION_POINTS
+ if (IS_INJECTION_POINT_ATTACHED("hash-aggregate-single-partition"))
+ {
+ npartitions = 1;
+ partition_bits = 0;
+ INJECTION_POINT_CACHED("hash-aggregate-single-partition");
+ }
+#endif
+
spill->partitions = palloc0(sizeof(LogicalTape *) * npartitions);
spill->ntuples = palloc0(sizeof(int64) * npartitions);
spill->hll_card = palloc0(sizeof(hyperLogLogState) * npartitions);
diff --git a/src/test/modules/injection_points/Makefile b/src/test/modules/injection_points/Makefile
index 4f0161fd33a..e680991f8d4 100644
--- a/src/test/modules/injection_points/Makefile
+++ b/src/test/modules/injection_points/Makefile
@@ -11,7 +11,7 @@ EXTENSION = injection_points
DATA = injection_points--1.0.sql
PGFILEDESC = "injection_points - facility for injection points"
-REGRESS = injection_points reindex_conc
+REGRESS = injection_points hashagg reindex_conc
REGRESS_OPTS = --dlpath=$(top_builddir)/src/test/regress
ISOLATION = basic inplace syscache-update-pruned
diff --git a/src/test/modules/injection_points/expected/hashagg.out b/src/test/modules/injection_points/expected/hashagg.out
new file mode 100644
index 00000000000..795a53210c4
--- /dev/null
+++ b/src/test/modules/injection_points/expected/hashagg.out
@@ -0,0 +1,68 @@
+-- Test for hash aggregation
+CREATE EXTENSION injection_points;
+SELECT injection_points_set_local();
+ injection_points_set_local
+----------------------------
+
+(1 row)
+
+SELECT injection_points_attach('hash-aggregate-enter-spill-mode', 'notice');
+ injection_points_attach
+-------------------------
+
+(1 row)
+
+SELECT injection_points_attach('hash-aggregate-process-batch', 'notice');
+ injection_points_attach
+-------------------------
+
+(1 row)
+
+SELECT injection_points_attach('hash-aggregate-single-partition', 'notice');
+ injection_points_attach
+-------------------------
+
+(1 row)
+
+CREATE TABLE hashagg_ij(x INTEGER);
+INSERT INTO hashagg_ij SELECT g FROM generate_series(1,100000) g;
+SET max_parallel_workers=0;
+SET max_parallel_workers_per_gather=0;
+SET enable_sort=FALSE;
+SET work_mem='1MB';
+SET hash_mem_multiplier=1.0;
+SELECT COUNT(*) FROM (SELECT DISTINCT x FROM hashagg_ij) s;
+NOTICE: notice triggered for injection point hash-aggregate-enter-spill-mode
+NOTICE: notice triggered for injection point hash-aggregate-single-partition
+NOTICE: notice triggered for injection point hash-aggregate-process-batch
+NOTICE: notice triggered for injection point hash-aggregate-enter-spill-mode
+NOTICE: notice triggered for injection point hash-aggregate-single-partition
+NOTICE: notice triggered for injection point hash-aggregate-process-batch
+NOTICE: notice triggered for injection point hash-aggregate-enter-spill-mode
+NOTICE: notice triggered for injection point hash-aggregate-single-partition
+NOTICE: notice triggered for injection point hash-aggregate-process-batch
+NOTICE: notice triggered for injection point hash-aggregate-enter-spill-mode
+NOTICE: notice triggered for injection point hash-aggregate-single-partition
+NOTICE: notice triggered for injection point hash-aggregate-process-batch
+NOTICE: notice triggered for injection point hash-aggregate-enter-spill-mode
+NOTICE: notice triggered for injection point hash-aggregate-single-partition
+NOTICE: notice triggered for injection point hash-aggregate-process-batch
+NOTICE: notice triggered for injection point hash-aggregate-enter-spill-mode
+NOTICE: notice triggered for injection point hash-aggregate-single-partition
+NOTICE: notice triggered for injection point hash-aggregate-process-batch
+NOTICE: notice triggered for injection point hash-aggregate-enter-spill-mode
+NOTICE: notice triggered for injection point hash-aggregate-single-partition
+NOTICE: notice triggered for injection point hash-aggregate-process-batch
+NOTICE: notice triggered for injection point hash-aggregate-enter-spill-mode
+NOTICE: notice triggered for injection point hash-aggregate-single-partition
+NOTICE: notice triggered for injection point hash-aggregate-process-batch
+NOTICE: notice triggered for injection point hash-aggregate-enter-spill-mode
+NOTICE: notice triggered for injection point hash-aggregate-single-partition
+NOTICE: notice triggered for injection point hash-aggregate-process-batch
+ count
+--------
+ 100000
+(1 row)
+
+DROP TABLE hashagg_ij;
+DROP EXTENSION injection_points;
diff --git a/src/test/modules/injection_points/meson.build b/src/test/modules/injection_points/meson.build
index 259045e5c2d..d61149712fd 100644
--- a/src/test/modules/injection_points/meson.build
+++ b/src/test/modules/injection_points/meson.build
@@ -35,6 +35,7 @@ tests += {
'regress': {
'sql': [
'injection_points',
+ 'hashagg',
'reindex_conc',
],
'regress_args': ['--dlpath', meson.build_root() / 'src/test/regress'],
diff --git a/src/test/modules/injection_points/sql/hashagg.sql b/src/test/modules/injection_points/sql/hashagg.sql
new file mode 100644
index 00000000000..c852c590771
--- /dev/null
+++ b/src/test/modules/injection_points/sql/hashagg.sql
@@ -0,0 +1,22 @@
+-- Test for hash aggregation
+CREATE EXTENSION injection_points;
+
+SELECT injection_points_set_local();
+
+SELECT injection_points_attach('hash-aggregate-enter-spill-mode', 'notice');
+SELECT injection_points_attach('hash-aggregate-process-batch', 'notice');
+SELECT injection_points_attach('hash-aggregate-single-partition', 'notice');
+
+CREATE TABLE hashagg_ij(x INTEGER);
+INSERT INTO hashagg_ij SELECT g FROM generate_series(1,100000) g;
+
+SET max_parallel_workers=0;
+SET max_parallel_workers_per_gather=0;
+SET enable_sort=FALSE;
+SET work_mem='1MB';
+SET hash_mem_multiplier=1.0;
+
+SELECT COUNT(*) FROM (SELECT DISTINCT x FROM hashagg_ij) s;
+
+DROP TABLE hashagg_ij;
+DROP EXTENSION injection_points;
--
2.34.1
