Hello hackers, I spotted a very rare test failure (a single one in two years, at least) generated by basilisk: tidscan ... FAILED 34 ms ...diff -U3 /mnt/build/REL_14_STABLE/pgsql.build/../pgsql/src/test/regress/expected/tidscan.out /mnt/build/REL_14_STABLE/pgsql.build/src/test/regress/results/tidscan.out
--- /mnt/build/REL_14_STABLE/pgsql.build/../pgsql/src/test/regress/expected/tidscan.out +++ /mnt/build/REL_14_STABLE/pgsql.build/src/test/regress/results/tidscan.out @@ -242,10 +242,10 @@ ---------------------------------------- Aggregate -> Hash Join - Hash Cond: (t1.ctid = t2.ctid) - -> Seq Scan on tenk1 t1 + Hash Cond: (t2.ctid = t1.ctid) + -> Seq Scan on tenk1 t2 -> Hash - -> Seq Scan on tenk1 t2 + -> Seq Scan on tenk1 t1 (6 rows)
SELECT count(*) FROM tenk1 t1 JOIN tenk1 t2 ON t1.ctid = t2.ctid; and was intrigued enough to find a reliable reproducer for it. With the following modification: --- a/src/backend/optimizer/util/plancat.c +++ b/src/backend/optimizer/util/plancat.c @@ -188,6 +188,7 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent, estimate_rel_size(relation, rel->attr_widths - rel->min_attr, &rel->pages, &rel->tuples, &rel->allvisfrac); +char *name = get_rel_name(relationObjectId); if (name != NULL && strcmp(name, "tenk1") == 0) pg_usleep(100000); /* Retrieve the parallel_workers reloption, or -1 if not set. */ rel->rel_parallel_workers = RelationGetParallelWorkers(relation, -1); and test: tidscan analyze in parallel_schedule (the full patch is attached), I get: parallel group (2 tests): analyze tidscan tidscan ... FAILED 900 ms analyze ... ok 63 ms (The basilisk's log contain no autovacuum messages, but I guess it was automatic analyze that processed tenk1 in the very lucky moment.) Given the current statistics, we won't see failures of this ilk anymore, because it is not reproduced in REL_15_STABLE..master, due to 74388a1ac + 4496020e6, which resulted in a different reltuples value returned for tenk1 during sanity_check/VACUUM and that indirectly affected the plan change. [1] https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=basilisk&dt=2026-06-15%2006%3A07%3A09 Best regards, Alexander
diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c index e7856b54bbb..6df0ed4da36 100644 --- a/src/backend/optimizer/util/plancat.c +++ b/src/backend/optimizer/util/plancat.c @@ -167,6 +167,7 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent, estimate_rel_size(relation, rel->attr_widths - rel->min_attr, &rel->pages, &rel->tuples, &rel->allvisfrac); +char *name = get_rel_name(relationObjectId); if (name != NULL && strcmp(name, "tenk1") == 0) pg_usleep(100000); /* Retrieve the parallel_workers reloption, or -1 if not set. */ rel->rel_parallel_workers = RelationGetParallelWorkers(relation, -1); diff --git a/src/test/regress/expected/analyze.out b/src/test/regress/expected/analyze.out new file mode 100644 index 00000000000..a0b9c748e86 --- /dev/null +++ b/src/test/regress/expected/analyze.out @@ -0,0 +1 @@ +ANALYZE tenk1; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index 52ef93828fa..68f293510f0 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -86,7 +86,9 @@ test: brin_bloom brin_multi # ---------- # Another group of parallel tests # ---------- -test: create_table_like alter_generic alter_operator misc async dbsize misc_functions sysviews tsrf tid tidscan tidrangescan collate.icu.utf8 incremental_sort +test: create_table_like alter_generic alter_operator misc async dbsize misc_functions sysviews tsrf tid tidrangescan collate.icu.utf8 incremental_sort + +test: tidscan analyze # rules cannot run concurrently with any test that creates # a view or rule in the public schema diff --git a/src/test/regress/sql/analyze.sql b/src/test/regress/sql/analyze.sql new file mode 100644 index 00000000000..a0b9c748e86 --- /dev/null +++ b/src/test/regress/sql/analyze.sql @@ -0,0 +1 @@ +ANALYZE tenk1;
