From 809c9b48f4bdd11dfc088f6d0b9a6c57936c32ca Mon Sep 17 00:00:00 2001 From: Andres Freund Date: Tue, 30 Apr 2019 17:45:32 -0700 Subject: [PATCH] Run catalog reindexing test from 3dbb317d32 serially, to avoid deadlocks. The tests turn out to cause deadlocks in some circumstances. Fairly reproducibly so with -DRELCACHE_FORCE_RELEASE -DCATCACHE_FORCE_RELEASE. Some of the deadlocks may be hard to fix without disproportionate measures, but others probably should be fixed - but not in 12. We discussed removing the new tests until we can fix the issues underlying the deadlocks, but results from buildfarm animal markhor (which runs with CLOBBER_CACHE_ALWAYS) indicates that there might be a more severe, as of yet undiagnosed, issue (including on stable branches) with reindexing catalogs. The failure is: ERROR: could not read block 0 in file "base/16384/28025": read only 0 of 8192 bytes Therefore it seems advisable to keep the tests. It's not certain that running the tests in isolation removes the risk of deadlocks. It's possible that additional locks are needed to protect against a concurrent auto-analyze or such. Per discussion with Tom Lane. Discussion: https://postgr.es/m/28926.1556664156@sss.pgh.pa.us Backpatch: 9.4-, like 3dbb317d3 --- src/test/regress/expected/create_index.out | 18 ---------- src/test/regress/expected/reindex_catalog.out | 33 +++++++++++++++++ src/test/regress/parallel_schedule | 5 +++ src/test/regress/serial_schedule | 1 + src/test/regress/sql/create_index.sql | 21 ----------- src/test/regress/sql/reindex_catalog.sql | 36 +++++++++++++++++++ 6 files changed, 75 insertions(+), 39 deletions(-) create mode 100644 src/test/regress/expected/reindex_catalog.out create mode 100644 src/test/regress/sql/reindex_catalog.sql diff --git a/src/test/regress/expected/create_index.out b/src/test/regress/expected/create_index.out index ef8c8cd654..326dc44177 100644 --- a/src/test/regress/expected/create_index.out +++ b/src/test/regress/expected/create_index.out @@ -1939,24 +1939,6 @@ INFO: index "reindex_verbose_pkey" was reindexed \set VERBOSITY default DROP TABLE reindex_verbose; -- --- check that system tables can be reindexed --- --- whole tables -REINDEX TABLE pg_class; -- mapped, non-shared, critical -REINDEX TABLE pg_index; -- non-mapped, non-shared, critical -REINDEX TABLE pg_operator; -- non-mapped, non-shared, critical -REINDEX TABLE pg_database; -- mapped, shared, critical -REINDEX TABLE pg_shdescription; -- mapped, shared non-critical --- Check that individual system indexes can be reindexed. That's a bit --- different from the entire-table case because reindex_relation --- treats e.g. pg_class special. -REINDEX INDEX pg_class_oid_index; -- mapped, non-shared, critical -REINDEX INDEX pg_class_relname_nsp_index; -- mapped, non-shared, non-critical -REINDEX INDEX pg_index_indexrelid_index; -- non-mapped, non-shared, critical -REINDEX INDEX pg_index_indrelid_index; -- non-mapped, non-shared, non-critical -REINDEX INDEX pg_database_oid_index; -- mapped, shared, critical -REINDEX INDEX pg_shdescription_o_c_index; -- mapped, shared, non-critical --- -- REINDEX CONCURRENTLY -- CREATE TABLE concur_reindex_tab (c1 int); diff --git a/src/test/regress/expected/reindex_catalog.out b/src/test/regress/expected/reindex_catalog.out new file mode 100644 index 0000000000..142616fccb --- /dev/null +++ b/src/test/regress/expected/reindex_catalog.out @@ -0,0 +1,33 @@ +-- +-- Check that system tables can be reindexed. +-- +-- Note that this test currently has to run without parallel tests +-- being scheduled, as currently reindex catalog tables can cause +-- deadlocks: +-- +-- * The lock upgrade between the ShareLock acquired for the reindex +-- and RowExclusiveLock needed for pg_class/pg_index locks can +-- trigger deadlocks. +-- +-- * The uniqueness checks performed when reindexing a unique/primary +-- key index possibly need to wait for the transaction of a +-- about-to-deleted row in pg_class to commit. That can cause +-- deadlocks because, in contrast to user tables, locks on catalog +-- tables are routinely released before commit - therefore the lock +-- held for reindexing doesn't guarantee that no running transaction +-- performed modifications in the table underlying the index. +-- Check reindexing of whole tables +REINDEX TABLE pg_class; -- mapped, non-shared, critical +REINDEX TABLE pg_index; -- non-mapped, non-shared, critical +REINDEX TABLE pg_operator; -- non-mapped, non-shared, critical +REINDEX TABLE pg_database; -- mapped, shared, critical +REINDEX TABLE pg_shdescription; -- mapped, shared non-critical +-- Check that individual system indexes can be reindexed. That's a bit +-- different from the entire-table case because reindex_relation +-- treats e.g. pg_class special. +REINDEX INDEX pg_class_oid_index; -- mapped, non-shared, critical +REINDEX INDEX pg_class_relname_nsp_index; -- mapped, non-shared, non-critical +REINDEX INDEX pg_index_indexrelid_index; -- non-mapped, non-shared, critical +REINDEX INDEX pg_index_indrelid_index; -- non-mapped, non-shared, non-critical +REINDEX INDEX pg_database_oid_index; -- mapped, shared, critical +REINDEX INDEX pg_shdescription_o_c_index; -- mapped, shared, non-critical diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index 8229e10909..3b7759b6fa 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -52,6 +52,11 @@ test: create_misc create_operator create_procedure # These depend on create_misc and create_operator test: create_index create_index_spgist create_view index_including index_including_gist +# ---------- +# Has to run in isolation, due to deadlock risk +# ---------- +test: reindex_catalog + # ---------- # Another group of parallel tests # ---------- diff --git a/src/test/regress/serial_schedule b/src/test/regress/serial_schedule index 9839087faa..43523c6fc6 100644 --- a/src/test/regress/serial_schedule +++ b/src/test/regress/serial_schedule @@ -67,6 +67,7 @@ test: create_index_spgist test: create_view test: index_including test: index_including_gist +test: reindex_catalog test: create_aggregate test: create_function_3 test: create_cast diff --git a/src/test/regress/sql/create_index.sql b/src/test/regress/sql/create_index.sql index f6f2d7c14b..f29b8ca826 100644 --- a/src/test/regress/sql/create_index.sql +++ b/src/test/regress/sql/create_index.sql @@ -747,27 +747,6 @@ REINDEX (VERBOSE) TABLE reindex_verbose; \set VERBOSITY default DROP TABLE reindex_verbose; --- --- check that system tables can be reindexed --- - --- whole tables -REINDEX TABLE pg_class; -- mapped, non-shared, critical -REINDEX TABLE pg_index; -- non-mapped, non-shared, critical -REINDEX TABLE pg_operator; -- non-mapped, non-shared, critical -REINDEX TABLE pg_database; -- mapped, shared, critical -REINDEX TABLE pg_shdescription; -- mapped, shared non-critical - --- Check that individual system indexes can be reindexed. That's a bit --- different from the entire-table case because reindex_relation --- treats e.g. pg_class special. -REINDEX INDEX pg_class_oid_index; -- mapped, non-shared, critical -REINDEX INDEX pg_class_relname_nsp_index; -- mapped, non-shared, non-critical -REINDEX INDEX pg_index_indexrelid_index; -- non-mapped, non-shared, critical -REINDEX INDEX pg_index_indrelid_index; -- non-mapped, non-shared, non-critical -REINDEX INDEX pg_database_oid_index; -- mapped, shared, critical -REINDEX INDEX pg_shdescription_o_c_index; -- mapped, shared, non-critical - -- -- REINDEX CONCURRENTLY -- diff --git a/src/test/regress/sql/reindex_catalog.sql b/src/test/regress/sql/reindex_catalog.sql new file mode 100644 index 0000000000..2180ee5791 --- /dev/null +++ b/src/test/regress/sql/reindex_catalog.sql @@ -0,0 +1,36 @@ +-- +-- Check that system tables can be reindexed. +-- +-- Note that this test currently has to run without parallel tests +-- being scheduled, as currently reindex catalog tables can cause +-- deadlocks: +-- +-- * The lock upgrade between the ShareLock acquired for the reindex +-- and RowExclusiveLock needed for pg_class/pg_index locks can +-- trigger deadlocks. +-- +-- * The uniqueness checks performed when reindexing a unique/primary +-- key index possibly need to wait for the transaction of a +-- about-to-deleted row in pg_class to commit. That can cause +-- deadlocks because, in contrast to user tables, locks on catalog +-- tables are routinely released before commit - therefore the lock +-- held for reindexing doesn't guarantee that no running transaction +-- performed modifications in the table underlying the index. + + +-- Check reindexing of whole tables +REINDEX TABLE pg_class; -- mapped, non-shared, critical +REINDEX TABLE pg_index; -- non-mapped, non-shared, critical +REINDEX TABLE pg_operator; -- non-mapped, non-shared, critical +REINDEX TABLE pg_database; -- mapped, shared, critical +REINDEX TABLE pg_shdescription; -- mapped, shared non-critical + +-- Check that individual system indexes can be reindexed. That's a bit +-- different from the entire-table case because reindex_relation +-- treats e.g. pg_class special. +REINDEX INDEX pg_class_oid_index; -- mapped, non-shared, critical +REINDEX INDEX pg_class_relname_nsp_index; -- mapped, non-shared, non-critical +REINDEX INDEX pg_index_indexrelid_index; -- non-mapped, non-shared, critical +REINDEX INDEX pg_index_indrelid_index; -- non-mapped, non-shared, non-critical +REINDEX INDEX pg_database_oid_index; -- mapped, shared, critical +REINDEX INDEX pg_shdescription_o_c_index; -- mapped, shared, non-critical