rdelaage
/
postgresql
mirror of https://git.postgresql.org/git/postgresql.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Split up a couple of long-running regression test scripts. 

The point of this change is to increase the potential for parallelism
while running the core regression tests.  Most people these days are
using parallel testing modes on multi-core machines, so we might as
well try a bit harder to keep multiple cores busy.  Hence, a test that
runs much longer than others in its parallel group is a candidate to
be sub-divided.

In this patch, create_index.sql and join.sql are split up.
I haven't changed the content of the tests in any way, just
moved them.

I moved create_index.sql's SP-GiST-related tests into a new script
create_index_spgist, and moved its btree multilevel page deletion test
over to the existing script btree_index.  (btree_index is a more natural
home for that test, and it's shorter than others in its parallel group,
so this doesn't hurt total runtime of that group.)  There might be
room for more aggressive splitting of create_index, but this is enough
to improve matters considerably.

Likewise, I moved join.sql's "exercises for the hash join code" into
a new file join_hash.  Those exercises contributed three-quarters of
the script's runtime.  Which might well be excessive ... but for the
moment, I'm satisfied with shoving them into a different parallel
group, where they can share runtime with the roughly-equally-lengthy
gist test.

(Note for anybody following along at home: there are interesting
interactions between the runtimes of create_index and anything running
in parallel with it, because the tests of CREATE INDEX CONCURRENTLY
in that file will repeatedly block waiting for concurrent transactions
to commit.  As committed in this patch, create_index and
create_index_spgist have roughly equal runtimes, but that's mostly an
artifact of forced synchronization of the CONCURRENTLY tests; when run
serially, create_index is much faster.  A followup patch will reduce
the runtime of create_index_spgist and thereby also create_index.)

Discussion: https://postgr.es/m/735.1554935715@sss.pgh.pa.us
This commit is contained in:
Tom Lane 2019-04-11 16:15:54 -04:00
parent 6726d8d476
commit 385d396b80
13 changed files with 3119 additions and 3085 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
src/test/regress/expected/btree_index.out
View File

@ -244,3 +244,21 @@ select reloptions from pg_class WHERE oid = 'btree_idx1'::regclass;
{vacuum_cleanup_index_scale_factor=70.0}
(1 row)
--
-- Test for multilevel page deletion
--
CREATE TABLE delete_test_table (a bigint, b bigint, c bigint, d bigint);
INSERT INTO delete_test_table SELECT i, 1, 2, 3 FROM generate_series(1,80000) i;
ALTER TABLE delete_test_table ADD PRIMARY KEY (a,b,c,d);
-- Delete most entries, and vacuum, deleting internal pages and creating "fast
-- root"
DELETE FROM delete_test_table WHERE a < 79990;
VACUUM delete_test_table;
--
-- Test B-tree insertion with a metapage update (XLOG_BTREE_INSERT_META
-- WAL record type). This happens when a "fast root" page is split. This
-- also creates coverage for nbtree FSM page recycling.
--
-- The vacuum above should've turned the leaf page into a fast root. We just
-- need to insert some rows to cause the fast root page to split.
INSERT INTO delete_test_table SELECT i, 1, 2, 3 FROM generate_series(1,1000) i;

1310
src/test/regress/expected/create_index.out
View File

File diff suppressed because it is too large Load Diff

1305
src/test/regress/expected/create_index_spgist.out Normal file
View File

File diff suppressed because it is too large Load Diff

880
src/test/regress/expected/join.out
View File

@ -6051,883 +6051,3 @@ where exists (select 1 from j3
(13 rows)
drop table j3;
--
-- exercises for the hash join code
--
begin;
set local min_parallel_table_scan_size = 0;
set local parallel_setup_cost = 0;
-- Extract bucket and batch counts from an explain analyze plan. In
-- general we can't make assertions about how many batches (or
-- buckets) will be required because it can vary, but we can in some
-- special cases and we can check for growth.
create or replace function find_hash(node json)
returns json language plpgsql
as
$$
declare
x json;
child json;
begin
if node->>'Node Type' = 'Hash' then
return node;
else
for child in select json_array_elements(node->'Plans')
loop
x := find_hash(child);
if x is not null then
return x;
end if;
end loop;
return null;
end if;
end;
$$;
create or replace function hash_join_batches(query text)
returns table (original int, final int) language plpgsql
as
$$
declare
whole_plan json;
hash_node json;
begin
for whole_plan in
execute 'explain (analyze, format ''json'') ' || query
loop
hash_node := find_hash(json_extract_path(whole_plan, '0', 'Plan'));
original := hash_node->>'Original Hash Batches';
final := hash_node->>'Hash Batches';
return next;
end loop;
end;
$$;
-- Make a simple relation with well distributed keys and correctly
-- estimated size.
create table simple as
select generate_series(1, 20000) AS id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa';
alter table simple set (parallel_workers = 2);
analyze simple;
-- Make a relation whose size we will under-estimate. We want stats
-- to say 1000 rows, but actually there are 20,000 rows.
create table bigger_than_it_looks as
select generate_series(1, 20000) as id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa';
alter table bigger_than_it_looks set (autovacuum_enabled = 'false');
alter table bigger_than_it_looks set (parallel_workers = 2);
analyze bigger_than_it_looks;
update pg_class set reltuples = 1000 where relname = 'bigger_than_it_looks';
-- Make a relation whose size we underestimate and that also has a
-- kind of skew that breaks our batching scheme. We want stats to say
-- 2 rows, but actually there are 20,000 rows with the same key.
create table extremely_skewed (id int, t text);
alter table extremely_skewed set (autovacuum_enabled = 'false');
alter table extremely_skewed set (parallel_workers = 2);
analyze extremely_skewed;
insert into extremely_skewed
select 42 as id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'
from generate_series(1, 20000);
update pg_class
set reltuples = 2, relpages = pg_relation_size('extremely_skewed') / 8192
where relname = 'extremely_skewed';
-- Make a relation with a couple of enormous tuples.
create table wide as select generate_series(1, 2) as id, rpad('', 320000, 'x') as t;
alter table wide set (parallel_workers = 2);
-- The "optimal" case: the hash table fits in memory; we plan for 1
-- batch, we stick to that number, and peak memory usage stays within
-- our work_mem budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '4MB';
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(6 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | f
(1 row)
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
-------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(9 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | f
(1 row)
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
-------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Parallel Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Parallel Hash
-> Parallel Seq Scan on simple s
(9 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | f
(1 row)
rollback to settings;
-- The "good" case: batches required, but we plan the right number; we
-- plan for some number of batches, and we stick to that number, and
-- peak memory usage says within our work_mem budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(6 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
t | f
(1 row)
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
-------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(9 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
t | f
(1 row)
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '192kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
-------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Parallel Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Parallel Hash
-> Parallel Seq Scan on simple s
(9 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
t | f
(1 row)
rollback to settings;
-- The "bad" case: during execution we need to increase number of
-- batches; in this case we plan for 1 batch, and increase at least a
-- couple of times, and peak memory usage stays within our work_mem
-- budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
QUERY PLAN
------------------------------------------------------
Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on bigger_than_it_looks s
(6 rows)
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | t
(1 row)
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join bigger_than_it_looks s using (id);
QUERY PLAN
------------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Hash
-> Seq Scan on bigger_than_it_looks s
(9 rows)
select count(*) from simple r join bigger_than_it_looks s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join bigger_than_it_looks s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | t
(1 row)
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 1;
set local work_mem = '192kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join bigger_than_it_looks s using (id);
QUERY PLAN
---------------------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 1
-> Partial Aggregate
-> Parallel Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Parallel Hash
-> Parallel Seq Scan on bigger_than_it_looks s
(9 rows)
select count(*) from simple r join bigger_than_it_looks s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join bigger_than_it_looks s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | t
(1 row)
rollback to settings;
-- The "ugly" case: increasing the number of batches during execution
-- doesn't help, so stop trying to fit in work_mem and hope for the
-- best; in this case we plan for 1 batch, increases just once and
-- then stop increasing because that didn't help at all, so we blow
-- right through the work_mem budget and hope for the best...
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
QUERY PLAN
--------------------------------------------------
Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on extremely_skewed s
(6 rows)
select count(*) from simple r join extremely_skewed s using (id);
count
-------
20000
(1 row)
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
original | final
----------+-------
1 | 2
(1 row)
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
QUERY PLAN
--------------------------------------------------------
Aggregate
-> Gather
Workers Planned: 2
-> Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Hash
-> Seq Scan on extremely_skewed s
(8 rows)
select count(*) from simple r join extremely_skewed s using (id);
count
-------
20000
(1 row)
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
original | final
----------+-------
1 | 2
(1 row)
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 1;
set local work_mem = '128kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
QUERY PLAN
-----------------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 1
-> Partial Aggregate
-> Parallel Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Parallel Hash
-> Parallel Seq Scan on extremely_skewed s
(9 rows)
select count(*) from simple r join extremely_skewed s using (id);
count
-------
20000
(1 row)
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
original | final
----------+-------
1 | 4
(1 row)
rollback to settings;
-- A couple of other hash join tests unrelated to work_mem management.
-- Check that EXPLAIN ANALYZE has data even if the leader doesn't participate
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local parallel_leader_participation = off;
select * from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
original | final
----------+-------
1 | 1
(1 row)
rollback to settings;
-- Exercise rescans. We'll turn off parallel_leader_participation so
-- that we can check that instrumentation comes back correctly.
create table join_foo as select generate_series(1, 3) as id, 'xxxxx'::text as t;
alter table join_foo set (parallel_workers = 0);
create table join_bar as select generate_series(1, 10000) as id, 'xxxxx'::text as t;
alter table join_bar set (parallel_workers = 2);
-- multi-batch with rescan, parallel-oblivious
savepoint settings;
set enable_parallel_hash = off;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '64kB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
QUERY PLAN
------------------------------------------------------------------------------------
Aggregate
-> Nested Loop Left Join
Join Filter: ((join_foo.id < (b1.id + 1)) AND (join_foo.id > (b1.id - 1)))
-> Seq Scan on join_foo
-> Gather
Workers Planned: 2
-> Hash Join
Hash Cond: (b1.id = b2.id)
-> Parallel Seq Scan on join_bar b1
-> Hash
-> Seq Scan on join_bar b2
(11 rows)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
count
-------
3
(1 row)
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
multibatch
------------
t
(1 row)
rollback to settings;
-- single-batch with rescan, parallel-oblivious
savepoint settings;
set enable_parallel_hash = off;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '4MB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
QUERY PLAN
------------------------------------------------------------------------------------
Aggregate
-> Nested Loop Left Join
Join Filter: ((join_foo.id < (b1.id + 1)) AND (join_foo.id > (b1.id - 1)))
-> Seq Scan on join_foo
-> Gather
Workers Planned: 2
-> Hash Join
Hash Cond: (b1.id = b2.id)
-> Parallel Seq Scan on join_bar b1
-> Hash
-> Seq Scan on join_bar b2
(11 rows)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
count
-------
3
(1 row)
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
multibatch
------------
f
(1 row)
rollback to settings;
-- multi-batch with rescan, parallel-aware
savepoint settings;
set enable_parallel_hash = on;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '64kB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
QUERY PLAN
------------------------------------------------------------------------------------
Aggregate
-> Nested Loop Left Join
Join Filter: ((join_foo.id < (b1.id + 1)) AND (join_foo.id > (b1.id - 1)))
-> Seq Scan on join_foo
-> Gather
Workers Planned: 2
-> Parallel Hash Join
Hash Cond: (b1.id = b2.id)
-> Parallel Seq Scan on join_bar b1
-> Parallel Hash
-> Parallel Seq Scan on join_bar b2
(11 rows)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
count
-------
3
(1 row)
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
multibatch
------------
t
(1 row)
rollback to settings;
-- single-batch with rescan, parallel-aware
savepoint settings;
set enable_parallel_hash = on;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '4MB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
QUERY PLAN
------------------------------------------------------------------------------------
Aggregate
-> Nested Loop Left Join
Join Filter: ((join_foo.id < (b1.id + 1)) AND (join_foo.id > (b1.id - 1)))
-> Seq Scan on join_foo
-> Gather
Workers Planned: 2
-> Parallel Hash Join
Hash Cond: (b1.id = b2.id)
-> Parallel Seq Scan on join_bar b1
-> Parallel Hash
-> Parallel Seq Scan on join_bar b2
(11 rows)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
count
-------
3
(1 row)
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
multibatch
------------
f
(1 row)
rollback to settings;
-- A full outer join where every record is matched.
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
explain (costs off)
select count(*) from simple r full outer join simple s using (id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Full Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(6 rows)
select count(*) from simple r full outer join simple s using (id);
count
-------
20000
(1 row)
rollback to settings;
-- parallelism not possible with parallel-oblivious outer hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
explain (costs off)
select count(*) from simple r full outer join simple s using (id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Full Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(6 rows)
select count(*) from simple r full outer join simple s using (id);
count
-------
20000
(1 row)
rollback to settings;
-- An full outer join where every record is not matched.
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
explain (costs off)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Full Join
Hash Cond: ((0 - s.id) = r.id)
-> Seq Scan on simple s
-> Hash
-> Seq Scan on simple r
(6 rows)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
count
-------
40000
(1 row)
rollback to settings;
-- parallelism not possible with parallel-oblivious outer hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
explain (costs off)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Full Join
Hash Cond: ((0 - s.id) = r.id)
-> Seq Scan on simple s
-> Hash
-> Seq Scan on simple r
(6 rows)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
count
-------
40000
(1 row)
rollback to settings;
-- exercise special code paths for huge tuples (note use of non-strict
-- expression and left join required to get the detoasted tuple into
-- the hash table)
-- parallel with parallel-aware hash join (hits ExecParallelHashLoadTuple and
-- sts_puttuple oversized tuple cases because it's multi-batch)
savepoint settings;
set max_parallel_workers_per_gather = 2;
set enable_parallel_hash = on;
set work_mem = '128kB';
explain (costs off)
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
QUERY PLAN
----------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Parallel Hash Left Join
Hash Cond: (wide.id = wide_1.id)
-> Parallel Seq Scan on wide
-> Parallel Hash
-> Parallel Seq Scan on wide wide_1
(9 rows)
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
length
--------
320000
(1 row)
select final > 1 as multibatch
from hash_join_batches(
$$
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
$$);
multibatch
------------
t
(1 row)
rollback to settings;
rollback;

880
src/test/regress/expected/join_hash.out Normal file
View File

@ -0,0 +1,880 @@
--
-- exercises for the hash join code
--
begin;
set local min_parallel_table_scan_size = 0;
set local parallel_setup_cost = 0;
-- Extract bucket and batch counts from an explain analyze plan. In
-- general we can't make assertions about how many batches (or
-- buckets) will be required because it can vary, but we can in some
-- special cases and we can check for growth.
create or replace function find_hash(node json)
returns json language plpgsql
as
$$
declare
x json;
child json;
begin
if node->>'Node Type' = 'Hash' then
return node;
else
for child in select json_array_elements(node->'Plans')
loop
x := find_hash(child);
if x is not null then
return x;
end if;
end loop;
return null;
end if;
end;
$$;
create or replace function hash_join_batches(query text)
returns table (original int, final int) language plpgsql
as
$$
declare
whole_plan json;
hash_node json;
begin
for whole_plan in
execute 'explain (analyze, format ''json'') ' || query
loop
hash_node := find_hash(json_extract_path(whole_plan, '0', 'Plan'));
original := hash_node->>'Original Hash Batches';
final := hash_node->>'Hash Batches';
return next;
end loop;
end;
$$;
-- Make a simple relation with well distributed keys and correctly
-- estimated size.
create table simple as
select generate_series(1, 20000) AS id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa';
alter table simple set (parallel_workers = 2);
analyze simple;
-- Make a relation whose size we will under-estimate. We want stats
-- to say 1000 rows, but actually there are 20,000 rows.
create table bigger_than_it_looks as
select generate_series(1, 20000) as id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa';
alter table bigger_than_it_looks set (autovacuum_enabled = 'false');
alter table bigger_than_it_looks set (parallel_workers = 2);
analyze bigger_than_it_looks;
update pg_class set reltuples = 1000 where relname = 'bigger_than_it_looks';
-- Make a relation whose size we underestimate and that also has a
-- kind of skew that breaks our batching scheme. We want stats to say
-- 2 rows, but actually there are 20,000 rows with the same key.
create table extremely_skewed (id int, t text);
alter table extremely_skewed set (autovacuum_enabled = 'false');
alter table extremely_skewed set (parallel_workers = 2);
analyze extremely_skewed;
insert into extremely_skewed
select 42 as id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'
from generate_series(1, 20000);
update pg_class
set reltuples = 2, relpages = pg_relation_size('extremely_skewed') / 8192
where relname = 'extremely_skewed';
-- Make a relation with a couple of enormous tuples.
create table wide as select generate_series(1, 2) as id, rpad('', 320000, 'x') as t;
alter table wide set (parallel_workers = 2);
-- The "optimal" case: the hash table fits in memory; we plan for 1
-- batch, we stick to that number, and peak memory usage stays within
-- our work_mem budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '4MB';
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(6 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | f
(1 row)
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
-------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(9 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | f
(1 row)
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
-------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Parallel Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Parallel Hash
-> Parallel Seq Scan on simple s
(9 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | f
(1 row)
rollback to settings;
-- The "good" case: batches required, but we plan the right number; we
-- plan for some number of batches, and we stick to that number, and
-- peak memory usage says within our work_mem budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(6 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
t | f
(1 row)
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
-------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(9 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
t | f
(1 row)
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '192kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join simple s using (id);
QUERY PLAN
-------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Parallel Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Parallel Hash
-> Parallel Seq Scan on simple s
(9 rows)
select count(*) from simple r join simple s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
t | f
(1 row)
rollback to settings;
-- The "bad" case: during execution we need to increase number of
-- batches; in this case we plan for 1 batch, and increase at least a
-- couple of times, and peak memory usage stays within our work_mem
-- budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
QUERY PLAN
------------------------------------------------------
Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on bigger_than_it_looks s
(6 rows)
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | t
(1 row)
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join bigger_than_it_looks s using (id);
QUERY PLAN
------------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Hash
-> Seq Scan on bigger_than_it_looks s
(9 rows)
select count(*) from simple r join bigger_than_it_looks s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join bigger_than_it_looks s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | t
(1 row)
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 1;
set local work_mem = '192kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join bigger_than_it_looks s using (id);
QUERY PLAN
---------------------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 1
-> Partial Aggregate
-> Parallel Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Parallel Hash
-> Parallel Seq Scan on bigger_than_it_looks s
(9 rows)
select count(*) from simple r join bigger_than_it_looks s using (id);
count
-------
20000
(1 row)
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join bigger_than_it_looks s using (id);
$$);
initially_multibatch | increased_batches
----------------------+-------------------
f | t
(1 row)
rollback to settings;
-- The "ugly" case: increasing the number of batches during execution
-- doesn't help, so stop trying to fit in work_mem and hope for the
-- best; in this case we plan for 1 batch, increases just once and
-- then stop increasing because that didn't help at all, so we blow
-- right through the work_mem budget and hope for the best...
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
QUERY PLAN
--------------------------------------------------
Aggregate
-> Hash Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on extremely_skewed s
(6 rows)
select count(*) from simple r join extremely_skewed s using (id);
count
-------
20000
(1 row)
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
original | final
----------+-------
1 | 2
(1 row)
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
QUERY PLAN
--------------------------------------------------------
Aggregate
-> Gather
Workers Planned: 2
-> Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Hash
-> Seq Scan on extremely_skewed s
(8 rows)
select count(*) from simple r join extremely_skewed s using (id);
count
-------
20000
(1 row)
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
original | final
----------+-------
1 | 2
(1 row)
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 1;
set local work_mem = '128kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
QUERY PLAN
-----------------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 1
-> Partial Aggregate
-> Parallel Hash Join
Hash Cond: (r.id = s.id)
-> Parallel Seq Scan on simple r
-> Parallel Hash
-> Parallel Seq Scan on extremely_skewed s
(9 rows)
select count(*) from simple r join extremely_skewed s using (id);
count
-------
20000
(1 row)
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
original | final
----------+-------
1 | 4
(1 row)
rollback to settings;
-- A couple of other hash join tests unrelated to work_mem management.
-- Check that EXPLAIN ANALYZE has data even if the leader doesn't participate
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local parallel_leader_participation = off;
select * from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
original | final
----------+-------
1 | 1
(1 row)
rollback to settings;
-- Exercise rescans. We'll turn off parallel_leader_participation so
-- that we can check that instrumentation comes back correctly.
create table join_foo as select generate_series(1, 3) as id, 'xxxxx'::text as t;
alter table join_foo set (parallel_workers = 0);
create table join_bar as select generate_series(1, 10000) as id, 'xxxxx'::text as t;
alter table join_bar set (parallel_workers = 2);
-- multi-batch with rescan, parallel-oblivious
savepoint settings;
set enable_parallel_hash = off;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '64kB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
QUERY PLAN
------------------------------------------------------------------------------------
Aggregate
-> Nested Loop Left Join
Join Filter: ((join_foo.id < (b1.id + 1)) AND (join_foo.id > (b1.id - 1)))
-> Seq Scan on join_foo
-> Gather
Workers Planned: 2
-> Hash Join
Hash Cond: (b1.id = b2.id)
-> Parallel Seq Scan on join_bar b1
-> Hash
-> Seq Scan on join_bar b2
(11 rows)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
count
-------
3
(1 row)
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
multibatch
------------
t
(1 row)
rollback to settings;
-- single-batch with rescan, parallel-oblivious
savepoint settings;
set enable_parallel_hash = off;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '4MB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
QUERY PLAN
------------------------------------------------------------------------------------
Aggregate
-> Nested Loop Left Join
Join Filter: ((join_foo.id < (b1.id + 1)) AND (join_foo.id > (b1.id - 1)))
-> Seq Scan on join_foo
-> Gather
Workers Planned: 2
-> Hash Join
Hash Cond: (b1.id = b2.id)
-> Parallel Seq Scan on join_bar b1
-> Hash
-> Seq Scan on join_bar b2
(11 rows)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
count
-------
3
(1 row)
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
multibatch
------------
f
(1 row)
rollback to settings;
-- multi-batch with rescan, parallel-aware
savepoint settings;
set enable_parallel_hash = on;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '64kB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
QUERY PLAN
------------------------------------------------------------------------------------
Aggregate
-> Nested Loop Left Join
Join Filter: ((join_foo.id < (b1.id + 1)) AND (join_foo.id > (b1.id - 1)))
-> Seq Scan on join_foo
-> Gather
Workers Planned: 2
-> Parallel Hash Join
Hash Cond: (b1.id = b2.id)
-> Parallel Seq Scan on join_bar b1
-> Parallel Hash
-> Parallel Seq Scan on join_bar b2
(11 rows)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
count
-------
3
(1 row)
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
multibatch
------------
t
(1 row)
rollback to settings;
-- single-batch with rescan, parallel-aware
savepoint settings;
set enable_parallel_hash = on;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '4MB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
QUERY PLAN
------------------------------------------------------------------------------------
Aggregate
-> Nested Loop Left Join
Join Filter: ((join_foo.id < (b1.id + 1)) AND (join_foo.id > (b1.id - 1)))
-> Seq Scan on join_foo
-> Gather
Workers Planned: 2
-> Parallel Hash Join
Hash Cond: (b1.id = b2.id)
-> Parallel Seq Scan on join_bar b1
-> Parallel Hash
-> Parallel Seq Scan on join_bar b2
(11 rows)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
count
-------
3
(1 row)
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
multibatch
------------
f
(1 row)
rollback to settings;
-- A full outer join where every record is matched.
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
explain (costs off)
select count(*) from simple r full outer join simple s using (id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Full Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(6 rows)
select count(*) from simple r full outer join simple s using (id);
count
-------
20000
(1 row)
rollback to settings;
-- parallelism not possible with parallel-oblivious outer hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
explain (costs off)
select count(*) from simple r full outer join simple s using (id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Full Join
Hash Cond: (r.id = s.id)
-> Seq Scan on simple r
-> Hash
-> Seq Scan on simple s
(6 rows)
select count(*) from simple r full outer join simple s using (id);
count
-------
20000
(1 row)
rollback to settings;
-- An full outer join where every record is not matched.
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
explain (costs off)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Full Join
Hash Cond: ((0 - s.id) = r.id)
-> Seq Scan on simple s
-> Hash
-> Seq Scan on simple r
(6 rows)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
count
-------
40000
(1 row)
rollback to settings;
-- parallelism not possible with parallel-oblivious outer hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
explain (costs off)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
QUERY PLAN
----------------------------------------
Aggregate
-> Hash Full Join
Hash Cond: ((0 - s.id) = r.id)
-> Seq Scan on simple s
-> Hash
-> Seq Scan on simple r
(6 rows)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
count
-------
40000
(1 row)
rollback to settings;
-- exercise special code paths for huge tuples (note use of non-strict
-- expression and left join required to get the detoasted tuple into
-- the hash table)
-- parallel with parallel-aware hash join (hits ExecParallelHashLoadTuple and
-- sts_puttuple oversized tuple cases because it's multi-batch)
savepoint settings;
set max_parallel_workers_per_gather = 2;
set enable_parallel_hash = on;
set work_mem = '128kB';
explain (costs off)
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
QUERY PLAN
----------------------------------------------------------------
Finalize Aggregate
-> Gather
Workers Planned: 2
-> Partial Aggregate
-> Parallel Hash Left Join
Hash Cond: (wide.id = wide_1.id)
-> Parallel Seq Scan on wide
-> Parallel Hash
-> Parallel Seq Scan on wide wide_1
(9 rows)
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
length
--------
320000
(1 row)
select final > 1 as multibatch
from hash_join_batches(
$$
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
$$);
multibatch
------------
t
(1 row)
rollback to settings;
rollback;

1
src/test/regress/expected/sanity_check.out
View File

@ -38,7 +38,6 @@ d_star|f
date_tbl|f
default_tbl|f
defaultexpr_tbl|f
delete_test_table|t
dept|f
dupindexcols|t
e_star|f

4
src/test/regress/parallel_schedule
View File

@ -55,7 +55,7 @@ test: copy copyselect copydml
# ----------
test: create_misc create_operator create_procedure
# These depend on the above two
test: create_index create_view index_including index_including_gist
test: create_index create_index_spgist create_view index_including index_including_gist
# ----------
# Another group of parallel tests
@ -84,7 +84,7 @@ test: select_into select_distinct select_distinct_on select_implicit select_havi
# ----------
# Another group of parallel tests
# ----------
test: brin gin gist spgist privileges init_privs security_label collate matview lock replica_identity rowsecurity object_address tablesample groupingsets drop_operator password identity generated
test: brin gin gist spgist privileges init_privs security_label collate matview lock replica_identity rowsecurity object_address tablesample groupingsets drop_operator password identity generated join_hash
# ----------
# Another group of parallel tests

2
src/test/regress/serial_schedule
View File

@ -63,6 +63,7 @@ test: create_misc
test: create_operator
test: create_procedure
test: create_index
test: create_index_spgist
test: index_including
test: index_including_gist
test: create_view
@ -123,6 +124,7 @@ test: drop_operator
test: password
test: identity
test: generated
test: join_hash
test: create_table_like
test: alter_generic
test: alter_operator

20
src/test/regress/sql/btree_index.sql
View File

@ -120,3 +120,23 @@ create index btree_idx_err on btree_test(a) with (vacuum_cleanup_index_scale_fac
-- Simple ALTER INDEX
alter index btree_idx1 set (vacuum_cleanup_index_scale_factor = 70.0);
select reloptions from pg_class WHERE oid = 'btree_idx1'::regclass;
--
-- Test for multilevel page deletion
--
CREATE TABLE delete_test_table (a bigint, b bigint, c bigint, d bigint);
INSERT INTO delete_test_table SELECT i, 1, 2, 3 FROM generate_series(1,80000) i;
ALTER TABLE delete_test_table ADD PRIMARY KEY (a,b,c,d);
-- Delete most entries, and vacuum, deleting internal pages and creating "fast
-- root"
DELETE FROM delete_test_table WHERE a < 79990;
VACUUM delete_test_table;
--
-- Test B-tree insertion with a metapage update (XLOG_BTREE_INSERT_META
-- WAL record type). This happens when a "fast root" page is split. This
-- also creates coverage for nbtree FSM page recycling.
--
-- The vacuum above should've turned the leaf page into a fast root. We just
-- need to insert some rows to cause the fast root page to split.
INSERT INTO delete_test_table SELECT i, 1, 2, 3 FROM generate_series(1,1000) i;

424
src/test/regress/sql/create_index.sql
View File

@ -97,35 +97,7 @@ CREATE INDEX ggpolygonind ON gpolygon_tbl USING gist (f1);
CREATE INDEX ggcircleind ON gcircle_tbl USING gist (f1);
--
-- SP-GiST
--
CREATE TABLE quad_point_tbl AS
SELECT point(unique1,unique2) AS p FROM tenk1;
INSERT INTO quad_point_tbl
SELECT '(333.0,400.0)'::point FROM generate_series(1,1000);
INSERT INTO quad_point_tbl VALUES (NULL), (NULL), (NULL);
CREATE INDEX sp_quad_ind ON quad_point_tbl USING spgist (p);
CREATE TABLE kd_point_tbl AS SELECT * FROM quad_point_tbl;
CREATE INDEX sp_kd_ind ON kd_point_tbl USING spgist (p kd_point_ops);
CREATE TABLE radix_text_tbl AS
SELECT name AS t FROM road WHERE name !~ '^[0-9]';
INSERT INTO radix_text_tbl
SELECT 'P0123456789abcdef' FROM generate_series(1,1000);
INSERT INTO radix_text_tbl VALUES ('P0123456789abcde');
INSERT INTO radix_text_tbl VALUES ('P0123456789abcdefF');
CREATE INDEX sp_radix_ind ON radix_text_tbl USING spgist (t);
--
-- Test GiST and SP-GiST indexes
-- Test GiST indexes
--
-- get non-indexed results for comparison purposes
@ -178,66 +150,6 @@ SELECT * FROM point_tbl WHERE f1 IS NOT NULL ORDER BY f1 <-> '0,1';
SELECT * FROM point_tbl WHERE f1 <@ '(-10,-10),(10,10)':: box ORDER BY f1 <-> '0,1';
SELECT count(*) FROM quad_point_tbl WHERE p IS NULL;
SELECT count(*) FROM quad_point_tbl WHERE p IS NOT NULL;
SELECT count(*) FROM quad_point_tbl;
SELECT count(*) FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT count(*) FROM quad_point_tbl WHERE box '(200,200,1000,1000)' @> p;
SELECT count(*) FROM quad_point_tbl WHERE p << '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >> '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p <^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p ~= '(4585, 365)';
CREATE TEMP TABLE quad_point_tbl_ord_seq1 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl;
CREATE TEMP TABLE quad_point_tbl_ord_seq2 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
CREATE TEMP TABLE quad_point_tbl_ord_seq3 AS
SELECT rank() OVER (ORDER BY p <-> '333,400') n, p <-> '333,400' dist, p
FROM quad_point_tbl WHERE p IS NOT NULL;
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdef';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcde';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdefF';
SELECT count(*) FROM radix_text_tbl WHERE t < 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t <= 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<=~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t >= 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>=~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t > 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ^@ 'Worth';
SELECT * FROM gpolygon_tbl ORDER BY f1 <-> '(0,0)'::point LIMIT 10;
SELECT circle_center(f1), round(radius(f1)) as radius FROM gcircle_tbl ORDER BY f1 <-> '(200,300)'::point LIMIT 10;
@ -335,196 +247,6 @@ EXPLAIN (COSTS OFF)
SELECT * FROM point_tbl WHERE f1 <@ '(-10,-10),(10,10)':: box ORDER BY f1 <-> '0,1';
SELECT * FROM point_tbl WHERE f1 <@ '(-10,-10),(10,10)':: box ORDER BY f1 <-> '0,1';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p IS NULL;
SELECT count(*) FROM quad_point_tbl WHERE p IS NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p IS NOT NULL;
SELECT count(*) FROM quad_point_tbl WHERE p IS NOT NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl;
SELECT count(*) FROM quad_point_tbl;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT count(*) FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE box '(200,200,1000,1000)' @> p;
SELECT count(*) FROM quad_point_tbl WHERE box '(200,200,1000,1000)' @> p;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p << '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p << '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p >> '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >> '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p <^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p <^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p >^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p ~= '(4585, 365)';
SELECT count(*) FROM quad_point_tbl WHERE p ~= '(4585, 365)';
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl;
CREATE TEMP TABLE quad_point_tbl_ord_idx1 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl;
SELECT * FROM quad_point_tbl_ord_seq1 seq FULL JOIN quad_point_tbl_ord_idx1 idx
ON seq.n = idx.n
AND (seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
CREATE TEMP TABLE quad_point_tbl_ord_idx2 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT * FROM quad_point_tbl_ord_seq2 seq FULL JOIN quad_point_tbl_ord_idx2 idx
ON seq.n = idx.n
AND (seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '333,400') n, p <-> '333,400' dist, p
FROM quad_point_tbl WHERE p IS NOT NULL;
CREATE TEMP TABLE quad_point_tbl_ord_idx3 AS
SELECT rank() OVER (ORDER BY p <-> '333,400') n, p <-> '333,400' dist, p
FROM quad_point_tbl WHERE p IS NOT NULL;
SELECT * FROM quad_point_tbl_ord_seq3 seq FULL JOIN quad_point_tbl_ord_idx3 idx
ON seq.n = idx.n
AND (seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT count(*) FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE box '(200,200,1000,1000)' @> p;
SELECT count(*) FROM kd_point_tbl WHERE box '(200,200,1000,1000)' @> p;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p << '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p << '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p >> '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p >> '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p <^ '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p <^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p >^ '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p >^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p ~= '(4585, 365)';
SELECT count(*) FROM kd_point_tbl WHERE p ~= '(4585, 365)';
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM kd_point_tbl;
CREATE TEMP TABLE kd_point_tbl_ord_idx1 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM kd_point_tbl;
SELECT * FROM quad_point_tbl_ord_seq1 seq FULL JOIN kd_point_tbl_ord_idx1 idx
ON seq.n = idx.n AND
(seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
CREATE TEMP TABLE kd_point_tbl_ord_idx2 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT * FROM quad_point_tbl_ord_seq2 seq FULL JOIN kd_point_tbl_ord_idx2 idx
ON seq.n = idx.n AND
(seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '333,400') n, p <-> '333,400' dist, p
FROM kd_point_tbl WHERE p IS NOT NULL;
CREATE TEMP TABLE kd_point_tbl_ord_idx3 AS
SELECT rank() OVER (ORDER BY p <-> '333,400') n, p <-> '333,400' dist, p
FROM kd_point_tbl WHERE p IS NOT NULL;
SELECT * FROM quad_point_tbl_ord_seq3 seq FULL JOIN kd_point_tbl_ord_idx3 idx
ON seq.n = idx.n AND
(seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdef';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdef';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcde';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcde';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdefF';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdefF';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t < 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t < 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~<~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<~ 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t <= 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t <= 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~<=~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<=~ 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t >= 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t >= 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~>=~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>=~ 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t > 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t > 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~>~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>~ 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ^@ 'Worth';
SELECT count(*) FROM radix_text_tbl WHERE t ^@ 'Worth';
EXPLAIN (COSTS OFF)
SELECT * FROM gpolygon_tbl ORDER BY f1 <-> '(0,0)'::point LIMIT 10;
SELECT * FROM gpolygon_tbl ORDER BY f1 <-> '(0,0)'::point LIMIT 10;
@ -542,130 +264,6 @@ EXPLAIN (COSTS OFF)
SELECT * FROM point_tbl WHERE f1 <@ '(-10,-10),(10,10)':: box ORDER BY f1 <-> '0,1';
SELECT * FROM point_tbl WHERE f1 <@ '(-10,-10),(10,10)':: box ORDER BY f1 <-> '0,1';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p IS NULL;
SELECT count(*) FROM quad_point_tbl WHERE p IS NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p IS NOT NULL;
SELECT count(*) FROM quad_point_tbl WHERE p IS NOT NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl;
SELECT count(*) FROM quad_point_tbl;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT count(*) FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE box '(200,200,1000,1000)' @> p;
SELECT count(*) FROM quad_point_tbl WHERE box '(200,200,1000,1000)' @> p;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p << '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p << '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p >> '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >> '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p <^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p <^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p >^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p ~= '(4585, 365)';
SELECT count(*) FROM quad_point_tbl WHERE p ~= '(4585, 365)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT count(*) FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE box '(200,200,1000,1000)' @> p;
SELECT count(*) FROM kd_point_tbl WHERE box '(200,200,1000,1000)' @> p;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p << '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p << '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p >> '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p >> '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p <^ '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p <^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p >^ '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p >^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p ~= '(4585, 365)';
SELECT count(*) FROM kd_point_tbl WHERE p ~= '(4585, 365)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdef';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdef';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcde';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcde';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdefF';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdefF';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t < 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t < 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~<~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<~ 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t <= 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t <= 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~<=~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<=~ 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t >= 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t >= 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~>=~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>=~ 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t > 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t > 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~>~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>~ 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ^@ 'Worth';
SELECT count(*) FROM radix_text_tbl WHERE t ^@ 'Worth';
RESET enable_seqscan;
RESET enable_indexscan;
RESET enable_bitmapscan;
@ -1140,26 +738,6 @@ explain (costs off)
explain (costs off)
select * from boolindex where b is false order by i desc limit 10;
--
-- Test for multilevel page deletion
--
CREATE TABLE delete_test_table (a bigint, b bigint, c bigint, d bigint);
INSERT INTO delete_test_table SELECT i, 1, 2, 3 FROM generate_series(1,80000) i;
ALTER TABLE delete_test_table ADD PRIMARY KEY (a,b,c,d);
-- Delete most entries, and vacuum, deleting internal pages and creating "fast
-- root"
DELETE FROM delete_test_table WHERE a < 79990;
VACUUM delete_test_table;
--
-- Test B-tree insertion with a metapage update (XLOG_BTREE_INSERT_META
-- WAL record type). This happens when a "fast root" page is split. This
-- also creates coverage for nbtree FSM page recycling.
--
-- The vacuum above should've turned the leaf page into a fast root. We just
-- need to insert some rows to cause the fast root page to split.
INSERT INTO delete_test_table SELECT i, 1, 2, 3 FROM generate_series(1,1000) i;
--
-- REINDEX (VERBOSE)
--

421
src/test/regress/sql/create_index_spgist.sql Normal file
View File

@ -0,0 +1,421 @@
--
-- SP-GiST index tests
--
CREATE TABLE quad_point_tbl AS
SELECT point(unique1,unique2) AS p FROM tenk1;
INSERT INTO quad_point_tbl
SELECT '(333.0,400.0)'::point FROM generate_series(1,1000);
INSERT INTO quad_point_tbl VALUES (NULL), (NULL), (NULL);
CREATE INDEX sp_quad_ind ON quad_point_tbl USING spgist (p);
CREATE TABLE kd_point_tbl AS SELECT * FROM quad_point_tbl;
CREATE INDEX sp_kd_ind ON kd_point_tbl USING spgist (p kd_point_ops);
CREATE TABLE radix_text_tbl AS
SELECT name AS t FROM road WHERE name !~ '^[0-9]';
INSERT INTO radix_text_tbl
SELECT 'P0123456789abcdef' FROM generate_series(1,1000);
INSERT INTO radix_text_tbl VALUES ('P0123456789abcde');
INSERT INTO radix_text_tbl VALUES ('P0123456789abcdefF');
CREATE INDEX sp_radix_ind ON radix_text_tbl USING spgist (t);
-- get non-indexed results for comparison purposes
SET enable_seqscan = ON;
SET enable_indexscan = OFF;
SET enable_bitmapscan = OFF;
SELECT count(*) FROM quad_point_tbl WHERE p IS NULL;
SELECT count(*) FROM quad_point_tbl WHERE p IS NOT NULL;
SELECT count(*) FROM quad_point_tbl;
SELECT count(*) FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT count(*) FROM quad_point_tbl WHERE box '(200,200,1000,1000)' @> p;
SELECT count(*) FROM quad_point_tbl WHERE p << '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >> '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p <^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p ~= '(4585, 365)';
CREATE TEMP TABLE quad_point_tbl_ord_seq1 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl;
CREATE TEMP TABLE quad_point_tbl_ord_seq2 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
CREATE TEMP TABLE quad_point_tbl_ord_seq3 AS
SELECT rank() OVER (ORDER BY p <-> '333,400') n, p <-> '333,400' dist, p
FROM quad_point_tbl WHERE p IS NOT NULL;
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdef';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcde';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdefF';
SELECT count(*) FROM radix_text_tbl WHERE t < 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t <= 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<=~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t >= 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>=~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t > 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ^@ 'Worth';
-- Now check the results from plain indexscan
SET enable_seqscan = OFF;
SET enable_indexscan = ON;
SET enable_bitmapscan = OFF;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p IS NULL;
SELECT count(*) FROM quad_point_tbl WHERE p IS NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p IS NOT NULL;
SELECT count(*) FROM quad_point_tbl WHERE p IS NOT NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl;
SELECT count(*) FROM quad_point_tbl;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT count(*) FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE box '(200,200,1000,1000)' @> p;
SELECT count(*) FROM quad_point_tbl WHERE box '(200,200,1000,1000)' @> p;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p << '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p << '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p >> '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >> '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p <^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p <^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p >^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p ~= '(4585, 365)';
SELECT count(*) FROM quad_point_tbl WHERE p ~= '(4585, 365)';
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl;
CREATE TEMP TABLE quad_point_tbl_ord_idx1 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl;
SELECT * FROM quad_point_tbl_ord_seq1 seq FULL JOIN quad_point_tbl_ord_idx1 idx
ON seq.n = idx.n
AND (seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
CREATE TEMP TABLE quad_point_tbl_ord_idx2 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT * FROM quad_point_tbl_ord_seq2 seq FULL JOIN quad_point_tbl_ord_idx2 idx
ON seq.n = idx.n
AND (seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '333,400') n, p <-> '333,400' dist, p
FROM quad_point_tbl WHERE p IS NOT NULL;
CREATE TEMP TABLE quad_point_tbl_ord_idx3 AS
SELECT rank() OVER (ORDER BY p <-> '333,400') n, p <-> '333,400' dist, p
FROM quad_point_tbl WHERE p IS NOT NULL;
SELECT * FROM quad_point_tbl_ord_seq3 seq FULL JOIN quad_point_tbl_ord_idx3 idx
ON seq.n = idx.n
AND (seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT count(*) FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE box '(200,200,1000,1000)' @> p;
SELECT count(*) FROM kd_point_tbl WHERE box '(200,200,1000,1000)' @> p;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p << '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p << '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p >> '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p >> '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p <^ '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p <^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p >^ '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p >^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p ~= '(4585, 365)';
SELECT count(*) FROM kd_point_tbl WHERE p ~= '(4585, 365)';
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM kd_point_tbl;
CREATE TEMP TABLE kd_point_tbl_ord_idx1 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM kd_point_tbl;
SELECT * FROM quad_point_tbl_ord_seq1 seq FULL JOIN kd_point_tbl_ord_idx1 idx
ON seq.n = idx.n AND
(seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
CREATE TEMP TABLE kd_point_tbl_ord_idx2 AS
SELECT rank() OVER (ORDER BY p <-> '0,0') n, p <-> '0,0' dist, p
FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT * FROM quad_point_tbl_ord_seq2 seq FULL JOIN kd_point_tbl_ord_idx2 idx
ON seq.n = idx.n AND
(seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT rank() OVER (ORDER BY p <-> '333,400') n, p <-> '333,400' dist, p
FROM kd_point_tbl WHERE p IS NOT NULL;
CREATE TEMP TABLE kd_point_tbl_ord_idx3 AS
SELECT rank() OVER (ORDER BY p <-> '333,400') n, p <-> '333,400' dist, p
FROM kd_point_tbl WHERE p IS NOT NULL;
SELECT * FROM quad_point_tbl_ord_seq3 seq FULL JOIN kd_point_tbl_ord_idx3 idx
ON seq.n = idx.n AND
(seq.dist = idx.dist AND seq.p ~= idx.p OR seq.p IS NULL AND idx.p IS NULL)
WHERE seq.n IS NULL OR idx.n IS NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdef';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdef';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcde';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcde';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdefF';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdefF';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t < 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t < 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~<~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<~ 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t <= 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t <= 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~<=~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<=~ 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t >= 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t >= 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~>=~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>=~ 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t > 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t > 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~>~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>~ 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ^@ 'Worth';
SELECT count(*) FROM radix_text_tbl WHERE t ^@ 'Worth';
-- Now check the results from bitmap indexscan
SET enable_seqscan = OFF;
SET enable_indexscan = OFF;
SET enable_bitmapscan = ON;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p IS NULL;
SELECT count(*) FROM quad_point_tbl WHERE p IS NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p IS NOT NULL;
SELECT count(*) FROM quad_point_tbl WHERE p IS NOT NULL;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl;
SELECT count(*) FROM quad_point_tbl;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT count(*) FROM quad_point_tbl WHERE p <@ box '(200,200,1000,1000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE box '(200,200,1000,1000)' @> p;
SELECT count(*) FROM quad_point_tbl WHERE box '(200,200,1000,1000)' @> p;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p << '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p << '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p >> '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >> '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p <^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p <^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p >^ '(5000, 4000)';
SELECT count(*) FROM quad_point_tbl WHERE p >^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM quad_point_tbl WHERE p ~= '(4585, 365)';
SELECT count(*) FROM quad_point_tbl WHERE p ~= '(4585, 365)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
SELECT count(*) FROM kd_point_tbl WHERE p <@ box '(200,200,1000,1000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE box '(200,200,1000,1000)' @> p;
SELECT count(*) FROM kd_point_tbl WHERE box '(200,200,1000,1000)' @> p;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p << '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p << '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p >> '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p >> '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p <^ '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p <^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p >^ '(5000, 4000)';
SELECT count(*) FROM kd_point_tbl WHERE p >^ '(5000, 4000)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM kd_point_tbl WHERE p ~= '(4585, 365)';
SELECT count(*) FROM kd_point_tbl WHERE p ~= '(4585, 365)';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdef';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdef';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcde';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcde';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdefF';
SELECT count(*) FROM radix_text_tbl WHERE t = 'P0123456789abcdefF';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t < 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t < 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~<~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<~ 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t <= 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t <= 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~<=~ 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t ~<=~ 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'Aztec Ct ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Aztec Ct ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t = 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t = 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t >= 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t >= 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~>=~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>=~ 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t > 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t > 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ~>~ 'Worth St ';
SELECT count(*) FROM radix_text_tbl WHERE t ~>~ 'Worth St ';
EXPLAIN (COSTS OFF)
SELECT count(*) FROM radix_text_tbl WHERE t ^@ 'Worth';
SELECT count(*) FROM radix_text_tbl WHERE t ^@ 'Worth';
RESET enable_seqscan;
RESET enable_indexscan;
RESET enable_bitmapscan;

470
src/test/regress/sql/join.sql
View File

@ -2067,473 +2067,3 @@ where exists (select 1 from j3
and t1.unique1 < 1;
drop table j3;
--
-- exercises for the hash join code
--
begin;
set local min_parallel_table_scan_size = 0;
set local parallel_setup_cost = 0;
-- Extract bucket and batch counts from an explain analyze plan. In
-- general we can't make assertions about how many batches (or
-- buckets) will be required because it can vary, but we can in some
-- special cases and we can check for growth.
create or replace function find_hash(node json)
returns json language plpgsql
as
$$
declare
x json;
child json;
begin
if node->>'Node Type' = 'Hash' then
return node;
else
for child in select json_array_elements(node->'Plans')
loop
x := find_hash(child);
if x is not null then
return x;
end if;
end loop;
return null;
end if;
end;
$$;
create or replace function hash_join_batches(query text)
returns table (original int, final int) language plpgsql
as
$$
declare
whole_plan json;
hash_node json;
begin
for whole_plan in
execute 'explain (analyze, format ''json'') ' || query
loop
hash_node := find_hash(json_extract_path(whole_plan, '0', 'Plan'));
original := hash_node->>'Original Hash Batches';
final := hash_node->>'Hash Batches';
return next;
end loop;
end;
$$;
-- Make a simple relation with well distributed keys and correctly
-- estimated size.
create table simple as
select generate_series(1, 20000) AS id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa';
alter table simple set (parallel_workers = 2);
analyze simple;
-- Make a relation whose size we will under-estimate. We want stats
-- to say 1000 rows, but actually there are 20,000 rows.
create table bigger_than_it_looks as
select generate_series(1, 20000) as id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa';
alter table bigger_than_it_looks set (autovacuum_enabled = 'false');
alter table bigger_than_it_looks set (parallel_workers = 2);
analyze bigger_than_it_looks;
update pg_class set reltuples = 1000 where relname = 'bigger_than_it_looks';
-- Make a relation whose size we underestimate and that also has a
-- kind of skew that breaks our batching scheme. We want stats to say
-- 2 rows, but actually there are 20,000 rows with the same key.
create table extremely_skewed (id int, t text);
alter table extremely_skewed set (autovacuum_enabled = 'false');
alter table extremely_skewed set (parallel_workers = 2);
analyze extremely_skewed;
insert into extremely_skewed
select 42 as id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'
from generate_series(1, 20000);
update pg_class
set reltuples = 2, relpages = pg_relation_size('extremely_skewed') / 8192
where relname = 'extremely_skewed';
-- Make a relation with a couple of enormous tuples.
create table wide as select generate_series(1, 2) as id, rpad('', 320000, 'x') as t;
alter table wide set (parallel_workers = 2);
-- The "optimal" case: the hash table fits in memory; we plan for 1
-- batch, we stick to that number, and peak memory usage stays within
-- our work_mem budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '4MB';
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- The "good" case: batches required, but we plan the right number; we
-- plan for some number of batches, and we stick to that number, and
-- peak memory usage says within our work_mem budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '192kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- The "bad" case: during execution we need to increase number of
-- batches; in this case we plan for 1 batch, and increase at least a
-- couple of times, and peak memory usage stays within our work_mem
-- budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
$$);
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join bigger_than_it_looks s using (id);
select count(*) from simple r join bigger_than_it_looks s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join bigger_than_it_looks s using (id);
$$);
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 1;
set local work_mem = '192kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join bigger_than_it_looks s using (id);
select count(*) from simple r join bigger_than_it_looks s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join bigger_than_it_looks s using (id);
$$);
rollback to settings;
-- The "ugly" case: increasing the number of batches during execution
-- doesn't help, so stop trying to fit in work_mem and hope for the
-- best; in this case we plan for 1 batch, increases just once and
-- then stop increasing because that didn't help at all, so we blow
-- right through the work_mem budget and hope for the best...
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
select count(*) from simple r join extremely_skewed s using (id);
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
select count(*) from simple r join extremely_skewed s using (id);
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 1;
set local work_mem = '128kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
select count(*) from simple r join extremely_skewed s using (id);
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
rollback to settings;
-- A couple of other hash join tests unrelated to work_mem management.
-- Check that EXPLAIN ANALYZE has data even if the leader doesn't participate
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local parallel_leader_participation = off;
select * from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- Exercise rescans. We'll turn off parallel_leader_participation so
-- that we can check that instrumentation comes back correctly.
create table join_foo as select generate_series(1, 3) as id, 'xxxxx'::text as t;
alter table join_foo set (parallel_workers = 0);
create table join_bar as select generate_series(1, 10000) as id, 'xxxxx'::text as t;
alter table join_bar set (parallel_workers = 2);
-- multi-batch with rescan, parallel-oblivious
savepoint settings;
set enable_parallel_hash = off;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '64kB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
rollback to settings;
-- single-batch with rescan, parallel-oblivious
savepoint settings;
set enable_parallel_hash = off;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '4MB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
rollback to settings;
-- multi-batch with rescan, parallel-aware
savepoint settings;
set enable_parallel_hash = on;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '64kB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
rollback to settings;
-- single-batch with rescan, parallel-aware
savepoint settings;
set enable_parallel_hash = on;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '4MB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
rollback to settings;
-- A full outer join where every record is matched.
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
explain (costs off)
select count(*) from simple r full outer join simple s using (id);
select count(*) from simple r full outer join simple s using (id);
rollback to settings;
-- parallelism not possible with parallel-oblivious outer hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
explain (costs off)
select count(*) from simple r full outer join simple s using (id);
select count(*) from simple r full outer join simple s using (id);
rollback to settings;
-- An full outer join where every record is not matched.
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
explain (costs off)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
rollback to settings;
-- parallelism not possible with parallel-oblivious outer hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
explain (costs off)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
rollback to settings;
-- exercise special code paths for huge tuples (note use of non-strict
-- expression and left join required to get the detoasted tuple into
-- the hash table)
-- parallel with parallel-aware hash join (hits ExecParallelHashLoadTuple and
-- sts_puttuple oversized tuple cases because it's multi-batch)
savepoint settings;
set max_parallel_workers_per_gather = 2;
set enable_parallel_hash = on;
set work_mem = '128kB';
explain (costs off)
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
select final > 1 as multibatch
from hash_join_batches(
$$
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
$$);
rollback to settings;
rollback;

469
src/test/regress/sql/join_hash.sql Normal file
View File

@ -0,0 +1,469 @@
--
-- exercises for the hash join code
--
begin;
set local min_parallel_table_scan_size = 0;
set local parallel_setup_cost = 0;
-- Extract bucket and batch counts from an explain analyze plan. In
-- general we can't make assertions about how many batches (or
-- buckets) will be required because it can vary, but we can in some
-- special cases and we can check for growth.
create or replace function find_hash(node json)
returns json language plpgsql
as
$$
declare
x json;
child json;
begin
if node->>'Node Type' = 'Hash' then
return node;
else
for child in select json_array_elements(node->'Plans')
loop
x := find_hash(child);
if x is not null then
return x;
end if;
end loop;
return null;
end if;
end;
$$;
create or replace function hash_join_batches(query text)
returns table (original int, final int) language plpgsql
as
$$
declare
whole_plan json;
hash_node json;
begin
for whole_plan in
execute 'explain (analyze, format ''json'') ' || query
loop
hash_node := find_hash(json_extract_path(whole_plan, '0', 'Plan'));
original := hash_node->>'Original Hash Batches';
final := hash_node->>'Hash Batches';
return next;
end loop;
end;
$$;
-- Make a simple relation with well distributed keys and correctly
-- estimated size.
create table simple as
select generate_series(1, 20000) AS id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa';
alter table simple set (parallel_workers = 2);
analyze simple;
-- Make a relation whose size we will under-estimate. We want stats
-- to say 1000 rows, but actually there are 20,000 rows.
create table bigger_than_it_looks as
select generate_series(1, 20000) as id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa';
alter table bigger_than_it_looks set (autovacuum_enabled = 'false');
alter table bigger_than_it_looks set (parallel_workers = 2);
analyze bigger_than_it_looks;
update pg_class set reltuples = 1000 where relname = 'bigger_than_it_looks';
-- Make a relation whose size we underestimate and that also has a
-- kind of skew that breaks our batching scheme. We want stats to say
-- 2 rows, but actually there are 20,000 rows with the same key.
create table extremely_skewed (id int, t text);
alter table extremely_skewed set (autovacuum_enabled = 'false');
alter table extremely_skewed set (parallel_workers = 2);
analyze extremely_skewed;
insert into extremely_skewed
select 42 as id, 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'
from generate_series(1, 20000);
update pg_class
set reltuples = 2, relpages = pg_relation_size('extremely_skewed') / 8192
where relname = 'extremely_skewed';
-- Make a relation with a couple of enormous tuples.
create table wide as select generate_series(1, 2) as id, rpad('', 320000, 'x') as t;
alter table wide set (parallel_workers = 2);
-- The "optimal" case: the hash table fits in memory; we plan for 1
-- batch, we stick to that number, and peak memory usage stays within
-- our work_mem budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '4MB';
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- The "good" case: batches required, but we plan the right number; we
-- plan for some number of batches, and we stick to that number, and
-- peak memory usage says within our work_mem budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '192kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join simple s using (id);
select count(*) from simple r join simple s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- The "bad" case: during execution we need to increase number of
-- batches; in this case we plan for 1 batch, and increase at least a
-- couple of times, and peak memory usage stays within our work_mem
-- budget
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) FROM simple r JOIN bigger_than_it_looks s USING (id);
$$);
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join bigger_than_it_looks s using (id);
select count(*) from simple r join bigger_than_it_looks s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join bigger_than_it_looks s using (id);
$$);
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 1;
set local work_mem = '192kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join bigger_than_it_looks s using (id);
select count(*) from simple r join bigger_than_it_looks s using (id);
select original > 1 as initially_multibatch, final > original as increased_batches
from hash_join_batches(
$$
select count(*) from simple r join bigger_than_it_looks s using (id);
$$);
rollback to settings;
-- The "ugly" case: increasing the number of batches during execution
-- doesn't help, so stop trying to fit in work_mem and hope for the
-- best; in this case we plan for 1 batch, increases just once and
-- then stop increasing because that didn't help at all, so we blow
-- right through the work_mem budget and hope for the best...
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
set local work_mem = '128kB';
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
select count(*) from simple r join extremely_skewed s using (id);
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
rollback to settings;
-- parallel with parallel-oblivious hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '128kB';
set local enable_parallel_hash = off;
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
select count(*) from simple r join extremely_skewed s using (id);
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
rollback to settings;
-- parallel with parallel-aware hash join
savepoint settings;
set local max_parallel_workers_per_gather = 1;
set local work_mem = '128kB';
set local enable_parallel_hash = on;
explain (costs off)
select count(*) from simple r join extremely_skewed s using (id);
select count(*) from simple r join extremely_skewed s using (id);
select * from hash_join_batches(
$$
select count(*) from simple r join extremely_skewed s using (id);
$$);
rollback to settings;
-- A couple of other hash join tests unrelated to work_mem management.
-- Check that EXPLAIN ANALYZE has data even if the leader doesn't participate
savepoint settings;
set local max_parallel_workers_per_gather = 2;
set local work_mem = '4MB';
set local parallel_leader_participation = off;
select * from hash_join_batches(
$$
select count(*) from simple r join simple s using (id);
$$);
rollback to settings;
-- Exercise rescans. We'll turn off parallel_leader_participation so
-- that we can check that instrumentation comes back correctly.
create table join_foo as select generate_series(1, 3) as id, 'xxxxx'::text as t;
alter table join_foo set (parallel_workers = 0);
create table join_bar as select generate_series(1, 10000) as id, 'xxxxx'::text as t;
alter table join_bar set (parallel_workers = 2);
-- multi-batch with rescan, parallel-oblivious
savepoint settings;
set enable_parallel_hash = off;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '64kB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
rollback to settings;
-- single-batch with rescan, parallel-oblivious
savepoint settings;
set enable_parallel_hash = off;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '4MB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
rollback to settings;
-- multi-batch with rescan, parallel-aware
savepoint settings;
set enable_parallel_hash = on;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '64kB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
rollback to settings;
-- single-batch with rescan, parallel-aware
savepoint settings;
set enable_parallel_hash = on;
set parallel_leader_participation = off;
set min_parallel_table_scan_size = 0;
set parallel_setup_cost = 0;
set parallel_tuple_cost = 0;
set max_parallel_workers_per_gather = 2;
set enable_material = off;
set enable_mergejoin = off;
set work_mem = '4MB';
explain (costs off)
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
select final > 1 as multibatch
from hash_join_batches(
$$
select count(*) from join_foo
left join (select b1.id, b1.t from join_bar b1 join join_bar b2 using (id)) ss
on join_foo.id < ss.id + 1 and join_foo.id > ss.id - 1;
$$);
rollback to settings;
-- A full outer join where every record is matched.
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
explain (costs off)
select count(*) from simple r full outer join simple s using (id);
select count(*) from simple r full outer join simple s using (id);
rollback to settings;
-- parallelism not possible with parallel-oblivious outer hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
explain (costs off)
select count(*) from simple r full outer join simple s using (id);
select count(*) from simple r full outer join simple s using (id);
rollback to settings;
-- An full outer join where every record is not matched.
-- non-parallel
savepoint settings;
set local max_parallel_workers_per_gather = 0;
explain (costs off)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
rollback to settings;
-- parallelism not possible with parallel-oblivious outer hash join
savepoint settings;
set local max_parallel_workers_per_gather = 2;
explain (costs off)
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
select count(*) from simple r full outer join simple s on (r.id = 0 - s.id);
rollback to settings;
-- exercise special code paths for huge tuples (note use of non-strict
-- expression and left join required to get the detoasted tuple into
-- the hash table)
-- parallel with parallel-aware hash join (hits ExecParallelHashLoadTuple and
-- sts_puttuple oversized tuple cases because it's multi-batch)
savepoint settings;
set max_parallel_workers_per_gather = 2;
set enable_parallel_hash = on;
set work_mem = '128kB';
explain (costs off)
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
select final > 1 as multibatch
from hash_join_batches(
$$
select length(max(s.t))
from wide left join (select id, coalesce(t, '') || '' as t from wide) s using (id);
$$);
rollback to settings;
rollback;