postgresql/src/test/regress/sql/select_parallel.sql

330 lines
10 KiB
MySQL
Raw Normal View History

--
-- PARALLEL
--
create or replace function parallel_restricted(int) returns int as
$$begin return $1; end$$ language plpgsql parallel restricted;
-- Serializable isolation would disable parallel query, so explicitly use an
-- arbitrary other level.
begin isolation level repeatable read;
-- encourage use of parallel plans
set parallel_setup_cost=0;
set parallel_tuple_cost=0;
set min_parallel_table_scan_size=0;
set max_parallel_workers_per_gather=4;
-- Parallel Append with partial-subplans
explain (costs off)
select round(avg(aa)), sum(aa) from a_star;
select round(avg(aa)), sum(aa) from a_star a1;
-- Parallel Append with both partial and non-partial subplans
alter table c_star set (parallel_workers = 0);
alter table d_star set (parallel_workers = 0);
explain (costs off)
select round(avg(aa)), sum(aa) from a_star;
select round(avg(aa)), sum(aa) from a_star a2;
-- Parallel Append with only non-partial subplans
alter table a_star set (parallel_workers = 0);
alter table b_star set (parallel_workers = 0);
alter table e_star set (parallel_workers = 0);
alter table f_star set (parallel_workers = 0);
explain (costs off)
select round(avg(aa)), sum(aa) from a_star;
select round(avg(aa)), sum(aa) from a_star a3;
-- Disable Parallel Append
alter table a_star reset (parallel_workers);
alter table b_star reset (parallel_workers);
alter table c_star reset (parallel_workers);
alter table d_star reset (parallel_workers);
alter table e_star reset (parallel_workers);
alter table f_star reset (parallel_workers);
set enable_parallel_append to off;
explain (costs off)
select round(avg(aa)), sum(aa) from a_star;
select round(avg(aa)), sum(aa) from a_star a4;
reset enable_parallel_append;
-- test with leader participation disabled
set parallel_leader_participation = off;
explain (costs off)
select count(*) from tenk1 where stringu1 = 'GRAAAA';
select count(*) from tenk1 where stringu1 = 'GRAAAA';
-- test with leader participation disabled, but no workers available (so
-- the leader will have to run the plan despite the setting)
set max_parallel_workers = 0;
explain (costs off)
select count(*) from tenk1 where stringu1 = 'GRAAAA';
select count(*) from tenk1 where stringu1 = 'GRAAAA';
reset max_parallel_workers;
reset parallel_leader_participation;
-- test that parallel_restricted function doesn't run in worker
alter table tenk1 set (parallel_workers = 4);
explain (verbose, costs off)
select parallel_restricted(unique1) from tenk1
where stringu1 = 'GRAAAA' order by 1;
-- test parallel plan when group by expression is in target list.
explain (costs off)
select length(stringu1) from tenk1 group by length(stringu1);
select length(stringu1) from tenk1 group by length(stringu1);
explain (costs off)
select stringu1, count(*) from tenk1 group by stringu1 order by stringu1;
-- test that parallel plan for aggregates is not selected when
-- target list contains parallel restricted clause.
explain (costs off)
select sum(parallel_restricted(unique1)) from tenk1
group by(parallel_restricted(unique1));
-- test prepared statement
prepare tenk1_count(integer) As select count((unique1)) from tenk1 where hundred > $1;
explain (costs off) execute tenk1_count(1);
execute tenk1_count(1);
deallocate tenk1_count;
-- test parallel plans for queries containing un-correlated subplans.
alter table tenk2 set (parallel_workers = 0);
explain (costs off)
select count(*) from tenk1 where (two, four) not in
(select hundred, thousand from tenk2 where thousand > 100);
select count(*) from tenk1 where (two, four) not in
(select hundred, thousand from tenk2 where thousand > 100);
-- this is not parallel-safe due to use of random() within SubLink's testexpr:
explain (costs off)
select * from tenk1 where (unique1 + random())::integer not in
(select ten from tenk2);
alter table tenk2 reset (parallel_workers);
-- test parallel plan for a query containing initplan.
set enable_indexscan = off;
set enable_indexonlyscan = off;
set enable_bitmapscan = off;
alter table tenk2 set (parallel_workers = 2);
explain (costs off)
select count(*) from tenk1
where tenk1.unique1 = (Select max(tenk2.unique1) from tenk2);
select count(*) from tenk1
where tenk1.unique1 = (Select max(tenk2.unique1) from tenk2);
reset enable_indexscan;
reset enable_indexonlyscan;
reset enable_bitmapscan;
alter table tenk2 reset (parallel_workers);
-- test parallel index scans.
set enable_seqscan to off;
set enable_bitmapscan to off;
explain (costs off)
select count((unique1)) from tenk1 where hundred > 1;
select count((unique1)) from tenk1 where hundred > 1;
-- test parallel index-only scans.
explain (costs off)
select count(*) from tenk1 where thousand > 95;
select count(*) from tenk1 where thousand > 95;
-- test rescan cases too
set enable_material = false;
explain (costs off)
select * from
(select count(unique1) from tenk1 where hundred > 10) ss
right join (values (1),(2),(3)) v(x) on true;
select * from
(select count(unique1) from tenk1 where hundred > 10) ss
right join (values (1),(2),(3)) v(x) on true;
explain (costs off)
select * from
(select count(*) from tenk1 where thousand > 99) ss
right join (values (1),(2),(3)) v(x) on true;
select * from
(select count(*) from tenk1 where thousand > 99) ss
right join (values (1),(2),(3)) v(x) on true;
reset enable_material;
reset enable_seqscan;
reset enable_bitmapscan;
-- test parallel bitmap heap scan.
set enable_seqscan to off;
set enable_indexscan to off;
set enable_hashjoin to off;
set enable_mergejoin to off;
set enable_material to off;
-- test prefetching, if the platform allows it
DO $$
BEGIN
SET effective_io_concurrency = 50;
EXCEPTION WHEN invalid_parameter_value THEN
END $$;
set work_mem='64kB'; --set small work mem to force lossy pages
explain (costs off)
select count(*) from tenk1, tenk2 where tenk1.hundred > 1 and tenk2.thousand=0;
select count(*) from tenk1, tenk2 where tenk1.hundred > 1 and tenk2.thousand=0;
create table bmscantest (a int, t text);
insert into bmscantest select r, 'fooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooo' FROM generate_series(1,100000) r;
create index i_bmtest ON bmscantest(a);
select count(*) from bmscantest where a>1;
reset enable_seqscan;
reset enable_indexscan;
reset enable_hashjoin;
reset enable_mergejoin;
reset enable_material;
reset effective_io_concurrency;
reset work_mem;
drop table bmscantest;
-- test parallel merge join path.
set enable_hashjoin to off;
set enable_nestloop to off;
explain (costs off)
select count(*) from tenk1, tenk2 where tenk1.unique1 = tenk2.unique1;
select count(*) from tenk1, tenk2 where tenk1.unique1 = tenk2.unique1;
reset enable_hashjoin;
reset enable_nestloop;
-- test gather merge
set enable_hashagg = false;
explain (costs off)
select count(*) from tenk1 group by twenty;
select count(*) from tenk1 group by twenty;
--test expressions in targetlist are pushed down for gather merge
create or replace function simple_func(var1 integer) returns integer
as $$
begin
return var1 + 10;
end;
$$ language plpgsql PARALLEL SAFE;
explain (costs off, verbose)
select ten, simple_func(ten) from tenk1 where ten < 100 order by ten;
drop function simple_func(integer);
-- test gather merge with parallel leader participation disabled
set parallel_leader_participation = off;
explain (costs off)
select count(*) from tenk1 group by twenty;
select count(*) from tenk1 group by twenty;
reset parallel_leader_participation;
--test rescan behavior of gather merge
set enable_material = false;
explain (costs off)
select * from
(select string4, count(unique2)
from tenk1 group by string4 order by string4) ss
right join (values (1),(2),(3)) v(x) on true;
select * from
(select string4, count(unique2)
from tenk1 group by string4 order by string4) ss
right join (values (1),(2),(3)) v(x) on true;
reset enable_material;
reset enable_hashagg;
Prevent int128 from requiring more than MAXALIGN alignment. Our initial work with int128 neglected alignment considerations, an oversight that came back to bite us in bug #14897 from Vincent Lachenal. It is unsurprising that int128 might have a 16-byte alignment requirement; what's slightly more surprising is that even notoriously lax Intel chips sometimes enforce that. Raising MAXALIGN seems out of the question: the costs in wasted disk and memory space would be significant, and there would also be an on-disk compatibility break. Nor does it seem very practical to try to allow some data structures to have more-than-MAXALIGN alignment requirement, as we'd have to push knowledge of that throughout various code that copies data structures around. The only way out of the box is to make type int128 conform to the system's alignment assumptions. Fortunately, gcc supports that via its __attribute__(aligned()) pragma; and since we don't currently support int128 on non-gcc-workalike compilers, we shouldn't be losing any platform support this way. Although we could have just done pg_attribute_aligned(MAXIMUM_ALIGNOF) and called it a day, I did a little bit of extra work to make the code more portable than that: it will also support int128 on compilers without __attribute__(aligned()), if the native alignment of their 128-bit-int type is no more than that of int64. Add a regression test case that exercises the one known instance of the problem, in parallel aggregation over a bigint column. This will need to be back-patched, along with the preparatory commit 91aec93e6. But let's see what the buildfarm makes of it first. Discussion: https://postgr.es/m/20171110185747.31519.28038@wrigleys.postgresql.org
2017-11-14 21:03:55 +01:00
-- check parallelized int8 aggregate (bug #14897)
explain (costs off)
select avg(unique1::int8) from tenk1;
select avg(unique1::int8) from tenk1;
-- gather merge test with a LIMIT
explain (costs off)
select fivethous from tenk1 order by fivethous limit 4;
select fivethous from tenk1 order by fivethous limit 4;
-- gather merge test with 0 worker
set max_parallel_workers = 0;
explain (costs off)
select string4 from tenk1 order by string4 limit 5;
select string4 from tenk1 order by string4 limit 5;
-- gather merge test with 0 workers, with parallel leader
-- participation disabled (the leader will have to run the plan
-- despite the setting)
set parallel_leader_participation = off;
explain (costs off)
select string4 from tenk1 order by string4 limit 5;
select string4 from tenk1 order by string4 limit 5;
reset parallel_leader_participation;
reset max_parallel_workers;
SAVEPOINT settings;
SET LOCAL force_parallel_mode = 1;
explain (costs off)
select stringu1::int2 from tenk1 where unique1 = 1;
ROLLBACK TO SAVEPOINT settings;
-- exercise record typmod remapping between backends
CREATE OR REPLACE FUNCTION make_record(n int)
RETURNS RECORD LANGUAGE plpgsql PARALLEL SAFE AS
$$
BEGIN
RETURN CASE n
WHEN 1 THEN ROW(1)
WHEN 2 THEN ROW(1, 2)
WHEN 3 THEN ROW(1, 2, 3)
WHEN 4 THEN ROW(1, 2, 3, 4)
ELSE ROW(1, 2, 3, 4, 5)
END;
END;
$$;
SAVEPOINT settings;
SET LOCAL force_parallel_mode = 1;
SELECT make_record(x) FROM (SELECT generate_series(1, 5) x) ss ORDER BY x;
ROLLBACK TO SAVEPOINT settings;
DROP function make_record(n int);
-- test the sanity of parallel query after the active role is dropped.
drop role if exists regress_parallel_worker;
create role regress_parallel_worker;
set role regress_parallel_worker;
reset session authorization;
drop role regress_parallel_worker;
set force_parallel_mode = 1;
select count(*) from tenk1;
reset force_parallel_mode;
reset role;
-- to increase the parallel query test coverage
SAVEPOINT settings;
SET LOCAL force_parallel_mode = 1;
EXPLAIN (analyze, timing off, summary off, costs off) SELECT * FROM tenk1;
ROLLBACK TO SAVEPOINT settings;
-- provoke error in worker
SAVEPOINT settings;
SET LOCAL force_parallel_mode = 1;
select stringu1::int2 from tenk1 where unique1 = 1;
ROLLBACK TO SAVEPOINT settings;
rollback;