-- -- 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; explain (costs off) select count(*) from a_star; QUERY PLAN ----------------------------------------------------------- Finalize Aggregate -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Gather Workers Planned: 1 -> Partial Aggregate -> Append -> Parallel Seq Scan on a_star -> Parallel Seq Scan on b_star -> Parallel Seq Scan on c_star -> Parallel Seq Scan on d_star -> Parallel Seq Scan on e_star -> Parallel Seq Scan on f_star (12 rows) select count(*) from a_star; count ------- 50 (1 row) -- 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; QUERY PLAN --------------------------------------------------------------- Remote Subquery Scan on all (datanode_1,datanode_2) Output: parallel_restricted(unique1) Sort Key: parallel_restricted(tenk1.unique1) -> Sort Output: (parallel_restricted(unique1)) Sort Key: (parallel_restricted(tenk1.unique1)) -> Gather Output: parallel_restricted(unique1) Workers Planned: 4 -> Parallel Seq Scan on public.tenk1 Output: unique1 Filter: (tenk1.stringu1 = 'GRAAAA'::name) (12 rows) -- test parallel plan when group by expression is in target list. explain (costs off) select length(stringu1) from tenk1 group by length(stringu1); QUERY PLAN ----------------------------------------------------------- Finalize HashAggregate Group Key: length((stringu1)::text) -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Gather Workers Planned: 4 -> Partial HashAggregate Group Key: length((stringu1)::text) -> Parallel Seq Scan on tenk1 (8 rows) select length(stringu1) from tenk1 group by length(stringu1); length -------- 6 (1 row) explain (costs off) select stringu1, count(*) from tenk1 group by stringu1 order by stringu1; QUERY PLAN ----------------------------------------------------------- Finalize GroupAggregate Group Key: stringu1 -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Sort Sort Key: stringu1 -> Partial HashAggregate Group Key: stringu1 -> Gather Workers Planned: 4 -> Parallel Seq Scan on tenk1 (10 rows) -- 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)); QUERY PLAN ------------------------------------------------------------------------- HashAggregate Group Key: parallel_restricted(unique1) -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Gather Workers Planned: 4 -> Parallel Index Only Scan using tenk1_unique1 on tenk1 (6 rows) -- 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); QUERY PLAN ------------------------------------------------------------------------------------- Finalize Aggregate -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Gather Workers Planned: 4 -> Partial Aggregate -> Parallel Seq Scan on tenk1 Filter: (NOT (hashed SubPlan 1)) SubPlan 1 -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Seq Scan on tenk2 Filter: (thousand > 100) (11 rows) select count(*) from tenk1 where (two, four) not in (select hundred, thousand from tenk2 where thousand > 100); count ------- 10000 (1 row) -- 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); QUERY PLAN ------------------------------------------------------------------- Remote Subquery Scan on all (datanode_1,datanode_2) -> Seq Scan on tenk1 Filter: (NOT (hashed SubPlan 1)) SubPlan 1 -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Seq Scan on tenk2 (6 rows) 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; QUERY PLAN -------------------------------------------------------------------------- Finalize Aggregate -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Gather Workers Planned: 4 -> Partial Aggregate -> Parallel Index Scan using tenk1_hundred on tenk1 Index Cond: (hundred > 1) (7 rows) select count((unique1)) from tenk1 where hundred > 1; count ------- 9800 (1 row) -- test parallel index-only scans. explain (costs off) select count(*) from tenk1 where thousand > 95; QUERY PLAN -------------------------------------------------------------------------------------- Finalize Aggregate -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Gather Workers Planned: 4 -> Partial Aggregate -> Parallel Index Only Scan using tenk1_thous_tenthous on tenk1 Index Cond: (thousand > 95) (7 rows) select count(*) from tenk1 where thousand > 95; count ------- 9040 (1 row) 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 $$ --BEGIN -- SET effective_io_concurrency = 50; --END $$; 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; QUERY PLAN ------------------------------------------------------------------------ Aggregate -> Nested Loop -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Seq Scan on tenk2 Filter: (thousand = 0) -> Materialize -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Gather Workers Planned: 4 -> Parallel Bitmap Heap Scan on tenk1 Recheck Cond: (hundred > 1) -> Bitmap Index Scan on tenk1_hundred Index Cond: (hundred > 1) (13 rows) select count(*) from tenk1, tenk2 where tenk1.hundred > 1 and tenk2.thousand=0; count ------- 98000 (1 row) 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; count ------- 99999 (1 row) 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; QUERY PLAN ------------------------------------------------------------------------------------- Finalize Aggregate -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Gather Workers Planned: 4 -> Partial Aggregate -> Merge Join Merge Cond: (tenk1.unique1 = tenk2.unique1) -> Parallel Index Only Scan using tenk1_unique1 on tenk1 -> Index Only Scan using tenk2_unique1 on tenk2 (9 rows) select count(*) from tenk1, tenk2 where tenk1.unique1 = tenk2.unique1; count ------- 10000 (1 row) reset enable_hashjoin; reset enable_nestloop; --test gather merge set enable_hashagg to off; explain (costs off) select string4, count((unique2)) from tenk1 group by string4 order by string4; QUERY PLAN ----------------------------------------------------------- Finalize GroupAggregate Group Key: string4 -> Remote Subquery Scan on all (datanode_1,datanode_2) -> Gather Merge Workers Planned: 4 -> Partial GroupAggregate Group Key: string4 -> Sort Sort Key: string4 -> Parallel Seq Scan on tenk1 (10 rows) select string4, count((unique2)) from tenk1 group by string4 order by string4; string4 | count ---------+------- AAAAxx | 2500 HHHHxx | 2500 OOOOxx | 2500 VVVVxx | 2500 (4 rows) reset enable_hashagg; set force_parallel_mode=1; explain (costs off) select stringu1::int2 from tenk1 where unique1 = 1; QUERY PLAN ----------------------------------------------------- Remote Fast Query Execution Node/s: datanode_1 -> Gather Workers Planned: 1 Single Copy: true -> Index Scan using tenk1_unique1 on tenk1 Index Cond: (unique1 = 1) (7 rows) -- to increase the parallel query test coverage EXPLAIN (timing off, summary off, costs off) SELECT * FROM tenk1; QUERY PLAN ---------------------------------------- Remote Fast Query Execution Node/s: datanode_1, datanode_2 -> Gather Workers Planned: 4 -> Parallel Seq Scan on tenk1 (5 rows) EXPLAIN (analyze, timing off, summary off, costs off) SELECT * FROM tenk1; QUERY PLAN --------------------------------------------------------- Remote Fast Query Execution (actual rows=10000 loops=1) Node/s: datanode_1, datanode_2 (2 rows) -- provoke error in worker select stringu1::int2 from tenk1 where unique1 = 1; ERROR: invalid input syntax for integer: "BAAAAA" CONTEXT: parallel worker rollback;