mirror of
https://github.com/apache/impala.git
synced 2026-01-05 03:01:02 -05:00
3e632ef6ad
Update PA/PHJ to use small (< io sized buffers) initially. Without this we would not be able to run at the QPS that we need just due to the buffering requirements of these operators. Change-Id: Ic8a777d147893567c9590fbab17f561eadb6ee19 Reviewed-on: http://gerrit.sjc.cloudera.com:8080/4623 Tested-by: jenkins Reviewed-by: Nong Li <nong@cloudera.com>
161 lines
3.1 KiB
Plaintext
161 lines
3.1 KiB
Plaintext
====
|
|
---- QUERY
|
|
set num_nodes=1;
|
|
set max_block_mgr_memory=15m;
|
|
select l_orderkey, count(*)
|
|
from lineitem
|
|
group by 1
|
|
order by 1 limit 10;
|
|
---- RESULTS
|
|
1,6
|
|
2,1
|
|
3,6
|
|
4,1
|
|
5,3
|
|
6,1
|
|
7,7
|
|
32,6
|
|
33,4
|
|
34,3
|
|
---- TYPES
|
|
BIGINT, BIGINT
|
|
====
|
|
---- QUERY
|
|
# Test query with string grouping column and string agg columns
|
|
set num_nodes=1;
|
|
set max_block_mgr_memory=20m;
|
|
select l_returnflag, l_orderkey, avg(l_tax), min(l_shipmode)
|
|
from lineitem
|
|
group by 1,2
|
|
order by 1,2 limit 3;
|
|
---- RESULTS
|
|
'A',3,0.05,'RAIL'
|
|
'A',5,0.03,'AIR'
|
|
'A',6,0.03,'TRUCK'
|
|
---- TYPES
|
|
STRING, BIGINT, DECIMAL, STRING
|
|
====
|
|
---- QUERY
|
|
# TODO: the distributed agg tests have a high likely of becoming flaking. The memory is
|
|
# split between the local and merge agg in an uncontrolled way which can lead to
|
|
# pathological cases causing the queries to fail with OOM. These cases are expected
|
|
# to be unlikely with reasonable limits but we are explicitly trying to pick very low
|
|
# limits. (IMPALA-1305)
|
|
set max_block_mgr_memory=45m;
|
|
select l_orderkey, count(*)
|
|
from lineitem
|
|
group by 1
|
|
order by 1 limit 10;
|
|
---- RESULTS
|
|
1,6
|
|
2,1
|
|
3,6
|
|
4,1
|
|
5,3
|
|
6,1
|
|
7,7
|
|
32,6
|
|
33,4
|
|
34,3
|
|
---- TYPES
|
|
BIGINT, BIGINT
|
|
====
|
|
---- QUERY
|
|
# Test query with string intermediate state.
|
|
set num_nodes=0;
|
|
set max_block_mgr_memory=50m;
|
|
select l_orderkey, avg(l_orderkey)
|
|
from lineitem
|
|
group by 1
|
|
order by 1 limit 5;
|
|
---- RESULTS
|
|
1,1
|
|
2,2
|
|
3,3
|
|
4,4
|
|
5,5
|
|
---- TYPES
|
|
BIGINT, DOUBLE
|
|
====
|
|
---- QUERY
|
|
# Test query with string grouping column
|
|
set num_nodes=0;
|
|
set max_block_mgr_memory=160m;
|
|
select l_comment, count(*)
|
|
from lineitem
|
|
group by 1
|
|
order by count(*) desc limit 5;
|
|
---- RESULTS
|
|
' furiously',943
|
|
' carefully',893
|
|
' carefully ',875
|
|
'carefully ',854
|
|
' furiously ',845
|
|
---- TYPES
|
|
STRING, BIGINT
|
|
====
|
|
---- QUERY
|
|
# Test query with string grouping column and string agg columns
|
|
set num_nodes=0;
|
|
set max_block_mgr_memory=80m;
|
|
select l_returnflag, l_orderkey, avg(l_tax), min(l_shipmode)
|
|
from lineitem
|
|
group by 1,2
|
|
order by 1,2 limit 3;
|
|
---- RESULTS
|
|
'A',3,0.05,'RAIL'
|
|
'A',5,0.03,'AIR'
|
|
'A',6,0.03,'TRUCK'
|
|
---- TYPES
|
|
STRING, BIGINT, DECIMAL, STRING
|
|
====
|
|
---- QUERY
|
|
set num_nodes=0;
|
|
set max_block_mgr_memory=100m;
|
|
select count(l1.l_tax)
|
|
from
|
|
lineitem l1,
|
|
lineitem l2,
|
|
lineitem l3
|
|
where
|
|
l1.l_tax < 0.01 and
|
|
l2.l_tax < 0.04 and
|
|
l1.l_orderkey = l2.l_orderkey and
|
|
l1.l_orderkey = l3.l_orderkey and
|
|
l1.l_comment = l3.l_comment and
|
|
l1.l_shipdate = l3.l_shipdate;
|
|
---- RESULTS
|
|
1846743
|
|
---- TYPES
|
|
BIGINT
|
|
====
|
|
---- QUERY
|
|
set num_nodes=0;
|
|
set max_block_mgr_memory=45m;
|
|
select max(t1.total_count), max(t1.l_shipinstruct), max(t1.l_comment) from
|
|
(select l_shipinstruct, l_comment, count(*) over () total_count from lineitem) t1
|
|
---- RESULTS
|
|
6001215,'TAKE BACK RETURN','zzle? slyly final platelets sleep quickly. '
|
|
---- TYPES
|
|
BIGINT, STRING, STRING
|
|
---- QUERY
|
|
# Run this query with very low memory. Since the tables are small, the PA/PHJ should be
|
|
# using buffers much smaller than the io buffer.
|
|
set max_block_mgr_memory=10m;
|
|
select a.int_col, count(*)
|
|
from functional.alltypessmall a, functional.alltypessmall b, functional.alltypessmall c
|
|
where a.id = b.id and b.id = c.id group by a.int_col;
|
|
---- RESULTS
|
|
0,12
|
|
1,12
|
|
2,12
|
|
3,12
|
|
4,12
|
|
5,8
|
|
6,8
|
|
7,8
|
|
8,8
|
|
9,8
|
|
---- TYPES
|
|
INT, BIGINT
|