mirror of
https://github.com/apache/impala.git
synced 2026-01-22 09:01:58 -05:00
6601327af6
This patch limits the number of rows produced by a query by tracking it at the PlanRootSink level. When the NUM_ROWS_PRODUCED_LIMIT is set, it cancels a query when its execution produces more rows than the specified limit. This limit only applies when the results are returned to a client, e.g. for a SELECT query, but not an INSERT query. Testing: Added tests to query-resource-limits.test to verify that the rows produced limit is honored. Manually tested on various combinations of tables, fileformats and ROWS_RETURNED_LIMIT values. Change-Id: I7b22dbe130a368f4be1f3662a559eb9aae7f0c1d Reviewed-on: http://gerrit.cloudera.org:8080/12328 Reviewed-by: Tim Armstrong <tarmstrong@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
71 lines
2.5 KiB
Plaintext
71 lines
2.5 KiB
Plaintext
====
|
|
---- QUERY
|
|
# Query should succeed.
|
|
set CPU_LIMIT_S=10000;
|
|
set SCAN_BYTES_LIMIT="10G";
|
|
select id from functional.alltypessmall order by 1 limit 1
|
|
---- TYPES
|
|
INT
|
|
---- RESULTS
|
|
0
|
|
====
|
|
---- QUERY
|
|
# Query should fail due to exceeding scan bytes limit.
|
|
# Added a sleep to make sure it runs long enough to get a non-zero update from the
|
|
# fragment instances on the num of bytes read and cpu time.
|
|
set SCAN_BYTES_LIMIT="100M";
|
|
select sleep(10000) union select count(*) from tpch.lineitem l1,tpch.lineitem l2,
|
|
tpch.lineitem l3 where l1.l_suppkey = l2.l_linenumber and l1.l_orderkey = l2.l_orderkey
|
|
and l1.l_orderkey = l3.l_orderkey group by l1.l_comment, l2.l_comment having count(*) = 99
|
|
---- CATCH
|
|
row_regex:.*terminated due to scan bytes limit of 100.00 M.*
|
|
====
|
|
---- QUERY
|
|
# Query should fail due to CPU time limit.
|
|
# Added a sleep to make sure it runs long enough to get a non-zero update from the
|
|
# fragment instances on the num of bytes read and cpu time.
|
|
set CPU_LIMIT_S=1;
|
|
select sleep(10000) union select count(*) from tpch.lineitem l1,tpch.lineitem l2,
|
|
tpch.lineitem l3 where l1.l_suppkey = l2.l_linenumber and l1.l_orderkey = l2.l_orderkey
|
|
and l1.l_orderkey = l3.l_orderkey group by l1.l_comment, l2.l_comment having count(*) = 99
|
|
---- CATCH
|
|
row_regex:.*terminated due to CPU limit of 1s000ms.*
|
|
====
|
|
---- QUERY
|
|
# Query should fail due to CPU time limit.
|
|
# Added a sleep to make sure it runs long enough to get a non-zero update from the
|
|
# fragment instances on the num of bytes read and cpu time.
|
|
set CPU_LIMIT_S=1;
|
|
set SCAN_BYTES_LIMIT="100G";
|
|
select sleep(10000) union select count(*) from tpch.lineitem l1,tpch.lineitem l2,
|
|
tpch.lineitem l3 where l1.l_suppkey = l2.l_linenumber and l1.l_orderkey = l2.l_orderkey
|
|
and l1.l_orderkey = l3.l_orderkey group by l1.l_comment, l2.l_comment having count(*) = 99
|
|
---- CATCH
|
|
row_regex:.*terminated due to CPU limit of 1s000ms.*
|
|
====
|
|
---- QUERY
|
|
# Query should fail due to exceeding time limit.
|
|
set EXEC_TIME_LIMIT_S=2;
|
|
select sleep(10000)
|
|
---- CATCH
|
|
row_regex:.*expired due to execution time limit of 2s000ms.*
|
|
====
|
|
---- QUERY
|
|
# Query should fail due to exceeding rows produced limit.
|
|
set NUM_ROWS_PRODUCED_LIMIT = 10000;
|
|
select * from tpch.lineitem;
|
|
---- CATCH
|
|
row_regex:.*terminated due to rows produced limit of 10000.*
|
|
====
|
|
---- QUERY
|
|
# The query should succeed when it doesn't exceed the rows produced limit.
|
|
set NUM_ROWS_PRODUCED_LIMIT = 3;
|
|
select * from functional.tinytable;
|
|
---- TYPES
|
|
STRING,STRING
|
|
---- RESULTS
|
|
'aaaaaaa','bbbbbbb'
|
|
'ccccc','dddd'
|
|
'eeeeeeee','f'
|
|
====
|