mirror of
https://github.com/apache/impala.git
synced 2026-01-01 18:00:30 -05:00
88448d1d4a
This patch ensures that setting the query option enable_expr_rewrites=false will disable both constant folding in the frontend (which it did already) and constant caching in the backend (which is enabled in this patch). This gives a way for users to revert to the old behaviour of non-deterministic UDFs before these optimisations were added in Impala 2.8. Before this patch, the backend would cache values based on IsConstant(). This meant that there was no way to override caching of values of non-deterministic UDFs, e.g. with enable_expr_rewrites. After this patch, we only cache literal values in the backend. This offers the same performance as before in the common case where the frontend will constant fold the expressions anyway. Also rename some functions to more cleanly separate the backend concepts of "constant" expressions and expressions that can be evaluated without a TupleRow. In a future change (IMPALA-4617) we should remove the IsConstant() analysis logic from the backend entirely and pass the information from the frontend. We should also fix isConstant() in the frontend so that it only returns true when it is safe to constant-fold the expression (IMPALA-4606). Once that is done, we could revert back to using IsConstant() instead of IsLiteral(). Testing: Added targeted test to test constant folding of UDFs: we expect different results depending on whether constant folding is enabled. Also run TestUdfs with expr rewrites enabled and disabled, since this can exercise different code paths. Refactored test_udfs somewhat to avoid running uninteresting combinations of query options for targeted tests and removed some 'drop * if not exists' statements that aren't necessary when using unique_database. This change revealed flakiness in test_mem_limit, which seems to have only worked by coincidence. Updated TrackAllocation() to actually set the query status when a memory limit is exceeded. Looped this test for a while to make sure it isn't flaky any more. Also fix other test bugs where the vector argument is modified in-place, which can leak out to other tests. Change-Id: I0c76e3c8a8d92749256c312080ecd7aac5d99ce7 Reviewed-on: http://gerrit.cloudera.org:8080/5391 Reviewed-by: Tim Armstrong <tarmstrong@cloudera.com> Tested-by: Impala Public Jenkins
114 lines
2.1 KiB
Plaintext
114 lines
2.1 KiB
Plaintext
====
|
|
---- QUERY
|
|
# hdfs table sink
|
|
drop table if exists udfinserttest;
|
|
create table udfinserttest (udf_was_opened boolean);
|
|
|
|
insert overwrite table udfinserttest
|
|
select validate_open(int_col) from functional.alltypestiny limit 1;
|
|
====
|
|
---- QUERY
|
|
select * from udfinserttest;
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
true
|
|
====
|
|
---- QUERY
|
|
# merge node
|
|
select validate_open(0);
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
true
|
|
====
|
|
---- QUERY
|
|
# merge node with conjuncts
|
|
select validate_open(0) from functional.alltypestiny where validate_open(0) limit 1;
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
true
|
|
====
|
|
---- QUERY
|
|
# hdfs scan node
|
|
select count(*) from functional.alltypestiny where validate_open(int_col);
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
8
|
|
====
|
|
---- QUERY
|
|
# aggregation
|
|
select validate_open(int_col), count(*) from functional.alltypestiny
|
|
group by validate_open(int_col)
|
|
---- TYPES
|
|
boolean, bigint
|
|
---- RESULTS
|
|
true,8
|
|
====
|
|
---- QUERY
|
|
# aggregation
|
|
select count(if(validate_open(int_col), null, 1)) from functional.alltypestiny
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
0
|
|
====
|
|
---- QUERY
|
|
# aggregation (conjuncts)
|
|
select int_col, count(*) from functional.alltypestiny
|
|
group by int_col having validate_open(int_col)
|
|
---- TYPES
|
|
int, bigint
|
|
---- RESULTS
|
|
0,4
|
|
1,4
|
|
====
|
|
---- QUERY
|
|
# hash join
|
|
select b.bool_col from functional.alltypestiny a join functional.alltypestiny b
|
|
on validate_open(a.int_col) = b.bool_col
|
|
where a.month = 3 and b.month = 3
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
true
|
|
true
|
|
====
|
|
---- QUERY
|
|
# hash join (other join predicate)
|
|
select count(*) from functional.alltypestiny a left outer join functional.alltypessmall b
|
|
on (a.bigint_col = b.bigint_col and validate_open(a.int_col))
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
96
|
|
====
|
|
---- QUERY
|
|
# hash join (other predicate)
|
|
select count(*) from functional.alltypestiny a left outer join functional.alltypessmall b
|
|
on (a.bigint_col = b.bigint_col)
|
|
where validate_open(a.int_col) = validate_open(b.int_col)
|
|
and validate_open(a.int_col)
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
96
|
|
====
|
|
---- QUERY
|
|
# coordinator
|
|
select validate_open(int_col) from functional.alltypestiny;
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
true
|
|
true
|
|
true
|
|
true
|
|
true
|
|
true
|
|
true
|
|
true
|
|
====
|