mirror of
https://github.com/apache/impala.git
synced 2026-01-07 09:02:19 -05:00
6f20df81f7
Fix a bug where the following queries on kudu and datasource tables were incorrectly being optimized as a 'small query' and therefore running on a single node with a single scanner thread: (A) that have all their predicates pushed to the underlying storage layer and have a limit (B) table stats missing + Conditions in (A) Testing: Added frontend planner tests. Change-Id: I93822d67ebda41d5d0456095c429e3915a3f40c4 Reviewed-on: http://gerrit.cloudera.org:8080/7560 Reviewed-by: Matthew Jacobs <mj@cloudera.com> Tested-by: Impala Public Jenkins
114 lines
4.0 KiB
Plaintext
114 lines
4.0 KiB
Plaintext
# Test implicit and explicit casts. Binary predicates containing an explicit cast
|
|
# cannot be offered to the data source.
|
|
select * from functional.alltypes_datasource
|
|
where tinyint_col < 256 and
|
|
float_col != 0 and
|
|
cast(int_col as bigint) < 10
|
|
---- PLAN
|
|
PLAN-ROOT SINK
|
|
|
|
|
00:SCAN DATA SOURCE [functional.alltypes_datasource]
|
|
data source predicates: tinyint_col < 256
|
|
predicates: float_col != 0, CAST(int_col AS BIGINT) < 10
|
|
====
|
|
# The first four predicates are in a form that can be offered to the data source
|
|
# and the first and third will be accepted (it accepts every other conjunct).
|
|
# The second and fourth will be evaluated by Impala. The negated predicates,
|
|
# i.e. NOT <PREDICATE>, are not in a form able to be offered to the data source,
|
|
# so they will always be evaluated by Impala.
|
|
select * from functional.alltypes_datasource
|
|
where 10 > int_col and
|
|
5 > double_col and
|
|
string_col != "Foo" and
|
|
string_col != "Bar" and
|
|
not true = bool_col and
|
|
not 5.0 = double_col
|
|
---- PLAN
|
|
PLAN-ROOT SINK
|
|
|
|
|
00:SCAN DATA SOURCE [functional.alltypes_datasource]
|
|
data source predicates: int_col < 10, string_col != 'Foo'
|
|
predicates: double_col < 5, NOT bool_col = TRUE, NOT double_col = 5.0, string_col != 'Bar'
|
|
====
|
|
# The 3rd predicate is not in a form that can be offered to the data source so
|
|
# the 4th will be offered and accepted instead.
|
|
select * from functional.alltypes_datasource
|
|
where int_col < 10 and
|
|
double_col > 5 and
|
|
string_col in ("Foo", "Bar") and
|
|
bool_col != false
|
|
---- PLAN
|
|
PLAN-ROOT SINK
|
|
|
|
|
00:SCAN DATA SOURCE [functional.alltypes_datasource]
|
|
data source predicates: int_col < 10, bool_col != FALSE
|
|
predicates: double_col > 5, string_col IN ('Foo', 'Bar')
|
|
====
|
|
# Tests that all predicates from the On-clause are applied (IMPALA-805)
|
|
# and that slot equivalences are enforced at lowest possible plan node
|
|
# for tables produced by a data source.
|
|
select 1 from functional.alltypes_datasource a
|
|
inner join functional.alltypes_datasource b
|
|
# equivalence class
|
|
on a.id = b.id and a.id = b.int_col and a.id = b.bigint_col
|
|
and a.tinyint_col = b.id and a.smallint_col = b.id
|
|
and a.int_col = b.id and a.bigint_col = b.id
|
|
# redundant predicates to test minimal spanning tree of equivalent slots
|
|
where a.tinyint_col = a.smallint_col and a.int_col = a.bigint_col
|
|
---- PLAN
|
|
PLAN-ROOT SINK
|
|
|
|
|
02:HASH JOIN [INNER JOIN]
|
|
| hash predicates: a.id = b.id
|
|
|
|
|
|--01:SCAN DATA SOURCE [functional.alltypes_datasource b]
|
|
|--predicates: b.id = b.int_col, b.id = b.bigint_col
|
|
|
|
|
00:SCAN DATA SOURCE [functional.alltypes_datasource a]
|
|
predicates: a.id = a.int_col, a.id = a.tinyint_col, a.int_col = a.bigint_col, a.tinyint_col = a.smallint_col
|
|
====
|
|
# Tests that <=>, IS DISTINCT FROM, and IS NOT DISTINCT FROM all can be offered to the
|
|
# data source.
|
|
select * from functional.alltypes_datasource
|
|
where id <=> 1
|
|
and bool_col <=> true
|
|
and tinyint_col IS DISTINCT FROM 2
|
|
and smallint_col IS DISTINCT FROM 3
|
|
and int_col is not distinct from 4
|
|
and bigint_col is not distinct from 5
|
|
---- PLAN
|
|
PLAN-ROOT SINK
|
|
|
|
|
00:SCAN DATA SOURCE [functional.alltypes_datasource]
|
|
data source predicates: id IS NOT DISTINCT FROM 1, tinyint_col IS DISTINCT FROM 2, int_col IS NOT DISTINCT FROM 4
|
|
predicates: bigint_col IS NOT DISTINCT FROM 5, bool_col IS NOT DISTINCT FROM TRUE, smallint_col IS DISTINCT FROM 3
|
|
====
|
|
# EmptySet datasource
|
|
select * from functional.alltypes_datasource
|
|
where id <=> 1 and id = 2
|
|
and bool_col <=> true
|
|
and tinyint_col IS DISTINCT FROM 2
|
|
and smallint_col IS DISTINCT FROM 3
|
|
and int_col is not distinct from 4
|
|
and bigint_col is not distinct from 5
|
|
---- PLAN
|
|
PLAN-ROOT SINK
|
|
|
|
|
00:EMPTYSET
|
|
====
|
|
---- QUERY
|
|
# IMPALA-5602: If a query contains predicates that are all pushed to the datasource and
|
|
# there is a limit, then the query should not incorrectly run with 'small query'
|
|
# optimization.
|
|
select * from functional.alltypes_datasource where id = 1 limit 15
|
|
---- DISTRIBUTEDPLAN
|
|
PLAN-ROOT SINK
|
|
|
|
|
01:EXCHANGE [UNPARTITIONED]
|
|
| limit: 15
|
|
|
|
|
00:SCAN DATA SOURCE [functional.alltypes_datasource]
|
|
data source predicates: id = 1
|
|
limit: 15
|
|
====
|