Pouria created ASTERIXDB-1295:
---------------------------------
Summary: Unable to switch an implicit "sort-based" grouping into
"hash-based"
Key: ASTERIXDB-1295
URL: https://issues.apache.org/jira/browse/ASTERIXDB-1295
Project: Apache AsterixDB
Issue Type: Bug
Reporter: Pouria
Switching from the default "sort-based" grouping into "hash-based" via a hint
needs an explicit "group by" clause in the query. However, there are cases -
such as left-outer joins (see below) - where an implicit grouping is required
and gets added to the query plan, by the Optimizer, and it is impossible to
provide the "hash" hint to switch the physical grouping operator.
drop dataverse test if exists;
create dataverse test;
use dataverse test;
create type typeA as {
id: int64
}
create type typeB as {
id: int64,
fk: int64
}
create dataset dsa(typeA) primary key id;
create dataset dsb(typeB) primary key id;
insert into dataset dsa ( {"id": 1} );
insert into dataset dsa ( {"id": 2} );
insert into dataset dsb ( {"id": 1000, "fk": 1} );
insert into dataset dsb ( {"id": 1001, "fk": 1} );
insert into dataset dsb ( {"id": 2000, "fk": 2} );
for $a in dataset dsa
return {
"aid" : $a.id,
"val" : for $b in dataset dsb
where $b.fk = $a.id
return $b.id
}
distribute result [%0->$$3]
-- DISTRIBUTE_RESULT |PARTITIONED|
exchange
-- ONE_TO_ONE_EXCHANGE |PARTITIONED|
project ([$$3])
-- STREAM_PROJECT |PARTITIONED|
assign [$$3] <- [function-call: asterix:closed-record-constructor,
Args:[AString: {aid}, %0->$$17, AString: {val}, %0->$$10]]
-- ASSIGN |PARTITIONED|
project ([$$17, $$10])
-- STREAM_PROJECT |PARTITIONED|
exchange
-- ONE_TO_ONE_EXCHANGE |PARTITIONED|
group by ([$$11 := %0->$$14]) decor ([$$17 := %0->$$14]) {
aggregate [$$10] <- [function-call: asterix:listify,
Args:[%0->$$12]]
-- AGGREGATE |LOCAL|
select (function-call: algebricks:not,
Args:[function-call: algebricks:is-null, Args:[%0->$$13]])
-- STREAM_SELECT |LOCAL|
nested tuple source
-- NESTED_TUPLE_SOURCE |LOCAL|
}
-- PRE_CLUSTERED_GROUP_BY[$$14] |PARTITIONED|
exchange
-- ONE_TO_ONE_EXCHANGE |PARTITIONED|
order (ASC, %0->$$14)
-- STABLE_SORT [$$14(ASC)] |PARTITIONED|
exchange
-- ONE_TO_ONE_EXCHANGE |PARTITIONED|
project ([$$12, $$13, $$14])
-- STREAM_PROJECT |PARTITIONED|
exchange
-- ONE_TO_ONE_EXCHANGE |PARTITIONED|
left outer join (function-call: algebricks:eq,
Args:[%0->$$15, %0->$$14])
-- HYBRID_HASH_JOIN [$$14][$$15] |PARTITIONED|
exchange
-- ONE_TO_ONE_EXCHANGE |PARTITIONED|
project ([$$14])
-- STREAM_PROJECT |PARTITIONED|
exchange
-- ONE_TO_ONE_EXCHANGE |PARTITIONED|
data-scan []<-[$$14, $$0] <- test:dsa
-- DATASOURCE_SCAN |PARTITIONED|
exchange
-- ONE_TO_ONE_EXCHANGE |PARTITIONED|
empty-tuple-source
-- EMPTY_TUPLE_SOURCE |PARTITIONED|
exchange
-- HASH_PARTITION_EXCHANGE [$$15] |PARTITIONED|
project ([$$12, $$13, $$15])
-- STREAM_PROJECT |PARTITIONED|
assign [$$13, $$15] <- [TRUE, function-call:
asterix:field-access-by-index, Args:[%0->$$1, AInt32: {1}]]
-- ASSIGN |PARTITIONED|
exchange
-- ONE_TO_ONE_EXCHANGE |PARTITIONED|
data-scan []<-[$$12, $$1] <- test:dsb
-- DATASOURCE_SCAN |PARTITIONED|
exchange
-- ONE_TO_ONE_EXCHANGE |PARTITIONED|
empty-tuple-source
-- EMPTY_TUPLE_SOURCE |PARTITIONED|
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
