lgbo-ustc opened a new issue, #5497:
URL: https://github.com/apache/incubator-gluten/issues/5497
### Backend
CH (ClickHouse)
### Bug description
Run following sql
```sql
select t1.n_nationkey as x, t1.n_regionkey, t2.n_nationkey as y from
tpch_pq.nation as t1 left join
default.nation as t2
on t1.n_nationkey = t2.n_nationkey
where t2.n_nationkey > 1 order by x;
```
We have following plan
```
== Physical Plan ==
CHNativeColumnarToRow
+- ^(61) SortExecTransformer [x#251L ASC NULLS FIRST], true, 0
+- ^(61) InputIteratorTransformer[x#251L, n_regionkey#4L, y#252L]
+- ^(61) InputAdapter
+- ^(61) ColumnarExchange rangepartitioning(x#251L ASC NULLS FIRST,
5), ENSURE_REQUIREMENTS, [plan_id=2232], [id=#2232], [OUTPUT] List(x:LongType,
n_regionkey:LongType, y:LongType), [OUTPUT] List(x:LongType,
n_regionkey:LongType, y:LongType)
+- ^(60) ProjectExecTransformer [n_nationkey#2L AS x#251L,
n_regionkey#4L, n_nationkey#172L AS y#252L]
+- ^(60) CHShuffledHashJoinExecTransformer [n_nationkey#2L],
[n_nationkey#172L], Inner, BuildRight
:- ^(60) InputIteratorTransformer[n_nationkey#2L,
n_regionkey#4L]
: +- ^(60) InputAdapter
: +- ^(60) ColumnarExchange
hashpartitioning(n_nationkey#2L, 5), ENSURE_REQUIREMENTS, [plan_id=2222],
[id=#2222], [OUTPUT] List(n_nationkey:LongType, n_regionkey:LongType), [OUTPUT]
List(n_nationkey:LongType, n_regionkey:LongType)
: +- ^(58) FilterExecTransformer (((n_nationkey#2L
> 1) AND isnotnull(n_nationkey#2L)) AND might_contain(Subquery
scalar-subquery#258, [id=#2138], xxhash64(n_nationkey#2L, 42)))
: : +- Subquery scalar-subquery#258, [id=#2138]
: : +- CHNativeColumnarToRow
: : +- ^(57)
HashAggregateTransformer(keys=[],
functions=[bloom_filter_agg(xxhash64(n_nationkey#172L, 42), 1000000, 8388608,
0, 0)], output=[bloomFilter#257])
: : +- ^(57)
InputIteratorTransformer[buf#260]
: : +- ^(57) InputAdapter
: : +- ^(57) ColumnarExchange
SinglePartition, ENSURE_REQUIREMENTS, [plan_id=2132], [id=#2132], [OUTPUT]
List(buf:BinaryType), [OUTPUT] List(buf:BinaryType)
: : +- ^(56)
HashAggregateTransformer(keys=[],
functions=[partial_bloom_filter_agg(_pre_6#261L, 1000000, 8388608, 0, 0)],
output=[buf#260])
: : +- ^(56)
ProjectExecTransformer [n_nationkey#172L, xxhash64(n_nationkey#172L, 42) AS
_pre_6#261L]
: : +- ^(56)
FilterExecTransformer (isnotnull(n_nationkey#172L) AND (n_nationkey#172L > 1))
: : +- ^(56)
NativeFileScan parquet default.nation[n_nationkey#172L] Batched: true,
DataFilters: [isnotnull(n_nationkey#172L), (n_nationkey#172L > 1)], Format:
Parquet, Location: InMemoryFileIndex(1
paths)[file:/data3/liangjiabiao/docker/local_gluten/spark-3.3.2-bin-hadoop3/s...,
PartitionFilters: [], PushedFilters: [IsNotNull(n_nationkey),
GreaterThan(n_nationkey,1)], ReadSchema: struct<n_nationkey:bigint>
: +- ^(58) NativeFileScan parquet
tpch_pq.nation[n_nationkey#2L,n_regionkey#4L] Batched: true, DataFilters:
[(n_nationkey#2L > 1), isnotnull(n_nationkey#2L)], Format: Parquet, Location:
InMemoryFileIndex(1
paths)[file:/home/liangjiabiao/workspace/docker/local_gluten/tpch_pq_data/nat...,
PartitionFilters: [], PushedFilters: [GreaterThan(n_nationkey,1),
IsNotNull(n_nationkey)], ReadSchema:
struct<n_nationkey:bigint,n_regionkey:bigint>
+- ^(60) InputIteratorTransformer[n_nationkey#172L]
+- ^(60) InputAdapter
+- ^(60) ColumnarExchange
hashpartitioning(n_nationkey#172L, 5), ENSURE_REQUIREMENTS, [plan_id=2226],
[id=#2226], [OUTPUT] List(n_nationkey:LongType), [OUTPUT]
List(n_nationkey:LongType)
+- ^(59) FilterExecTransformer
(isnotnull(n_nationkey#172L) AND (n_nationkey#172L > 1))
+- ^(59) NativeFileScan parquet
default.nation[n_nationkey#172L] Batched: true, DataFilters:
[isnotnull(n_nationkey#172L), (n_nationkey#172L > 1)], Format: Parquet,
Location: InMemoryFileIndex(1
paths)[file:/data3/liangjiabiao/docker/local_gluten/spark-3.3.2-bin-hadoop3/s...,
PartitionFilters: [], PushedFilters: [IsNotNull(n_nationkey),
GreaterThan(n_nationkey,1)], ReadSchema: struct<n_nationkey:bigint>
```
the fallback stages are
```
: +- ^(58) FilterExecTransformer (((n_nationkey#2L
> 1) AND isnotnull(n_nationkey#2L)) AND might_contain(Subquery
scalar-subquery#258, [id=#2138], xxhash64(n_nationkey#2L, 42)))
: : +- Subquery scalar-subquery#258, [id=#2138]
: : +- CHNativeColumnarToRow
: : +- ^(57)
HashAggregateTransformer(keys=[],
functions=[bloom_filter_agg(xxhash64(n_nationkey#172L, 42), 1000000, 8388608,
0, 0)], output=[bloomFilter#257])
: : +- ^(57)
InputIteratorTransformer[buf#260]
```
### Spark version
None
### Spark configurations
_No response_
### System information
_No response_
### Relevant logs
_No response_
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
