viirya commented on code in PR #8794: URL: https://github.com/apache/arrow-datafusion/pull/8794#discussion_r1445475557
########## datafusion/sqllogictest/test_files/repartition.slt: ########## @@ -0,0 +1,76 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at + +# http://www.apache.org/licenses/LICENSE-2.0 + +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +########## +# Tests for repartitioning +########## + +# Set 4 partitions for deterministic output plans +statement ok +set datafusion.execution.target_partitions = 4; + +statement ok +COPY (VALUES (1, 2), (2, 5), (3, 2), (4, 5), (5, 0)) TO 'test_files/scratch/repartition_scan/parquet_table/2.parquet' +(FORMAT PARQUET, SINGLE_FILE_OUTPUT true); + +statement ok +CREATE EXTERNAL TABLE parquet_table(column1 int, column2 int) +STORED AS PARQUET +LOCATION 'test_files/scratch/repartition_scan/parquet_table/'; + +# enable round robin repartitioning +statement ok +set datafusion.optimizer.enable_round_robin_repartition = true; + +query TT +EXPLAIN SELECT column1, SUM(column2) FROM parquet_table GROUP BY column1; +---- +logical_plan +Aggregate: groupBy=[[parquet_table.column1]], aggr=[[SUM(CAST(parquet_table.column2 AS Int64))]] +--TableScan: parquet_table projection=[column1, column2] +physical_plan +AggregateExec: mode=FinalPartitioned, gby=[column1@0 as column1], aggr=[SUM(parquet_table.column2)] +--CoalesceBatchesExec: target_batch_size=8192 +----RepartitionExec: partitioning=Hash([column1@0], 4), input_partitions=4 +------AggregateExec: mode=Partial, gby=[column1@0 as column1], aggr=[SUM(parquet_table.column2)] +--------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1 +----------ParquetExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet]]}, projection=[column1, column2] + +# disable round robin repartitioning +statement ok +set datafusion.optimizer.enable_round_robin_repartition = false; + +query TT +EXPLAIN SELECT column1, SUM(column2) FROM parquet_table GROUP BY column1; +---- +logical_plan +Aggregate: groupBy=[[parquet_table.column1]], aggr=[[SUM(CAST(parquet_table.column2 AS Int64))]] +--TableScan: parquet_table projection=[column1, column2] +physical_plan +AggregateExec: mode=FinalPartitioned, gby=[column1@0 as column1], aggr=[SUM(parquet_table.column2)] +--CoalesceBatchesExec: target_batch_size=8192 +----RepartitionExec: partitioning=Hash([column1@0], 4), input_partitions=1 +------AggregateExec: mode=Partial, gby=[column1@0 as column1], aggr=[SUM(parquet_table.column2)] Review Comment: Currently roundrobin partitioning is still added even it is disabled. We should make the config behavior consistent. -- 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]
