philo-he commented on code in PR #12188: URL: https://github.com/apache/gluten/pull/12188#discussion_r3339408547
########## gluten-substrait/src/main/scala/org/apache/spark/sql/execution/ColumnarAttachDistributedSequenceBaseExec.scala: ########## @@ -0,0 +1,85 @@ +/* + * 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. + */ +package org.apache.spark.sql.execution + +import org.apache.gluten.backendsapi.BackendsApiManager +import org.apache.gluten.execution.ValidatablePlan +import org.apache.gluten.extension.columnar.transition.Convention + +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeSet} +import org.apache.spark.sql.catalyst.plans.physical.Partitioning +import org.apache.spark.sql.catalyst.util.truncatedString +import org.apache.spark.sql.execution.python.AttachDistributedSequenceExec + +/** + * Base class for [[AttachDistributedSequenceExec]] transformation that can be implemented by + * supported backends. The exec prepends a contiguous, globally increasing `Long` id column to the + * child output. Used by pandas-on-Spark distributed-sequence default index and + * `DataFrame.zipWithIndex`. + */ +abstract class ColumnarAttachDistributedSequenceBaseExec( + sequenceAttr: Attribute, + override val child: SparkPlan) + extends UnaryExecNode + with ValidatablePlan { + + override def producedAttributes: AttributeSet = AttributeSet(sequenceAttr) + + override val output: Seq[Attribute] = sequenceAttr +: child.output + + override def outputPartitioning: Partitioning = child.outputPartitioning + + override def rowType(): Convention.RowType = Convention.RowType.None + + override protected def doExecute(): RDD[InternalRow] = { + throw new UnsupportedOperationException(s"This operator doesn't support doExecute().") + } + + override def simpleString(maxFields: Int): String = { + val truncatedOutputString = truncatedString(output, "[", ", ", "]", maxFields) + val indexColumn = s"Index: $sequenceAttr" + s"$nodeName$truncatedOutputString $indexColumn" + } + + /** + * Hook for backend implementations to release any resources (e.g. cached RDDs) that were + * materialized during execution. Called from [[cleanupResources]] after children have been + * cleaned up. The default implementation is a no-op. + */ + protected def doColumnarCleanup(): Unit = {} Review Comment: Do we still need this? It seems to be useless. ########## backends-velox/src/test/scala/org/apache/gluten/execution/VeloxAttachDistributedSequenceExecSuite.scala: ########## @@ -0,0 +1,127 @@ +/* + * 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. + */ +package org.apache.gluten.execution + +import org.apache.gluten.config.GlutenConfig + +import org.apache.spark.SparkConf +import org.apache.spark.sql.DataFrame +import org.apache.spark.sql.catalyst.expressions.AttributeReference +import org.apache.spark.sql.catalyst.plans.logical.AttachDistributedSequence +import org.apache.spark.sql.classic.ClassicDataset +import org.apache.spark.sql.execution.python.AttachDistributedSequenceExec +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types.LongType + +class VeloxAttachDistributedSequenceExecSuite extends VeloxWholeStageTransformerSuite { + + override protected val resourcePath: String = "/tpch-data-parquet" + override protected val fileFormat: String = "parquet" + + override def sparkConf: SparkConf = { + super.sparkConf + .set("spark.sql.shuffle.partitions", "3") + .set("spark.default.parallelism", "3") + .set(SQLConf.ANSI_ENABLED.key, "false") Review Comment: Can we also set Spark master "local[3]" explicitly? ########## backends-velox/src/test/scala/org/apache/gluten/execution/VeloxAttachDistributedSequenceExecSuite.scala: ########## @@ -0,0 +1,127 @@ +/* + * 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. + */ +package org.apache.gluten.execution + +import org.apache.gluten.config.GlutenConfig + +import org.apache.spark.SparkConf +import org.apache.spark.sql.DataFrame +import org.apache.spark.sql.catalyst.expressions.AttributeReference +import org.apache.spark.sql.catalyst.plans.logical.AttachDistributedSequence +import org.apache.spark.sql.classic.ClassicDataset +import org.apache.spark.sql.execution.python.AttachDistributedSequenceExec +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types.LongType + +class VeloxAttachDistributedSequenceExecSuite extends VeloxWholeStageTransformerSuite { + + override protected val resourcePath: String = "/tpch-data-parquet" + override protected val fileFormat: String = "parquet" + + override def sparkConf: SparkConf = { + super.sparkConf + .set("spark.sql.shuffle.partitions", "3") + .set("spark.default.parallelism", "3") + .set(SQLConf.ANSI_ENABLED.key, "false") Review Comment: It seems that gluten columnar shuffle is not set. Do we need to set it in the base class WholeStageTransformerSuite? -- 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]
