viirya commented on code in PR #100: URL: https://github.com/apache/arrow-datafusion-comet/pull/100#discussion_r1506317109
########## spark/src/main/scala/org/apache/spark/sql/comet/CometCollectLimitExec.scala: ########## @@ -0,0 +1,112 @@ +/* + * 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.comet + +import java.util.Objects + +import org.apache.spark.rdd.RDD +import org.apache.spark.serializer.Serializer +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.comet.execution.shuffle.{CometShuffledBatchRDD, CometShuffleExchangeExec} +import org.apache.spark.sql.execution.{ColumnarToRowExec, SparkPlan, UnaryExecNode, UnsafeRowSerializer} +import org.apache.spark.sql.execution.metric.{SQLMetric, SQLMetrics, SQLShuffleReadMetricsReporter, SQLShuffleWriteMetricsReporter} +import org.apache.spark.sql.vectorized.ColumnarBatch + +/** + * Comet physical plan node for Spark `CollectLimitExec`. + * + * Similar to `CometTakeOrderedAndProjectExec`, it contains two native executions seperated by a + * Comet shuffle. + * + * TODO: support offset semantics + */ +case class CometCollectLimitExec( + override val originalPlan: SparkPlan, + limit: Int, + offset: Int, + child: SparkPlan) + extends CometExec + with UnaryExecNode { + + private lazy val writeMetrics = + SQLShuffleWriteMetricsReporter.createShuffleWriteMetrics(sparkContext) + private lazy val readMetrics = + SQLShuffleReadMetricsReporter.createShuffleReadMetrics(sparkContext) + override lazy val metrics: Map[String, SQLMetric] = Map( + "dataSize" -> SQLMetrics.createSizeMetric(sparkContext, "data size"), + "shuffleReadElapsedCompute" -> + SQLMetrics.createNanoTimingMetric(sparkContext, "shuffle read elapsed compute at native"), + "numPartitions" -> SQLMetrics.createMetric( + sparkContext, + "number of partitions")) ++ readMetrics ++ writeMetrics + + private lazy val serializer: Serializer = + new UnsafeRowSerializer(child.output.size, longMetric("dataSize")) + + override def executeCollect(): Array[InternalRow] = { + ColumnarToRowExec(child).executeTake(limit) Review Comment: Okay -- 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]
