icexelloss commented on a change in pull request #24981: [WIP][SPARK-27463][PYTHON] Support Dataframe Cogroup via Pandas UDFs- Arrow Stream Impl URL: https://github.com/apache/spark/pull/24981#discussion_r299703032
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/python/InterleavedArrowPythonRunner.scala ########## @@ -0,0 +1,102 @@ +/* + * 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.python + +import java.io._ +import java.net._ + +import org.apache.arrow.vector.VectorSchemaRoot +import org.apache.arrow.vector.ipc.ArrowStreamWriter + +import org.apache.spark._ +import org.apache.spark.api.python._ +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.execution.arrow.ArrowWriter +import org.apache.spark.sql.types._ +import org.apache.spark.sql.util.ArrowUtils +import org.apache.spark.util.Utils + + +class InterleavedArrowPythonRunner( + funcs: Seq[ChainedPythonFunctions], + evalType: Int, + argOffsets: Array[Array[Int]], + leftSchema: StructType, + rightSchema: StructType, + timeZoneId: String, + conf: Map[String, String]) + extends BaseArrowPythonRunner[(Iterator[InternalRow], Iterator[InternalRow])]( + funcs, evalType, argOffsets) { + + protected def newWriterThread( + env: SparkEnv, + worker: Socket, + inputIterator: Iterator[(Iterator[InternalRow], Iterator[InternalRow])], + partitionIndex: Int, + context: TaskContext): WriterThread = { + new WriterThread(env, worker, inputIterator, partitionIndex, context) { + + protected override def writeCommand(dataOut: DataOutputStream): Unit = { + + // Write config for the worker as a number of key -> value pairs of strings + dataOut.writeInt(conf.size) + for ((k, v) <- conf) { + PythonRDD.writeUTF(k, dataOut) + PythonRDD.writeUTF(v, dataOut) + } + + PythonUDFRunner.writeUDFs(dataOut, funcs, argOffsets) + } + + protected override def writeIteratorToStream(dataOut: DataOutputStream): Unit = { + while (inputIterator.hasNext) { + dataOut.writeInt(SpecialLengths.START_ARROW_STREAM) + val (nextLeft, nextRight) = inputIterator.next() + writeGroup(nextLeft, leftSchema, dataOut) Review comment: I see. In this implementation we are writing out the complete arrow stream for each group. I think I'd like to understand the performance diffs between the two POCs. Is it possible to do a microbenchmark of maybe 100M of data with very small to very large groups? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
