jordepic commented on code in PR #4658: URL: https://github.com/apache/datafusion-comet/pull/4658#discussion_r3650434058
########## spark/src/main/scala/org/apache/spark/sql/comet/IcebergCommitExec.scala: ########## @@ -0,0 +1,77 @@ +/* + * 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 org.apache.spark.internal.Logging +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.Attribute +import org.apache.spark.sql.connector.write.{BatchWrite, WriterCommitMessage} +import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode} +import org.apache.spark.sql.execution.datasources.v2.V2CommandExec +import org.apache.spark.sql.execution.metric.{SQLMetric, SQLMetrics} + +/** + * Driver-side committer for Comet's split-operator Iceberg V2 write. + */ +case class IcebergCommitExec( + // Neither of these fields are serialized, this is all run on the driver. + @transient batchWrite: BatchWrite, + @transient refreshCache: () => Unit, Review Comment: Done -- added `IcebergCommitExec.RefreshCache` (`type RefreshCache = () => Unit`) and used it for the constructor param. ########## spark/src/main/scala/org/apache/spark/sql/comet/IcebergWriteExec.scala: ########## @@ -0,0 +1,177 @@ +/* + * 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.io.{ByteArrayInputStream, ByteArrayOutputStream, ObjectInputStream, ObjectOutputStream} + +import org.apache.spark.TaskContext +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference} +import org.apache.spark.sql.catalyst.expressions.UnsafeProjection +import org.apache.spark.sql.catalyst.plans.physical.{Distribution, UnspecifiedDistribution} +import org.apache.spark.sql.connector.write.{BatchWrite, DataWriter, PhysicalWriteInfoImpl, WriterCommitMessage} +import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode} +import org.apache.spark.sql.execution.metric.{SQLMetric, SQLMetrics} +import org.apache.spark.sql.types.{BinaryType, StructField, StructType} +import org.apache.spark.util.Utils + +import org.apache.comet.iceberg.ReplaceDataDispatchInfo + +/** + * Executor-side file writer for Comet's split-operator Iceberg V2 write. + */ +case class IcebergWriteExec( + // `batchWrite` only stored driver side, only the writer factory is shipped to executors. + @transient batchWrite: BatchWrite, + child: SparkPlan, + replaceDataDispatch: Option[ReplaceDataDispatchInfo] = None) + extends UnaryExecNode { + + override def output: Seq[Attribute] = Seq( + AttributeReference(IcebergWriteExec.CommitMessageColumn, BinaryType, nullable = false)()) + + // Spark already adds a distribution for the V2 write; adding another here is redundant. + override def requiredChildDistribution: Seq[Distribution] = Seq(UnspecifiedDistribution) + + override lazy val metrics: Map[String, SQLMetric] = Map( + "numOutputRows" -> SQLMetrics.createMetric(sparkContext, "number of output rows")) + + override protected def doExecute(): RDD[InternalRow] = { + val rdd = child.execute() + val factory = batchWrite.createBatchWriterFactory(PhysicalWriteInfoImpl(rdd.getNumPartitions)) + require( Review Comment: Correct -- with the planning-time fallback it's unreachable through `IcebergWriteStrategy`. I kept it as a backstop for direct construction of the node and marked it as such with a short comment. Happy to drop it instead if you'd rather not carry it. -- 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]
