dwsmith1983 commented on code in PR #5365: URL: https://github.com/apache/datafusion-comet/pull/5365#discussion_r3835744306
########## contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/CometDeltaNativeScanExec.scala: ########## @@ -0,0 +1,250 @@ +/* + * 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.rdd.RDD +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.catalyst.plans.QueryPlan +import org.apache.spark.sql.catalyst.plans.physical.{Partitioning, UnknownPartitioning} +import org.apache.spark.sql.execution.{FileSourceScanExec, InSubqueryExec, SparkPlan} +import org.apache.spark.sql.execution.datasources.HadoopFsRelation +import org.apache.spark.sql.execution.metric.SQLMetric +import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.vectorized.ColumnarBatch + +import org.apache.comet.contrib.delta.DeltaSparkScanEnvelope +import org.apache.comet.serde.OperatorOuterClass +import org.apache.comet.serde.OperatorOuterClass.Operator + +/** + * Native scan node for Delta Lake tables (contrib). Delta's own planning (log replay, snapshot + * resolution, partition pruning) has already run inside delta-spark by the time this node is + * created from the DSv1 [[FileSourceScanExec]]; file listing and split planning are delegated to + * a [[CometScanExec]] helper, and data reads execute through Comet's native DataFusion parquet + * machinery, inheriting row-group and page-index pruning. + * + * DPP: `runtimeFilters` is a constructor field included in equality, so + * `CometPlanAdaptiveDynamicPruningFilters`'s rewrite (via [[CometScanWithPlanData]]) survives + * plan copies, the lesson from CometIcebergNativeScanExec (a transient field is dropped by + * `TreeNode.makeCopy` on MERGE re-planning). + */ +case class CometDeltaNativeScanExec( + override val nativeOp: Operator, + override val output: Seq[Attribute], + requiredSchema: StructType, + runtimeFilters: Seq[Expression], + dataFilters: Seq[Expression], + @transient relation: HadoopFsRelation, + originalPlan: FileSourceScanExec, + override val serializedPlanOpt: SerializedPlan, + sourceKey: String) + extends CometLeafExec + with CometScanWithPlanData { + + override val nodeName: String = s"CometDeltaNativeScan $relation" + + // Derived from (originalPlan, runtimeFilters), never stored: any copy of this node, our + // own withDynamicPruningFilters, or a generic Catalyst expression rewrite going through + // TreeNode.makeCopy, automatically gets a helper consistent with ITS runtimeFilters. A + // stored helper field would desync from rewritten filters (the #3510 class of bug). The + // cost is that file listing runs once per executed instance (planning listed separately in + // the rule extension); correctness over the duplicate driver-side listing. + @transient private lazy val scanHelper: CometScanExec = + CometDeltaNativeScanExec.planningHelper(originalPlan, runtimeFilters) + + override lazy val outputPartitioning: Partitioning = + UnknownPartitioning(perPartitionData.length) Review Comment: Fixed as described: outputPartitioning is now a plain def returning UnknownPartitioning(0) while any runtime filter still holds an adaptive broadcast placeholder, so AQE validation never forces perPartitionData. Rewrote the DPP test to filter at query time and added your UNION ALL shape as a regression. That shape didn't reproduce the crash pre-fix on my Spark 3.5.9 / Delta 3.3.2 profile, so it likely needs your Spark 4.0.2 harness, but the guard matches your analysis. -- 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]
