minni31 commented on code in PR #12077: URL: https://github.com/apache/gluten/pull/12077#discussion_r3235052933
########## backends-velox/src/main/scala/org/apache/gluten/execution/VeloxRDDScanTransformer.scala: ########## @@ -0,0 +1,111 @@ +/* + * 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.backendsapi.velox.VeloxValidatorApi +import org.apache.gluten.config.{GlutenConfig, VeloxConfig} + +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.{Attribute, SortOrder} +import org.apache.spark.sql.catalyst.plans.physical.Partitioning +import org.apache.spark.sql.execution.{RDDScanTransformer, SparkPlan} +import org.apache.spark.sql.execution.metric.{SQLMetric, SQLMetrics} +import org.apache.spark.sql.vectorized.ColumnarBatch + +/** + * Velox-backend implementation of RDDScanTransformer. + * + * Converts an RDD[InternalRow] into columnar batches using Velox's native row-to-columnar + * conversion (same JNI path as RowToVeloxColumnarExec). + */ +case class VeloxRDDScanTransformer( + outputAttributes: Seq[Attribute], + rdd: RDD[InternalRow], + name: String, + // Row-to-columnar conversion preserves data distribution, so we carry through + // the original partitioning. This differs from CH which uses UnknownPartitioning(0) + // but is consistent with RowToVeloxColumnarExec's behavior. + override val outputPartitioning: Partitioning, + override val outputOrdering: Seq[SortOrder] +) extends RDDScanTransformer(outputAttributes, outputPartitioning, outputOrdering) { + + @transient override lazy val metrics: Map[String, SQLMetric] = Map( + "numInputRows" -> SQLMetrics.createMetric(sparkContext, "number of input rows"), + "numOutputBatches" -> SQLMetrics.createMetric(sparkContext, "number of output batches"), + "convertTime" -> SQLMetrics.createTimingMetric(sparkContext, "time to convert") + ) + + override protected def doValidateInternal(): ValidationResult = { + for (field <- schema.fields) { + val reason = VeloxValidatorApi.validateSchema(field.dataType) + if (reason.isDefined) { + return ValidationResult.failed(reason.get) + } + } + ValidationResult.succeeded Review Comment: updated the BatchCarrierRow unwrap path to increment numOutputBatches and numInputRows per batch, so Spark UI now shows correct metrics for checkpointed data. convertTime is intentionally omitted since no row-to-columnar conversion happens in this path. -- 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]
