aokolnychyi commented on a change in pull request #2021: URL: https://github.com/apache/iceberg/pull/2021#discussion_r552631706
########## File path: spark3-extensions/src/main/scala/org/apache/spark/sql/catalyst/utils/PlanHelper.scala ########## @@ -0,0 +1,117 @@ +/* + * 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.catalyst.utils + +import java.util.UUID +import org.apache.spark.sql.{AnalysisException, SparkSession} +import org.apache.spark.sql.catalyst.expressions.{AccumulateFiles, Alias, Attribute, AttributeReference, GreaterThan, Literal, PredicateHelper} +import org.apache.spark.sql.catalyst.expressions.aggregate.{AggregateExpression, Complete, Sum} +import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, DynamicFileFilter, DynamicFileFilterWithCountCheck, Filter, LogicalPlan, Project} +import org.apache.spark.sql.connector.catalog.Table +import org.apache.spark.sql.connector.iceberg.read.SupportsFileFilter +import org.apache.spark.sql.connector.iceberg.write.MergeBuilder +import org.apache.spark.sql.connector.write.{LogicalWriteInfo, LogicalWriteInfoImpl} +import org.apache.spark.sql.execution.datasources.v2.{DataSourceV2ScanRelation} +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.util.CaseInsensitiveStringMap + +trait PlanHelper extends PredicateHelper { + val FILE_NAME_COL = "_file" + val ROW_POS_COL = "_pos" + val ROW_ID_COL = "_row_id" + val AFFECTED_FILES_ACC_NAME = "affectedFiles" + val AFFECTED_FILES_ACC_ALIAS_NAME = "_affectedFiles_" + val SUM_ROW_ID_ALIAS_NAME = "_sum_" + + def buildScanPlan(spark: SparkSession, + table: Table, + output: Seq[AttributeReference], + mergeBuilder: MergeBuilder, + prunedTargetPlan: LogicalPlan, + performCountCheckForMerge: Boolean = false): LogicalPlan = { + + val scanBuilder = mergeBuilder.asScanBuilder + val scan = scanBuilder.build() + val scanRelation = DataSourceV2ScanRelation(table, scan, toOutputAttrs(scan.readSchema(), output)) + + scan match { + case filterable: SupportsFileFilter => + if (performCountCheckForMerge) { + val affectedFilesAcc = new SetAccumulator[String]() Review comment: One thing I should mention here (not a blocker). The accumulator approach may take a substantial amount of driver memory. The problem happens when each executor accumulates a set of entries that covers a large portion of files to overwrite. For example, if you have to overwrite 10K files to perform a merge and each executor accumulates a set of let's say 5K and you have 200 executors, then you bring all 200 intermediate sets on the driver and then merge them into a single set. This may put a lot of pressure on the driver. ---------------------------------------------------------------- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
