alexeykudinkin commented on a change in pull request #4877: URL: https://github.com/apache/hudi/pull/4877#discussion_r831474571
########## File path: hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/execution/datasources/HoodieInMemoryFileIndex.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.execution.datasources + +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs.{FileStatus, Path, PathFilter} +import org.apache.hadoop.mapred.{FileInputFormat, JobConf} +import org.apache.spark.HoodieHadoopFSUtils +import org.apache.spark.metrics.source.HiveCatalogMetrics +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.execution.datasources._ +import org.apache.spark.sql.types.StructType + +import scala.collection.mutable +import scala.collection.mutable.ArrayBuffer + +class HoodieInMemoryFileIndex(sparkSession: SparkSession, + rootPathsSpecified: Seq[Path], + parameters: Map[String, String], + userSpecifiedSchema: Option[StructType], + fileStatusCache: FileStatusCache = NoopCache) + extends InMemoryFileIndex(sparkSession, rootPathsSpecified, parameters, userSpecifiedSchema, fileStatusCache) { + + /** + * List leaf files of given paths. This method will submit a Spark job to do parallel + * listing whenever there is a path having more files than the parallel partition discovery threshold. + * + * This is publicly visible for testing. + * + * NOTE: This method replicates the one it overrides, however it uses custom method to run parallel + * listing that accepts files starting with "." + */ + override def listLeafFiles(paths: Seq[Path]): mutable.LinkedHashSet[FileStatus] = { + val startTime = System.nanoTime() + val output = mutable.LinkedHashSet[FileStatus]() + val pathsToFetch = mutable.ArrayBuffer[Path]() + for (path <- paths) { + fileStatusCache.getLeafFiles(path) match { + case Some(files) => + HiveCatalogMetrics.incrementFileCacheHits(files.length) + output ++= files + case None => + pathsToFetch += path + } + () // for some reasons scalac 2.12 needs this; return type doesn't matter + } + val filter = FileInputFormat.getInputPathFilter(new JobConf(hadoopConf, this.getClass)) + val discovered = bulkListLeafFiles(sparkSession, pathsToFetch, filter, hadoopConf) + + discovered.foreach { case (path, leafFiles) => + HiveCatalogMetrics.incrementFilesDiscovered(leafFiles.size) + fileStatusCache.putLeafFiles(path, leafFiles.toArray) + output ++= leafFiles + } + + logInfo(s"It took ${(System.nanoTime() - startTime) / (1000 * 1000)} ms to list leaf files" + + s" for ${paths.length} paths.") + + output + } + + protected def bulkListLeafFiles(sparkSession: SparkSession, paths: ArrayBuffer[Path], filter: PathFilter, hadoopConf: Configuration): Seq[(Path, Seq[FileStatus])] = { + HoodieHadoopFSUtils.parallelListLeafFiles( + sc = sparkSession.sparkContext, + paths = paths, + hadoopConf = hadoopConf, + filter = new PathFilterWrapper(filter), + ignoreMissingFiles = sparkSession.sessionState.conf.ignoreMissingFiles, + // NOTE: We're disabling fetching Block Info to speed up file listing Review comment: Gotcha. It's gonna be tough to identify all such places with markers, instead i'm referencing respective Spark release version this is borrowed from so that we can simply diff against it and see what has changed. -- 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]
