sunchao commented on a change in pull request #29471: URL: https://github.com/apache/spark/pull/29471#discussion_r480290788
########## File path: core/src/main/scala/org/apache/spark/util/HadoopFSUtils.scala ########## @@ -0,0 +1,259 @@ +/* + * 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.util + +import java.io.FileNotFoundException + +import scala.collection.mutable + +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs._ +import org.apache.hadoop.fs.viewfs.ViewFileSystem +import org.apache.hadoop.hdfs.DistributedFileSystem + +import org.apache.spark._ +import org.apache.spark.annotation.DeveloperApi +import org.apache.spark.internal.Logging +import org.apache.spark.metrics.source.HiveCatalogMetrics + +/** + * :: DeveloperApi :: + * Utility functions to simplify and speed-up file listing. + */ +@DeveloperApi +object HadoopFSUtils extends Logging { + /** + * :: DeveloperApi :: + * Lists a collection of paths recursively. Picks the listing strategy adaptively depending + * on the number of paths to list. + * + * This may only be called on the driver. + * + * @return for each input path, the set of discovered files for the path + */ + @DeveloperApi + def parallelListLeafFiles(sc: SparkContext, paths: Seq[Path], hadoopConf: Configuration, + filter: PathFilter, areSQLRootPaths: Boolean, ignoreMissingFiles: Boolean, + ignoreLocality: Boolean, maxParallelism: Int, + filterFun: Option[String => Boolean] = None): Seq[(Path, Seq[FileStatus])] = { + HiveCatalogMetrics.incrementParallelListingJobCount(1) Review comment: Yeah move this to SQL will not work - I think we can perhaps add a callback later just like @holdenk suggested (if you don't mind leaving it here in this PR). On the other hand, I think the `HiveCatalogMetrics` is already misleading - `InMemoryFileIndex` is used by non-Hive data sources like file-based ones and this particular metric itself has nothing to do with Hive catalog. Perhaps a better approach is to move the metrics to some place in core that are for storage-specific things. In future we can include more such as listing total time etc. ---------------------------------------------------------------- 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]
