Github user ericl commented on a diff in the pull request: https://github.com/apache/spark/pull/15539#discussion_r95073488 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileStatusCache.scala --- @@ -0,0 +1,149 @@ +/* + * 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.execution.datasources + +import java.util.concurrent.ConcurrentHashMap +import java.util.concurrent.atomic.AtomicBoolean + +import scala.collection.JavaConverters._ + +import com.google.common.cache._ +import org.apache.hadoop.fs.{FileStatus, Path} + +import org.apache.spark.internal.Logging +import org.apache.spark.metrics.source.HiveCatalogMetrics +import org.apache.spark.sql.SparkSession +import org.apache.spark.util.{SerializableConfiguration, SizeEstimator} + +/** + * A cache of the leaf files of partition directories. We cache these files in order to speed + * up iterated queries over the same set of partitions. Otherwise, each query would have to + * hit remote storage in order to gather file statistics for physical planning. + * + * Each resolved catalog table has its own FileStatusCache. When the backing relation for the + * table is refreshed via refreshTable() or refreshByPath(), this cache will be invalidated. + */ +abstract class FileStatusCache { + /** + * @return the leaf files for the specified path from this cache, or None if not cached. + */ + def getLeafFiles(path: Path): Option[Array[FileStatus]] = None + + /** + * Saves the given set of leaf files for a path in this cache. + */ + def putLeafFiles(path: Path, leafFiles: Array[FileStatus]): Unit + + /** + * Invalidates all data held by this cache. + */ + def invalidateAll(): Unit +} + +object FileStatusCache { + private var sharedCache: SharedInMemoryCache = null + + /** + * @return a new FileStatusCache based on session configuration. Cache memory quota is + * shared across all clients. + */ + def newCache(session: SparkSession): FileStatusCache = { + synchronized { + if (session.sqlContext.conf.filesourcePartitionPruning && + session.sqlContext.conf.filesourcePartitionFileCacheSize > 0) { --- End diff -- Sounds good, as long as you can still change it at runtime.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org