Github user zsxwing commented on a diff in the pull request: https://github.com/apache/spark/pull/13513#discussion_r79023964 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSourceLog.scala --- @@ -0,0 +1,133 @@ +/* + * 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.streaming + +import scala.collection.mutable + +import org.json4s.NoTypeHints +import org.json4s.jackson.Serialization + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.execution.streaming.FileStreamSource.FileEntry +import org.apache.spark.sql.internal.SQLConf + +class FileStreamSourceLog( + metadataLogVersion: String, + sparkSession: SparkSession, + path: String) + extends CompactibleFileStreamLog[FileEntry](metadataLogVersion, sparkSession, path) { + + import CompactibleFileStreamLog._ + + // Configurations about metadata compaction + protected override val compactInterval = + sparkSession.conf.get(SQLConf.FILE_SOURCE_LOG_COMPACT_INTERVAL) + require(compactInterval > 0, + s"Please set ${SQLConf.FILE_SOURCE_LOG_COMPACT_INTERVAL.key} (was $compactInterval) to a " + + s"positive value.") + + protected override val fileCleanupDelayMs = + sparkSession.conf.get(SQLConf.FILE_SOURCE_LOG_CLEANUP_DELAY) + + protected override val isDeletingExpiredLog = + sparkSession.conf.get(SQLConf.FILE_SOURCE_LOG_DELETION) + + private implicit val formats = Serialization.formats(NoTypeHints) + + // A fixed size log cache to cache the file entries belong to the compaction batch. It is used + // to avoid scanning the compacted log file to retrieve it's own batch data. + private val cacheSize = compactInterval + private val fileEntryCache = new mutable.LinkedHashMap[Long, Array[FileEntry]] + + private def updateCache(batchId: Long, logs: Array[FileEntry]): Unit = { + if (fileEntryCache.size >= cacheSize) { + fileEntryCache.drop(1) --- End diff -- `drop` doesn't change the original map. ```Scala scala> val m = scala.collection.mutable.LinkedHashMap[Int, Int]() m: scala.collection.mutable.LinkedHashMap[Int,Int] = Map() scala> scala> m(2) = 1 scala> m res1: scala.collection.mutable.LinkedHashMap[Int,Int] = Map(2 -> 1) scala> m.drop(1) res2: scala.collection.mutable.LinkedHashMap[Int,Int] = Map() scala> m res3: scala.collection.mutable.LinkedHashMap[Int,Int] = Map(2 -> 1) ``` I think it should be Java LinkedHashMap. This is an example: https://github.com/apache/spark/blob/03d46aafe561b03e25f4e25cf01e631c18dd827c/streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingJobProgressListener.scala#L45
--- 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