Github user tdas commented on a diff in the pull request: https://github.com/apache/spark/pull/2882#discussion_r19318338 --- Diff: streaming/src/main/scala/org/apache/spark/streaming/util/WriteAheadLogManager.scala --- @@ -0,0 +1,224 @@ +/* + * 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.streaming.util + +import java.nio.ByteBuffer + +import scala.collection.mutable.ArrayBuffer +import scala.concurrent.{ExecutionContext, Future} + +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs.Path +import org.apache.hadoop.fs.permission.FsPermission +import org.apache.spark.Logging +import org.apache.spark.util.Utils +import WriteAheadLogManager._ + +/** + * This class manages write ahead log files. + * - Writes records (bytebuffers) to periodically rotating log files. + * - Recovers the log files and the reads the recovered records upon failures. + * - Cleans up old log files. + * + * Uses [[org.apache.spark.streaming.util.WriteAheadLogWriter]] to write + * and [[org.apache.spark.streaming.util.WriteAheadLogReader]] to read. + * + *@param logDirectory Directory when rotating log files will be created. + * @param hadoopConf Hadoop configuration for reading/writing log files. + * @param rollingIntervalSecs The interval in seconds with which logs will be rolled over. + * Default is one minute. + * @param maxFailures Max number of failures that is tolerated for every attempt to write to log. + * Default is three. + * @param callerName Optional name of the class who is using this manager. + * @param clock Optional clock that is used to check for rotation interval. + */ +private[streaming] class WriteAheadLogManager( + logDirectory: String, + hadoopConf: Configuration, + rollingIntervalSecs: Int = 60, + maxFailures: Int = 3, + callerName: String = "", + clock: Clock = new SystemClock + ) extends Logging { + + private val pastLogs = new ArrayBuffer[LogInfo] + private val callerNameTag = + if (callerName != null && callerName.nonEmpty) s" for $callerName" else "" --- End diff -- If someone explicitly passes null. But checking that can be avoided.
--- 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