xuanyuanking commented on a change in pull request #32928: URL: https://github.com/apache/spark/pull/32928#discussion_r659627986
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala ########## @@ -0,0 +1,453 @@ +/* + * 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.state + +import java.io.File +import java.util.Locale + +import scala.collection.{mutable, Map} +import scala.ref.WeakReference +import scala.util.Try + +import org.apache.hadoop.conf.Configuration +import org.rocksdb.{RocksDB => NativeRocksDB, _} + +import org.apache.spark.TaskContext +import org.apache.spark.internal.Logging +import org.apache.spark.sql.catalyst.util.CaseInsensitiveMap +import org.apache.spark.sql.util.RocksDBLoader +import org.apache.spark.util.{NextIterator, Utils} + +/** + * Class representing a RocksDB instance that checkpoints version of data to DFS. + * After a set of updates, a new version can be committed by calling `commit()`. + * Any past version can be loaded by calling `load(version)`. + * + * @note This class is not thread-safe, so use it only from one thread. + * @see [[RocksDBFileManager]] to see how the files are laid out in local disk and DFS. + * @param dfsRootDir Remote directory where checkpoints are going to be written + * @param conf Configuration for RocksDB + * @param localRootDir Root directory in local disk that is used to working and checkpoing dirs + * @param hadoopConf Hadoop configuration for talking to the remote file system + * @param loggingId Id that will be prepended in logs for isolating concurrent RocksDBs + */ +class RocksDB( + dfsRootDir: String, + val conf: RocksDBConf = RocksDBConf(), Review comment: It's mainly used in the UT. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
