dongjoon-hyun commented on code in PR #44173: URL: https://github.com/apache/spark/pull/44173#discussion_r1415142557
########## core/src/main/scala/org/apache/spark/deploy/master/RocksDBPersistenceEngine.scala: ########## @@ -0,0 +1,103 @@ +/* + * 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.deploy.master + +import java.nio.ByteBuffer +import java.nio.charset.StandardCharsets.UTF_8 +import java.nio.file.{Files, Paths} + +import scala.collection.mutable.ArrayBuffer +import scala.reflect.ClassTag + +import org.rocksdb._ + +import org.apache.spark.internal.Logging +import org.apache.spark.serializer.Serializer + + +/** + * Stores data in RocksDB. + * + * @param dir Directory to setup RocksDB. Created if non-existent. + * @param serializer Used to serialize our objects. + */ +private[master] class RocksDBPersistenceEngine( + val dir: String, + val serializer: Serializer) + extends PersistenceEngine with Logging { + + RocksDB.loadLibrary() + + private val path = Files.createDirectories(Paths.get(dir)) + + /** + * Use full filter. + * Disable compression in index data. + * + * https://github.com/facebook/rocksdb/wiki/RocksDB-Bloom-Filter#full-filters-new-format + */ + private val tableFormatConfig = new BlockBasedTableConfig() + .setFilterPolicy(new BloomFilter(10.0D, false)) + .setEnableIndexCompression(false) + .setIndexBlockRestartInterval(8) + .setFormatVersion(5) + + /** + * Use ZSTD at the bottom most level to reduce the disk space + * Use LZ4 at the other levels because it's better than Snappy in general. + * + * https://github.com/facebook/rocksdb/wiki/Compression#configuration + */ + private val options = new Options() + .setCreateIfMissing(true) + .setBottommostCompressionType(CompressionType.ZSTD_COMPRESSION) + .setCompressionType(CompressionType.LZ4_COMPRESSION) + .setTableFormatConfig(tableFormatConfig) + + private val db: RocksDB = RocksDB.open(options, path.toString) + + override def persist(name: String, obj: Object): Unit = { + val serialized = serializer.newInstance().serialize(obj) + if (serialized.hasArray) { + db.put(name.getBytes(UTF_8), serialized.array()) Review Comment: To @yaooqinn , `PersistenceEngine` is a secondary storage instead of lookup tables. In general, `Master` has a way to keep the uniqueness in the memory structure before reaching here. For example, `WorkerInfo` is under tracking of https://github.com/apache/spark/blob/1d80d80a56c418f841e282ad753fad6671c3baae/core/src/main/scala/org/apache/spark/deploy/master/Master.scala#L76C9-L76C9 ``` private val idToWorker = new HashMap[String, WorkerInfo] ``` In addition, Driver IDs and App IDs are generated by Master in the unique way including timestamps. -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
