Ngone51 commented on a change in pull request #28708: URL: https://github.com/apache/spark/pull/28708#discussion_r454898370
########## File path: core/src/test/scala/org/apache/spark/storage/BlockManagerDecommissionIntegrationSuite.scala ########## @@ -0,0 +1,230 @@ +/* + * 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.storage + +import java.util.concurrent.Semaphore + +import scala.collection.mutable.ArrayBuffer +import scala.concurrent.duration._ + +import org.scalatest.concurrent.Eventually + +import org.apache.spark._ +import org.apache.spark.internal.config +import org.apache.spark.scheduler._ +import org.apache.spark.scheduler.cluster.StandaloneSchedulerBackend +import org.apache.spark.util.{ResetSystemProperties, ThreadUtils} + +class BlockManagerDecommissionIntegrationSuite extends SparkFunSuite with LocalSparkContext + with ResetSystemProperties with Eventually { + + val numExecs = 3 + val numParts = 3 + + test(s"verify that an already running task which is going to cache data succeeds " + + s"on a decommissioned executor") { + runDecomTest(true, false, true) + } + + test(s"verify that shuffle blocks are migrated") { + runDecomTest(false, true, false) + } + + test(s"verify that both migrations can work at the same time.") { + runDecomTest(true, true, false) + } + + private def runDecomTest(persist: Boolean, shuffle: Boolean, migrateDuring: Boolean) = { + + val master = s"local-cluster[${numExecs}, 1, 1024]" + val conf = new SparkConf().setAppName("test").setMaster(master) + .set(config.Worker.WORKER_DECOMMISSION_ENABLED, true) + .set(config.STORAGE_DECOMMISSION_ENABLED, true) + .set(config.STORAGE_DECOMMISSION_RDD_BLOCKS_ENABLED, persist) + .set(config.STORAGE_DECOMMISSION_SHUFFLE_BLOCKS_ENABLED, shuffle) + // Just replicate blocks as fast as we can during testing, there isn't another + // workload we need to worry about. + .set(config.STORAGE_DECOMMISSION_REPLICATION_REATTEMPT_INTERVAL, 1L) + + sc = new SparkContext(master, "test", conf) + + // Wait for the executors to start + TestUtils.waitUntilExecutorsUp(sc = sc, + numExecutors = numExecs, + timeout = 60000) // 60s + + // Create input RDD with 10 partitions Review comment: the comment is out of date? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
