Github user vanzin commented on a diff in the pull request:
https://github.com/apache/spark/pull/19041#discussion_r138757437
--- Diff: core/src/main/scala/org/apache/spark/RecoverCacheShutdown.scala
---
@@ -0,0 +1,234 @@
+/*
+ * 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
+
+import java.util.concurrent.{ScheduledFuture, TimeUnit}
+
+import scala.collection.mutable
+import scala.concurrent.{ExecutionContext, Future}
+import scala.util.Failure
+
+import org.apache.spark.internal.Logging
+import org.apache.spark.rpc.RpcEndpointRef
+import org.apache.spark.storage.{BlockId, BlockManagerId, RDDBlockId}
+import org.apache.spark.storage.BlockManagerMessages.{GetCachedBlocks,
GetMemoryStatus, GetSizeOfBlocks, ReplicateOneBlock}
+import org.apache.spark.util.ThreadUtils
+
+/**
+ * Responsible for asynchronously replicating all of an executors cached
blocks, and then shutting
+ * it down.
+ */
+final private class RecoverCacheShutdown(
+ state: RecoverCacheShutdownState,
+ conf: SparkConf)
+ extends Logging {
+
+ private val threadPool =
ThreadUtils.newDaemonCachedThreadPool("recover-cache-shutdown-pool")
+ private implicit val asyncExecutionContext =
ExecutionContext.fromExecutorService(threadPool)
+
+ /**
+ * Start the recover cache shutdown process for these executors
+ *
+ * @param execIds the executors to start shutting down
+ */
+ def startExecutorKill(execIds: Seq[String]): Unit = {
+ logDebug(s"Recover cached data before shutting down executors
${execIds.mkString(", ")}.")
+ checkForReplicableBlocks(execIds)
+ }
+
+ /**
+ * Stops all thread pools
+ *
+ * @return
+ */
+ def stop(): java.util.List[Runnable] = {
+ threadPool.shutdownNow()
+ state.stop()
+ }
+
+ /**
+ * Get list of cached blocks from BlockManagerMaster. If there are
cached blocks, replicate them,
+ * otherwise kill the executors
+ *
+ * @param execIds the executors to check
+ */
+ private def checkForReplicableBlocks(execIds: Seq[String]) =
state.getBlocks(execIds).foreach {
+ case (executorId, NoMoreBlocks) => state.killExecutor(executorId)
--- End diff --
not 100% scalac will accept it, but maybe:
case (executorId, NoMoreBlocks | NotEnoughMemory) =>
Or you could invert things.
case (executorId, HasCachedBlocks) => replicateBlocks(executorId)
case (executorId, _) = kill()
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
