diff options
Diffstat (limited to 'yarn/src')
-rw-r--r-- | yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala | 20 | ||||
-rw-r--r-- | yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala | 3 |
2 files changed, 21 insertions, 2 deletions
diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala index 7d71a642f6..b0bfe855e9 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala +++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala @@ -40,6 +40,7 @@ import org.apache.spark.internal.config._ import org.apache.spark.rpc.{RpcCallContext, RpcEndpointRef} import org.apache.spark.scheduler.{ExecutorExited, ExecutorLossReason} import org.apache.spark.scheduler.cluster.CoarseGrainedClusterMessages.RemoveExecutor +import org.apache.spark.scheduler.cluster.CoarseGrainedClusterMessages.RetrieveLastAllocatedExecutorId import org.apache.spark.util.ThreadUtils /** @@ -83,8 +84,23 @@ private[yarn] class YarnAllocator( new ConcurrentHashMap[ContainerId, java.lang.Boolean]) @volatile private var numExecutorsRunning = 0 - // Used to generate a unique ID per executor - private var executorIdCounter = 0 + + /** + * Used to generate a unique ID per executor + * + * Init `executorIdCounter`. when AM restart, `executorIdCounter` will reset to 0. Then + * the id of new executor will start from 1, this will conflict with the executor has + * already created before. So, we should initialize the `executorIdCounter` by getting + * the max executorId from driver. + * + * And this situation of executorId conflict is just in yarn client mode, so this is an issue + * in yarn client mode. For more details, can check in jira. + * + * @see SPARK-12864 + */ + private var executorIdCounter: Int = + driverRef.askWithRetry[Int](RetrieveLastAllocatedExecutorId) + @volatile private var numExecutorsFailed = 0 @volatile private var targetNumExecutors = diff --git a/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala b/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala index a8781636f2..5aeaf44732 100644 --- a/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala +++ b/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala @@ -292,6 +292,9 @@ private[spark] abstract class YarnSchedulerBackend( logWarning("Attempted to kill executors before the AM has registered!") context.reply(false) } + + case RetrieveLastAllocatedExecutorId => + context.reply(currentExecutorIdCounter) } override def onDisconnected(remoteAddress: RpcAddress): Unit = { |