Github user shenh062326 commented on a diff in the pull request:
https://github.com/apache/spark/pull/4363#discussion_r24574765
--- Diff: core/src/main/scala/org/apache/spark/HeartbeatReceiver.scala ---
@@ -17,33 +17,84 @@
package org.apache.spark
-import akka.actor.Actor
+import scala.concurrent.duration._
+import scala.collection.mutable
+
+import akka.actor.{Actor, Cancellable}
+
import org.apache.spark.executor.TaskMetrics
import org.apache.spark.storage.BlockManagerId
-import org.apache.spark.scheduler.TaskScheduler
+import org.apache.spark.scheduler.{SlaveLost, TaskScheduler}
import org.apache.spark.util.ActorLogReceive
/**
* A heartbeat from executors to the driver. This is a shared message used
by several internal
- * components to convey liveness or execution information for in-progress
tasks.
+ * components to convey liveness or execution information for in-progress
tasks. It will also
+ * expire the hosts that have not heartbeated for more than
spark.driver.executorTimeoutMs.
*/
private[spark] case class Heartbeat(
executorId: String,
taskMetrics: Array[(Long, TaskMetrics)], // taskId -> TaskMetrics
blockManagerId: BlockManagerId)
+private[spark] case object ExpireDeadHosts
+
private[spark] case class HeartbeatResponse(reregisterBlockManager:
Boolean)
/**
* Lives in the driver to receive heartbeats from executors..
*/
-private[spark] class HeartbeatReceiver(scheduler: TaskScheduler)
+private[spark] class HeartbeatReceiver(sc: SparkContext, scheduler:
TaskScheduler)
extends Actor with ActorLogReceive with Logging {
+ val executorLastSeen = new mutable.HashMap[String, Long]
+
+ val executorTimeout = sc.conf.getLong("spark.driver.executorTimeoutMs",
+ sc.conf.getLong("spark.storage.blockManagerSlaveTimeoutMs", 120 *
1000))
+
+ val checkTimeoutInterval =
sc.conf.getLong("spark.driver.executorTimeoutIntervalMs",
+ sc.conf.getLong("spark.storage.blockManagerTimeoutIntervalMs", 60000))
+
+ var timeoutCheckingTask: Cancellable = null
+
+ override def preStart(): Unit = {
+ import context.dispatcher
+ timeoutCheckingTask = context.system.scheduler.schedule(0.seconds,
+ checkTimeoutInterval.milliseconds, self, ExpireDeadHosts)
+ super.preStart()
+ }
+
override def receiveWithLogging = {
case Heartbeat(executorId, taskMetrics, blockManagerId) =>
val response = HeartbeatResponse(
!scheduler.executorHeartbeatReceived(executorId, taskMetrics,
blockManagerId))
+ executorLastSeen(executorId) = System.currentTimeMillis()
sender ! response
+ case ExpireDeadHosts =>
+ expireDeadHosts()
+ }
+
+ private def expireDeadHosts(): Unit = {
+ logTrace("Checking for hosts with no recent heartbeats in
HeartbeatReceiver.")
+ val now = System.currentTimeMillis()
+ val minSeenTime = now - executorTimeout
+ for ((executorId, lastSeenMs) <- executorLastSeen) {
+ if (lastSeenMs < minSeenTime) {
+ logWarning(s"Removing executor $executorId with no recent
heartbeats: " +
+ s"${now - lastSeenMs} ms exceeds timeout $executorTimeout ms")
+ scheduler.executorLost(executorId, SlaveLost())
+ if(sc.supportKillExecutor()) {
+ sc.killExecutor(executorId)
+ }
+ executorLastSeen.remove(executorId)
--- End diff --
Because the akka connection is still alive, we can kill executor by send
kill message to applicationMaster.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
