Skip to content

[SPARK-1620] Handle uncaught exceptions in function run by Akka scheduler #622

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 5 commits into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 10 additions & 8 deletions core/src/main/scala/org/apache/spark/deploy/client/AppClient.scala
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ import org.apache.spark.{Logging, SparkConf, SparkException}
import org.apache.spark.deploy.{ApplicationDescription, ExecutorState}
import org.apache.spark.deploy.DeployMessages._
import org.apache.spark.deploy.master.Master
import org.apache.spark.util.AkkaUtils
import org.apache.spark.util.{Utils, AkkaUtils}

/**
* Interface allowing applications to speak with a Spark deploy cluster. Takes a master URL,
Expand Down Expand Up @@ -88,13 +88,15 @@ private[spark] class AppClient(
var retries = 0
registrationRetryTimer = Some {
context.system.scheduler.schedule(REGISTRATION_TIMEOUT, REGISTRATION_TIMEOUT) {
retries += 1
if (registered) {
registrationRetryTimer.foreach(_.cancel())
} else if (retries >= REGISTRATION_RETRIES) {
markDead("All masters are unresponsive! Giving up.")
} else {
tryRegisterAllMasters()
Utils.tryOrExit {
retries += 1
if (registered) {
registrationRetryTimer.foreach(_.cancel())
} else if (retries >= REGISTRATION_RETRIES) {
markDead("All masters are unresponsive! Giving up.")
} else {
tryRegisterAllMasters()
}
}
}
}
Expand Down
18 changes: 10 additions & 8 deletions core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala
Original file line number Diff line number Diff line change
Expand Up @@ -166,14 +166,16 @@ private[spark] class Worker(
var retries = 0
registrationRetryTimer = Some {
context.system.scheduler.schedule(REGISTRATION_TIMEOUT, REGISTRATION_TIMEOUT) {
retries += 1
if (registered) {
registrationRetryTimer.foreach(_.cancel())
} else if (retries >= REGISTRATION_RETRIES) {
logError("All masters are unresponsive! Giving up.")
System.exit(1)
} else {
tryRegisterAllMasters()
Utils.tryOrExit {
retries += 1
if (registered) {
registrationRetryTimer.foreach(_.cancel())
} else if (retries >= REGISTRATION_RETRIES) {
logError("All masters are unresponsive! Giving up.")
System.exit(1)
} else {
tryRegisterAllMasters()
}
}
}
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@ import scala.util.Random
import org.apache.spark._
import org.apache.spark.TaskState.TaskState
import org.apache.spark.scheduler.SchedulingMode.SchedulingMode
import org.apache.spark.util.Utils

/**
* Schedules tasks for multiple types of clusters by acting through a SchedulerBackend.
Expand Down Expand Up @@ -139,7 +140,7 @@ private[spark] class TaskSchedulerImpl(
import sc.env.actorSystem.dispatcher
sc.env.actorSystem.scheduler.schedule(SPECULATION_INTERVAL milliseconds,
SPECULATION_INTERVAL milliseconds) {
checkSpeculatableTasks()
Utils.tryOrExit { checkSpeculatableTasks() }
}
}
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -155,7 +155,7 @@ private[spark] class BlockManager(
BlockManagerWorker.startBlockManagerWorker(this)
if (!BlockManager.getDisableHeartBeatsForTesting(conf)) {
heartBeatTask = actorSystem.scheduler.schedule(0.seconds, heartBeatFrequency.milliseconds) {
heartBeat()
Utils.tryOrExit { heartBeat() }
}
}
}
Expand Down
13 changes: 13 additions & 0 deletions core/src/main/scala/org/apache/spark/util/Utils.scala
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@ import tachyon.client.{TachyonFile,TachyonFS}

import org.apache.spark.{Logging, SecurityManager, SparkConf, SparkException}
import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.spark.executor.ExecutorUncaughtExceptionHandler
import org.apache.spark.serializer.{DeserializationStream, SerializationStream, SerializerInstance}

/**
Expand Down Expand Up @@ -778,6 +779,18 @@ private[spark] object Utils extends Logging {
output.toString
}

/**
* Execute a block of code that evaluates to Unit, forwarding any uncaught exceptions to the
* default UncaughtExceptionHandler
*/
def tryOrExit(block: => Unit) {
try {
block
} catch {
case t: Throwable => ExecutorUncaughtExceptionHandler.uncaughtException(t)
}
}

/**
* A regular expression to match classes of the "core" Spark API that we want to skip when
* finding the call site of a method.
Expand Down