Skip to content

[SPARK-1685] Cancel retryTimer on restart of Worker or AppClient #602

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.

Sign up for GitHub

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 2 commits into from
Closed

[SPARK-1685] Cancel retryTimer on restart of Worker or AppClient #602

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
69c348c
Cancel retryTimer on restart of Worker or AppClient
markhamstra Apr 30, 2014
11cc088
retryTimer -> registrationRetryTimer
markhamstra Apr 30, 2014
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
13 changes: 9 additions & 4 deletions core/src/main/scala/org/apache/spark/deploy/client/AppClient.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,7 @@ private[spark] class AppClient(
var master: ActorSelection = null
var alreadyDisconnected = false // To avoid calling listener.disconnected() multiple times
var alreadyDead = false // To avoid calling listener.dead() multiple times
var registrationRetryTimer: Option[Cancellable] = None

override def preStart() {
context.system.eventStream.subscribe(self, classOf[RemotingLifecycleEvent])
Expand All @@ -83,22 +84,21 @@ private[spark] class AppClient(

def registerWithMaster() {
tryRegisterAllMasters()

import context.dispatcher
var retries = 0
lazy val retryTimer: Cancellable =
registrationRetryTimer = Some {
context.system.scheduler.schedule(REGISTRATION_TIMEOUT, REGISTRATION_TIMEOUT) {
retries += 1
if (registered) {
retryTimer.cancel()
registrationRetryTimer.foreach(_.cancel())
} else if (retries >= REGISTRATION_RETRIES) {
logError("All masters are unresponsive! Giving up.")
markDead()
} else {
tryRegisterAllMasters()
}
}
retryTimer // start timer
}
}

def changeMaster(url: String) {
Expand Down Expand Up @@ -179,6 +179,11 @@ private[spark] class AppClient(
alreadyDead = true
}
}

override def postStop() {
registrationRetryTimer.foreach(_.cancel())
}

}

def start() {
Expand Down
10 changes: 6 additions & 4 deletions core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,6 +102,8 @@ private[spark] class Worker(
val metricsSystem = MetricsSystem.createMetricsSystem("worker", conf, securityMgr)
val workerSource = new WorkerSource(this)

var registrationRetryTimer: Option[Cancellable] = None

def coresFree: Int = cores - coresUsed
def memoryFree: Int = memory - memoryUsed

Expand Down Expand Up @@ -163,21 +165,20 @@ private[spark] class Worker(

def registerWithMaster() {
tryRegisterAllMasters()

var retries = 0
lazy val retryTimer: Cancellable =
registrationRetryTimer = Some {
context.system.scheduler.schedule(REGISTRATION_TIMEOUT, REGISTRATION_TIMEOUT) {
retries += 1
if (registered) {
retryTimer.cancel()
registrationRetryTimer.foreach(_.cancel())
} else if (retries >= REGISTRATION_RETRIES) {
logError("All masters are unresponsive! Giving up.")
System.exit(1)
} else {
tryRegisterAllMasters()
}
}
retryTimer // start timer
}
}

override def receive = {
Expand Down Expand Up @@ -346,6 +347,7 @@ private[spark] class Worker(
}

override def postStop() {
registrationRetryTimer.foreach(_.cancel())
executors.values.foreach(_.kill())
drivers.values.foreach(_.kill())
webUi.stop()
Expand Down