Skip to content

[SPARK-28483][FOLLOW-UP] Fix flaky test in BarrierTaskContextSuite #25799

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
WeichenXu123 wants to merge 3 commits into from
Closed

[SPARK-28483][FOLLOW-UP] Fix flaky test in BarrierTaskContextSuite #25799

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f4d7a64
fix flaky test
WeichenXu123 Sep 12, 2019
9dbdcb8
address comments
WeichenXu123 Sep 16, 2019
c8dcf42
update
WeichenXu123 Sep 17, 2019
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
36 changes: 23 additions & 13 deletions core/src/test/scala/org/apache/spark/scheduler/BarrierTaskContextSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,10 +156,7 @@ class BarrierTaskContextSuite extends SparkFunSuite with LocalSparkContext {
assert(error.contains("within 1 second(s)"))
}


def testBarrierTaskKilled(sc: SparkContext, interruptOnCancel: Boolean): Unit = {
sc.setLocalProperty(SparkContext.SPARK_JOB_INTERRUPT_ON_CANCEL, interruptOnCancel.toString)

def testBarrierTaskKilled(interruptOnKill: Boolean): Unit = {
withTempDir { dir =>
val killedFlagFile = "barrier.task.killed"
val rdd = sc.makeRDD(Seq(0, 1), 2)
Expand All @@ -181,12 +178,15 @@ class BarrierTaskContextSuite extends SparkFunSuite with LocalSparkContext {

val listener = new SparkListener {
override def onTaskStart(taskStart: SparkListenerTaskStart): Unit = {
new Thread {
override def run: Unit = {
Thread.sleep(1000)
sc.killTaskAttempt(taskStart.taskInfo.taskId, interruptThread = false)
}
}.start()
val partitionId = taskStart.taskInfo.index
if (partitionId == 0) {
new Thread {
override def run: Unit = {
Thread.sleep(1000)
sc.killTaskAttempt(taskStart.taskInfo.taskId, interruptThread = interruptOnKill)
}
}.start()
}
}
}
sc.addSparkListener(listener)
Expand All @@ -201,15 +201,25 @@ class BarrierTaskContextSuite extends SparkFunSuite with LocalSparkContext {
}
}

test("barrier task killed") {
test("barrier task killed, no interrupt") {
val conf = new SparkConf()
.set("spark.barrier.sync.timeout", "1")
.set(TEST_NO_STAGE_RETRY, true)
.setMaster("local-cluster[4, 1, 1024]")
.setAppName("test-cluster")
sc = new SparkContext(conf)

testBarrierTaskKilled(interruptOnKill = false)
}

test("barrier task killed, interrupt") {
val conf = new SparkConf()
.set("spark.barrier.sync.timeout", "1")
.set(TEST_NO_STAGE_RETRY, true)
.setMaster("local-cluster[4, 1, 1024]")
.setAppName("test-cluster")
sc = new SparkContext(conf)

testBarrierTaskKilled(sc, true)
testBarrierTaskKilled(sc, false)
testBarrierTaskKilled(interruptOnKill = true)
}
}