[
https://issues.apache.org/jira/browse/SPARK-5559?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Kousuke Saruta updated SPARK-5559:
----------------------------------
Description:
When we run FlumeStreamSuite on Jenkins, sometimes we get error like as follows.
{code}
sbt.ForkMain$ForkError: The code passed to eventually never returned normally.
Attempted 52 times over 10.094849836 seconds. Last failure message: Error
connecting to localhost/127.0.0.1:23456.
at
org.scalatest.concurrent.Eventually$class.tryTryAgain$1(Eventually.scala:420)
at
org.scalatest.concurrent.Eventually$class.eventually(Eventually.scala:438)
at org.scalatest.concurrent.Eventually$.eventually(Eventually.scala:478)
at
org.scalatest.concurrent.Eventually$class.eventually(Eventually.scala:307)
at org.scalatest.concurrent.Eventually$.eventually(Eventually.scala:478)
at
org.apache.spark.streaming.flume.FlumeStreamSuite.writeAndVerify(FlumeStreamSuite.scala:116)
at
org.apache.spark.streaming.flume.FlumeStreamSuite.org$apache$spark$streaming$flume$FlumeStreamSuite$$testFlumeStream(FlumeStreamSuite.scala:74)
at
org.apache.spark.streaming.flume.FlumeStreamSuite$$anonfun$3.apply$mcV$sp(FlumeStreamSuite.scala:66)
at
org.apache.spark.streaming.flume.FlumeStreamSuite$$anonfun$3.apply(FlumeStreamSuite.scala:66)
at
org.apache.spark.streaming.flume.FlumeStreamSuite$$anonfun$3.apply(FlumeStreamSuite.scala:66)
at
org.scalatest.Transformer$$anonfun$apply$1.apply$mcV$sp(Transformer.scala:22)
at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
at org.scalatest.Transformer.apply(Transformer.scala:22)
at org.scalatest.Transformer.apply(Transformer.scala:20)
at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:166)
at org.scalatest.Suite$class.withFixture(Suite.scala:1122)
at org.scalatest.FunSuite.withFixture(FunSuite.scala:1555)
at
org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163)
at
org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
at
org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306)
at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:175)
{code}
This error is caused by check-then-act logic when it find free-port .
{code}
/** Find a free port */
private def findFreePort(): Int = {
Utils.startServiceOnPort(23456, (trialPort: Int) => {
val socket = new ServerSocket(trialPort)
socket.close()
(null, trialPort)
}, conf)._2
}
{code}
Removing the check-then-act is not easy but we can reduce the chance of having
the error by choosing random value for initial port instead of 23456.
was:
When we run FlumeStreamSuite on Jenkins, sometimes we get error like as follows.
{code}
sbt.ForkMain$ForkError: The code passed to eventually never returned normally.
Attempted 52 times over 10.094849836 seconds. Last failure message: Error
connecting to localhost/127.0.0.1:23456.
at
org.scalatest.concurrent.Eventually$class.tryTryAgain$1(Eventually.scala:420)
at
org.scalatest.concurrent.Eventually$class.eventually(Eventually.scala:438)
at org.scalatest.concurrent.Eventually$.eventually(Eventually.scala:478)
at
org.scalatest.concurrent.Eventually$class.eventually(Eventually.scala:307)
at org.scalatest.concurrent.Eventually$.eventually(Eventually.scala:478)
at
org.apache.spark.streaming.flume.FlumeStreamSuite.writeAndVerify(FlumeStreamSuite.scala:116)
at
org.apache.spark.streaming.flume.FlumeStreamSuite.org$apache$spark$streaming$flume$FlumeStreamSuite$$testFlumeStream(FlumeStreamSuite.scala:74)
at
org.apache.spark.streaming.flume.FlumeStreamSuite$$anonfun$3.apply$mcV$sp(FlumeStreamSuite.scala:66)
at
org.apache.spark.streaming.flume.FlumeStreamSuite$$anonfun$3.apply(FlumeStreamSuite.scala:66)
at
org.apache.spark.streaming.flume.FlumeStreamSuite$$anonfun$3.apply(FlumeStreamSuite.scala:66)
at
org.scalatest.Transformer$$anonfun$apply$1.apply$mcV$sp(Transformer.scala:22)
at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
at org.scalatest.Transformer.apply(Transformer.scala:22)
at org.scalatest.Transformer.apply(Transformer.scala:20)
at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:166)
at org.scalatest.Suite$class.withFixture(Suite.scala:1122)
at org.scalatest.FunSuite.withFixture(FunSuite.scala:1555)
at
org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163)
at
org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
at
org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306)
at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:175)
{code}
This error is caused by check-then-act logic when it find free-port .
{code}
/** Find a free port */
private def findFreePort(): Int = {
Utils.startServiceOnPort((math.random * Int.MaxValue).toInt, (trialPort:
Int) => {
val socket = new ServerSocket(trialPort)
socket.close()
(null, trialPort)
}, conf)._2
}
{code}
Removing the check-then-act is not easy but we can reduce the chance of having
the error by choosing random value for initial port instead of 23456.
> Remove oppotunity we met flakiness when running FlumeStreamSuite
> ----------------------------------------------------------------
>
> Key: SPARK-5559
> URL: https://issues.apache.org/jira/browse/SPARK-5559
> Project: Spark
> Issue Type: Improvement
> Components: Project Infra, Streaming
> Affects Versions: 1.3.0
> Reporter: Kousuke Saruta
>
> When we run FlumeStreamSuite on Jenkins, sometimes we get error like as
> follows.
> {code}
> sbt.ForkMain$ForkError: The code passed to eventually never returned
> normally. Attempted 52 times over 10.094849836 seconds. Last failure message:
> Error connecting to localhost/127.0.0.1:23456.
> at
> org.scalatest.concurrent.Eventually$class.tryTryAgain$1(Eventually.scala:420)
> at
> org.scalatest.concurrent.Eventually$class.eventually(Eventually.scala:438)
> at org.scalatest.concurrent.Eventually$.eventually(Eventually.scala:478)
> at
> org.scalatest.concurrent.Eventually$class.eventually(Eventually.scala:307)
> at org.scalatest.concurrent.Eventually$.eventually(Eventually.scala:478)
> at
> org.apache.spark.streaming.flume.FlumeStreamSuite.writeAndVerify(FlumeStreamSuite.scala:116)
> at
> org.apache.spark.streaming.flume.FlumeStreamSuite.org$apache$spark$streaming$flume$FlumeStreamSuite$$testFlumeStream(FlumeStreamSuite.scala:74)
> at
> org.apache.spark.streaming.flume.FlumeStreamSuite$$anonfun$3.apply$mcV$sp(FlumeStreamSuite.scala:66)
> at
> org.apache.spark.streaming.flume.FlumeStreamSuite$$anonfun$3.apply(FlumeStreamSuite.scala:66)
> at
> org.apache.spark.streaming.flume.FlumeStreamSuite$$anonfun$3.apply(FlumeStreamSuite.scala:66)
> at
> org.scalatest.Transformer$$anonfun$apply$1.apply$mcV$sp(Transformer.scala:22)
> at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
> at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
> at org.scalatest.Transformer.apply(Transformer.scala:22)
> at org.scalatest.Transformer.apply(Transformer.scala:20)
> at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:166)
> at org.scalatest.Suite$class.withFixture(Suite.scala:1122)
> at org.scalatest.FunSuite.withFixture(FunSuite.scala:1555)
> at
> org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163)
> at
> org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
> at
> org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
> at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306)
> at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:175)
> {code}
> This error is caused by check-then-act logic when it find free-port .
> {code}
> /** Find a free port */
> private def findFreePort(): Int = {
> Utils.startServiceOnPort(23456, (trialPort: Int) => {
> val socket = new ServerSocket(trialPort)
> socket.close()
> (null, trialPort)
> }, conf)._2
> }
> {code}
> Removing the check-then-act is not easy but we can reduce the chance of
> having the error by choosing random value for initial port instead of 23456.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
