From ebbf85f07bb8de0d566f1ae4b41f26421180bebe Mon Sep 17 00:00:00 2001 From: zsxwing Date: Mon, 21 Sep 2015 11:39:04 -0700 Subject: [SPARK-7989] [SPARK-10651] [CORE] [TESTS] Increase timeout to fix flaky tests I noticed only one block manager registered with master in an unsuccessful build (https://amplab.cs.berkeley.edu/jenkins/job/Spark-Master-SBT/AMPLAB_JENKINS_BUILD_PROFILE=hadoop2.2,label=spark-test/3534/) ``` 15/09/16 13:02:30.981 pool-1-thread-1-ScalaTest-running-BroadcastSuite INFO SparkContext: Running Spark version 1.6.0-SNAPSHOT ... 15/09/16 13:02:38.133 sparkDriver-akka.actor.default-dispatcher-19 INFO BlockManagerMasterEndpoint: Registering block manager localhost:48196 with 530.3 MB RAM, BlockManagerId(0, localhost, 48196) ``` In addition, the first block manager needed 7+ seconds to start. But the test expected 2 block managers so it failed. However, there was no exception in this log file. So I checked a successful build (https://amplab.cs.berkeley.edu/jenkins/job/Spark-Master-SBT/3536/AMPLAB_JENKINS_BUILD_PROFILE=hadoop2.2,label=spark-test/) and it needed 4-5 seconds to set up the local cluster: ``` 15/09/16 18:11:27.738 sparkWorker1-akka.actor.default-dispatcher-5 INFO Worker: Running Spark version 1.6.0-SNAPSHOT ... 15/09/16 18:11:30.838 sparkDriver-akka.actor.default-dispatcher-20 INFO BlockManagerMasterEndpoint: Registering block manager localhost:54202 with 530.3 MB RAM, BlockManagerId(1, localhost, 54202) 15/09/16 18:11:32.112 sparkDriver-akka.actor.default-dispatcher-20 INFO BlockManagerMasterEndpoint: Registering block manager localhost:32955 with 530.3 MB RAM, BlockManagerId(0, localhost, 32955) ``` In this build, the first block manager needed only 3+ seconds to start. Comparing these two builds, I guess it's possible that the local cluster in `BroadcastSuite` cannot be ready in 10 seconds if the Jenkins worker is busy. So I just increased the timeout to 60 seconds to see if this can fix the issue. Author: zsxwing Closes #8813 from zsxwing/fix-BroadcastSuite. --- core/src/test/scala/org/apache/spark/ExternalShuffleServiceSuite.scala | 2 +- core/src/test/scala/org/apache/spark/broadcast/BroadcastSuite.scala | 2 +- .../org/apache/spark/scheduler/SparkListenerWithClusterSuite.scala | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'core') diff --git a/core/src/test/scala/org/apache/spark/ExternalShuffleServiceSuite.scala b/core/src/test/scala/org/apache/spark/ExternalShuffleServiceSuite.scala index e846a72c88..231f4631e0 100644 --- a/core/src/test/scala/org/apache/spark/ExternalShuffleServiceSuite.scala +++ b/core/src/test/scala/org/apache/spark/ExternalShuffleServiceSuite.scala @@ -61,7 +61,7 @@ class ExternalShuffleServiceSuite extends ShuffleSuite with BeforeAndAfterAll { // local blocks from the local BlockManager and won't send requests to ExternalShuffleService. // In this case, we won't receive FetchFailed. And it will make this test fail. // Therefore, we should wait until all slaves are up - sc.jobProgressListener.waitUntilExecutorsUp(2, 10000) + sc.jobProgressListener.waitUntilExecutorsUp(2, 60000) val rdd = sc.parallelize(0 until 1000, 10).map(i => (i, 1)).reduceByKey(_ + _) diff --git a/core/src/test/scala/org/apache/spark/broadcast/BroadcastSuite.scala b/core/src/test/scala/org/apache/spark/broadcast/BroadcastSuite.scala index fb7a8ae3f9..ba21075ce6 100644 --- a/core/src/test/scala/org/apache/spark/broadcast/BroadcastSuite.scala +++ b/core/src/test/scala/org/apache/spark/broadcast/BroadcastSuite.scala @@ -311,7 +311,7 @@ class BroadcastSuite extends SparkFunSuite with LocalSparkContext { new SparkContext("local-cluster[%d, 1, 1024]".format(numSlaves), "test", broadcastConf) // Wait until all salves are up try { - _sc.jobProgressListener.waitUntilExecutorsUp(numSlaves, 10000) + _sc.jobProgressListener.waitUntilExecutorsUp(numSlaves, 60000) _sc } catch { case e: Throwable => diff --git a/core/src/test/scala/org/apache/spark/scheduler/SparkListenerWithClusterSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/SparkListenerWithClusterSuite.scala index d1e23ed527..9fa8859382 100644 --- a/core/src/test/scala/org/apache/spark/scheduler/SparkListenerWithClusterSuite.scala +++ b/core/src/test/scala/org/apache/spark/scheduler/SparkListenerWithClusterSuite.scala @@ -43,7 +43,7 @@ class SparkListenerWithClusterSuite extends SparkFunSuite with LocalSparkContext // This test will check if the number of executors received by "SparkListener" is same as the // number of all executors, so we need to wait until all executors are up - sc.jobProgressListener.waitUntilExecutorsUp(2, 10000) + sc.jobProgressListener.waitUntilExecutorsUp(2, 60000) val rdd1 = sc.parallelize(1 to 100, 4) val rdd2 = rdd1.map(_.toString) -- cgit v1.2.3