This is an automated email from the ASF dual-hosted git repository. jiangxb1987 pushed a commit to branch branch-3.0 in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.0 by this push: new 00e2bf8 [SPARK-30987][CORE] Increase the timeout on local-cluster waitUntilExecutorsUp calls 00e2bf8 is described below commit 00e2bf8a9a96cf421fa5257f72d46334306b92fa Author: Thomas Graves <tgra...@nvidia.com> AuthorDate: Fri Feb 28 11:43:05 2020 -0800 [SPARK-30987][CORE] Increase the timeout on local-cluster waitUntilExecutorsUp calls ### What changes were proposed in this pull request? The ResourceDiscoveryPlugin tests intermittently timeout. They are timing out on just bringing up the local-cluster. I am not able to reproduce locally. I suspect the jenkins boxes are overloaded and taking longer then 10 seconds. There was another jira SPARK-29139 that increased timeout for some other of these as well. So try increasing the timeout to 60 seconds. Examples of timeouts: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119030/testReport/ https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119005/testReport/ https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119029/testReport/ ### Why are the changes needed? tests should no longer intermittently fail. ### Does this PR introduce any user-facing change? no ### How was this patch tested? unit tests ran. Closes #27738 from tgravescs/SPARK-30987. Authored-by: Thomas Graves <tgra...@nvidia.com> Signed-off-by: Xingbo Jiang <xingbo.ji...@databricks.com> (cherry picked from commit 6c0c41fa0d1e119b16980405b5dc69b953380d7d) Signed-off-by: Xingbo Jiang <xingbo.ji...@databricks.com> --- core/src/test/scala/org/apache/spark/DistributedSuite.scala | 2 +- .../org/apache/spark/internal/plugin/PluginContainerSuite.scala | 4 ++-- .../org/apache/spark/resource/ResourceDiscoveryPluginSuite.scala | 8 ++++---- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/core/src/test/scala/org/apache/spark/DistributedSuite.scala b/core/src/test/scala/org/apache/spark/DistributedSuite.scala index 3f30981..4d157b9 100644 --- a/core/src/test/scala/org/apache/spark/DistributedSuite.scala +++ b/core/src/test/scala/org/apache/spark/DistributedSuite.scala @@ -174,7 +174,7 @@ class DistributedSuite extends SparkFunSuite with Matchers with LocalSparkContex private def testCaching(conf: SparkConf, storageLevel: StorageLevel): Unit = { sc = new SparkContext(conf.setMaster(clusterUrl).setAppName("test")) - TestUtils.waitUntilExecutorsUp(sc, 2, 30000) + TestUtils.waitUntilExecutorsUp(sc, 2, 60000) val data = sc.parallelize(1 to 1000, 10) val cachedData = data.persist(storageLevel) assert(cachedData.count === 1000) diff --git a/core/src/test/scala/org/apache/spark/internal/plugin/PluginContainerSuite.scala b/core/src/test/scala/org/apache/spark/internal/plugin/PluginContainerSuite.scala index cf2d929..7888796 100644 --- a/core/src/test/scala/org/apache/spark/internal/plugin/PluginContainerSuite.scala +++ b/core/src/test/scala/org/apache/spark/internal/plugin/PluginContainerSuite.scala @@ -139,7 +139,7 @@ class PluginContainerSuite extends SparkFunSuite with BeforeAndAfterEach with Lo .set(NonLocalModeSparkPlugin.TEST_PATH_CONF, path.getAbsolutePath()) sc = new SparkContext(conf) - TestUtils.waitUntilExecutorsUp(sc, 2, 10000) + TestUtils.waitUntilExecutorsUp(sc, 2, 60000) eventually(timeout(10.seconds), interval(100.millis)) { val children = path.listFiles() @@ -169,7 +169,7 @@ class PluginContainerSuite extends SparkFunSuite with BeforeAndAfterEach with Lo sc = new SparkContext(conf) // Ensure all executors has started - TestUtils.waitUntilExecutorsUp(sc, 1, 10000) + TestUtils.waitUntilExecutorsUp(sc, 1, 60000) var children = Array.empty[File] eventually(timeout(10.seconds), interval(100.millis)) { diff --git a/core/src/test/scala/org/apache/spark/resource/ResourceDiscoveryPluginSuite.scala b/core/src/test/scala/org/apache/spark/resource/ResourceDiscoveryPluginSuite.scala index 7a05daa..437c903 100644 --- a/core/src/test/scala/org/apache/spark/resource/ResourceDiscoveryPluginSuite.scala +++ b/core/src/test/scala/org/apache/spark/resource/ResourceDiscoveryPluginSuite.scala @@ -56,7 +56,7 @@ class ResourceDiscoveryPluginSuite extends SparkFunSuite with LocalSparkContext .set(EXECUTOR_FPGA_ID.amountConf, "1") sc = new SparkContext(conf) - TestUtils.waitUntilExecutorsUp(sc, 2, 10000) + TestUtils.waitUntilExecutorsUp(sc, 2, 60000) eventually(timeout(10.seconds), interval(100.millis)) { val children = dir.listFiles() @@ -84,7 +84,7 @@ class ResourceDiscoveryPluginSuite extends SparkFunSuite with LocalSparkContext .set(SPARK_RESOURCES_DIR, dir.getName()) sc = new SparkContext(conf) - TestUtils.waitUntilExecutorsUp(sc, 2, 10000) + TestUtils.waitUntilExecutorsUp(sc, 2, 60000) eventually(timeout(10.seconds), interval(100.millis)) { val children = dir.listFiles() @@ -111,7 +111,7 @@ class ResourceDiscoveryPluginSuite extends SparkFunSuite with LocalSparkContext .set(SPARK_RESOURCES_DIR, dir.getName()) sc = new SparkContext(conf) - TestUtils.waitUntilExecutorsUp(sc, 2, 10000) + TestUtils.waitUntilExecutorsUp(sc, 2, 60000) eventually(timeout(10.seconds), interval(100.millis)) { val children = dir.listFiles() @@ -137,7 +137,7 @@ class ResourceDiscoveryPluginSuite extends SparkFunSuite with LocalSparkContext .set(SPARK_RESOURCES_DIR, dir.getName()) sc = new SparkContext(conf) - TestUtils.waitUntilExecutorsUp(sc, 2, 10000) + TestUtils.waitUntilExecutorsUp(sc, 2, 60000) assert(sc.resources.size === 1) assert(sc.resources.get(GPU).get.addresses === Array("5", "6")) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org