Incorporate Tom's comments - update doc and code to reflect that core requests may not always be honored
Project: http://git-wip-us.apache.org/repos/asf/incubator-spark/repo Commit: http://git-wip-us.apache.org/repos/asf/incubator-spark/commit/adf42611 Tree: http://git-wip-us.apache.org/repos/asf/incubator-spark/tree/adf42611 Diff: http://git-wip-us.apache.org/repos/asf/incubator-spark/diff/adf42611 Branch: refs/heads/master Commit: adf42611f16daec091af10f2c9b39bd154dc67b3 Parents: 3e85b87 Author: Sandy Ryza <sa...@cloudera.com> Authored: Tue Jan 21 00:38:02 2014 -0800 Committer: Sandy Ryza <sa...@cloudera.com> Committed: Tue Jan 21 00:38:02 2014 -0800 ---------------------------------------------------------------------- docs/running-on-yarn.md | 2 +- .../org/apache/spark/deploy/yarn/YarnAllocationHandler.scala | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/incubator-spark/blob/adf42611/docs/running-on-yarn.md ---------------------------------------------------------------------- diff --git a/docs/running-on-yarn.md b/docs/running-on-yarn.md index fb8a043..5dadd54 100644 --- a/docs/running-on-yarn.md +++ b/docs/running-on-yarn.md @@ -133,7 +133,7 @@ See [Building Spark with Maven](building-with-maven.html) for instructions on ho # Important Notes -- Before Hadoop 2.2, YARN does not support cores in container resource requests. Thus, when running against an earlier version, the numbers of cores given via command line arguments cannot be guaranteed. +- Before Hadoop 2.2, YARN does not support cores in container resource requests. Thus, when running against an earlier version, the numbers of cores given via command line arguments cannot be passed to YARN. Whether core requests are honored in scheduling decisions depends on which scheduler is in use and how it is configured. - The local directories used for spark will be the local directories configured for YARN (Hadoop Yarn config yarn.nodemanager.local-dirs). If the user specifies spark.local.dir, it will be ignored. - The --files and --archives options support specifying file names with the # similar to Hadoop. For example you can specify: --files localtest.txt#appSees.txt and this will upload the file you have locally named localtest.txt into HDFS but this will be linked to by the name appSees.txt and your application should use the name as appSees.txt to reference it when running on YARN. - The --addJars option allows the SparkContext.addJar function to work if you are using it with local files. It does not need to be used if you are using it with HDFS, HTTP, HTTPS, or FTP files. http://git-wip-us.apache.org/repos/asf/incubator-spark/blob/adf42611/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala ---------------------------------------------------------------------- diff --git a/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala index f53c130..1ac6112 100644 --- a/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala +++ b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala @@ -102,8 +102,7 @@ private[yarn] class YarnAllocationHandler( def getNumWorkersFailed: Int = numWorkersFailed.intValue def isResourceConstraintSatisfied(container: Container): Boolean = { - (container.getResource.getMemory >= (workerMemory + YarnAllocationHandler.MEMORY_OVERHEAD) - && container.getResource.getVirtualCores >= workerCores) + container.getResource.getMemory >= (workerMemory + YarnAllocationHandler.MEMORY_OVERHEAD) } def releaseContainer(container: Container) {
