Github user pwendell commented on a diff in the pull request:
https://github.com/apache/spark/pull/102#discussion_r10505246
--- Diff:
yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientBase.scala ---
@@ -379,9 +381,48 @@ object ClientBase {
// Based on code from org.apache.hadoop.mapreduce.v2.util.MRApps
def populateHadoopClasspath(conf: Configuration, env: HashMap[String,
String]) {
- for (c <-
conf.getStrings(YarnConfiguration.YARN_APPLICATION_CLASSPATH)) {
+ val classpathEntries = Option(conf.getStrings(
+ YarnConfiguration.YARN_APPLICATION_CLASSPATH)).getOrElse(
+ getDefaultYarnApplicationClasspath())
+ for (c <- classpathEntries) {
Apps.addToEnvironment(env, Environment.CLASSPATH.name, c.trim)
}
+
+ val mrClasspathEntries = Option(conf.getStrings(
+ "mapreduce.application.classpath")).getOrElse(
+ getDefaultMRApplicationClasspath())
+ if (mrClasspathEntries != null) {
+ for (c <- mrClasspathEntries) {
+ Apps.addToEnvironment(env, Environment.CLASSPATH.name, c.trim)
+ }
+ }
+ }
+
+ def getDefaultYarnApplicationClasspath(): Array[String] = {
+ try {
+ val field =
classOf[MRJobConfig].getField("DEFAULT_YARN_APPLICATION_CLASSPATH")
--- End diff --
Hey @sryza rather than use reflection here why not just modify the
`Client.scala` classes in `common` and `stable`? I think the main reason of
separating those two was so that we don't have to use reflection everywhere. Is
that hard to do in this case?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
