Github user andrewor14 commented on a diff in the pull request:
https://github.com/apache/spark/pull/433#discussion_r11746787
--- Diff:
yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientBase.scala ---
@@ -378,55 +378,48 @@ object ClientBase {
val APP_JAR: String = "app.jar"
val LOG4J_PROP: String = "log4j.properties"
- // Based on code from org.apache.hadoop.mapreduce.v2.util.MRApps
- def populateHadoopClasspath(conf: Configuration, env: HashMap[String,
String]) {
- val classpathEntries = Option(conf.getStrings(
- YarnConfiguration.YARN_APPLICATION_CLASSPATH)).getOrElse(
- getDefaultYarnApplicationClasspath())
- for (c <- classpathEntries) {
- YarnSparkHadoopUtil.addToEnvironment(env,
Environment.CLASSPATH.name, c.trim,
- File.pathSeparator)
- }
+ def populateHadoopClasspath(conf: Configuration, env: HashMap[String,
String]) = {
+ val classPathElementsToAdd = getYarnAppClasspath(conf) ++
getMRAppClasspath(conf)
+ addToAppClasspath(env, classPathElementsToAdd)
+ classPathElementsToAdd
+ }
- val mrClasspathEntries = Option(conf.getStrings(
- "mapreduce.application.classpath")).getOrElse(
- getDefaultMRApplicationClasspath())
- if (mrClasspathEntries != null) {
- for (c <- mrClasspathEntries) {
- YarnSparkHadoopUtil.addToEnvironment(env,
Environment.CLASSPATH.name, c.trim,
- File.pathSeparator)
- }
- }
+ protected[yarn] def getYarnAppClasspath(conf: Configuration) =
+ getAppClasspathForKey(YarnConfiguration.YARN_APPLICATION_CLASSPATH,
conf)(getDefaultYarnApplicationClasspath)
+
+ protected[yarn] def getMRAppClasspath(conf: Configuration) =
+ getAppClasspathForKey("mapreduce.application.classpath",
conf)(getDefaultMRApplicationClasspath)
--- End diff --
I actually prefer that you move all of the logic of `getAppClasspathForKey`
and `getDefaultMRApplicationClasspath` into this method. Right now you have to
jump a few levels to understand what's going on, and I think it'll be clearer
if it's in one isolated place. (Same in getYarnAppClasspath)
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
