Github user vanzin commented on a diff in the pull request:
https://github.com/apache/spark/pull/5580#discussion_r29373080
--- Diff: core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala ---
@@ -328,6 +328,47 @@ object SparkSubmit {
}
}
+ // In yarn mode for a python app, add pyspark archives to files
+ // that can be distributed with the job
+ if (args.isPython && clusterManager == YARN) {
+ var pyArchives: String = null
+ val pyArchivesEnvOpt = sys.env.get("PYSPARK_ARCHIVES_PATH")
+ if (pyArchivesEnvOpt.isDefined) {
+ pyArchives = pyArchivesEnvOpt.get
+ } else {
+ if (!sys.env.contains("SPARK_HOME")) {
+ printErrorAndExit("SPARK_HOME does not exist for python
application in yarn mode.")
+ }
+ val pythonPath = new ArrayBuffer[String]
+ for (sparkHome <- sys.env.get("SPARK_HOME")) {
+ val pyLibPath = Seq(sparkHome, "python",
"lib").mkString(File.separator)
+ val pyArchivesFile = new File(pyLibPath, "pyspark.zip")
+ if (!pyArchivesFile.exists()) {
+ printErrorAndExit("pyspark.zip does not exist for python
application in yarn mode.")
+ }
+ val py4jFile = new File(pyLibPath, "py4j-0.8.2.1-src.zip")
+ if (!py4jFile.exists()) {
+ printErrorAndExit("py4j-0.8.2.1-src.zip does not exist for
python application " +
+ "in yarn mode.")
+ }
+ pythonPath += pyArchivesFile.getAbsolutePath()
+ pythonPath += py4jFile.getAbsolutePath()
+ }
+ pyArchives = pythonPath.mkString(",")
+ }
+
+ pyArchives = pyArchives.split(",").map { localPath=>
+ val localURI = Utils.resolveURI(localPath)
+ if (localURI.getScheme != "local") {
+ args.files = mergeFileLists(args.files, localURI.toString)
+ (new Path(localPath)).getName
+ } else {
+ localURI.getPath.toString
--- End diff --
`getPath` already returns a `String`.
---
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.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
