Github user andrewor14 commented on a diff in the pull request:
https://github.com/apache/spark/pull/6360#discussion_r31765999
--- Diff: core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala ---
@@ -315,62 +315,59 @@ object SparkSubmit {
case _ =>
}
- // If we're running a python app, set the main class to our specific
python runner
- if (args.isPython && deployMode == CLIENT) {
- if (args.primaryResource == PYSPARK_SHELL) {
- args.mainClass = "org.apache.spark.api.python.PythonGatewayServer"
- } else {
- // If a python file is provided, add it to the child arguments and
list of files to deploy.
- // Usage: PythonAppRunner <main python file> <extra python files>
[app arguments]
- args.mainClass = "org.apache.spark.deploy.PythonRunner"
- args.childArgs = ArrayBuffer(args.primaryResource, args.pyFiles)
++ args.childArgs
- args.files = mergeFileLists(args.files, args.primaryResource)
- }
- args.files = mergeFileLists(args.files, args.pyFiles)
- if (args.pyFiles != null) {
- sysProps("spark.submit.pyFiles") = args.pyFiles
- }
- }
-
- // 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.")
+ if (args.isPython) {
+ // In yarn mode for a python app, add pyspark archives to files
+ // that can be distributed with the job
+ if (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 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.")
+ 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")
--- End diff --
not your code, but at some point we should factor this out instead of
hardcoding the version here
---
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]
