Skip to content

[SPARK-16110][YARN][PYSPARK] Fix allowing python version to be specified per submit for cluster mode. #13824

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
KevinGrealish wants to merge 7 commits into from
Closed

[SPARK-16110][YARN][PYSPARK] Fix allowing python version to be specified per submit for cluster mode. #13824

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
2eb3833
SPARK-16110 ensure that PYSPARK_PYTHON and PYSPARK_DRIVER_PYTHON are
KevinGrealish Jun 21, 2016
4ad7904
Alter apprach to instead set env vars from config last, thus
KevinGrealish Jun 22, 2016
cb41e9e
Add a test that spark.yarn.appMasterEnv overrides env vars.
KevinGrealish Jul 26, 2016
6791edc
Fix spark.yarn.appMasterEnv to set rather than java path style append.
KevinGrealish Jul 26, 2016
f2c2e4a
Still use CLASSPATH style append for other env vars. Narrows fix.
KevinGrealish Jul 27, 2016
ca4d5fa
Narrow fix further to avoid issues with append.
KevinGrealish Jul 27, 2016
7ad3d77
Minor code formatting change.
KevinGrealish Jul 27, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -804,8 +804,11 @@ private[spark] class Client(
env("SPARK_JAVA_OPTS") = value
}
// propagate PYSPARK_DRIVER_PYTHON and PYSPARK_PYTHON to driver in cluster mode
sys.env.get("PYSPARK_DRIVER_PYTHON").foreach(env("PYSPARK_DRIVER_PYTHON") = _)
sys.env.get("PYSPARK_PYTHON").foreach(env("PYSPARK_PYTHON") = _)
Seq("PYSPARK_DRIVER_PYTHON", "PYSPARK_PYTHON").foreach { envname =>
if (!env.contains(envname)) {
sys.env.get(envname).foreach(env(envname) = _)
}
}
}

sys.env.get(ENV_DIST_CLASSPATH).foreach { dcp =>
Expand Down
26 changes: 22 additions & 4 deletions yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,6 +128,20 @@ class YarnClusterSuite extends BaseYarnClusterSuite {
testPySpark(false)
}

test("run Python application in yarn-cluster mode using " +
" spark.yarn.appMasterEnv to override local envvar") {
testPySpark(
clientMode = false,
extraConf = Map(
"spark.yarn.appMasterEnv.PYSPARK_DRIVER_PYTHON"
-> sys.env.getOrElse("PYSPARK_DRIVER_PYTHON", "python"),
"spark.yarn.appMasterEnv.PYSPARK_PYTHON"
-> sys.env.getOrElse("PYSPARK_PYTHON", "python")),
extraEnv = Map(
"PYSPARK_DRIVER_PYTHON" -> "not python",
"PYSPARK_PYTHON" -> "not python"))
}

test("user class path first in client mode") {
testUseClassPathFirst(true)
}
Expand Down Expand Up @@ -188,7 +202,10 @@ class YarnClusterSuite extends BaseYarnClusterSuite {
checkResult(finalState, executorResult, "ORIGINAL")
}

private def testPySpark(clientMode: Boolean): Unit = {
private def testPySpark(
clientMode: Boolean,
extraConf: Map[String, String] = Map(),
extraEnv: Map[String, String] = Map()): Unit = {
val primaryPyFile = new File(tempDir, "test.py")
Files.write(TEST_PYFILE, primaryPyFile, StandardCharsets.UTF_8)

Expand All @@ -199,9 +216,9 @@ class YarnClusterSuite extends BaseYarnClusterSuite {
val pythonPath = Seq(
s"$sparkHome/python/lib/py4j-0.10.1-src.zip",
s"$sparkHome/python")
val extraEnv = Map(
val extraEnvVars = Map(
"PYSPARK_ARCHIVES_PATH" -> pythonPath.map("local:" + _).mkString(File.pathSeparator),
"PYTHONPATH" -> pythonPath.mkString(File.pathSeparator))
"PYTHONPATH" -> pythonPath.mkString(File.pathSeparator)) ++ extraEnv

val moduleDir =
if (clientMode) {
Expand All @@ -223,7 +240,8 @@ class YarnClusterSuite extends BaseYarnClusterSuite {
val finalState = runSpark(clientMode, primaryPyFile.getAbsolutePath(),
sparkArgs = Seq("--py-files" -> pyFiles),
appArgs = Seq(result.getAbsolutePath()),
extraEnv = extraEnv)
extraEnv = extraEnvVars,
extraConf = extraConf)
checkResult(finalState, result)
}

Expand Down