Skip to content

[SPARK-40635][YARN][TESTS] Fix yarn module daily test failed with hadoop2 #38079

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
LuciferYang wants to merge 8 commits into from
Closed

[SPARK-40635][YARN][TESTS] Fix yarn module daily test failed with hadoop2 #38079

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
e8e6b7f
try filter some test deps from classpath
LuciferYang Oct 3, 2022
5ad8024
test hadoop 2
LuciferYang Oct 2, 2022
93bdf77
try dedup
LuciferYang Oct 3, 2022
64f0e0b
use File.pathSeparator
LuciferYang Oct 3, 2022
b17b27f
test hadoop3
LuciferYang Oct 3, 2022
bd89c95
do de duplication only when Utils.isTesting is true
LuciferYang Oct 5, 2022
4e9a0d8
re test haddop2
LuciferYang Oct 5, 2022
2712ae0
add comments and re-test hadoop-3
LuciferYang Oct 5, 2022
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
2 changes: 1 addition & 1 deletion .github/workflows/build_and_test.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ on:
description: Hadoop version to run with. HADOOP_PROFILE environment variable should accept it.
required: false
type: string
default: hadoop3
default: hadoop2

@LuciferYang LuciferYang Oct 3, 2022

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

for test hadoop-2, will revert after confirmation takes effect

envs:
description: Additional environment variables to set when running the tests. Should be in JSON format.
required: false
Expand Down
13 changes: 11 additions & 2 deletions resource-managers/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 @@ -909,7 +909,12 @@ private[spark] class Client(
pySparkArchives: Seq[String]): HashMap[String, String] = {
logInfo("Setting up the launch environment for our AM container")
val env = new HashMap[String, String]()
populateClasspath(args, hadoopConf, sparkConf, env, sparkConf.get(DRIVER_CLASS_PATH))
val driverClassPath = sparkConf.get(DRIVER_CLASS_PATH).map { s =>
val strings = s.split(":")
val ret = strings.filter(v => !v.contains("selenium") && !v.contains("opentelemetry"))
ret.mkString(":")
}
populateClasspath(args, hadoopConf, sparkConf, env, driverClassPath)
env("SPARK_YARN_STAGING_DIR") = stagingDirPath.toString
env("SPARK_USER") = UserGroupInformation.getCurrentUser().getShortUserName()
env("SPARK_PREFER_IPV6") = Utils.preferIPv6.toString
Expand Down Expand Up @@ -1512,7 +1517,11 @@ private[spark] object Client extends Logging {
populateHadoopClasspath(conf, env)
}

sys.env.get(ENV_DIST_CLASSPATH).foreach { cp =>
sys.env.get(ENV_DIST_CLASSPATH).map { s =>
val strings = s.split(":")
val ret = strings.filter(v => !v.contains("selenium") && !v.contains("opentelemetry"))
ret.mkString(":")
}.foreach { cp =>
addClasspathEntry(getClusterPath(sparkConf, cp), env)
}

Expand Down
7 changes: 6 additions & 1 deletion resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,12 @@ private[yarn] class ExecutorRunnable(

private def prepareEnvironment(): HashMap[String, String] = {
val env = new HashMap[String, String]()
Client.populateClasspath(null, conf, sparkConf, env, sparkConf.get(EXECUTOR_CLASS_PATH))
val executorClassPath = sparkConf.get(EXECUTOR_CLASS_PATH).map { s =>
val strings = s.split(":")
val ret = strings.filter(v => !v.contains("selenium") && !v.contains("opentelemetry"))
ret.mkString(":")
}
Client.populateClasspath(null, conf, sparkConf, env, executorClassPath)

System.getenv().asScala.filterKeys(_.startsWith("SPARK"))
.foreach { case (k, v) => env(k) = v }
Expand Down