Skip to content

[ZEPPELIN-1883] Can't import spark submitted packages in PySpark #1831

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
1ambda wants to merge 3 commits into from
Closed

[ZEPPELIN-1883] Can't import spark submitted packages in PySpark #1831

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c735bd5
fix: Import spark submit packages in pyspark
1ambda Jan 2, 2017
f76d2c8
fix: Do not extend PYTHONPATH in yarn-client
1ambda Jan 10, 2017
585d48a
Use spark.jars instead of classpath
1ambda Jan 11, 2017
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
17 changes: 15 additions & 2 deletions spark/src/main/java/org/apache/zeppelin/spark/PySparkInterpreter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -153,7 +153,6 @@ public void open() {
}

urls = urlList.toArray(urls);

ClassLoader oldCl = Thread.currentThread().getContextClassLoader();
try {
URLClassLoader newCl = new URLClassLoader(urls, oldCl);
Expand All @@ -169,11 +168,25 @@ public void open() {

private Map setupPySparkEnv() throws IOException{
Map env = EnvironmentUtils.getProcEnvironment();

if (!env.containsKey("PYTHONPATH")) {
SparkConf conf = getSparkConf();
env.put("PYTHONPATH", conf.get("spark.submit.pyFiles").replaceAll(",", ":") +
env.put("PYTHONPATH", conf.get("spark.submit.pyFiles").replaceAll(",", ":") +
":../interpreter/lib/python");
}

// get additional class paths when using SPARK_SUBMIT and not using YARN-CLIENT
// also, add all packages to PYTHONPATH since there might be transitive dependencies
if (SparkInterpreter.useSparkSubmit() &&
!getSparkInterpreter().isYarnMode()) {

String sparkSubmitJars = getSparkConf().get("spark.jars").replace(",", ":");

if (!"".equals(sparkSubmitJars)) {
env.put("PYTHONPATH", env.get("PYTHONPATH") + sparkSubmitJars);
}
}

return env;
}

Expand Down
7 changes: 3 additions & 4 deletions spark/src/main/java/org/apache/zeppelin/spark/SparkInterpreter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -296,7 +296,7 @@ private DepInterpreter getDepInterpreter() {
return (DepInterpreter) p;
}

private boolean isYarnMode() {
public boolean isYarnMode() {
return getProperty("master").startsWith("yarn");
}

Expand Down Expand Up @@ -556,7 +556,7 @@ static final String toString(Object o) {
return (o instanceof String) ? (String) o : "";
}

private boolean useSparkSubmit() {
public static boolean useSparkSubmit() {
return null != System.getenv("SPARK_SUBMIT");
}

Expand Down Expand Up @@ -727,7 +727,6 @@ public void open() {
pathSettings.v_$eq(classpath);
settings.scala$tools$nsc$settings$ScalaSettings$_setter_$classpath_$eq(pathSettings);


// set classloader for scala compiler
settings.explicitParentLoader_$eq(new Some<>(Thread.currentThread()
.getContextClassLoader()));
Expand Down Expand Up @@ -976,7 +975,7 @@ public void populateSparkWebUrl(InterpreterContext ctx) {
}
}

private List<File> currentClassPath() {
public List<File> currentClassPath() {
List<File> paths = classPath(Thread.currentThread().getContextClassLoader());
String[] cps = System.getProperty("java.class.path").split(File.pathSeparator);
if (cps != null) {
Expand Down