[SPARK-19964][CORE] Avoid reading from remote repos in SparkSubmitSuite.

These tests can fail with a timeout if the remote repos are not responding, or slow. The tests don't need anything from those repos, so use an empty ivy config file to avoid setting up the defaults. The tests are passing reliably for me locally now, and failing more often than not today without this change since http://dl.bintray.com/spark-packages/maven doesn't seem to be loading from my machine. Author: Marcelo Vanzin <[email protected]> Closes apache#20916 from vanzin/SPARK-19964.
mshtelma · Apr 5, 2018 · 9b81269 · 9b81269
1 parent 2934384
commit 9b81269
Show file tree

Hide file tree

Showing 5 changed files with 27 additions and 13 deletions.
diff --git a/core/src/main/scala/org/apache/spark/deploy/DependencyUtils.scala b/core/src/main/scala/org/apache/spark/deploy/DependencyUtils.scala
@@ -33,18 +33,21 @@ private[deploy] object DependencyUtils {
       packagesExclusions: String,
       packages: String,
       repositories: String,
-      ivyRepoPath: String): String = {
+      ivyRepoPath: String,
+      ivySettingsPath: Option[String]): String = {
     val exclusions: Seq[String] =
       if (!StringUtils.isBlank(packagesExclusions)) {
         packagesExclusions.split(",")
       } else {
         Nil
       }
     // Create the IvySettings, either load from file or build defaults
-    val ivySettings = sys.props.get("spark.jars.ivySettings").map { ivySettingsFile =>
-      SparkSubmitUtils.loadIvySettings(ivySettingsFile, Option(repositories), Option(ivyRepoPath))
-    }.getOrElse {
-      SparkSubmitUtils.buildIvySettings(Option(repositories), Option(ivyRepoPath))
+    val ivySettings = ivySettingsPath match {
+      case Some(path) =>
+        SparkSubmitUtils.loadIvySettings(path, Option(repositories), Option(ivyRepoPath))
+
+      case None =>
+        SparkSubmitUtils.buildIvySettings(Option(repositories), Option(ivyRepoPath))
     }
 
     SparkSubmitUtils.resolveMavenCoordinates(packages, ivySettings, exclusions = exclusions)

diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala
@@ -359,7 +359,8 @@ object SparkSubmit extends CommandLineUtils with Logging {
       // Resolve maven dependencies if there are any and add classpath to jars. Add them to py-files
       // too for packages that include Python code
       val resolvedMavenCoordinates = DependencyUtils.resolveMavenDependencies(
-        args.packagesExclusions, args.packages, args.repositories, args.ivyRepoPath)
+        args.packagesExclusions, args.packages, args.repositories, args.ivyRepoPath,
+        args.ivySettingsPath)
 
       if (!StringUtils.isBlank(resolvedMavenCoordinates)) {
         args.jars = mergeFileLists(args.jars, resolvedMavenCoordinates)

diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala
@@ -63,6 +63,7 @@ private[deploy] class SparkSubmitArguments(args: Seq[String], env: Map[String, S
   var packages: String = null
   var repositories: String = null
   var ivyRepoPath: String = null
+  var ivySettingsPath: Option[String] = None
   var packagesExclusions: String = null
   var verbose: Boolean = false
   var isPython: Boolean = false
@@ -184,6 +185,7 @@ private[deploy] class SparkSubmitArguments(args: Seq[String], env: Map[String, S
     jars = Option(jars).orElse(sparkProperties.get("spark.jars")).orNull
     files = Option(files).orElse(sparkProperties.get("spark.files")).orNull
     ivyRepoPath = sparkProperties.get("spark.jars.ivy").orNull
+    ivySettingsPath = sparkProperties.get("spark.jars.ivySettings")
     packages = Option(packages).orElse(sparkProperties.get("spark.jars.packages")).orNull
     packagesExclusions = Option(packagesExclusions)
       .orElse(sparkProperties.get("spark.jars.excludes")).orNull

diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/DriverWrapper.scala b/core/src/main/scala/org/apache/spark/deploy/worker/DriverWrapper.scala
@@ -79,12 +79,17 @@ object DriverWrapper extends Logging {
     val secMgr = new SecurityManager(sparkConf)
     val hadoopConf = SparkHadoopUtil.newConfiguration(sparkConf)
 
-    val Seq(packagesExclusions, packages, repositories, ivyRepoPath) =
-      Seq("spark.jars.excludes", "spark.jars.packages", "spark.jars.repositories", "spark.jars.ivy")
-        .map(sys.props.get(_).orNull)
+    val Seq(packagesExclusions, packages, repositories, ivyRepoPath, ivySettingsPath) =
+      Seq(
+        "spark.jars.excludes",
+        "spark.jars.packages",
+        "spark.jars.repositories",
+        "spark.jars.ivy",
+        "spark.jars.ivySettings"
+      ).map(sys.props.get(_).orNull)
 
     val resolvedMavenCoordinates = DependencyUtils.resolveMavenDependencies(packagesExclusions,
-      packages, repositories, ivyRepoPath)
+      packages, repositories, ivyRepoPath, Option(ivySettingsPath))
     val jars = {
       val jarsProp = sys.props.get("spark.jars").orNull
       if (!StringUtils.isBlank(resolvedMavenCoordinates)) {

diff --git a/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala b/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala
@@ -106,6 +106,9 @@ class SparkSubmitSuite
   // Necessary to make ScalaTest 3.x interrupt a thread on the JVM like ScalaTest 2.2.x
   implicit val defaultSignaler: Signaler = ThreadSignaler
 
+  private val emptyIvySettings = File.createTempFile("ivy", ".xml")
+  FileUtils.write(emptyIvySettings, "<ivysettings />", StandardCharsets.UTF_8)
+
   override def beforeEach() {
     super.beforeEach()
   }
@@ -520,6 +523,7 @@ class SparkSubmitSuite
         "--repositories", repo,
         "--conf", "spark.ui.enabled=false",
         "--conf", "spark.master.rest.enabled=false",
+        "--conf", s"spark.jars.ivySettings=${emptyIvySettings.getAbsolutePath()}",
         unusedJar.toString,
         "my.great.lib.MyLib", "my.great.dep.MyLib")
       runSparkSubmit(args)
@@ -530,7 +534,6 @@ class SparkSubmitSuite
     val unusedJar = TestUtils.createJarWithClasses(Seq.empty)
     val main = MavenCoordinate("my.great.lib", "mylib", "0.1")
     val dep = MavenCoordinate("my.great.dep", "mylib", "0.1")
-    // Test using "spark.jars.packages" and "spark.jars.repositories" configurations.
     IvyTestUtils.withRepository(main, Some(dep.toString), None) { repo =>
       val args = Seq(
         "--class", JarCreationTest.getClass.getName.stripSuffix("$"),
@@ -540,6 +543,7 @@ class SparkSubmitSuite
         "--conf", s"spark.jars.repositories=$repo",
         "--conf", "spark.ui.enabled=false",
         "--conf", "spark.master.rest.enabled=false",
+        "--conf", s"spark.jars.ivySettings=${emptyIvySettings.getAbsolutePath()}",
         unusedJar.toString,
         "my.great.lib.MyLib", "my.great.dep.MyLib")
       runSparkSubmit(args)
@@ -550,7 +554,6 @@ class SparkSubmitSuite
   // See https://gist.github.com/shivaram/3a2fecce60768a603dac for a error log
   ignore("correctly builds R packages included in a jar with --packages") {
     assume(RUtils.isRInstalled, "R isn't installed on this machine.")
-    // Check if the SparkR package is installed
     assume(RUtils.isSparkRInstalled, "SparkR is not installed in this build.")
     val main = MavenCoordinate("my.great.lib", "mylib", "0.1")
     val sparkHome = sys.props.getOrElse("spark.test.home", fail("spark.test.home is not set!"))
@@ -563,6 +566,7 @@ class SparkSubmitSuite
         "--master", "local-cluster[2,1,1024]",
         "--packages", main.toString,
         "--repositories", repo,
+        "--conf", s"spark.jars.ivySettings=${emptyIvySettings.getAbsolutePath()}",
         "--verbose",
         "--conf", "spark.ui.enabled=false",
         rScriptDir)
@@ -573,7 +577,6 @@ class SparkSubmitSuite
   test("include an external JAR in SparkR") {
     assume(RUtils.isRInstalled, "R isn't installed on this machine.")
     val sparkHome = sys.props.getOrElse("spark.test.home", fail("spark.test.home is not set!"))
-    // Check if the SparkR package is installed
     assume(RUtils.isSparkRInstalled, "SparkR is not installed in this build.")
     val rScriptDir =
       Seq(sparkHome, "R", "pkg", "tests", "fulltests", "jarTest.R").mkString(File.separator)