[SPARK-8126] [BUILD] Use custom temp directory during build.

Even with all the efforts to cleanup the temp directories created by
unit tests, Spark leaves a lot of garbage in /tmp after a test run.
This change overrides java.io.tmpdir to place those files under the
build directory instead.

After an sbt full unit test run, I was left with > 400 MB of temp
files. Since they're now under the build dir, it's much easier to
clean them up.

Also make a slight change to a unit test to make it not pollute the
source directory with test data.

Author: Marcelo Vanzin <[email protected]>

Closes apache#6674 from vanzin/SPARK-8126 and squashes the following commits:

0f8ad41 [Marcelo Vanzin] Make sure tmp dir exists when tests run.
643e916 [Marcelo Vanzin] [MINOR] [BUILD] Use custom temp directory during build.

Author: Marcelo Vanzin

core/src/test/scala/org/apache/spark/deploy/SparkSubmitUtilsSuite.scala

@@ -27,9 +27,12 @@ import org.apache.ivy.core.settings.IvySettings
 import org.apache.ivy.plugins.resolver.IBiblioResolver
 
 import org.apache.spark.deploy.SparkSubmitUtils.MavenCoordinate
+import org.apache.spark.util.Utils
 
 class SparkSubmitUtilsSuite extends FunSuite with BeforeAndAfterAll {
 
+  private var tempIvyPath: String = _
+
   private val noOpOutputStream = new OutputStream {
     def write(b: Int) = {}
   }
@@ -46,6 +49,7 @@ class SparkSubmitUtilsSuite extends FunSuite with BeforeAndAfterAll {
     super.beforeAll()
     // We don't want to write logs during testing
     SparkSubmitUtils.printStream = new BufferPrintStream
+    tempIvyPath = Utils.createTempDir(namePrefix = "ivy").getAbsolutePath()
   }
 
   test("incorrect maven coordinate throws error") {
@@ -89,21 +93,20 @@ class SparkSubmitUtilsSuite extends FunSuite with BeforeAndAfterAll {
   }
 
   test("ivy path works correctly") {
-    val ivyPath = "dummy" + File.separator +  "ivy"
     val md = SparkSubmitUtils.getModuleDescriptor
     val artifacts = for (i <- 0 until 3) yield new MDArtifact(md, s"jar-$i", "jar", "jar")
-    var jPaths = SparkSubmitUtils.resolveDependencyPaths(artifacts.toArray, new File(ivyPath))
+    var jPaths = SparkSubmitUtils.resolveDependencyPaths(artifacts.toArray, new File(tempIvyPath))
     for (i <- 0 until 3) {
-      val index = jPaths.indexOf(ivyPath)
+      val index = jPaths.indexOf(tempIvyPath)
       assert(index >= 0)
-      jPaths = jPaths.substring(index + ivyPath.length)
+      jPaths = jPaths.substring(index + tempIvyPath.length)
     }
     val main = MavenCoordinate("my.awesome.lib", "mylib", "0.1")
     IvyTestUtils.withRepository(main, None, None) { repo =>
       // end to end
       val jarPath = SparkSubmitUtils.resolveMavenCoordinates(main.toString, Option(repo),
-        Option(ivyPath), true)
-      assert(jarPath.indexOf(ivyPath) >= 0, "should use non-default ivy path")
+        Option(tempIvyPath), true)
+      assert(jarPath.indexOf(tempIvyPath) >= 0, "should use non-default ivy path")
     }
   }
 
@@ -122,13 +125,12 @@ class SparkSubmitUtilsSuite extends FunSuite with BeforeAndAfterAll {
       assert(jarPath.indexOf("mylib") >= 0, "should find artifact")
     }
     // Local ivy repository with modified home
-    val dummyIvyPath = "dummy" + File.separator + "ivy"
-    val dummyIvyLocal = new File(dummyIvyPath, "local" + File.separator)
+    val dummyIvyLocal = new File(tempIvyPath, "local" + File.separator)
     IvyTestUtils.withRepository(main, None, Some(dummyIvyLocal), true) { repo =>
       val jarPath = SparkSubmitUtils.resolveMavenCoordinates(main.toString, None,
-        Some(dummyIvyPath), true)
+        Some(tempIvyPath), true)
       assert(jarPath.indexOf("mylib") >= 0, "should find artifact")
-      assert(jarPath.indexOf(dummyIvyPath) >= 0, "should be in new ivy path")
+      assert(jarPath.indexOf(tempIvyPath) >= 0, "should be in new ivy path")
     }
   }
 

pom.xml

@@ -180,7 +180,7 @@
     <parquet.deps.scope>compile</parquet.deps.scope>
 
     <!--
-      Overridable test home. So that you can call individual pom files directory without
+      Overridable test home. So that you can call individual pom files directly without
       things breaking.
     -->
     <spark.test.home>${session.executionRootDirectory}</spark.test.home>
@@ -1253,6 +1253,7 @@
             </environmentVariables>
             <systemProperties>
               <java.awt.headless>true</java.awt.headless>
+              <java.io.tmpdir>${project.build.directory}/tmp</java.io.tmpdir>
               <spark.test.home>${spark.test.home}</spark.test.home>
               <spark.testing>1</spark.testing>
               <spark.ui.enabled>false</spark.ui.enabled>
@@ -1285,6 +1286,7 @@
             </environmentVariables>
             <systemProperties>
               <java.awt.headless>true</java.awt.headless>
+              <java.io.tmpdir>${project.build.directory}/tmp</java.io.tmpdir>
               <spark.test.home>${spark.test.home}</spark.test.home>
               <spark.testing>1</spark.testing>
               <spark.ui.enabled>false</spark.ui.enabled>
@@ -1542,6 +1544,26 @@
           </execution>
         </executions>
       </plugin>
+
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-antrun-plugin</artifactId>
+        <executions>
+          <execution>
+            <id>create-tmp-dir</id>
+            <phase>generate-test-resources</phase>
+            <goals>
+              <goal>run</goal>
+            </goals>
+            <configuration>
+              <target>
+                <mkdir dir="${project.build.directory}/tmp" />
+              </target>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
+
       <!-- Enable surefire and scalatest in all children, in one place: -->
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>

project/SparkBuild.scala

@@ -51,6 +51,11 @@ object BuildCommons {
   // Root project.
   val spark = ProjectRef(buildLocation, "spark")
   val sparkHome = buildLocation
+
+  val testTempDir = s"$sparkHome/target/tmp"
+  if (!new File(testTempDir).isDirectory()) {
+    require(new File(testTempDir).mkdirs())
+  }
 }
 
 object SparkBuild extends PomBuild {
@@ -507,6 +512,7 @@ object TestSettings {
       "SPARK_DIST_CLASSPATH" ->
         (fullClasspath in Test).value.files.map(_.getAbsolutePath).mkString(":").stripSuffix(":"),
       "JAVA_HOME" -> sys.env.get("JAVA_HOME").getOrElse(sys.props("java.home"))),
+    javaOptions in Test += s"-Djava.io.tmpdir=$testTempDir",
     javaOptions in Test += "-Dspark.test.home=" + sparkHome,
     javaOptions in Test += "-Dspark.testing=1",
     javaOptions in Test += "-Dspark.port.maxRetries=100",