Merge branch 'master' of https://github.com/apache/spark

Author: zhzhan

CONTRIBUTING.md

@@ -0,0 +1,12 @@
+## Contributing to Spark
+
+Contributions via GitHub pull requests are gladly accepted from their original
+author. Along with any pull requests, please state that the contribution is
+your original work and that you license the work to the project under the
+project's open source license. Whether or not you state this explicitly, by
+submitting any copyrighted material via pull request, email, or other means
+you agree to license the material under the project's open source license and
+warrant that you have the legal authority to do so.
+
+Please see [Contributing to Spark wiki page](https://cwiki.apache.org/SPARK/Contributing+to+Spark)
+for more information.

README.md

@@ -13,16 +13,19 @@ and Spark Streaming for stream processing.
 ## Online Documentation
 
 You can find the latest Spark documentation, including a programming
-guide, on the project webpage at <http://spark.apache.org/documentation.html>.
+guide, on the [project web page](http://spark.apache.org/documentation.html).
 This README file only contains basic setup instructions.
 
 ## Building Spark
 
-Spark is built on Scala 2.10. To build Spark and its example programs, run:
+Spark is built using [Apache Maven](http://maven.apache.org/).
+To build Spark and its example programs, run:
 
-    ./sbt/sbt assembly
+    mvn -DskipTests clean package
 
 (You do not need to do this if you downloaded a pre-built package.)
+More detailed documentation is available from the project site, at
+["Building Spark"](http://spark.apache.org/docs/latest/building-spark.html).
 
 ## Interactive Scala Shell
 
@@ -71,73 +74,24 @@ can be run using:
 
     ./dev/run-tests
 
+Please see the guidance on how to 
+[run all automated tests](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark#ContributingtoSpark-AutomatedTesting).
+
 ## A Note About Hadoop Versions
 
 Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported
 storage systems. Because the protocols have changed in different versions of
 Hadoop, you must build Spark against the same version that your cluster runs.
-You can change the version by setting `-Dhadoop.version` when building Spark.
-
-For Apache Hadoop versions 1.x, Cloudera CDH MRv1, and other Hadoop
-versions without YARN, use:
-
-    # Apache Hadoop 1.2.1
-    $ sbt/sbt -Dhadoop.version=1.2.1 assembly
-
-    # Cloudera CDH 4.2.0 with MapReduce v1
-    $ sbt/sbt -Dhadoop.version=2.0.0-mr1-cdh4.2.0 assembly
-
-For Apache Hadoop 2.2.X, 2.1.X, 2.0.X, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions
-with YARN, also set `-Pyarn`:
-
-    # Apache Hadoop 2.0.5-alpha
-    $ sbt/sbt -Dhadoop.version=2.0.5-alpha -Pyarn assembly
-
-    # Cloudera CDH 4.2.0 with MapReduce v2
-    $ sbt/sbt -Dhadoop.version=2.0.0-cdh4.2.0 -Pyarn assembly
-
-    # Apache Hadoop 2.2.X and newer
-    $ sbt/sbt -Dhadoop.version=2.2.0 -Pyarn assembly
-
-When developing a Spark application, specify the Hadoop version by adding the
-"hadoop-client" artifact to your project's dependencies. For example, if you're
-using Hadoop 1.2.1 and build your application using SBT, add this entry to
-`libraryDependencies`:
-
-    "org.apache.hadoop" % "hadoop-client" % "1.2.1"
 
-If your project is built with Maven, add this to your POM file's `<dependencies>` section:
-
-    <dependency>
-      <groupId>org.apache.hadoop</groupId>
-      <artifactId>hadoop-client</artifactId>
-      <version>1.2.1</version>
-    </dependency>
-
-
-## A Note About Thrift JDBC server and CLI for Spark SQL
-
-Spark SQL supports Thrift JDBC server and CLI.
-See sql-programming-guide.md for more information about using the JDBC server and CLI.
-You can use those features by setting `-Phive` when building Spark as follows.
-
-    $ sbt/sbt -Phive  assembly
+Please refer to the build documentation at
+["Specifying the Hadoop Version"](http://spark.apache.org/docs/latest/building-spark.html#specifying-the-hadoop-version)
+for detailed guidance on building for a particular distribution of Hadoop, including
+building for particular Hive and Hive Thriftserver distributions. See also
+["Third Party Hadoop Distributions"](http://spark.apache.org/docs/latest/hadoop-third-party-distributions.html)
+for guidance on building a Spark application that works with a particular
+distribution.
 
 ## Configuration
 
 Please refer to the [Configuration guide](http://spark.apache.org/docs/latest/configuration.html)
 in the online documentation for an overview on how to configure Spark.
-
-
-## Contributing to Spark
-
-Contributions via GitHub pull requests are gladly accepted from their original
-author. Along with any pull requests, please state that the contribution is
-your original work and that you license the work to the project under the
-project's open source license. Whether or not you state this explicitly, by
-submitting any copyrighted material via pull request, email, or other means
-you agree to license the material under the project's open source license and
-warrant that you have the legal authority to do so.
-
-Please see [Contributing to Spark wiki page](https://cwiki.apache.org/SPARK/Contributing+to+Spark)
-for more information.

assembly/pom.xml

@@ -88,6 +88,20 @@
 
   <build>
     <plugins>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-deploy-plugin</artifactId>
+        <configuration>
+          <skip>true</skip>
+        </configuration>
+      </plugin>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-install-plugin</artifactId>
+        <configuration>
+          <skip>true</skip>
+        </configuration>
+      </plugin>
       <!-- Use the shade plugin to create a big JAR with all the dependencies -->
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>

bagel/src/test/scala/org/apache/spark/bagel/BagelSuite.scala

@@ -24,8 +24,6 @@ import org.scalatest.time.SpanSugar._
 import org.apache.spark._
 import org.apache.spark.storage.StorageLevel
 
-import scala.language.postfixOps
-
 class TestVertex(val active: Boolean, val age: Int) extends Vertex with Serializable
 class TestMessage(val targetId: String) extends Message[String] with Serializable
 

bin/compute-classpath.sh

@@ -43,6 +43,7 @@ if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\
     "classes ahead of assembly." >&2
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
   CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SCALA_VERSION/classes"

bin/spark-class

@@ -105,7 +105,7 @@ else
     exit 1
   fi
 fi
-JAVA_VERSION=$("$RUNNER" -version 2>&1 | sed 's/java version "\(.*\)\.\(.*\)\..*"/\1\2/; 1q')
+JAVA_VERSION=$("$RUNNER" -version 2>&1 | sed 's/.* version "\(.*\)\.\(.*\)\..*"/\1\2/; 1q')
 
 # Set JAVA_OPTS to be able to load native libraries and to set heap size
 if [ "$JAVA_VERSION" -ge 18 ]; then

core/pom.xml

@@ -351,6 +351,33 @@
           </execution>
         </executions>
       </plugin>
+      <!--
+        Copy guava to the build directory. This is needed to make the SPARK_PREPEND_CLASSES
+        option work in compute-classpath.sh, since it would put the non-shaded Spark classes in
+        the runtime classpath.
+      -->
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-dependency-plugin</artifactId>
+        <executions>
+          <execution>
+            <id>copy-dependencies</id>
+            <phase>package</phase>
+            <goals>
+              <goal>copy-dependencies</goal>
+            </goals>
+            <configuration>
+              <outputDirectory>${project.build.directory}</outputDirectory>
+              <overWriteReleases>false</overWriteReleases>
+              <overWriteSnapshots>false</overWriteSnapshots>
+              <overWriteIfNewer>true</overWriteIfNewer>
+              <useSubDirectoryPerType>true</useSubDirectoryPerType>
+              <includeArtifactIds>guava</includeArtifactIds>
+              <silent>true</silent>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
     </plugins>
 
     <resources>

core/src/main/scala/org/apache/spark/SecurityManager.scala

@@ -162,7 +162,7 @@ private[spark] class SecurityManager(sparkConf: SparkConf) extends Logging {
 
   // always add the current user and SPARK_USER to the viewAcls
   private val defaultAclUsers = Set[String](System.getProperty("user.name", ""),
-    Option(System.getenv("SPARK_USER")).getOrElse(""))
+    Option(System.getenv("SPARK_USER")).getOrElse("")).filter(!_.isEmpty)
 
   setViewAcls(defaultAclUsers, sparkConf.get("spark.ui.view.acls", ""))
   setModifyAcls(defaultAclUsers, sparkConf.get("spark.modify.acls", ""))

core/src/main/scala/org/apache/spark/SparkContext.scala

@@ -220,8 +220,14 @@ class SparkContext(config: SparkConf) extends Logging {
     new MetadataCleaner(MetadataCleanerType.SPARK_CONTEXT, this.cleanup, conf)
 
   // Initialize the Spark UI, registering all associated listeners
-  private[spark] val ui = new SparkUI(this)
-  ui.bind()
+  private[spark] val ui: Option[SparkUI] =
+    if (conf.getBoolean("spark.ui.enabled", true)) {
+      Some(new SparkUI(this))
+    } else {
+      // For tests, do not enable the UI
+      None
+    }
+  ui.foreach(_.bind())
 
   /** A default Hadoop Configuration for the Hadoop code (e.g. file systems) that we reuse. */
   val hadoopConfiguration = SparkHadoopUtil.get.newConfiguration(conf)
@@ -990,7 +996,7 @@ class SparkContext(config: SparkConf) extends Logging {
   /** Shut down the SparkContext. */
   def stop() {
     postApplicationEnd()
-    ui.stop()
+    ui.foreach(_.stop())
     // Do this only if not stopped already - best case effort.
     // prevent NPE if stopped more than once.
     val dagSchedulerCopy = dagScheduler
@@ -1066,11 +1072,8 @@ class SparkContext(config: SparkConf) extends Logging {
     val callSite = getCallSite
     val cleanedFunc = clean(func)
     logInfo("Starting job: " + callSite.shortForm)
-    val start = System.nanoTime
     dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, allowLocal,
       resultHandler, localProperties.get)
-    logInfo(
-      "Job finished: " + callSite.shortForm + ", took " + (System.nanoTime - start) / 1e9 + " s")
     rdd.doCheckpoint()
   }
 

core/src/main/scala/org/apache/spark/SparkEnv.scala

@@ -108,6 +108,14 @@ class SparkEnv (
       pythonWorkers.get(key).foreach(_.stopWorker(worker))
     }
   }
+
+  private[spark]
+  def releasePythonWorker(pythonExec: String, envVars: Map[String, String], worker: Socket) {
+    synchronized {
+      val key = (pythonExec, envVars)
+      pythonWorkers.get(key).foreach(_.releaseWorker(worker))
+    }
+  }
 }
 
 object SparkEnv extends Logging {