Merge remote-tracking branch 'origin/master' into SPARK-5190-register-sparklistener-in-sc-constructor

Conflicts:
	core/src/main/scala/org/apache/spark/scheduler/LiveListenerBus.scala
	core/src/main/scala/org/apache/spark/scheduler/SparkListenerBus.scala

Author: JoshRosen

assembly/pom.xml

@@ -43,12 +43,6 @@
   </properties>
 
   <dependencies>
-    <!-- Promote Guava to compile scope in this module so it's included while shading. -->
-    <dependency>
-      <groupId>com.google.guava</groupId>
-      <artifactId>guava</artifactId>
-      <scope>compile</scope>
-    </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-core_${scala.binary.version}</artifactId>
@@ -133,20 +127,6 @@
               <goal>shade</goal>
             </goals>
             <configuration>
-              <relocations>
-                <relocation>
-                  <pattern>com.google</pattern>
-                  <shadedPattern>org.spark-project.guava</shadedPattern>
-                  <includes>
-                    <include>com.google.common.**</include>
-                  </includes>
-                  <excludes>
-                    <exclude>com/google/common/base/Absent*</exclude>
-                    <exclude>com/google/common/base/Optional*</exclude>
-                    <exclude>com/google/common/base/Present*</exclude>
-                  </excludes>
-                </relocation>
-              </relocations>
               <transformers>
                 <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
                 <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">

bin/compute-classpath.sh

@@ -50,8 +50,8 @@ fi
 if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\
     "classes ahead of assembly." >&2
+  # Spark classes
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SPARK_SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
   CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SPARK_SCALA_VERSION/classes"
@@ -63,6 +63,8 @@ if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SPARK_SCALA_VERSION/classes"
+  # Jars for shaded deps in their original form (copied here during build)
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
 fi
 
 # Use spark-assembly jar from either RELEASE or assembly directory

bin/spark-class

@@ -29,6 +29,7 @@ FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
+export SPARK_CONF_DIR="${SPARK_CONF_DIR:-"$SPARK_HOME/conf"}"
 
 . "$FWDIR"/bin/load-spark-env.sh
 
@@ -120,8 +121,8 @@ fi
 JAVA_OPTS="$JAVA_OPTS -Xms$OUR_JAVA_MEM -Xmx$OUR_JAVA_MEM"
 
 # Load extra JAVA_OPTS from conf/java-opts, if it exists
-if [ -e "$FWDIR/conf/java-opts" ] ; then
-  JAVA_OPTS="$JAVA_OPTS `cat "$FWDIR"/conf/java-opts`"
+if [ -e "$SPARK_CONF_DIR/java-opts" ] ; then
+  JAVA_OPTS="$JAVA_OPTS `cat "$SPARK_CONF_DIR"/java-opts`"
 fi
 
 # Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in CommandUtils.scala!

build/mvn

@@ -48,11 +48,11 @@ install_app() {
     # check if we already have the tarball
     # check if we have curl installed
     # download application
-    [ ! -f "${local_tarball}" ] && [ -n "`which curl 2>/dev/null`" ] && \
+    [ ! -f "${local_tarball}" ] && [ $(command -v curl) ] && \
       echo "exec: curl ${curl_opts} ${remote_tarball}" && \
       curl ${curl_opts} "${remote_tarball}" > "${local_tarball}"
     # if the file still doesn't exist, lets try `wget` and cross our fingers
-    [ ! -f "${local_tarball}" ] && [ -n "`which wget 2>/dev/null`" ] && \
+    [ ! -f "${local_tarball}" ] && [ $(command -v wget) ] && \
       echo "exec: wget ${wget_opts} ${remote_tarball}" && \
       wget ${wget_opts} -O "${local_tarball}" "${remote_tarball}"
     # if both were unsuccessful, exit
@@ -68,10 +68,10 @@ install_app() {
 # Install maven under the build/ folder
 install_mvn() {
   install_app \
-    "http://apache.claz.org/maven/maven-3/3.2.3/binaries" \
-    "apache-maven-3.2.3-bin.tar.gz" \
-    "apache-maven-3.2.3/bin/mvn"
-  MVN_BIN="${_DIR}/apache-maven-3.2.3/bin/mvn"
+    "http://archive.apache.org/dist/maven/maven-3/3.2.5/binaries" \
+    "apache-maven-3.2.5-bin.tar.gz" \
+    "apache-maven-3.2.5/bin/mvn"
+  MVN_BIN="${_DIR}/apache-maven-3.2.5/bin/mvn"
 }
 
 # Install zinc under the build/ folder

build/sbt-launch-lib.bash

@@ -50,9 +50,9 @@ acquire_sbt_jar () {
     # Download
     printf "Attempting to fetch sbt\n"
     JAR_DL="${JAR}.part"
-    if hash curl 2>/dev/null; then
+    if [ $(command -v curl) ]; then
       (curl --silent ${URL1} > "${JAR_DL}" || curl --silent ${URL2} > "${JAR_DL}") && mv "${JAR_DL}" "${JAR}"
-    elif hash wget 2>/dev/null; then
+    elif [ $(command -v wget) ]; then
       (wget --quiet ${URL1} -O "${JAR_DL}" || wget --quiet ${URL2} -O "${JAR_DL}") && mv "${JAR_DL}" "${JAR}"
     else
       printf "You do not have curl or wget installed, please install sbt manually from http://www.scala-sbt.org/\n"

conf/metrics.properties.template

@@ -87,6 +87,7 @@
 #   period    10            Poll period
 #   unit      seconds       Units of poll period
 #   prefix    EMPTY STRING  Prefix to prepend to metric name
+#   protocol  tcp           Protocol ("tcp" or "udp") to use
 
 ## Examples
 # Enable JmxSink for all instances by class name

core/pom.xml

@@ -34,6 +34,10 @@
   <name>Spark Project Core</name>
   <url>http://spark.apache.org/</url>
   <dependencies>
+    <dependency>
+      <groupId>com.google.guava</groupId>
+      <artifactId>guava</artifactId>
+    </dependency>
     <dependency>
       <groupId>com.twitter</groupId>
       <artifactId>chill_${scala.binary.version}</artifactId>
@@ -90,32 +94,35 @@
       <groupId>org.apache.curator</groupId>
       <artifactId>curator-recipes</artifactId>
     </dependency>
+
+    <!-- Jetty dependencies promoted to compile here so they are shaded
+         and inlined into spark-core jar -->
     <dependency>
       <groupId>org.eclipse.jetty</groupId>
       <artifactId>jetty-plus</artifactId>
+      <scope>compile</scope>
     </dependency>
     <dependency>
       <groupId>org.eclipse.jetty</groupId>
       <artifactId>jetty-security</artifactId>
+      <scope>compile</scope>
     </dependency>
     <dependency>
       <groupId>org.eclipse.jetty</groupId>
       <artifactId>jetty-util</artifactId>
+      <scope>compile</scope>
     </dependency>
     <dependency>
       <groupId>org.eclipse.jetty</groupId>
       <artifactId>jetty-server</artifactId>
+      <scope>compile</scope>
     </dependency>
-    <!--
-      Promote Guava to "compile" so that maven-shade-plugin picks it up (for packaging the Optional
-      class exposed in the Java API). The plugin will then remove this dependency from the published
-      pom, so that Guava does not pollute the client's compilation classpath.
-    -->
     <dependency>
-      <groupId>com.google.guava</groupId>
-      <artifactId>guava</artifactId>
+      <groupId>org.eclipse.jetty</groupId>
+      <artifactId>jetty-http</artifactId>
       <scope>compile</scope>
     </dependency>
+
     <dependency>
       <groupId>org.apache.commons</groupId>
       <artifactId>commons-lang3</artifactId>
@@ -204,19 +211,19 @@
       <artifactId>stream</artifactId>
     </dependency>
     <dependency>
-      <groupId>com.codahale.metrics</groupId>
+      <groupId>io.dropwizard.metrics</groupId>
       <artifactId>metrics-core</artifactId>
     </dependency>
     <dependency>
-      <groupId>com.codahale.metrics</groupId>
+      <groupId>io.dropwizard.metrics</groupId>
       <artifactId>metrics-jvm</artifactId>
     </dependency>
     <dependency>
-      <groupId>com.codahale.metrics</groupId>
+      <groupId>io.dropwizard.metrics</groupId>
       <artifactId>metrics-json</artifactId>
     </dependency>
     <dependency>
-      <groupId>com.codahale.metrics</groupId>
+      <groupId>io.dropwizard.metrics</groupId>
       <artifactId>metrics-graphite</artifactId>
     </dependency>
     <dependency>
@@ -350,59 +357,28 @@
           <verbose>true</verbose>
         </configuration>
       </plugin>
-      <plugin>
-        <groupId>org.apache.maven.plugins</groupId>
-        <artifactId>maven-shade-plugin</artifactId>
-        <executions>
-          <execution>
-            <phase>package</phase>
-            <goals>
-              <goal>shade</goal>
-            </goals>
-            <configuration>
-              <shadedArtifactAttached>false</shadedArtifactAttached>
-              <artifactSet>
-                <includes>
-                  <include>com.google.guava:guava</include>
-                </includes>
-              </artifactSet>
-              <filters>
-                <!-- See comment in the guava dependency declaration above. -->
-                <filter>
-                  <artifact>com.google.guava:guava</artifact>
-                  <includes>
-                    <include>com/google/common/base/Absent*</include>
-                    <include>com/google/common/base/Optional*</include>
-                    <include>com/google/common/base/Present*</include>
-                  </includes>
-                </filter>
-              </filters>
-            </configuration>
-          </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>
+          <!-- When using SPARK_PREPEND_CLASSES Spark classes compiled locally don't use
+               shaded deps. So here we store jars in their original form which are added
+               when the classpath is computed. -->
           <execution>
             <id>copy-dependencies</id>
             <phase>package</phase>
             <goals>
               <goal>copy-dependencies</goal>
             </goals>
-            <configuration>
+           <configuration>
               <outputDirectory>${project.build.directory}</outputDirectory>
               <overWriteReleases>false</overWriteReleases>
               <overWriteSnapshots>false</overWriteSnapshots>
               <overWriteIfNewer>true</overWriteIfNewer>
               <useSubDirectoryPerType>true</useSubDirectoryPerType>
-              <includeArtifactIds>guava</includeArtifactIds>
+              <includeArtifactIds>
+                guava,jetty-io,jetty-http,jetty-plus,jetty-util,jetty-server
+              </includeArtifactIds>
               <silent>true</silent>
             </configuration>
           </execution>

core/src/main/resources/org/apache/spark/ui/static/webui.css

@@ -121,6 +121,14 @@ pre {
   border: none;
 }
 
+.description-input {
+  overflow: hidden;
+  text-overflow: ellipsis;
+  width: 100%;
+  white-space: nowrap;
+  display: block;
+}
+
 .stacktrace-details {
   max-height: 300px;
   overflow-y: auto;
@@ -182,6 +190,7 @@ span.additional-metric-title {
 
 /* Hide all additional metrics by default. This is done here rather than using JavaScript to
  * avoid slow page loads for stage pages with large numbers (e.g., thousands) of tasks. */
-.scheduler_delay, .deserialization_time, .serialization_time, .getting_result_time {
+.scheduler_delay, .deserialization_time, .fetch_wait_time, .serialization_time,
+.getting_result_time {
   display: none;
 }

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

@@ -158,7 +158,7 @@ private[spark] class ExecutorAllocationManager(
         "shuffle service. You may enable this through spark.shuffle.service.enabled.")
     }
     if (tasksPerExecutor == 0) {
-      throw new SparkException("spark.executor.cores must not be less than spark.task.cpus.cores")
+      throw new SparkException("spark.executor.cores must not be less than spark.task.cpus.")
     }
   }
 

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

@@ -118,15 +118,17 @@ trait Logging {
     // org.slf4j.impl.Log4jLoggerFactory, from the log4j 2.0 binding, currently
     // org.apache.logging.slf4j.Log4jLoggerFactory
     val usingLog4j12 = "org.slf4j.impl.Log4jLoggerFactory".equals(binderClass)
-    val log4j12Initialized = LogManager.getRootLogger.getAllAppenders.hasMoreElements
-    if (!log4j12Initialized && usingLog4j12) {
-      val defaultLogProps = "org/apache/spark/log4j-defaults.properties"
-      Option(Utils.getSparkClassLoader.getResource(defaultLogProps)) match {
-        case Some(url) =>
-          PropertyConfigurator.configure(url)
-          System.err.println(s"Using Spark's default log4j profile: $defaultLogProps")
-        case None =>
-          System.err.println(s"Spark was unable to load $defaultLogProps")
+    if (usingLog4j12) {
+      val log4j12Initialized = LogManager.getRootLogger.getAllAppenders.hasMoreElements
+      if (!log4j12Initialized) {
+        val defaultLogProps = "org/apache/spark/log4j-defaults.properties"
+        Option(Utils.getSparkClassLoader.getResource(defaultLogProps)) match {
+          case Some(url) =>
+            PropertyConfigurator.configure(url)
+            System.err.println(s"Using Spark's default log4j profile: $defaultLogProps")
+          case None =>
+            System.err.println(s"Spark was unable to load $defaultLogProps")
+        }
       }
     }
     Logging.initialized = true