Merge remote-tracking branch 'upstream/master' into SPARK-3278

Author: zapletal-martin

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/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"

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>
@@ -106,16 +110,6 @@
       <groupId>org.eclipse.jetty</groupId>
       <artifactId>jetty-server</artifactId>
     </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>
-      <scope>compile</scope>
-    </dependency>
     <dependency>
       <groupId>org.apache.commons</groupId>
       <artifactId>commons-lang3</artifactId>
@@ -350,42 +344,6 @@
           <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>

core/src/main/resources/org/apache/spark/log4j-defaults.properties

@@ -10,4 +10,3 @@ log4j.logger.org.eclipse.jetty=WARN
 log4j.logger.org.eclipse.jetty.util.component.AbstractLifeCycle=ERROR
 log4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO
 log4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO
-log4j.logger.org.apache.hadoop.yarn.util.RackResolver=WARN

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

@@ -190,6 +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/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

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

@@ -17,9 +17,11 @@
 
 package org.apache.spark
 
+import java.util.concurrent.ConcurrentHashMap
+
 import scala.collection.JavaConverters._
-import scala.collection.concurrent.TrieMap
-import scala.collection.mutable.{HashMap, LinkedHashSet}
+import scala.collection.mutable.LinkedHashSet
+
 import org.apache.spark.serializer.KryoSerializer
 
 /**
@@ -47,12 +49,12 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging {
   /** Create a SparkConf that loads defaults from system properties and the classpath */
   def this() = this(true)
 
-  private[spark] val settings = new TrieMap[String, String]()
+  private val settings = new ConcurrentHashMap[String, String]()
 
   if (loadDefaults) {
     // Load any spark.* system properties
     for ((k, v) <- System.getProperties.asScala if k.startsWith("spark.")) {
-      settings(k) = v
+      set(k, v)
     }
   }
 
@@ -64,7 +66,7 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging {
     if (value == null) {
       throw new NullPointerException("null value for " + key)
     }
-    settings(key) = value
+    settings.put(key, value)
     this
   }
 
@@ -130,15 +132,13 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging {
 
   /** Set multiple parameters together */
   def setAll(settings: Traversable[(String, String)]) = {
-    this.settings ++= settings
+    this.settings.putAll(settings.toMap.asJava)
     this
   }
 
   /** Set a parameter if it isn't already configured */
   def setIfMissing(key: String, value: String): SparkConf = {
-    if (!settings.contains(key)) {
-      settings(key) = value
-    }
+    settings.putIfAbsent(key, value)
     this
   }
 
@@ -164,21 +164,23 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging {
 
   /** Get a parameter; throws a NoSuchElementException if it's not set */
   def get(key: String): String = {
-    settings.getOrElse(key, throw new NoSuchElementException(key))
+    getOption(key).getOrElse(throw new NoSuchElementException(key))
   }
 
   /** Get a parameter, falling back to a default if not set */
   def get(key: String, defaultValue: String): String = {
-    settings.getOrElse(key, defaultValue)
+    getOption(key).getOrElse(defaultValue)
   }
 
   /** Get a parameter as an Option */
   def getOption(key: String): Option[String] = {
-    settings.get(key)
+    Option(settings.get(key))
   }
 
   /** Get all parameters as a list of pairs */
-  def getAll: Array[(String, String)] = settings.toArray
+  def getAll: Array[(String, String)] = {
+    settings.entrySet().asScala.map(x => (x.getKey, x.getValue)).toArray
+  }
 
   /** Get a parameter as an integer, falling back to a default if not set */
   def getInt(key: String, defaultValue: Int): Int = {
@@ -225,11 +227,11 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging {
   def getAppId: String = get("spark.app.id")
 
   /** Does the configuration contain a given parameter? */
-  def contains(key: String): Boolean = settings.contains(key)
+  def contains(key: String): Boolean = settings.containsKey(key)
 
   /** Copy this object */
   override def clone: SparkConf = {
-    new SparkConf(false).setAll(settings)
+    new SparkConf(false).setAll(getAll)
   }
 
   /**
@@ -241,7 +243,7 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging {
   /** Checks for illegal or deprecated config settings. Throws an exception for the former. Not
     * idempotent - may mutate this conf object to convert deprecated settings to supported ones. */
   private[spark] def validateSettings() {
-    if (settings.contains("spark.local.dir")) {
+    if (contains("spark.local.dir")) {
       val msg = "In Spark 1.0 and later spark.local.dir will be overridden by the value set by " +
         "the cluster manager (via SPARK_LOCAL_DIRS in mesos/standalone and LOCAL_DIRS in YARN)."
       logWarning(msg)
@@ -266,7 +268,7 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging {
     }
 
     // Validate spark.executor.extraJavaOptions
-    settings.get(executorOptsKey).map { javaOpts =>
+    getOption(executorOptsKey).map { javaOpts =>
       if (javaOpts.contains("-Dspark")) {
         val msg = s"$executorOptsKey is not allowed to set Spark options (was '$javaOpts'). " +
           "Set them directly on a SparkConf or in a properties file when using ./bin/spark-submit."
@@ -346,7 +348,7 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging {
    * configuration out for debugging.
    */
   def toDebugString: String = {
-    settings.toArray.sorted.map{case (k, v) => k + "=" + v}.mkString("\n")
+    getAll.sorted.map{case (k, v) => k + "=" + v}.mkString("\n")
   }
 }