Merge branch 'master' of git://git.apache.org/spark into SPARK-2677

Author: sarutak

bin/pyspark

@@ -23,12 +23,18 @@ FWDIR="$(cd `dirname $0`/..; pwd)"
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
 
+source $FWDIR/bin/utils.sh
+
 SCALA_VERSION=2.10
 
-if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
+function usage() {
   echo "Usage: ./bin/pyspark [options]" 1>&2
   $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
   exit 0
+}
+
+if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
+  usage
 fi
 
 # Exit if the user hasn't compiled Spark
@@ -66,10 +72,11 @@ fi
 # Build up arguments list manually to preserve quotes and backslashes.
 # We export Spark submit arguments as an environment variable because shell.py must run as a
 # PYTHONSTARTUP script, which does not take in arguments. This is required for IPython notebooks.
-
+SUBMIT_USAGE_FUNCTION=usage
+gatherSparkSubmitOpts "$@"
 PYSPARK_SUBMIT_ARGS=""
 whitespace="[[:space:]]"
-for i in "$@"; do
+for i in "${SUBMISSION_OPTS[@]}"; do
   if [[ $i =~ \" ]]; then i=$(echo $i | sed 's/\"/\\\"/g'); fi
   if [[ $i =~ $whitespace ]]; then i=\"$i\"; fi
   PYSPARK_SUBMIT_ARGS="$PYSPARK_SUBMIT_ARGS $i"
@@ -90,7 +97,10 @@ fi
 if [[ "$1" =~ \.py$ ]]; then
   echo -e "\nWARNING: Running python applications through ./bin/pyspark is deprecated as of Spark 1.0." 1>&2
   echo -e "Use ./bin/spark-submit <python file>\n" 1>&2
-  exec $FWDIR/bin/spark-submit "$@"
+  primary=$1
+  shift
+  gatherSparkSubmitOpts "$@"
+  exec $FWDIR/bin/spark-submit "${SUBMISSION_OPTS[@]}" $primary "${APPLICATION_OPTS[@]}"
 else
   # Only use ipython if no command line arguments were provided [SPARK-1134]
   if [[ "$IPYTHON" = "1" ]]; then

bin/spark-shell

@@ -31,13 +31,21 @@ set -o posix
 ## Global script variables
 FWDIR="$(cd `dirname $0`/..; pwd)"
 
+function usage() {
+    echo "Usage: ./bin/spark-shell [options]"
+    $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
+    exit 0
+}
+
 if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
-  echo "Usage: ./bin/spark-shell [options]"
-  $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
-  exit 0
+  usage
 fi
 
-function main(){
+source $FWDIR/bin/utils.sh
+SUBMIT_USAGE_FUNCTION=usage
+gatherSparkSubmitOpts "$@"
+
+function main() {
     if $cygwin; then
         # Workaround for issue involving JLine and Cygwin
         # (see http://sourceforge.net/p/jline/bugs/40/).
@@ -46,11 +54,11 @@ function main(){
         # (see https://github.com/sbt/sbt/issues/562).
         stty -icanon min 1 -echo > /dev/null 2>&1
         export SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Djline.terminal=unix"
-        $FWDIR/bin/spark-submit --class org.apache.spark.repl.Main spark-shell "$@"
+        $FWDIR/bin/spark-submit --class org.apache.spark.repl.Main "${SUBMISSION_OPTS[@]}" spark-shell "${APPLICATION_OPTS[@]}"
         stty icanon echo > /dev/null 2>&1
     else
         export SPARK_SUBMIT_OPTS
-        $FWDIR/bin/spark-submit --class org.apache.spark.repl.Main spark-shell "$@"
+        $FWDIR/bin/spark-submit --class org.apache.spark.repl.Main "${SUBMISSION_OPTS[@]}" spark-shell "${APPLICATION_OPTS[@]}"
     fi
 }
 

bin/utils.sh

@@ -0,0 +1,59 @@
+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Gather all all spark-submit options into SUBMISSION_OPTS
+function gatherSparkSubmitOpts() {
+
+  if [ -z "$SUBMIT_USAGE_FUNCTION" ]; then
+    echo "Function for printing usage of $0 is not set." 1>&2
+    echo "Please set usage function to shell variable 'SUBMIT_USAGE_FUNCTION' in $0" 1>&2
+    exit 1
+  fi
+
+  # NOTE: If you add or remove spark-sumbmit options,
+  # modify NOT ONLY this script but also SparkSubmitArgument.scala
+  SUBMISSION_OPTS=()
+  APPLICATION_OPTS=()
+  while (($#)); do
+    case "$1" in
+      --master | --deploy-mode | --class | --name | --jars | --py-files | --files | \
+      --conf | --properties-file | --driver-memory | --driver-java-options | \
+      --driver-library-path | --driver-class-path | --executor-memory | --driver-cores | \
+      --total-executor-cores | --executor-cores | --queue | --num-executors | --archives)
+        if [[ $# -lt 2 ]]; then
+          "$SUBMIT_USAGE_FUNCTION"
+          exit 1;
+        fi
+        SUBMISSION_OPTS+=("$1"); shift
+        SUBMISSION_OPTS+=("$1"); shift
+        ;;
+
+      --verbose | -v | --supervise)
+        SUBMISSION_OPTS+=("$1"); shift
+        ;;
+
+      *)
+        APPLICATION_OPTS+=("$1"); shift
+        ;;
+    esac
+  done
+
+  export SUBMISSION_OPTS
+  export APPLICATION_OPTS
+}

core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala

@@ -224,6 +224,10 @@ private[spark] class SparkSubmitArguments(args: Seq[String]) {
     // Delineates parsing of Spark options from parsing of user options.
     parse(opts)
 
+    /**
+     * NOTE: If you add or remove spark-submit options,
+     * modify NOT ONLY this file but also utils.sh
+     */
     def parse(opts: Seq[String]): Unit = opts match {
       case ("--name") :: value :: tail =>
         name = value

core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala

@@ -237,6 +237,25 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
     combineByKey[V]((v: V) => v, func, func, partitioner)
   }
 
+  /**
+   * Merge the values for each key using an associative reduce function. This will also perform
+   * the merging locally on each mapper before sending results to a reducer, similarly to a
+   * "combiner" in MapReduce. Output will be hash-partitioned with numPartitions partitions.
+   */
+  def reduceByKey(func: (V, V) => V, numPartitions: Int): RDD[(K, V)] = {
+    reduceByKey(new HashPartitioner(numPartitions), func)
+  }
+
+  /**
+   * Merge the values for each key using an associative reduce function. This will also perform
+   * the merging locally on each mapper before sending results to a reducer, similarly to a
+   * "combiner" in MapReduce. Output will be hash-partitioned with the existing partitioner/
+   * parallelism level.
+   */
+  def reduceByKey(func: (V, V) => V): RDD[(K, V)] = {
+    reduceByKey(defaultPartitioner(self), func)
+  }
+
   /**
    * Merge the values for each key using an associative reduce function, but return the results
    * immediately to the master as a Map. This will also perform the merging locally on each mapper
@@ -374,15 +393,6 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
     countApproxDistinctByKey(relativeSD, defaultPartitioner(self))
   }
 
-  /**
-   * Merge the values for each key using an associative reduce function. This will also perform
-   * the merging locally on each mapper before sending results to a reducer, similarly to a
-   * "combiner" in MapReduce. Output will be hash-partitioned with numPartitions partitions.
-   */
-  def reduceByKey(func: (V, V) => V, numPartitions: Int): RDD[(K, V)] = {
-    reduceByKey(new HashPartitioner(numPartitions), func)
-  }
-
   /**
    * Group the values for each key in the RDD into a single sequence. Allows controlling the
    * partitioning of the resulting key-value pair RDD by passing a Partitioner.
@@ -482,16 +492,6 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
     combineByKey(createCombiner, mergeValue, mergeCombiners, defaultPartitioner(self))
   }
 
-  /**
-   * Merge the values for each key using an associative reduce function. This will also perform
-   * the merging locally on each mapper before sending results to a reducer, similarly to a
-   * "combiner" in MapReduce. Output will be hash-partitioned with the existing partitioner/
-   * parallelism level.
-   */
-  def reduceByKey(func: (V, V) => V): RDD[(K, V)] = {
-    reduceByKey(defaultPartitioner(self), func)
-  }
-
   /**
    * Group the values for each key in the RDD into a single sequence. Hash-partitions the
    * resulting RDD with the existing partitioner/parallelism level.

core/src/main/scala/org/apache/spark/storage/BlockManagerMessages.scala

@@ -53,7 +53,7 @@ private[spark] object BlockManagerMessages {
       sender: ActorRef)
     extends ToBlockManagerMaster
 
-  class UpdateBlockInfo(
+  case class UpdateBlockInfo(
       var blockManagerId: BlockManagerId,
       var blockId: BlockId,
       var storageLevel: StorageLevel,
@@ -84,24 +84,6 @@ private[spark] object BlockManagerMessages {
     }
   }
 
-  object UpdateBlockInfo {
-    def apply(
-        blockManagerId: BlockManagerId,
-        blockId: BlockId,
-        storageLevel: StorageLevel,
-        memSize: Long,
-        diskSize: Long,
-        tachyonSize: Long): UpdateBlockInfo = {
-      new UpdateBlockInfo(blockManagerId, blockId, storageLevel, memSize, diskSize, tachyonSize)
-    }
-
-    // For pattern-matching
-    def unapply(h: UpdateBlockInfo)
-      : Option[(BlockManagerId, BlockId, StorageLevel, Long, Long, Long)] = {
-      Some((h.blockManagerId, h.blockId, h.storageLevel, h.memSize, h.diskSize, h.tachyonSize))
-    }
-  }
-
   case class GetLocations(blockId: BlockId) extends ToBlockManagerMaster
 
   case class GetLocationsMultipleBlockIds(blockIds: Array[BlockId]) extends ToBlockManagerMaster

dev/merge_spark_pr.py

@@ -74,8 +74,10 @@ def fail(msg):
 
 def run_cmd(cmd):
     if isinstance(cmd, list):
+        print " ".join(cmd)
         return subprocess.check_output(cmd)
     else:
+        print cmd
         return subprocess.check_output(cmd.split(" "))
 
 

python/pyspark/java_gateway.py

@@ -39,7 +39,7 @@ def launch_gateway():
         submit_args = os.environ.get("PYSPARK_SUBMIT_ARGS")
         submit_args = submit_args if submit_args is not None else ""
         submit_args = shlex.split(submit_args)
-        command = [os.path.join(SPARK_HOME, script), "pyspark-shell"] + submit_args
+        command = [os.path.join(SPARK_HOME, script)] + submit_args + ["pyspark-shell"]
         if not on_windows:
             # Don't send ctrl-c / SIGINT to the Java gateway:
             def preexec_func():

sql/README.md

@@ -3,10 +3,11 @@ Spark SQL
 
 This module provides support for executing relational queries expressed in either SQL or a LINQ-like Scala DSL.
 
-Spark SQL is broken up into three subprojects:
+Spark SQL is broken up into four subprojects:
  - Catalyst (sql/catalyst) - An implementation-agnostic framework for manipulating trees of relational operators and expressions.
  - Execution (sql/core) - A query planner / execution engine for translating Catalyst’s logical query plans into Spark RDDs.  This component also includes a new public interface, SQLContext, that allows users to execute SQL or LINQ statements against existing RDDs and Parquet files.
  - Hive Support (sql/hive) - Includes an extension of SQLContext called HiveContext that allows users to write queries using a subset of HiveQL and access data from a Hive Metastore using Hive SerDes.  There are also wrappers that allows users to run queries that include Hive UDFs, UDAFs, and UDTFs.
+ - HiveServer and CLI support (sql/hive-thriftserver) - Includes support for the SQL CLI (bin/spark-sql) and a HiveServer2 (for JDBC/ODBC) compatible server.
 
 
 Other dependencies for developers