apache · AhyoungRyu · Aug 16, 2016 · Aug 17, 2016 · Aug 17, 2016 · Aug 17, 2016
diff --git a/.gitignore b/.gitignore
@@ -14,6 +14,7 @@
 spark/derby.log
 spark/metastore_db
 spark-1.*-bin-hadoop*
+spark-2.*-bin-hadoop*
 .spark-dist
 zeppelin-server/derby.log
 

diff --git a/.travis.yml b/.travis.yml
@@ -40,27 +40,27 @@ matrix:
 
     # Test all modules with spark 2.0.0 and scala 2.11
     - jdk: "oraclejdk7"
-      env: SCALA_VER="2.11" SPARK_VER="2.0.0" HADOOP_VER="2.3" PROFILE="-Pspark-2.0 -Phadoop-2.3 -Ppyspark -Psparkr -Pscalding -Pexamples -Pscala-2.11" BUILD_FLAG="package -Pbuild-distr -DskipRat" TEST_FLAG="verify -Pusing-packaged-distr -DskipRat" TEST_PROJECTS=""
+      env: SCALA_VER="2.11" SPARK_VER="2.0.0" HADOOP_VER="2.3" PROFILE="-Pspark-2.0 -Phadoop-2.3 -Psparkr -Pscalding -Pexamples -Pscala-2.11" BUILD_FLAG="package -Pbuild-distr -DskipRat" TEST_FLAG="verify -Pusing-packaged-distr -DskipRat" TEST_PROJECTS=""
 
     # Test all modules with scala 2.10
     - jdk: "oraclejdk7"
-      env: SCALA_VER="2.10" SPARK_VER="1.6.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.6 -Pr -Phadoop-2.3 -Ppyspark -Psparkr -Pscalding -Pbeam -Pexamples -Pscala-2.10" BUILD_FLAG="package -Pbuild-distr -DskipRat" TEST_FLAG="verify -Pusing-packaged-distr -DskipRat" TEST_PROJECTS=""
+      env: SCALA_VER="2.10" SPARK_VER="1.6.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.6 -Pr -Phadoop-2.3 -Psparkr -Pscalding -Pbeam -Pexamples -Pscala-2.10" BUILD_FLAG="package -Pbuild-distr -DskipRat" TEST_FLAG="verify -Pusing-packaged-distr -DskipRat" TEST_PROJECTS=""
 
     # Test all modules with scala 2.11
     - jdk: "oraclejdk7"
-      env: SCALA_VER="2.11" SPARK_VER="1.6.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.6 -Pr -Phadoop-2.3 -Ppyspark -Psparkr -Pscalding -Pexamples -Pscala-2.11" BUILD_FLAG="package -Pbuild-distr -DskipRat" TEST_FLAG="verify -Pusing-packaged-distr -DskipRat" TEST_PROJECTS=""
+      env: SCALA_VER="2.11" SPARK_VER="1.6.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.6 -Pr -Phadoop-2.3 -Psparkr -Pscalding -Pexamples -Pscala-2.11" BUILD_FLAG="package -Pbuild-distr -DskipRat" TEST_FLAG="verify -Pusing-packaged-distr -DskipRat" TEST_PROJECTS=""
 
     # Test spark module for 1.5.2
     - jdk: "oraclejdk7"
-      env: SCALA_VER="2.10" SPARK_VER="1.5.2" HADOOP_VER="2.3" PROFILE="-Pspark-1.5 -Pr -Phadoop-2.3 -Ppyspark -Psparkr" BUILD_FLAG="package -DskipTests -DskipRat" TEST_FLAG="verify -DskipRat" TEST_PROJECTS="-pl zeppelin-interpreter,zeppelin-zengine,zeppelin-server,zeppelin-display,spark-dependencies,spark,r -Dtest=org.apache.zeppelin.rest.*Test,org.apache.zeppelin.spark.* -DfailIfNoTests=false"
+      env: SCALA_VER="2.10" SPARK_VER="1.5.2" HADOOP_VER="2.3" PROFILE="-Pspark-1.5 -Pr -Phadoop-2.3 -Psparkr" BUILD_FLAG="package -DskipTests -DskipRat" TEST_FLAG="verify -DskipRat" TEST_PROJECTS="-pl zeppelin-interpreter,zeppelin-zengine,zeppelin-server,zeppelin-display,spark,r -Dtest=org.apache.zeppelin.rest.*Test,org.apache.zeppelin.spark.* -DfailIfNoTests=false"
 
     # Test spark module for 1.4.1
     - jdk: "oraclejdk7"
-      env: SCALA_VER="2.10" SPARK_VER="1.4.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.4 -Pr -Phadoop-2.3 -Ppyspark -Psparkr" BUILD_FLAG="package -DskipTests -DskipRat" TEST_FLAG="verify -DskipRat" TEST_PROJECTS="-pl zeppelin-interpreter,zeppelin-zengine,zeppelin-server,zeppelin-display,spark-dependencies,spark,r -Dtest=org.apache.zeppelin.rest.*Test,org.apache.zeppelin.spark.* -DfailIfNoTests=false"
+      env: SCALA_VER="2.10" SPARK_VER="1.4.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.4 -Pr -Phadoop-2.3 -Psparkr" BUILD_FLAG="package -DskipTests -DskipRat" TEST_FLAG="verify -DskipRat" TEST_PROJECTS="-pl zeppelin-interpreter,zeppelin-zengine,zeppelin-server,zeppelin-display,spark,r -Dtest=org.apache.zeppelin.rest.*Test,org.apache.zeppelin.spark.* -DfailIfNoTests=false"
 
     # Test selenium with spark module for 1.6.1
     - jdk: "oraclejdk7"
-      env: TEST_SELENIUM="true" SCALA_VER="2.10" SPARK_VER="1.6.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.6 -Phadoop-2.3 -Ppyspark -Pexamples" BUILD_FLAG="package -DskipTests -DskipRat" TEST_FLAG="verify -DskipRat" TEST_PROJECTS="-pl zeppelin-interpreter,zeppelin-zengine,zeppelin-server,zeppelin-display,spark-dependencies,spark -Dtest=org.apache.zeppelin.AbstractFunctionalSuite -DfailIfNoTests=false"
+      env: TEST_SELENIUM="true" SCALA_VER="2.10" SPARK_VER="1.6.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.6 -Phadoop-2.3 -Pexamples" BUILD_FLAG="package -DskipTests -DskipRat" TEST_FLAG="verify -DskipRat" TEST_PROJECTS="-pl zeppelin-interpreter,zeppelin-zengine,zeppelin-server,zeppelin-display,spark -Dtest=org.apache.zeppelin.AbstractFunctionalSuite -DfailIfNoTests=false"
 
 before_install:
   - "ls -la .spark-dist ${HOME}/.m2/repository/.cache/maven-download-plugin"
@@ -77,6 +77,7 @@ install:
 
 before_script:
   - travis_retry ./testing/downloadSpark.sh $SPARK_VER $HADOOP_VER
+  - export SPARK_HOME=`pwd`/spark-$SPARK_VER-bin-hadoop$HADOOP_VER
   - echo "export SPARK_HOME=`pwd`/spark-$SPARK_VER-bin-hadoop$HADOOP_VER" > conf/zeppelin-env.sh
   - tail conf/zeppelin-env.sh
 
@@ -95,4 +96,3 @@ after_failure:
   - cat zeppelin-distribution/target/zeppelin-*-SNAPSHOT/zeppelin-*-SNAPSHOT/logs/zeppelin*.out
   - cat zeppelin-web/npm-debug.log
   - cat spark-*/logs/*
-
diff --git a/README.md b/README.md
@@ -21,9 +21,7 @@ To know more about Zeppelin, visit our web site [http://zeppelin.apache.org](htt
 ## Getting Started
 
 ### Install binary package
-Please go to [install](http://zeppelin.apache.org/docs/snapshot/install/install.html) to install Apache Zeppelin from binary package.
+Please refer to [Zeppelin installation guide](http://zeppelin.apache.org/docs/snapshot/install/install.html) to install Apache Zeppelin from binary package.
 
 ### Build from source
-Please check [Build from source](http://zeppelin.apache.org/docs/snapshot/install/build.html) to build Zeppelin from source.
-
-
+Please check [How to build Zeppelin from source](http://zeppelin.apache.org/docs/snapshot/install/build.html) to build Zeppelin.
diff --git a/bin/common.sh b/bin/common.sh
@@ -58,31 +58,31 @@ fi
 
 ZEPPELIN_CLASSPATH+=":${ZEPPELIN_CONF_DIR}"
 
-function addEachJarInDir(){
+function addEachJarInDir() {
   if [[ -d "${1}" ]]; then
     for jar in $(find -L "${1}" -maxdepth 1 -name '*jar'); do
       ZEPPELIN_CLASSPATH="$jar:$ZEPPELIN_CLASSPATH"
     done
   fi
 }
 
-function addEachJarInDirRecursive(){
+function addEachJarInDirRecursive() {
   if [[ -d "${1}" ]]; then
     for jar in $(find -L "${1}" -type f -name '*jar'); do
       ZEPPELIN_CLASSPATH="$jar:$ZEPPELIN_CLASSPATH"
     done
   fi
 }
 
-function addEachJarInDirRecursiveForIntp(){
+function addEachJarInDirRecursiveForIntp() {
   if [[ -d "${1}" ]]; then
     for jar in $(find -L "${1}" -type f -name '*jar'); do
       ZEPPELIN_INTP_CLASSPATH="$jar:$ZEPPELIN_INTP_CLASSPATH"
     done
   fi
 }
 
-function addJarInDir(){
+function addJarInDir() {
   if [[ -d "${1}" ]]; then
     ZEPPELIN_CLASSPATH="${1}/*:${ZEPPELIN_CLASSPATH}"
   fi
@@ -96,17 +96,31 @@ function addJarInDirForIntp() {
 
 ZEPPELIN_COMMANDLINE_MAIN=org.apache.zeppelin.utils.CommandLineUtils
 
-function getZeppelinVersion(){
-    if [[ -d "${ZEPPELIN_HOME}/zeppelin-server/target/classes" ]]; then
-      ZEPPELIN_CLASSPATH+=":${ZEPPELIN_HOME}/zeppelin-server/target/classes"
-    fi
-    addJarInDir "${ZEPPELIN_HOME}/zeppelin-server/target/lib"
-    CLASSPATH+=":${ZEPPELIN_CLASSPATH}"
-    $ZEPPELIN_RUNNER -cp $CLASSPATH $ZEPPELIN_COMMANDLINE_MAIN -v
-    exit 0
+function getZeppelinVersion() {
+  if [[ -d "${ZEPPELIN_HOME}/zeppelin-server/target/classes" ]]; then
+    ZEPPELIN_CLASSPATH+=":${ZEPPELIN_HOME}/zeppelin-server/target/classes"
+  fi
+  addJarInDir "${ZEPPELIN_HOME}/zeppelin-server/target/lib"
+  CLASSPATH+=":${ZEPPELIN_CLASSPATH}"
+  $ZEPPELIN_RUNNER -cp $CLASSPATH $ZEPPELIN_COMMANDLINE_MAIN -v
+  exit 0
+}
+
+
+SPARK_VERSION="2.0.1"
+HADOOP_VERSION="2.7"
+SPARK_CACHE="local-spark"
+SPARK_ARCHIVE="spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}"
+
+function downloadSparkBinary() {
+  if [[ ! -d "${SPARK_CACHE}/${SPARK_ARCHIVE}" ]]; then
+    . "${ZEPPELIN_HOME}/bin/download-spark.sh"
+  else
+    echo -e "${SPARK_ARCHIVE} already exists under local-spark."
+  fi
 }
 
-# Text encoding for 
+# Text encoding for
 # read/write job into files,
 # receiving/displaying query/result.
 if [[ -z "${ZEPPELIN_ENCODING}" ]]; then

diff --git a/bin/download-spark.sh b/bin/download-spark.sh
@@ -0,0 +1,76 @@
+#!/bin/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.
+#
+
+bin=$(dirname "${BASH_SOURCE-$0}")
+bin=$(cd "${bin}">/dev/null; pwd)
+
+. "${bin}/common.sh"
+
+# Download Spark binary package from the given URL.
+# Ties 3 times with 1s delay
+# Arguments: url - source URL
+function download_with_retry() {
+  local url="$1"
+  curl -O --retry 3 --retry-delay 1 "${url}"
+
+  if [[ "$?" -ne 0 ]]; then
+    echo -e "\nStop downloading with unexpected error."
+  fi
+}
+
+function unzip_spark_bin() {
+  if ! tar zxf "${SPARK_ARCHIVE}.tgz" ; then
+    echo "Unable to extract ${SPARK_ARCHIVE}.tgz" >&2
+    rm -rf "${SPARK_ARCHIVE}"
+  fi
+
+  rm -f "${SPARK_ARCHIVE}.tgz"
+  echo -e "\n${SPARK_ARCHIVE} is successfully downloaded and saved under ${ZEPPELIN_HOME}/${SPARK_CACHE}\n"
+}
+
+function create_local_spark_dir() {
+  if [[ ! -d "${SPARK_CACHE}" ]]; then
+    mkdir -p "${SPARK_CACHE}"
+  fi
+}
+
+function check_local_spark_dir() {
+  if [[ -d "${ZEPPELIN_HOME}/${SPARK_CACHE}" ]]; then
+    rm -r "${ZEPPELIN_HOME}/${SPARK_CACHE}"
+  fi
+}
+
+function save_local_spark() {
+  # echo -e "For using Spark interpreter in local mode(without external Spark installation), Spark binary needs to be downloaded."
+  trap "echo -e '\n\nForced termination by user.'; check_local_spark_dir; exit 1" SIGTERM SIGINT SIGQUIT
+  create_local_spark_dir
+  cd "${SPARK_CACHE}"
+
+  printf "Download ${SPARK_ARCHIVE}.tgz from mirror ...\n\n"
+
+  MIRROR_INFO=$(curl -s "http://www.apache.org/dyn/closer.cgi/spark/spark-${SPARK_VERSION}/${SPARK_ARCHIVE}.tgz?asjson=1")
+  PREFFERED=$(echo "${MIRROR_INFO}" | grep preferred | sed 's/[^"]*.preferred.: .\([^"]*\).*/\1/g')
+  PATHINFO=$(echo "${MIRROR_INFO}" | grep path_info | sed 's/[^"]*.path_info.: .\([^"]*\).*/\1/g')
+
+  download_with_retry "${PREFFERED}${PATHINFO}"
+  unzip_spark_bin
+}
+
+save_local_spark
+
+set +xe
diff --git a/bin/interpreter.sh b/bin/interpreter.sh
@@ -20,7 +20,7 @@ bin=$(dirname "${BASH_SOURCE-$0}")
 bin=$(cd "${bin}">/dev/null; pwd)
 
 function usage() {
-    echo "usage) $0 -p <port> -d <interpreter dir to load> -l <local interpreter repo dir to load>"
+  echo "usage) $0 -p <port> -d <interpreter dir to load> -l <local interpreter repo dir to load>"
 }
 
 while getopts "hp:d:l:v:u:" o; do
@@ -55,8 +55,8 @@ done
 
 
 if [ -z "${PORT}" ] || [ -z "${INTERPRETER_DIR}" ]; then
-    usage
-    exit 1
+  usage
+  exit 1
 fi
 
 . "${bin}/common.sh"
@@ -98,17 +98,18 @@ fi
 
 # set spark related env variables
 if [[ "${INTERPRETER_ID}" == "spark" ]]; then
+  SPARK_APP_JAR="$(ls ${ZEPPELIN_HOME}/interpreter/spark/zeppelin-spark*.jar)"
+  # This will eventually passes SPARK_APP_JAR to classpath of SparkIMain
+  ZEPPELIN_INTP_CLASSPATH+=":${SPARK_APP_JAR}"
+
   if [[ -n "${SPARK_HOME}" ]]; then
     export SPARK_SUBMIT="${SPARK_HOME}/bin/spark-submit"
-    SPARK_APP_JAR="$(ls ${ZEPPELIN_HOME}/interpreter/spark/zeppelin-spark*.jar)"
-    # This will evantually passes SPARK_APP_JAR to classpath of SparkIMain
-    ZEPPELIN_INTP_CLASSPATH+=":${SPARK_APP_JAR}"
 
-    pattern="$SPARK_HOME/python/lib/py4j-*-src.zip"
+    pattern="${SPARK_HOME}/python/lib/py4j-*-src.zip"
     py4j=($pattern)
     # pick the first match py4j zip - there should only be one
-    export PYTHONPATH="$SPARK_HOME/python/:$PYTHONPATH"
-    export PYTHONPATH="${py4j[0]}:$PYTHONPATH"
+    export PYTHONPATH="${SPARK_HOME}/python/:${PYTHONPATH}"
+    export PYTHONPATH="${py4j[0]}:${PYTHONPATH}"
   else
     # add Hadoop jars into classpath
     if [[ -n "${HADOOP_HOME}" ]]; then
@@ -120,12 +121,13 @@ if [[ "${INTERPRETER_ID}" == "spark" ]]; then
       addJarInDirForIntp "${HADOOP_HOME}/lib"
     fi
 
-    addJarInDirForIntp "${INTERPRETER_DIR}/dep"
+    # If there is not SPARK_HOME in the system, Zeppelin will use local Spark binary for Spark interpreter
+    export SPARK_SUBMIT="${ZEPPELIN_HOME}/${SPARK_CACHE}/${SPARK_ARCHIVE}/bin/spark-submit"
 
-    pattern="${ZEPPELIN_HOME}/interpreter/spark/pyspark/py4j-*-src.zip"
+    pattern="${ZEPPELIN_HOME}/${SPARK_CACHE}/${SPARK_ARCHIVE}/python/lib/py4j-*-src.zip"
     py4j=($pattern)
     # pick the first match py4j zip - there should only be one
-    PYSPARKPATH="${ZEPPELIN_HOME}/interpreter/spark/pyspark/pyspark.zip:${py4j[0]}"
+    PYSPARKPATH="${ZEPPELIN_HOME}/${SPARK_CACHE}/${SPARK_ARCHIVE}/python/lib/pyspark.zip:${py4j[0]}"
 
     if [[ -z "${PYTHONPATH}" ]]; then
       export PYTHONPATH="${PYSPARKPATH}"
@@ -146,8 +148,6 @@ if [[ "${INTERPRETER_ID}" == "spark" ]]; then
     if [[ -n "${HADOOP_CONF_DIR}" ]] && [[ -d "${HADOOP_CONF_DIR}" ]]; then
       ZEPPELIN_INTP_CLASSPATH+=":${HADOOP_CONF_DIR}"
     fi
-
-    export SPARK_CLASSPATH+=":${ZEPPELIN_INTP_CLASSPATH}"
   fi
 elif [[ "${INTERPRETER_ID}" == "hbase" ]]; then
   if [[ -n "${HBASE_CONF_DIR}" ]]; then
@@ -186,9 +186,9 @@ addJarInDirForIntp "${LOCAL_INTERPRETER_REPO}"
 CLASSPATH+=":${ZEPPELIN_INTP_CLASSPATH}"
 
 if [[ -n "${SPARK_SUBMIT}" ]]; then
-    ${ZEPPELIN_IMPERSONATE_RUN_CMD} `${SPARK_SUBMIT} --class ${ZEPPELIN_SERVER} --driver-class-path "${ZEPPELIN_INTP_CLASSPATH_OVERRIDES}:${CLASSPATH}" --driver-java-options "${JAVA_INTP_OPTS}" ${SPARK_SUBMIT_OPTIONS} ${SPARK_APP_JAR} ${PORT} &`
+  ${ZEPPELIN_IMPERSONATE_RUN_CMD} `${SPARK_SUBMIT} --class ${ZEPPELIN_SERVER} --driver-class-path "${ZEPPELIN_INTP_CLASSPATH_OVERRIDES}:${CLASSPATH}" --driver-java-options "${JAVA_INTP_OPTS}" ${SPARK_SUBMIT_OPTIONS} ${SPARK_APP_JAR} ${PORT} &`
 else
-    ${ZEPPELIN_IMPERSONATE_RUN_CMD} ${ZEPPELIN_RUNNER} ${JAVA_INTP_OPTS} ${ZEPPELIN_INTP_MEM} -cp ${ZEPPELIN_INTP_CLASSPATH_OVERRIDES}:${CLASSPATH} ${ZEPPELIN_SERVER} ${PORT} &
+  ${ZEPPELIN_IMPERSONATE_RUN_CMD} ${ZEPPELIN_RUNNER} ${JAVA_INTP_OPTS} ${ZEPPELIN_INTP_MEM} -cp ${ZEPPELIN_INTP_CLASSPATH_OVERRIDES}:${CLASSPATH} ${ZEPPELIN_SERVER} ${PORT} &
 fi
 
 pid=$!

diff --git a/bin/zeppelin-daemon.sh b/bin/zeppelin-daemon.sh
@@ -20,7 +20,7 @@
 #
 
 USAGE="-e Usage: zeppelin-daemon.sh\n\t
-        [--config <conf-dir>] {start|stop|upstart|restart|reload|status}\n\t
+        [--config <conf-dir>] {start|stop|upstart|restart|reload|status|get-spark}\n\t
         [--version | -v]"
 
 if [[ "$1" == "--config" ]]; then
@@ -179,6 +179,10 @@ function start() {
 
   initialize_default_directories
 
+  if [[ ! -d "${SPARK_CACHE}/${SPARK_ARCHIVE}" && -z "${SPARK_HOME}" ]]; then
+    echo -e "\nYou do not have neither local-spark, nor external SPARK_HOME set up.\nIf you want to use Spark interpreter, you need to run get-spark at least one time or set SPARK_HOME.\n"
+  fi
+
   echo "ZEPPELIN_CLASSPATH: ${ZEPPELIN_CLASSPATH_OVERRIDES}:${CLASSPATH}" >> "${ZEPPELIN_OUTFILE}"
 
   nohup nice -n $ZEPPELIN_NICENESS $ZEPPELIN_RUNNER $JAVA_OPTS -cp $ZEPPELIN_CLASSPATH_OVERRIDES:$CLASSPATH $ZEPPELIN_MAIN >> "${ZEPPELIN_OUTFILE}" 2>&1 < /dev/null &
@@ -265,6 +269,9 @@ case "${1}" in
   status)
     find_zeppelin_process
     ;;
+  get-spark)
+    downloadSparkBinary
+    ;;
   -v | --version)
     getZeppelinVersion
     ;;

diff --git a/bin/zeppelin.sh b/bin/zeppelin.sh
@@ -43,6 +43,10 @@ if [ "$1" == "--version" ] || [ "$1" == "-v" ]; then
     getZeppelinVersion
 fi
 
+if [ "$1" == "get-spark" ]; then
+    downloadSparkBinary
+fi
+
 HOSTNAME=$(hostname)
 ZEPPELIN_LOGFILE="${ZEPPELIN_LOG_DIR}/zeppelin-${ZEPPELIN_IDENT_STRING}-${HOSTNAME}.log"
 LOG="${ZEPPELIN_LOG_DIR}/zeppelin-cli-${ZEPPELIN_IDENT_STRING}-${HOSTNAME}.out"
@@ -87,4 +91,8 @@ if [[ ! -d "${ZEPPELIN_NOTEBOOK_DIR}" ]]; then
   $(mkdir -p "${ZEPPELIN_NOTEBOOK_DIR}")
 fi
 
+if [[ ! -d "${SPARK_CACHE}/${SPARK_ARCHIVE}" && -z "${SPARK_HOME}" ]]; then
+  echo -e "\nYou do not have neither local-spark, nor external SPARK_HOME set up.\nIf you want to use Spark interpreter, you need to run get-spark at least one time or set SPARK_HOME.\n"
+fi
+
 exec $ZEPPELIN_RUNNER $JAVA_OPTS -cp $ZEPPELIN_CLASSPATH_OVERRIDES:$CLASSPATH $ZEPPELIN_SERVER "$@"
diff --git a/conf/zeppelin-env.sh.template b/conf/zeppelin-env.sh.template
@@ -41,16 +41,17 @@
 
 #### Spark interpreter configuration ####
 
-## Use provided spark installation ##
-## defining SPARK_HOME makes Zeppelin run spark interpreter process using spark-submit
+## Use provided Spark installation ##
+## defining SPARK_HOME makes Zeppelin run Spark interpreter process using spark-submit
 ##
 # export SPARK_HOME                             # (required) When it is defined, load it instead of Zeppelin embedded Spark libraries
 # export SPARK_SUBMIT_OPTIONS                   # (optional) extra options to pass to spark submit. eg) "--driver-memory 512M --executor-memory 1G".
 # export SPARK_APP_NAME                         # (optional) The name of spark application.
 
-## Use embedded spark binaries ##
-## without SPARK_HOME defined, Zeppelin still able to run spark interpreter process using embedded spark binaries.
-## however, it is not encouraged when you can define SPARK_HOME
+## Use embedded Spark binaries ##
+## You can simply get the embedded Spark binaries by running "ZEPPELIN_HOME/bin/zeppelin-daemon.sh get-spark" or "ZEPPELIN_HOME/bin/zeppelin.sh get-spark".
+## Zeppelin can run Spark interpreter process using this embedded Spark without any configurations.
+## If you can define SPARK_HOME, then you don't need to download it.
 ##
 # Options read in YARN client mode
 # export HADOOP_CONF_DIR         		# yarn-site.xml is located in configuration directory in HADOOP_CONF_DIR.

diff --git a/dev/create_release.sh b/dev/create_release.sh
@@ -103,8 +103,8 @@ function make_binary_release() {
 
 git_clone
 make_source_package
-make_binary_release all "-Pspark-2.0 -Phadoop-2.4 -Pyarn -Ppyspark -Psparkr -Pr -Pscala-2.11"
-make_binary_release netinst "-Pspark-2.0 -Phadoop-2.4 -Pyarn -Ppyspark -Psparkr -Pr -Pscala-2.11 -pl !alluxio,!angular,!cassandra,!elasticsearch,!file,!flink,!hbase,!ignite,!jdbc,!kylin,!lens,!livy,!markdown,!postgresql,!python,!shell,!bigquery"
+make_binary_release all "-Pspark-2.0 -Phadoop-2.4 -Pyarn -Psparkr -Pr -Pscala-2.11"
+make_binary_release netinst "-Pspark-2.0 -Phadoop-2.4 -Pyarn -Psparkr -Pr -Pscala-2.11 -pl !alluxio,!angular,!cassandra,!elasticsearch,!file,!flink,!hbase,!ignite,!jdbc,!kylin,!lens,!livy,!markdown,!postgresql,!python,!shell,!bigquery"
 
 # remove non release files and dirs
 rm -rf "${WORKING_DIR}/zeppelin"

diff --git a/dev/publish_release.sh b/dev/publish_release.sh
@@ -44,7 +44,7 @@ NC='\033[0m' # No Color
 RELEASE_VERSION="$1"
 GIT_TAG="$2"
 
-PUBLISH_PROFILES="-Ppublish-distr -Pspark-2.0 -Phadoop-2.4 -Pyarn -Ppyspark -Psparkr -Pr"
+PUBLISH_PROFILES="-Ppublish-distr -Pspark-2.0 -Phadoop-2.4 -Pyarn -Psparkr -Pr"
 PROJECT_OPTIONS="-pl !zeppelin-distribution"
 NEXUS_STAGING="https://repository.apache.org/service/local/staging"
 NEXUS_PROFILE="153446d1ac37c4"