mirror of
https://github.com/apache/zeppelin
synced 2026-05-24 09:38:26 +00:00
Have recreated this from https://github.com/apache/zeppelin/pull/1322 ### What is this PR for? While running a Notebook using shell, spark, python uses same user as which zeppelin server is running. Which means these interprets have same permission on file system as zeppelin server. IMO users should be able to impersonate themselves as a complete security system. ### What type of PR is it? [Improvement] ### Todos - [x] - Update doc - [x] - FIX NPEs - [x] - FIX CI ### What is the Jira issue? - [ZEPPELIN-1320](https://issues.apache.org/jira/browse/ZEPPELIN-1320) ### How should this be tested? - Enable shiro auth in shiro.ini - Add ssh key for the same user you want to try and impersonate (say user1). ``` adduser user1 ssh-keygen ssh user1localhost mkdir -p .ssh cat ~/.ssh/id_rsa.pub | ssh user1localhost 'cat >> .ssh/authorized_keys' ``` - Start zeppelin server, try and run following in paragraph in a notebook - Go to interpreter setting page, and enable "User Impersonate" in any of the interpreter (in my example its shell interpreter) ``` %sh whoami ``` Check that it should run as new user, i.e. "user1" ### Screenshots (if appropriate)  ### Questions: - Does the licenses files need update? no - Is there breaking changes for older versions? no - Does this needs documentation? yes Author: Prabhjyot Singh <prabhjyotsingh@gmail.org> Closes #1554 from prabhjyotsingh/ZEPPELIN-1320-2 and squashes the following commits:dc69c9d[Prabhjyot Singh] @Leemoonsoo review comment: making ZEPPELIN_SSH_COMMAND configurable1b26cc0[Prabhjyot Singh] add doc5a76839[Prabhjyot Singh] show User Impersonate only when interpreter setting is "per user" and "isolated"02c3084[Prabhjyot Singh] Merge remote-tracking branch 'origin/master' into ZEPPELIN-1320-203b2f20[Prabhjyot Singh] use user instead of ""0ff80ec[Prabhjyot Singh] Merge remote-tracking branch 'origin/master' into ZEPPELIN-1320-2dd0731d[Prabhjyot Singh] fix missing test casesaff1bf0[Prabhjyot Singh] user should have option to run these interpreters as different user.
222 lines
7.2 KiB
Bash
Executable file
222 lines
7.2 KiB
Bash
Executable file
#!/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)
|
|
|
|
function usage() {
|
|
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
|
|
case ${o} in
|
|
h)
|
|
usage
|
|
exit 0
|
|
;;
|
|
d)
|
|
INTERPRETER_DIR=${OPTARG}
|
|
;;
|
|
p)
|
|
PORT=${OPTARG}
|
|
;;
|
|
l)
|
|
LOCAL_INTERPRETER_REPO=${OPTARG}
|
|
;;
|
|
v)
|
|
. "${bin}/common.sh"
|
|
getZeppelinVersion
|
|
;;
|
|
u)
|
|
ZEPPELIN_IMPERSONATE_USER="${OPTARG}"
|
|
if [[ -z "$ZEPPELIN_IMPERSONATE_CMD" ]]; then
|
|
ZEPPELIN_IMPERSONATE_RUN_CMD=`echo "ssh ${ZEPPELIN_IMPERSONATE_USER}@localhost" `
|
|
else
|
|
ZEPPELIN_IMPERSONATE_RUN_CMD=$(eval "echo ${ZEPPELIN_IMPERSONATE_CMD} ")
|
|
fi
|
|
;;
|
|
esac
|
|
done
|
|
|
|
|
|
if [ -z "${PORT}" ] || [ -z "${INTERPRETER_DIR}" ]; then
|
|
usage
|
|
exit 1
|
|
fi
|
|
|
|
. "${bin}/common.sh"
|
|
|
|
ZEPPELIN_INTP_CLASSPATH=""
|
|
|
|
# construct classpath
|
|
if [[ -d "${ZEPPELIN_HOME}/zeppelin-interpreter/target/classes" ]]; then
|
|
ZEPPELIN_INTP_CLASSPATH+=":${ZEPPELIN_HOME}/zeppelin-interpreter/target/classes"
|
|
else
|
|
ZEPPELIN_INTERPRETER_JAR="$(ls ${ZEPPELIN_HOME}/lib/zeppelin-interpreter*.jar)"
|
|
ZEPPELIN_INTP_CLASSPATH+=":${ZEPPELIN_INTERPRETER_JAR}"
|
|
fi
|
|
|
|
# add test classes for unittest
|
|
if [[ -d "${ZEPPELIN_HOME}/zeppelin-interpreter/target/test-classes" ]]; then
|
|
ZEPPELIN_INTP_CLASSPATH+=":${ZEPPELIN_HOME}/zeppelin-interpreter/target/test-classes"
|
|
fi
|
|
if [[ -d "${ZEPPELIN_HOME}/zeppelin-zengine/target/test-classes" ]]; then
|
|
ZEPPELIN_INTP_CLASSPATH+=":${ZEPPELIN_HOME}/zeppelin-zengine/target/test-classes"
|
|
fi
|
|
|
|
|
|
addJarInDirForIntp "${ZEPPELIN_HOME}/zeppelin-interpreter/target/lib"
|
|
addJarInDirForIntp "${INTERPRETER_DIR}"
|
|
|
|
HOSTNAME=$(hostname)
|
|
ZEPPELIN_SERVER=org.apache.zeppelin.interpreter.remote.RemoteInterpreterServer
|
|
|
|
INTERPRETER_ID=$(basename "${INTERPRETER_DIR}")
|
|
ZEPPELIN_PID="${ZEPPELIN_PID_DIR}/zeppelin-interpreter-${INTERPRETER_ID}-${ZEPPELIN_IDENT_STRING}-${HOSTNAME}.pid"
|
|
ZEPPELIN_LOGFILE="${ZEPPELIN_LOG_DIR}/zeppelin-interpreter-${INTERPRETER_ID}-${ZEPPELIN_IDENT_STRING}-${HOSTNAME}.log"
|
|
JAVA_INTP_OPTS+=" -Dzeppelin.log.file=${ZEPPELIN_LOGFILE}"
|
|
|
|
if [[ ! -d "${ZEPPELIN_LOG_DIR}" ]]; then
|
|
echo "Log dir doesn't exist, create ${ZEPPELIN_LOG_DIR}"
|
|
$(mkdir -p "${ZEPPELIN_LOG_DIR}")
|
|
fi
|
|
|
|
# set spark related env variables
|
|
if [[ "${INTERPRETER_ID}" == "spark" ]]; then
|
|
if [[ -n "${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="$SPARK_HOME/python/lib/py4j-*-src.zip"
|
|
py4j=($pattern)
|
|
# pick the first match py4j zip - there should only be one
|
|
export PYTHONPATH="$SPARK_HOME/python/:$PYTHONPATH"
|
|
export PYTHONPATH="${py4j[0]}:$PYTHONPATH"
|
|
else
|
|
# add Hadoop jars into classpath
|
|
if [[ -n "${HADOOP_HOME}" ]]; then
|
|
# Apache
|
|
addEachJarInDirRecursiveForIntp "${HADOOP_HOME}/share"
|
|
|
|
# CDH
|
|
addJarInDirForIntp "${HADOOP_HOME}"
|
|
addJarInDirForIntp "${HADOOP_HOME}/lib"
|
|
fi
|
|
|
|
addJarInDirForIntp "${INTERPRETER_DIR}/dep"
|
|
|
|
pattern="${ZEPPELIN_HOME}/interpreter/spark/pyspark/py4j-*-src.zip"
|
|
py4j=($pattern)
|
|
# pick the first match py4j zip - there should only be one
|
|
PYSPARKPATH="${ZEPPELIN_HOME}/interpreter/spark/pyspark/pyspark.zip:${py4j[0]}"
|
|
|
|
if [[ -z "${PYTHONPATH}" ]]; then
|
|
export PYTHONPATH="${PYSPARKPATH}"
|
|
else
|
|
export PYTHONPATH="${PYTHONPATH}:${PYSPARKPATH}"
|
|
fi
|
|
unset PYSPARKPATH
|
|
|
|
# autodetect HADOOP_CONF_HOME by heuristic
|
|
if [[ -n "${HADOOP_HOME}" ]] && [[ -z "${HADOOP_CONF_DIR}" ]]; then
|
|
if [[ -d "${HADOOP_HOME}/etc/hadoop" ]]; then
|
|
export HADOOP_CONF_DIR="${HADOOP_HOME}/etc/hadoop"
|
|
elif [[ -d "/etc/hadoop/conf" ]]; then
|
|
export HADOOP_CONF_DIR="/etc/hadoop/conf"
|
|
fi
|
|
fi
|
|
|
|
if [[ -n "${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 "${HBASE_CONF_DIR}" ]]; then
|
|
ZEPPELIN_INTP_CLASSPATH+=":${HBASE_CONF_DIR}"
|
|
elif [[ -n "${HBASE_HOME}" ]]; then
|
|
ZEPPELIN_INTP_CLASSPATH+=":${HBASE_HOME}/conf"
|
|
else
|
|
echo "HBASE_HOME and HBASE_CONF_DIR are not set, configuration might not be loaded"
|
|
fi
|
|
elif [[ "${INTERPRETER_ID}" == "pig" ]]; then
|
|
# autodetect HADOOP_CONF_HOME by heuristic
|
|
if [[ -n "${HADOOP_HOME}" ]] && [[ -z "${HADOOP_CONF_DIR}" ]]; then
|
|
if [[ -d "${HADOOP_HOME}/etc/hadoop" ]]; then
|
|
export HADOOP_CONF_DIR="${HADOOP_HOME}/etc/hadoop"
|
|
elif [[ -d "/etc/hadoop/conf" ]]; then
|
|
export HADOOP_CONF_DIR="/etc/hadoop/conf"
|
|
fi
|
|
fi
|
|
|
|
if [[ -n "${HADOOP_CONF_DIR}" ]] && [[ -d "${HADOOP_CONF_DIR}" ]]; then
|
|
ZEPPELIN_INTP_CLASSPATH+=":${HADOOP_CONF_DIR}"
|
|
fi
|
|
|
|
# autodetect TEZ_CONF_DIR
|
|
if [[ -n "${TEZ_CONF_DIR}" ]]; then
|
|
ZEPPELIN_INTP_CLASSPATH+=":${TEZ_CONF_DIR}"
|
|
elif [[ -d "/etc/tez/conf" ]]; then
|
|
ZEPPELIN_INTP_CLASSPATH+=":/etc/tez/conf"
|
|
else
|
|
echo "TEZ_CONF_DIR is not set, configuration might not be loaded"
|
|
fi
|
|
fi
|
|
|
|
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} &`
|
|
else
|
|
${ZEPPELIN_IMPERSONATE_RUN_CMD} ${ZEPPELIN_RUNNER} ${JAVA_INTP_OPTS} ${ZEPPELIN_INTP_MEM} -cp ${ZEPPELIN_INTP_CLASSPATH_OVERRIDES}:${CLASSPATH} ${ZEPPELIN_SERVER} ${PORT} &
|
|
fi
|
|
|
|
pid=$!
|
|
if [[ -z "${pid}" ]]; then
|
|
return 1;
|
|
else
|
|
echo ${pid} > ${ZEPPELIN_PID}
|
|
fi
|
|
|
|
|
|
trap 'shutdown_hook;' SIGTERM SIGINT SIGQUIT
|
|
function shutdown_hook() {
|
|
local count
|
|
count=0
|
|
while [[ "${count}" -lt 10 ]]; do
|
|
$(kill ${pid} > /dev/null 2> /dev/null)
|
|
if kill -0 ${pid} > /dev/null 2>&1; then
|
|
sleep 3
|
|
let "count+=1"
|
|
else
|
|
rm -f "${ZEPPELIN_PID}"
|
|
break
|
|
fi
|
|
if [[ "${count}" == "5" ]]; then
|
|
$(kill -9 ${pid} > /dev/null 2> /dev/null)
|
|
rm -f "${ZEPPELIN_PID}"
|
|
fi
|
|
done
|
|
}
|
|
|
|
wait
|