8aff36e91d
This PR is based on the work of roji to support running Spark scripts from symlinks. Thanks for the great work roji . Would you mind taking a look at this PR, thanks a lot. For releases like HDP and others, normally it will expose the Spark executables as symlinks and put in `PATH`, but current Spark's scripts do not support finding real path from symlink recursively, this will make spark fail to execute from symlink. This PR try to solve this issue by finding the absolute path from symlink. Instead of using `readlink -f` like what this PR (https://github.com/apache/spark/pull/2386) implemented is that `-f` is not support for Mac, so here manually seeking the path through loop. I've tested with Mac and Linux (Cent OS), looks fine. This PR did not fix the scripts under `sbin` folder, not sure if it needs to be fixed also? Please help to review, any comment is greatly appreciated. Author: jerryshao <sshao@hortonworks.com> Author: Shay Rojansky <roji@roji.org> Closes #8669 from jerryshao/SPARK-2960.
86 lines
2.8 KiB
Bash
Executable file
86 lines
2.8 KiB
Bash
Executable file
#!/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.
|
|
#
|
|
|
|
# Starts a slave on the machine this script is executed on.
|
|
#
|
|
# Environment Variables
|
|
#
|
|
# SPARK_WORKER_INSTANCES The number of worker instances to run on this
|
|
# slave. Default is 1.
|
|
# SPARK_WORKER_PORT The base port number for the first worker. If set,
|
|
# subsequent workers will increment this number. If
|
|
# unset, Spark will find a valid port number, but
|
|
# with no guarantee of a predictable pattern.
|
|
# SPARK_WORKER_WEBUI_PORT The base port for the web interface of the first
|
|
# worker. Subsequent workers will increment this
|
|
# number. Default is 8081.
|
|
|
|
usage="Usage: start-slave.sh <spark-master-URL> where <spark-master-URL> is like spark://localhost:7077"
|
|
|
|
if [ $# -lt 1 ]; then
|
|
echo $usage
|
|
echo Called as start-slave.sh $*
|
|
exit 1
|
|
fi
|
|
|
|
if [ -z "${SPARK_HOME}" ]; then
|
|
export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
|
|
fi
|
|
|
|
. "${SPARK_HOME}/sbin/spark-config.sh"
|
|
|
|
. "${SPARK_HOME}/bin/load-spark-env.sh"
|
|
|
|
# First argument should be the master; we need to store it aside because we may
|
|
# need to insert arguments between it and the other arguments
|
|
MASTER=$1
|
|
shift
|
|
|
|
# Determine desired worker port
|
|
if [ "$SPARK_WORKER_WEBUI_PORT" = "" ]; then
|
|
SPARK_WORKER_WEBUI_PORT=8081
|
|
fi
|
|
|
|
# Start up the appropriate number of workers on this machine.
|
|
# quick local function to start a worker
|
|
function start_instance {
|
|
WORKER_NUM=$1
|
|
shift
|
|
|
|
if [ "$SPARK_WORKER_PORT" = "" ]; then
|
|
PORT_FLAG=
|
|
PORT_NUM=
|
|
else
|
|
PORT_FLAG="--port"
|
|
PORT_NUM=$(( $SPARK_WORKER_PORT + $WORKER_NUM - 1 ))
|
|
fi
|
|
WEBUI_PORT=$(( $SPARK_WORKER_WEBUI_PORT + $WORKER_NUM - 1 ))
|
|
|
|
"${SPARK_HOME}/sbin"/spark-daemon.sh start org.apache.spark.deploy.worker.Worker $WORKER_NUM \
|
|
--webui-port "$WEBUI_PORT" $PORT_FLAG $PORT_NUM $MASTER "$@"
|
|
}
|
|
|
|
if [ "$SPARK_WORKER_INSTANCES" = "" ]; then
|
|
start_instance 1 "$@"
|
|
else
|
|
for ((i=0; i<$SPARK_WORKER_INSTANCES; i++)); do
|
|
start_instance $(( 1 + $i )) "$@"
|
|
done
|
|
fi
|