Skip to content

Commit

Permalink
Spark standalone mode cluster scripts.
Browse files Browse the repository at this point in the history
Heavily inspired by Hadoop cluster scripts ;-)
  • Loading branch information
dennybritz committed Aug 2, 2012
1 parent 545165e commit 0ee44c2
Show file tree
Hide file tree
Showing 18 changed files with 825 additions and 4 deletions.
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -26,3 +26,4 @@ project/build/target/
project/plugins/target/
project/plugins/lib_managed/
project/plugins/src_managed/
logs/
59 changes: 59 additions & 0 deletions bin/slaves.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
#!/usr/bin/env bash

# Run a shell command on all slave hosts.
#
# Environment Variables
#
# SPARK_SLAVES File naming remote hosts.
# Default is ${SPARK_CONF_DIR}/slaves.
# SPARK_CONF_DIR Alternate conf dir. Default is ${SPARK_HOME}/conf.
# SPARK_SLAVE_SLEEP Seconds to sleep between spawning remote commands.
# SPARK_SSH_OPTS Options passed to ssh when running remote commands.
##

usage="Usage: slaves.sh [--config confdir] command..."

# if no args specified, show usage
if [ $# -le 0 ]; then
echo $usage
exit 1
fi

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

. "$bin/spark-config.sh"

# If the slaves file is specified in the command line,
# then it takes precedence over the definition in
# spark-env.sh. Save it here.
HOSTLIST=$SPARK_SLAVES

if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then
. "${SPARK_CONF_DIR}/spark-env.sh"
fi

if [ "$HOSTLIST" = "" ]; then
if [ "$SPARK_SLAVES" = "" ]; then
export HOSTLIST="${SPARK_CONF_DIR}/slaves"
else
export HOSTLIST="${SPARK_SLAVES}"
fi
fi

echo $"${@// /\\ }"

# By default disable strict host key checking
if [ "$SPARK_SSH_OPTS" = "" ]; then
SPARK_SSH_OPTS="-o StrictHostKeyChecking=no"
fi

for slave in `cat "$HOSTLIST"|sed "s/#.*$//;/^$/d"`; do
ssh $SPARK_SSH_OPTS $slave $"${@// /\\ }" \
2>&1 | sed "s/^/$slave: /" &
if [ "$SPARK_SLAVE_SLEEP" != "" ]; then
sleep $SPARK_SLAVE_SLEEP
fi
done

wait
19 changes: 19 additions & 0 deletions bin/spark-config.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
# included in all the spark scripts with source command
# should not be executable directly
# also should not be passed any arguments, since we need original $*

# resolve links - $0 may be a softlink
this="${BASH_SOURCE-$0}"
common_bin=$(cd -P -- "$(dirname -- "$this")" && pwd -P)
script="$(basename -- "$this")"
this="$common_bin/$script"

# convert relative path to absolute path
config_bin=`dirname "$this"`
script=`basename "$this"`
config_bin=`cd "$config_bin"; pwd`
this="$config_bin/$script"

export SPARK_PREFIX=`dirname "$this"`/..
export SPARK_HOME=${SPARK_PREFIX}
export SPARK_CONF_DIR="$SPARK_HOME/conf"
135 changes: 135 additions & 0 deletions bin/spark-daemon.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,135 @@
#!/usr/bin/env bash

# Runs a Spark command as a daemon.
#
# Environment Variables
#
# SPARK_CONF_DIR Alternate conf dir. Default is ${SPARK_PREFIX}/conf.
# SPARK_LOG_DIR Where log files are stored. PWD by default.
# SPARK_MASTER host:path where spark code should be rsync'd from
# SPARK_PID_DIR The pid files are stored. /tmp by default.
# SPARK_IDENT_STRING A string representing this instance of spark. $USER by default
# SPARK_NICENESS The scheduling priority for daemons. Defaults to 0.
##

usage="Usage: spark-daemon.sh [--config <conf-dir>] [--hosts hostlistfile] (start|stop) <spark-command> <args...>"

# if no args specified, show usage
if [ $# -le 1 ]; then
echo $usage
exit 1
fi

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

. "$bin/spark-config.sh"

# get arguments
startStop=$1
shift
command=$1
shift

spark_rotate_log ()
{
log=$1;
num=5;
if [ -n "$2" ]; then
num=$2
fi
if [ -f "$log" ]; then # rotate logs
while [ $num -gt 1 ]; do
prev=`expr $num - 1`
[ -f "$log.$prev" ] && mv "$log.$prev" "$log.$num"
num=$prev
done
mv "$log" "$log.$num";
fi
}

if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then
. "${SPARK_CONF_DIR}/spark-env.sh"
fi

if [ "$SPARK_IDENT_STRING" = "" ]; then
export SPARK_IDENT_STRING="$USER"
fi

# get log directory
if [ "$SPARK_LOG_DIR" = "" ]; then
export SPARK_LOG_DIR="$SPARK_HOME/logs"
fi
mkdir -p "$SPARK_LOG_DIR"
touch $SPARK_LOG_DIR/.spark_test > /dev/null 2>&1
TEST_LOG_DIR=$?
if [ "${TEST_LOG_DIR}" = "0" ]; then
rm -f $SPARK_LOG_DIR/.spark_test
else
chown $SPARK_IDENT_STRING $SPARK_LOG_DIR
fi

if [ "$SPARK_PID_DIR" = "" ]; then
SPARK_PID_DIR=/tmp
fi

# some variables
export SPARK_LOGFILE=spark-$SPARK_IDENT_STRING-$command-$HOSTNAME.log
export SPARK_ROOT_LOGGER="INFO,DRFA"
log=$SPARK_LOG_DIR/spark-$SPARK_IDENT_STRING-$command-$HOSTNAME.out
pid=$SPARK_PID_DIR/spark-$SPARK_IDENT_STRING-$command.pid

# Set default scheduling priority
if [ "$SPARK_NICENESS" = "" ]; then
export SPARK_NICENESS=0
fi


case $startStop in

(start)

mkdir -p "$SPARK_PID_DIR"

if [ -f $pid ]; then
if kill -0 `cat $pid` > /dev/null 2>&1; then
echo $command running as process `cat $pid`. Stop it first.
exit 1
fi
fi

if [ "$SPARK_MASTER" != "" ]; then
echo rsync from $SPARK_MASTER
rsync -a -e ssh --delete --exclude=.svn --exclude='logs/*' --exclude='contrib/hod/logs/*' $SPARK_MASTER/ "$SPARK_HOME"
fi

spark_rotate_log $log
echo starting $command, logging to $log
cd "$SPARK_PREFIX"
nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/run $command "$@" > "$log" 2>&1 < /dev/null &
echo $! > $pid
sleep 1; head "$log"
;;

(stop)

if [ -f $pid ]; then
if kill -0 `cat $pid` > /dev/null 2>&1; then
echo stopping $command
kill `cat $pid`
else
echo no $command to stop
fi
else
echo no $command to stop
fi
;;

(*)
echo $usage
exit 1
;;

esac


18 changes: 18 additions & 0 deletions bin/spark-daemons.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
#!/usr/bin/env bash

# Run a Spark command on all slave hosts.

usage="Usage: spark-daemons.sh [--config confdir] [--hosts hostlistfile] [start|stop] command args..."

# if no args specified, show usage
if [ $# -le 1 ]; then
echo $usage
exit 1
fi

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

. "$bin/spark-config.sh"

exec "$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/spark-daemon.sh" "$@"
17 changes: 17 additions & 0 deletions bin/start-all.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
#!/usr/bin/env bash

# Start all spark daemons.
# Starts the master on this node.
# Starts a worker on each node specified in conf/slaves

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

# Load the Spark configuration
. "$bin/spark-config.sh"

# Start Master
"$bin"/start-master.sh --config $SPARK_CONF_DIR

# Start Workers
"$bin"/start-slaves.sh --config $SPARK_CONF_DIR
10 changes: 10 additions & 0 deletions bin/start-master.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
#!/usr/bin/env bash

# Starts the master on the machine this script is executed on.

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

. "$bin/spark-config.sh"

"$bin"/spark-daemon.sh start spark.deploy.master.Master
16 changes: 16 additions & 0 deletions bin/start-slaves.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
#!/usr/bin/env bash

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

. "$bin/spark-config.sh"

# Find the port number for the master
if [ "$SPARK_MASTER_PORT" = "" ]; then
SPARK_MASTER_PORT=7077
fi

hostname=`hostname`
ip=`host "$hostname" | cut -d " " -f 4`

"$bin"/spark-daemons.sh start spark.deploy.worker.Worker spark://$ip:$SPARK_MASTER_PORT
14 changes: 14 additions & 0 deletions bin/stop-all.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
#!/usr/bin/env bash

# Start all spark daemons.
# Run this on the master nde

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

# Load the Spark configuration
. "$bin/spark-config.sh"

# Stop the slaves, then the master
"$bin"/stop-slaves.sh
"$bin"/stop-master.sh
10 changes: 10 additions & 0 deletions bin/stop-master.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
#!/usr/bin/env bash

# Starts the master on the machine this script is executed on.

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

. "$bin/spark-config.sh"

"$bin"/spark-daemon.sh stop spark.deploy.worker.Worker
10 changes: 10 additions & 0 deletions bin/stop-slaves.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
#!/usr/bin/env bash

# Starts the master on the machine this script is executed on.

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

. "$bin/spark-config.sh"

"$bin"/spark-daemon.sh stop spark.deploy.master.Master
2 changes: 2 additions & 0 deletions conf/slaves
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
# A Spark Worker will be started on each of the machines listes below.
localhost
2 changes: 1 addition & 1 deletion conf/spark-env.sh.template
Original file line number Diff line number Diff line change
Expand Up @@ -9,5 +9,5 @@
# - SPARK_MEM, to change the amount of memory used per node (this should
# be in the same format as the JVM's -Xmx option, e.g. 300m or 1g).
# - SPARK_LIBRARY_PATH, to add extra search paths for native libraries.

# - SPARK_MASTER_PORT, to start the spark master on a different port (standalone mode only)

2 changes: 1 addition & 1 deletion core/src/main/scala/spark/deploy/master/Master.scala
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ class Master(ip: String, port: Int, webUiPort: Int) extends Actor with Logging {
def startWebUi() {
val webUi = new MasterWebUI(context.system, self)
try {
AkkaUtils.startSprayServer(context.system, ip, webUiPort, webUi.handler)
AkkaUtils.startSprayServer(context.system, "0.0.0.0", webUiPort, webUi.handler)
} catch {
case e: Exception =>
logError("Failed to create web UI", e)
Expand Down
2 changes: 1 addition & 1 deletion core/src/main/scala/spark/deploy/worker/Worker.scala
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,7 @@ class Worker(ip: String, port: Int, webUiPort: Int, cores: Int, memory: Int, mas
def startWebUi() {
val webUi = new WorkerWebUI(context.system, self)
try {
AkkaUtils.startSprayServer(context.system, ip, webUiPort, webUi.handler)
AkkaUtils.startSprayServer(context.system, "0.0.0.0", webUiPort, webUi.handler)
} catch {
case e: Exception =>
logError("Failed to create web UI", e)
Expand Down
20 changes: 20 additions & 0 deletions ec2/spark-ec2-standalone
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
#!/bin/sh

# 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.

cd "`dirname $0`"
PYTHONPATH="./third_party/boto-2.4.1.zip/boto-2.4.1:$PYTHONPATH" python ./spark_ec2_standalone.py $@
Loading

0 comments on commit 0ee44c2

Please sign in to comment.