Merge remote-tracking branch 'kalpit/master'

Conflicts:
	project/SparkBuild.scala
This commit is contained in:
Matei Zaharia 2013-04-07 20:54:18 -04:00
commit 1cb3eb9762
13 changed files with 40 additions and 18 deletions

View file

@ -30,7 +30,7 @@
# 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...>"
usage="Usage: spark-daemon.sh [--config <conf-dir>] [--hosts hostlistfile] (start|stop) <spark-command> <spark-instance-number> <args...>"
# if no args specified, show usage
if [ $# -le 1 ]; then
@ -48,6 +48,8 @@ startStop=$1
shift
command=$1
shift
instance=$1
shift
spark_rotate_log ()
{
@ -92,10 +94,10 @@ if [ "$SPARK_PID_DIR" = "" ]; then
fi
# some variables
export SPARK_LOGFILE=spark-$SPARK_IDENT_STRING-$command-$HOSTNAME.log
export SPARK_LOGFILE=spark-$SPARK_IDENT_STRING-$command-$instance-$HOSTNAME.log
export SPARK_ROOT_LOGGER="INFO,DRFA"
log=$SPARK_LOG_DIR/spark-$SPARK_IDENT_STRING-$command-$HOSTNAME.out
pid=$SPARK_PID_DIR/spark-$SPARK_IDENT_STRING-$command.pid
log=$SPARK_LOG_DIR/spark-$SPARK_IDENT_STRING-$command-$instance-$HOSTNAME.out
pid=$SPARK_PID_DIR/spark-$SPARK_IDENT_STRING-$command-$instance.pid
# Set default scheduling priority
if [ "$SPARK_NICENESS" = "" ]; then

View file

@ -2,7 +2,7 @@
# Run a Spark command on all slave hosts.
usage="Usage: spark-daemons.sh [--config confdir] [--hosts hostlistfile] [start|stop] command args..."
usage="Usage: spark-daemons.sh [--config confdir] [--hosts hostlistfile] [start|stop] command instance-number args..."
# if no args specified, show usage
if [ $# -le 1 ]; then

View file

@ -32,4 +32,4 @@ if [ "$SPARK_PUBLIC_DNS" = "" ]; then
fi
fi
"$bin"/spark-daemon.sh start spark.deploy.master.Master --ip $SPARK_MASTER_IP --port $SPARK_MASTER_PORT --webui-port $SPARK_MASTER_WEBUI_PORT
"$bin"/spark-daemon.sh start spark.deploy.master.Master 1 --ip $SPARK_MASTER_IP --port $SPARK_MASTER_PORT --webui-port $SPARK_MASTER_WEBUI_PORT

View file

@ -11,4 +11,4 @@ if [ "$SPARK_PUBLIC_DNS" = "" ]; then
fi
fi
"$bin"/spark-daemon.sh start spark.deploy.worker.Worker $1
"$bin"/spark-daemon.sh start spark.deploy.worker.Worker "$@"

View file

@ -21,4 +21,13 @@ fi
echo "Master IP: $SPARK_MASTER_IP"
# Launch the slaves
exec "$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/start-slave.sh" spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT
if [ "$SPARK_WORKER_INSTANCES" = "" ]; then
exec "$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/start-slave.sh" 1 spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT
else
if [ "$SPARK_WORKER_WEBUI_PORT" = "" ]; then
SPARK_WORKER_WEBUI_PORT=8081
fi
for ((i=0; i<$SPARK_WORKER_INSTANCES; i++)); do
"$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/start-slave.sh" $(( $i + 1 )) spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT --webui-port $(( $SPARK_WORKER_WEBUI_PORT + $i ))
done
fi

View file

@ -7,4 +7,4 @@ bin=`cd "$bin"; pwd`
. "$bin/spark-config.sh"
"$bin"/spark-daemon.sh stop spark.deploy.master.Master
"$bin"/spark-daemon.sh stop spark.deploy.master.Master 1

View file

@ -7,4 +7,14 @@ bin=`cd "$bin"; pwd`
. "$bin/spark-config.sh"
"$bin"/spark-daemons.sh stop spark.deploy.worker.Worker
if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then
. "${SPARK_CONF_DIR}/spark-env.sh"
fi
if [ "$SPARK_WORKER_INSTANCES" = "" ]; then
"$bin"/spark-daemons.sh stop spark.deploy.worker.Worker 1
else
for ((i=0; i<$SPARK_WORKER_INSTANCES; i++)); do
"$bin"/spark-daemons.sh stop spark.deploy.worker.Worker $(( $i + 1 ))
done
fi

View file

@ -12,6 +12,7 @@
# - SPARK_WORKER_CORES, to set the number of cores to use on this machine
# - SPARK_WORKER_MEMORY, to set how much memory to use (e.g. 1000m, 2g)
# - SPARK_WORKER_PORT / SPARK_WORKER_WEBUI_PORT
# - SPARK_WORKER_INSTANCES, to set the number of worker instances/processes to be spawned on every slave machine
#
# Finally, Spark also relies on the following variables, but these can be set
# on just the *master* (i.e. in your driver program), and will automatically

View file

@ -92,10 +92,10 @@ object SparkBuild extends Build {
*/
libraryDependencies ++= Seq(
"org.eclipse.jetty" % "jetty-server" % "7.5.3.v20111011",
"org.eclipse.jetty" % "jetty-server" % "7.6.8.v20121106",
"org.scalatest" %% "scalatest" % "1.9.1" % "test",
"org.scalacheck" %% "scalacheck" % "1.10.0" % "test",
"com.novocode" % "junit-interface" % "0.8" % "test",
"com.novocode" % "junit-interface" % "0.9" % "test",
"org.easymock" % "easymock" % "3.1" % "test"
),
parallelExecution := false,

View file

@ -1 +1 @@
sbt.version=0.11.3
sbt.version=0.12.2

View file

@ -4,11 +4,11 @@ resolvers += "Typesafe Repository" at "http://repo.typesafe.com/typesafe/release
resolvers += "Spray Repository" at "http://repo.spray.cc/"
addSbtPlugin("com.eed3si9n" % "sbt-assembly" % "0.8.3")
addSbtPlugin("com.eed3si9n" % "sbt-assembly" % "0.8.5")
addSbtPlugin("com.typesafe.sbteclipse" % "sbteclipse-plugin" % "2.1.0-RC1")
addSbtPlugin("com.typesafe.sbteclipse" % "sbteclipse-plugin" % "2.1.1")
addSbtPlugin("com.github.mpeltonen" % "sbt-idea" % "1.0.0")
addSbtPlugin("com.github.mpeltonen" % "sbt-idea" % "1.2.0")
addSbtPlugin("io.spray" %% "sbt-twirl" % "0.6.1")

2
run
View file

@ -1,6 +1,6 @@
#!/bin/bash
SCALA_VERSION=2.9.2
SCALA_VERSION=2.9.3
# Figure out where the Scala framework is installed
FWDIR="$(cd `dirname $0`; pwd)"

View file

@ -1,6 +1,6 @@
@echo off
set SCALA_VERSION=2.9.2
set SCALA_VERSION=2.9.3
rem Figure out where the Spark framework is installed
set FWDIR=%~dp0