aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJosh Rosen <joshrosen@eecs.berkeley.edu>2012-12-14 01:19:00 +0000
committerJosh Rosen <joshrosen@eecs.berkeley.edu>2012-12-14 01:20:00 +0000
commit1948f46093d2934284daeae06cc2891541c39e68 (patch)
tree95a73168c599effef49be72eea938837460772d2
parent8fd374dfb2dad636b119954940a11b332678e098 (diff)
downloadspark-1948f46093d2934284daeae06cc2891541c39e68.tar.gz
spark-1948f46093d2934284daeae06cc2891541c39e68.tar.bz2
spark-1948f46093d2934284daeae06cc2891541c39e68.zip
Use spark-env.sh to configure standalone master. See SPARK-638.
Also fixed a typo in the standalone mode documentation.
-rwxr-xr-xbin/start-all.sh4
-rwxr-xr-xbin/start-master.sh19
-rwxr-xr-xbin/start-slave.sh1
-rw-r--r--docs/spark-standalone.md2
4 files changed, 20 insertions, 6 deletions
diff --git a/bin/start-all.sh b/bin/start-all.sh
index 9bd6c50654..b9891ad2f6 100755
--- a/bin/start-all.sh
+++ b/bin/start-all.sh
@@ -11,7 +11,7 @@ bin=`cd "$bin"; pwd`
. "$bin/spark-config.sh"
# Start Master
-"$bin"/start-master.sh --config $SPARK_CONF_DIR
+"$bin"/start-master.sh
# Start Workers
-"$bin"/start-slaves.sh --config $SPARK_CONF_DIR \ No newline at end of file
+"$bin"/start-slaves.sh
diff --git a/bin/start-master.sh b/bin/start-master.sh
index ad19d48331..a901b1c260 100755
--- a/bin/start-master.sh
+++ b/bin/start-master.sh
@@ -7,13 +7,28 @@ bin=`cd "$bin"; pwd`
. "$bin/spark-config.sh"
+if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then
+ . "${SPARK_CONF_DIR}/spark-env.sh"
+fi
+
+if [ "$SPARK_MASTER_PORT" = "" ]; then
+ SPARK_MASTER_PORT=7077
+fi
+
+if [ "$SPARK_MASTER_IP" = "" ]; then
+ SPARK_MASTER_IP=`hostname`
+fi
+
+if [ "$SPARK_MASTER_WEBUI_PORT" = "" ]; then
+ SPARK_MASTER_WEBUI_PORT=8080
+fi
+
# Set SPARK_PUBLIC_DNS so the master report the correct webUI address to the slaves
if [ "$SPARK_PUBLIC_DNS" = "" ]; then
# If we appear to be running on EC2, use the public address by default:
if [[ `hostname` == *ec2.internal ]]; then
- echo "RUNNING ON EC2"
export SPARK_PUBLIC_DNS=`wget -q -O - http://instance-data.ec2.internal/latest/meta-data/public-hostname`
fi
fi
-"$bin"/spark-daemon.sh start spark.deploy.master.Master
+"$bin"/spark-daemon.sh start spark.deploy.master.Master --ip $SPARK_MASTER_IP --port $SPARK_MASTER_PORT --webui-port $SPARK_MASTER_WEBUI_PORT
diff --git a/bin/start-slave.sh b/bin/start-slave.sh
index 10cce9c17b..45a0cf7a6b 100755
--- a/bin/start-slave.sh
+++ b/bin/start-slave.sh
@@ -7,7 +7,6 @@ bin=`cd "$bin"; pwd`
if [ "$SPARK_PUBLIC_DNS" = "" ]; then
# If we appear to be running on EC2, use the public address by default:
if [[ `hostname` == *ec2.internal ]]; then
- echo "RUNNING ON EC2"
export SPARK_PUBLIC_DNS=`wget -q -O - http://instance-data.ec2.internal/latest/meta-data/public-hostname`
fi
fi
diff --git a/docs/spark-standalone.md b/docs/spark-standalone.md
index ae630a0371..e0ba7c35cb 100644
--- a/docs/spark-standalone.md
+++ b/docs/spark-standalone.md
@@ -68,7 +68,7 @@ Finally, the following configuration options can be passed to the master and wor
To launch a Spark standalone cluster with the deploy scripts, you need to set up two files, `conf/spark-env.sh` and `conf/slaves`. The `conf/spark-env.sh` file lets you specify global settings for the master and slave instances, such as memory, or port numbers to bind to, while `conf/slaves` is a list of slave nodes. The system requires that all the slave machines have the same configuration files, so *copy these files to each machine*.
-In `conf/spark-env.sh`, you can set the following parameters, in addition to the [standard Spark configuration settongs](configuration.html):
+In `conf/spark-env.sh`, you can set the following parameters, in addition to the [standard Spark configuration settings](configuration.html):
<table class="table">
<tr><th style="width:21%">Environment Variable</th><th>Meaning</th></tr>