Merge pull request #11047 from gurvindersingh/master
modified spark example to use kubectl exec to interact with cluster a…
This commit is contained in:
Brendan Burns
commit
df5553ce9e
|
|
@ -317,6 +317,7 @@ func TestExampleObjectSchemas(t *testing.T) {
|
||||||
"spark-master-service": &api.Service{},
|
"spark-master-service": &api.Service{},
|
||||||
"spark-master": &api.Pod{},
|
"spark-master": &api.Pod{},
|
||||||
"spark-worker-controller": &api.ReplicationController{},
|
"spark-worker-controller": &api.ReplicationController{},
|
||||||
|
"spark-driver": &api.Pod{},
|
||||||
},
|
},
|
||||||
"../examples/storm": {
|
"../examples/storm": {
|
||||||
"storm-nimbus-service": &api.Service{},
|
"storm-nimbus-service": &api.Service{},
|
||||||
|
|
|
||||||
|
|
@ -144,44 +144,35 @@ $ kubectl logs spark-master
|
||||||
15/06/26 14:15:55 INFO Master: Registering worker 10.244.0.19:60970 with 1 cores, 2.6 GB RAM
|
15/06/26 14:15:55 INFO Master: Registering worker 10.244.0.19:60970 with 1 cores, 2.6 GB RAM
|
||||||
```
|
```
|
||||||
|
|
||||||
## Step Three: Do something with the cluster
|
## Step Three: Start your Spark driver to launch jobs on your Spark cluster
|
||||||
|
|
||||||
Get the address and port of the Master service.
|
The Spark driver is used to launch jobs into Spark cluster. You can read more about it in
|
||||||
|
[Spark architecture](http://spark.apache.org/docs/latest/cluster-overview.html).
|
||||||
|
|
||||||
```sh
|
```shell
|
||||||
$ kubectl get service spark-master
|
$ kubectl create -f examples/spark/spark-driver.json
|
||||||
NAME LABELS SELECTOR IP(S) PORT(S)
|
|
||||||
spark-master name=spark-master name=spark-master 10.0.204.187 7077/TCP
|
|
||||||
```
|
```
|
||||||
|
|
||||||
SSH to one of your cluster nodes. On GCE/GKE you can either use [Developers Console](https://console.developers.google.com)
|
The Spark driver needs the Master service to be running.
|
||||||
(more details [here](https://cloud.google.com/compute/docs/ssh-in-browser))
|
|
||||||
or run `gcloud compute ssh <name>` where the name can be taken from `kubectl get nodes`
|
|
||||||
(more details [here](https://cloud.google.com/compute/docs/gcloud-compute/#connecting)).
|
|
||||||
|
|
||||||
```
|
### Check to see if the driver is running
|
||||||
$ kubectl get nodes
|
|
||||||
NAME LABELS STATUS
|
|
||||||
kubernetes-minion-5jvu kubernetes.io/hostname=kubernetes-minion-5jvu Ready
|
|
||||||
kubernetes-minion-6fbi kubernetes.io/hostname=kubernetes-minion-6fbi Ready
|
|
||||||
kubernetes-minion-8y2v kubernetes.io/hostname=kubernetes-minion-8y2v Ready
|
|
||||||
kubernetes-minion-h0tr kubernetes.io/hostname=kubernetes-minion-h0tr Ready
|
|
||||||
|
|
||||||
$ gcloud compute ssh kubernetes-minion-5jvu --zone=us-central1-b
|
```shell
|
||||||
Linux kubernetes-minion-5jvu 3.16.0-0.bpo.4-amd64 #1 SMP Debian 3.16.7-ckt9-3~deb8u1~bpo70+1 (2015-04-27) x86_64
|
$ kubectl get pods
|
||||||
|
NAME READY REASON RESTARTS AGE
|
||||||
=== GCE Kubernetes node setup complete ===
|
[...]
|
||||||
|
spark-master 1/1 Running 0 14m
|
||||||
me@kubernetes-minion-5jvu:~$
|
spark-driver 1/1 Running 0 10m
|
||||||
```
|
```
|
||||||
|
|
||||||
Once logged in run spark-base image. Inside of the image there is a script
|
## Step Four: Do something with the cluster
|
||||||
that sets up the environment based on the provided IP and port of the Master.
|
|
||||||
|
Use the kubectl exec to connect to Spark driver
|
||||||
|
|
||||||
```
|
```
|
||||||
cluster-node $ sudo docker run -it gcr.io/google_containers/spark-base
|
$ kubectl exec spark-driver -it bash
|
||||||
root@f12a6fec45ce:/# . /setup_client.sh 10.0.204.187 7077
|
root@spark-driver:/#
|
||||||
root@f12a6fec45ce:/# pyspark
|
root@spark-driver:/# pyspark
|
||||||
Python 2.7.9 (default, Mar 1 2015, 12:57:24)
|
Python 2.7.9 (default, Mar 1 2015, 12:57:24)
|
||||||
[GCC 4.9.2] on linux2
|
[GCC 4.9.2] on linux2
|
||||||
Type "help", "copyright", "credits" or "license" for more information.
|
Type "help", "copyright", "credits" or "license" for more information.
|
||||||
|
|
@ -201,7 +192,7 @@ SparkContext available as sc, HiveContext available as sqlContext.
|
||||||
|
|
||||||
## Result
|
## Result
|
||||||
|
|
||||||
You now have services, replication controllers, and pods for the Spark master and Spark workers.
|
You now have services, replication controllers, and pods for the Spark master , Spark driver and Spark workers.
|
||||||
You can take this example to the next step and start using the Apache Spark cluster
|
You can take this example to the next step and start using the Apache Spark cluster
|
||||||
you just created, see [Spark documentation](https://spark.apache.org/documentation.html)
|
you just created, see [Spark documentation](https://spark.apache.org/documentation.html)
|
||||||
for more information.
|
for more information.
|
||||||
|
|
@ -216,6 +207,8 @@ Make sure the Master Pod is running (use: ```kubectl get pods```).
|
||||||
|
|
||||||
```kubectl create -f spark-worker-controller.json```
|
```kubectl create -f spark-worker-controller.json```
|
||||||
|
|
||||||
|
```kubectl create -f spark-driver.json```
|
||||||
|
|
||||||
|
|
||||||
<!-- BEGIN MUNGE: GENERATED_ANALYTICS -->
|
<!-- BEGIN MUNGE: GENERATED_ANALYTICS -->
|
||||||
[]()
|
[]()
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,4 @@
|
||||||
|
FROM gcr.io/google_containers/spark-base
|
||||||
|
ADD start.sh /start.sh
|
||||||
|
ADD log4j.properties /opt/spark/conf/log4j.properties
|
||||||
|
CMD ["/start.sh"]
|
||||||
|
|
@ -0,0 +1,37 @@
|
||||||
|
<!-- BEGIN MUNGE: UNVERSIONED_WARNING -->
|
||||||
|
|
||||||
|
<!-- BEGIN STRIP_FOR_RELEASE -->
|
||||||
|
|
||||||
|
<img src="http://kubernetes.io/img/warning.png" alt="WARNING"
|
||||||
|
width="25" height="25">
|
||||||
|
<img src="http://kubernetes.io/img/warning.png" alt="WARNING"
|
||||||
|
width="25" height="25">
|
||||||
|
<img src="http://kubernetes.io/img/warning.png" alt="WARNING"
|
||||||
|
width="25" height="25">
|
||||||
|
<img src="http://kubernetes.io/img/warning.png" alt="WARNING"
|
||||||
|
width="25" height="25">
|
||||||
|
<img src="http://kubernetes.io/img/warning.png" alt="WARNING"
|
||||||
|
width="25" height="25">
|
||||||
|
|
||||||
|
<h2>PLEASE NOTE: This document applies to the HEAD of the source tree</h2>
|
||||||
|
|
||||||
|
If you are using a released version of Kubernetes, you should
|
||||||
|
refer to the docs that go with that version.
|
||||||
|
|
||||||
|
<strong>
|
||||||
|
The latest 1.0.x release of this document can be found
|
||||||
|
[here](http://releases.k8s.io/release-1.0/examples/spark/images/driver/README.md).
|
||||||
|
|
||||||
|
Documentation for other releases can be found at
|
||||||
|
[releases.k8s.io](http://releases.k8s.io).
|
||||||
|
</strong>
|
||||||
|
--
|
||||||
|
|
||||||
|
<!-- END STRIP_FOR_RELEASE -->
|
||||||
|
|
||||||
|
<!-- END MUNGE: UNVERSIONED_WARNING -->
|
||||||
|
|
||||||
|
|
||||||
|
<!-- BEGIN MUNGE: GENERATED_ANALYTICS -->
|
||||||
|
[]()
|
||||||
|
<!-- END MUNGE: GENERATED_ANALYTICS -->
|
||||||
|
|
@ -0,0 +1,23 @@
|
||||||
|
#!/bin/bash
|
||||||
|
|
||||||
|
# Copyright 2015 The Kubernetes Authors All rights reserved.
|
||||||
|
#
|
||||||
|
# Licensed 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.
|
||||||
|
|
||||||
|
echo "$SPARK_MASTER_SERVICE_HOST spark-master" >> /etc/hosts
|
||||||
|
echo "SPARK_LOCAL_HOSTNAME=$(hostname -i)" >> /opt/spark/conf/spark-env.sh
|
||||||
|
echo "MASTER=spark://spark-master:$SPARK_MASTER_SERVICE_PORT" >> /opt/spark/conf/spark-env.sh
|
||||||
|
|
||||||
|
while true; do
|
||||||
|
sleep 100
|
||||||
|
done
|
||||||
|
|
@ -0,0 +1,23 @@
|
||||||
|
{
|
||||||
|
"kind": "Pod",
|
||||||
|
"apiVersion": "v1",
|
||||||
|
"metadata": {
|
||||||
|
"name": "spark-driver",
|
||||||
|
"labels": {
|
||||||
|
"name": "spark-driver"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"spec": {
|
||||||
|
"containers": [
|
||||||
|
{
|
||||||
|
"name": "spark-driver",
|
||||||
|
"image": "gurvin/spark-driver",
|
||||||
|
"resources": {
|
||||||
|
"limits": {
|
||||||
|
"cpu": "100m"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
}
|
||||||
Loading…
Reference in New Issue