mirror of
https://github.com/newnius/Dockerfiles.git
synced 2025-06-07 16:41:55 +00:00
update spark
This commit is contained in:
parent
5d78cbb18c
commit
922ddd57d1
@ -1,30 +0,0 @@
|
|||||||
FROM alpine:3.8
|
|
||||||
|
|
||||||
MAINTAINER Newnius <newnius.cn@gmail.com>
|
|
||||||
|
|
||||||
USER root
|
|
||||||
|
|
||||||
# Prerequisites
|
|
||||||
RUN apk add --no-cache openssh openssl openjdk8-jre rsync bash procps coreutils
|
|
||||||
|
|
||||||
ENV JAVA_HOME /usr/lib/jvm/java-1.8-openjdk
|
|
||||||
|
|
||||||
ENV PATH $PATH:$JAVA_HOME/bin
|
|
||||||
|
|
||||||
ENV SPARK_VER 1.6.0
|
|
||||||
|
|
||||||
RUN wget https://archive.apache.org/dist/spark/spark-$SPARK_VER/spark-$SPARK_VER-bin-hadoop2.6.tgz && \
|
|
||||||
tar -xvf spark-$SPARK_VER-bin-hadoop2.6.tgz -C /usr/local && \
|
|
||||||
rm spark-$SPARK_VER-bin-hadoop2.6.tgz
|
|
||||||
|
|
||||||
RUN ln -s /usr/local/spark-$SPARK_VER-bin-hadoop2.6 /usr/local/spark
|
|
||||||
|
|
||||||
ENV SPARK_HOME /usr/local/spark
|
|
||||||
|
|
||||||
ENV PATH $PATH:$SPARK_HOME/bin
|
|
||||||
|
|
||||||
ADD bootstrap.sh /etc/bootstrap.sh
|
|
||||||
|
|
||||||
WORKDIR /usr/local/spark
|
|
||||||
|
|
||||||
ENTRYPOINT ["/etc/bootstrap.sh"]
|
|
@ -1,64 +0,0 @@
|
|||||||
# Deploy Spark Cluster of standalone mode
|
|
||||||
|
|
||||||
## Master
|
|
||||||
|
|
||||||
```bash
|
|
||||||
docker service create \
|
|
||||||
--name spark-master \
|
|
||||||
--hostname spark-master \
|
|
||||||
--network swarm-net \
|
|
||||||
--replicas 1 \
|
|
||||||
--detach true \
|
|
||||||
--endpoint-mode dnsrr \
|
|
||||||
newnius/spark:1.6.0 master
|
|
||||||
```
|
|
||||||
|
|
||||||
## Slaves
|
|
||||||
|
|
||||||
```bash
|
|
||||||
docker service create \
|
|
||||||
--name spark-slave \
|
|
||||||
--network swarm-net \
|
|
||||||
--replicas 5 \
|
|
||||||
--detach true \
|
|
||||||
--endpoint-mode dnsrr \
|
|
||||||
newnius/spark:1.6.0 slave spark://spark-master:7077
|
|
||||||
```
|
|
||||||
|
|
||||||
## Validate installation
|
|
||||||
|
|
||||||
#### spark-submit PI
|
|
||||||
|
|
||||||
```bash
|
|
||||||
spark-submit \
|
|
||||||
--master spark://spark-master:7077 \
|
|
||||||
--deploy-mode cluster \
|
|
||||||
--class org.apache.spark.examples.JavaSparkPi \
|
|
||||||
./examples/jars/spark-examples_2.11-1.6.0.jar 100
|
|
||||||
```
|
|
||||||
|
|
||||||
#### spark-shell HDFS wordcount
|
|
||||||
|
|
||||||
Enter `spark-shell --master spark://spark-master:7077` to enter shell.
|
|
||||||
|
|
||||||
```shell
|
|
||||||
val lines = sc.textFile("hdfs://hadoop-master:8020/user/root/input")
|
|
||||||
|
|
||||||
val words = lines.flatMap(_.split("\\s+"))
|
|
||||||
|
|
||||||
val wc = words.map(word => (word, 1)).reduceByKey(_ + _)
|
|
||||||
|
|
||||||
wc.collect()
|
|
||||||
|
|
||||||
val cnt = words.map(word => 1).reduce(_ + _)
|
|
||||||
```
|
|
||||||
|
|
||||||
## Browse the web UI
|
|
||||||
|
|
||||||
You can expose the ports in the script, but I'd rather not since the slaves shoule occupy the same ports.
|
|
||||||
|
|
||||||
To access the web UI, deploy another (socks5) proxy to route the traffic.
|
|
||||||
|
|
||||||
If you don't one, try [newnius/docker-proxy](https://hub.docker.com/r/newnius/docker-proxy/), it is rather easy to use.
|
|
||||||
|
|
||||||
Visit [spark-master:8080](http://spark-master:8080) to view the cluster.
|
|
@ -1,11 +0,0 @@
|
|||||||
#! /bin/bash
|
|
||||||
|
|
||||||
if [[ $1 == "master" ]]; then
|
|
||||||
/usr/local/spark/sbin/start-master.sh
|
|
||||||
fi
|
|
||||||
|
|
||||||
if [[ $1 == "slave" ]]; then
|
|
||||||
/usr/local/spark/sbin/start-slave.sh $2
|
|
||||||
fi
|
|
||||||
|
|
||||||
while true; do sleep 1000; done
|
|
Loading…
Reference in New Issue
Block a user