update spark

spark/2.2.1-yarn/Dockerfile

@@ -0,0 +1,26 @@
+FROM newnius/hadoop:2.8.1
+
+MAINTAINER Newnius <newnius.cn@gmail.com>
+
+RUN wget http://mirrors.ocf.berkeley.edu/apache/spark/spark-2.2.1/spark-2.2.1-bin-hadoop2.7.tgz && \
+	tar -xvf spark-2.2.1-bin-hadoop2.7.tgz -C /usr/local && \
+	rm spark-2.2.1-bin-hadoop2.7.tgz
+
+RUN ln -s /usr/local/spark-2.2.1-bin-hadoop2.7 /usr/local/spark
+
+ENV SPARK_HOME /usr/local/spark
+
+ENV PATH $PATH:$SPARK_HOME/bin
+
+# Default Conf Files
+ADD core-site.xml $HADOOP_HOME/etc/hadoop/core-site.xml
+ADD hdfs-site.xml $HADOOP_HOME/etc/hadoop/hdfs-site.xml
+ADD mapred-site.xml $HADOOP_HOME/etc/hadoop/mapred-site.xml
+ADD yarn-site.xml $HADOOP_HOME/etc/hadoop/yarn-site.xml
+ADD slaves $HADOOP_HOME/etc/hadoop/slaves
+
+ADD bootstrap.sh /etc/bootstrap-spark.sh
+
+WORKDIR /usr/local/spark
+
+CMD ["/etc/bootstrap-spark.sh", "-d"]

spark/2.2.1-yarn/README.md

@@ -2,6 +2,8 @@
 
 ## Create a spark cluster in swarm mode
 
+`--hostname` needs 1.13 or higher
+
 ```bash
 docker service create \
 --name spark-master \

spark/2.2.1-yarn/bootstrap.sh

@@ -0,0 +1,6 @@
+#! /bin/bash
+# replace config
+
+cp /mnt/config/spark/* $SPARK_HOME/conf
+
+bash -c "/etc/bootstrap.sh -d"

spark/2.2.1/Dockerfile

@@ -1,26 +1,30 @@
-FROM newnius/hadoop:2.8.1
+FROM alpine:3.8
 
 MAINTAINER Newnius <newnius.cn@gmail.com>
 
-RUN wget http://mirrors.ocf.berkeley.edu/apache/spark/spark-2.2.1/spark-2.2.1-bin-hadoop2.7.tgz && \
+USER root
-	tar -xvf spark-2.2.1-bin-hadoop2.7.tgz -C /usr/local && \
-	rm spark-2.2.1-bin-hadoop2.7.tgz
 
-RUN ln -s /usr/local/spark-2.2.1-bin-hadoop2.7 /usr/local/spark
+# 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 2.2.1
+
+RUN wget https://archive.apache.org/dist/spark/spark-$SPARK_VER/spark-$SPARK_VER-bin-hadoop2.7.tgz && \
+	tar -xvf spark-$SPARK_VER-bin-hadoop2.7.tgz -C /usr/local && \
+	rm spark-$SPARK_VER-bin-hadoop2.7.tgz
+
+RUN ln -s /usr/local/spark-$SPARK_VER-bin-hadoop2.7 /usr/local/spark
 
 ENV SPARK_HOME /usr/local/spark
 
 ENV PATH $PATH:$SPARK_HOME/bin
 
-# Default Conf Files
+ADD bootstrap.sh /etc/bootstrap.sh
-ADD core-site.xml $HADOOP_HOME/etc/hadoop/core-site.xml
-ADD hdfs-site.xml $HADOOP_HOME/etc/hadoop/hdfs-site.xml
-ADD mapred-site.xml $HADOOP_HOME/etc/hadoop/mapred-site.xml
-ADD yarn-site.xml $HADOOP_HOME/etc/hadoop/yarn-site.xml
-ADD slaves $HADOOP_HOME/etc/hadoop/slaves
-
-ADD bootstrap.sh /etc/bootstrap-spark.sh
 
 WORKDIR /usr/local/spark
 
-CMD ["/etc/bootstrap-spark.sh", "-d"]
+ENTRYPOINT ["/etc/bootstrap.sh"]

spark/2.2.1/README.md

@@ -1,93 +1,64 @@
-# Spark on yarn
+# Deploy Spark Cluster of standalone mode
 
-## Create a spark cluster in swarm mode
+## Master
-
-`--hostname` needs 1.13 or higher
 
 ```bash
 docker service create \
---name spark-master \
+	--name spark-master \
---hostname spark-master \
+	--hostname spark-master \
---detach true \
+	--network swarm-net \
---network swarm-net \
+	--replicas 1 \
---replicas 1 \
+	--detach true \
---endpoint-mode dnsrr \
+	--endpoint-mode dnsrr \
-newnius/spark:2.2.1
+	newnius/spark:2.2.1 master
 ```
 
+## Slaves
+
 ```bash
 docker service create \
---name spark-slave1 \
+	--name spark-slave \
---hostname spark-slave1 \
+	--network swarm-net \
---detach true \
+	--replicas 5 \
---network swarm-net \
+	--detach true \
---replicas 1 \
+	--endpoint-mode dnsrr \
---endpoint-mode dnsrr \
+	newnius/spark:2.2.1 slave spark://spark-master:7077
-newnius/spark:2.2.1
 ```
 
-```bash
+## Validate installation
-docker service create \
---name spark-slave2 \
---hostname spark-slave2 \
---detach true \
---network swarm-net \
---replicas 1 \
---endpoint-mode dnsrr \
-newnius/spark:2.2.1
-```
 
-## Init && Test
+#### spark-submit PI
 
-In the first deploy, format hdfs
-
-### Stop HDFS (in master)
-```bash
-sbin/stop-dfs.sh
-```
-
-### Format HDFS (in master)
-```
-bin/hadoop namenode -format
-```
-
-### Start HDFS (in master)
-```bash
-sbin/start-dfs.sh
-```
-
-### Run Hello World
 ```bash
 spark-submit \
-	--master yarn \
+	--master spark://spark-master:7077 \
 	--deploy-mode cluster \
 	--class org.apache.spark.examples.JavaSparkPi \
 	./examples/jars/spark-examples_2.11-2.2.1.jar 100
 ```
 
-### UI
+#### spark-shell HDFS wordcount
 
-YARN: spark-master:8088
+Enter `spark-shell --master spark://spark-master:7077` to enter shell.
 
-HDFS: spark-master:50070
+```shell
+val lines = sc.textFile("hdfs://hadoop-master:8020/user/root/input")
 
-_Proxy needed, e.g. [newnius/docker-proxy](https://hub.docker.com/r/newnius/docker-proxy/)_
+val words = lines.flatMap(_.split("\\s+"))
 
-## customized config
+val wc = words.map(word => (word, 1)).reduceByKey(_ + _)
 
-```bash
+wc.collect()
-docker service create \
+
---name spark-master \
+val cnt = words.map(word => 1).reduce(_ + _)
---hostname spark-master \
---detach=true \
---network swarm-net \
---replicas 1 \
---mount type=bind,source=/mnt/data/spark/hdfs/master,target=/tmp/hadoop-root \
---mount type=bind,source=/mnt/data/spark/logs/master,target=/usr/local/hadoop/logs \
---mount type=bind,source=/mnt/data/spark/config/hadoop,target=/mnt/config/hadoop \
---mount type=bind,source=/mnt/data/spark/config/spark,target=/mnt/config/spark \
---endpoint-mode dnsrr \
-newnius/spark:2.2.1
 ```
 
-You dont't need to put all files in dir, only add files to be replaced.
+## 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.

spark/2.2.1/bootstrap.sh

@@ -1,6 +1,11 @@
 #! /bin/bash
-# replace config
 
-cp /mnt/config/spark/* $SPARK_HOME/conf
+if [[ $1 == "master" ]]; then
+	/usr/local/spark/sbin/start-master.sh
+fi
 
-bash -c "/etc/bootstrap.sh -d"
+if [[ $1 == "slave" ]]; then
+	/usr/local/spark/sbin/start-slave.sh $2
+fi
+
+while true; do sleep 1000; done

spark/test/Dockerfile

@@ -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 2.2.1
-
-RUN wget https://archive.apache.org/dist/spark/spark-$SPARK_VER/spark-$SPARK_VER-bin-hadoop2.7.tgz && \
-	tar -xvf spark-$SPARK_VER-bin-hadoop2.7.tgz -C /usr/local && \
-	rm spark-$SPARK_VER-bin-hadoop2.7.tgz
-
-RUN ln -s /usr/local/spark-$SPARK_VER-bin-hadoop2.7 /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"]

spark/test/bootstrap.sh

@@ -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