linux上运行spark完成图计算引擎的demo（java代码）

1、安装spark和hadoop的配置

自行百度

2、编写代码

@Slf4j
public class HelloGraphx {
    public static void main(String[] args) {
        // TODO Auto-generated method stub
        SparkConf conf = new SparkConf()
                .setAppName("Graphx Learning")
                .setMaster("spark://xxx:7077")
                .set("spark.driver.host","xxx.xxx.xxx.xxx");
                //xxx 修改你的ip

        JavaSparkContext sc = new JavaSparkContext(conf);
        ClassTag<String> stringTag = scala.reflect.ClassTag$.MODULE$.apply(String.class);
        List<Edge<String>> edges = new ArrayList<>();
        edges.add(new Edge<String>(1L, 2L, "Friend1"));
        edges.add(new Edge<String>(1L, 4L, "Friend2"));
        edges.add(new Edge<String>(2L, 4L, "Friend3"));
        edges.add(new Edge<String>(3L, 1L, "Friend4"));
        edges.add(new Edge<String>(3L, 4L, "Friend5"));
        JavaRDD<Edge<String>> edgesRDD = sc.parallelize(edges);
        Graph<String, String> graph = Graph.
                         fromEdges(edgesRDD.rdd(), "", StorageLevel.MEMORY_ONLY(),
                        StorageLevel.MEMORY_ONLY(), stringTag, stringTag);
        List<Edge<String>> e = graph.edges().toJavaRDD().collect();
        System.out.println(e);
        log.info("当前执行完成：{},执行的graph：{}",e,graph);
    }
}

3、打jar包，放到hdfs上面

4、运行

进入spark的bin目录执行
./spark-submit --class com.xxx.graphx.HelloGraphx --master spark://xxx.xx.xxx.xxx:7077 /root/hadoop-1.0-SNAPSHOT.jar

5、执行结果