大数据处理框架之Strom：DRPC

环境
　　虚拟机：VMware 10
　　Linux版本：CentOS-6.5-x86_64
　　客户端：Xshell4
　　FTP：Xftp4
　　jdk1.8
　　storm-0.9

一、DRPC
DRPC：Distributed remote procedure call，分布式远程过程调用，DRPC是通过一个DRPC服务端(DRPC server)来实现分布式 RPC 功能的。

Strom DRPC设计目的：
为了充分利用Storm的计算能力实现高密度的并行实时计算：Storm接收若干个数据流输入，数据在Topology当中运行完成，然后通过DRPC将结果进行输出。
DRPC Server负责接收RPC请求，并将该请求发送到Storm中运行的 Topology，等待接收 Topology 发送的处理结果，并将该结果返回给发送请求的客户端。（其实，从客户端的角度来说，DPRC 与普通的 RPC 调用并没有什么区别。）

二、strom DRPC处理流程
客户端通过向DRPC服务器发送待执行函数的名称以及该函数的参数来获取处理结果。实现该函数的拓扑使用一个DRPCSpout 从 DRPC 服务器中接收一个函数调用流。DRPC 服务器会为每个函数调用都标记了一个唯一的 id。随后拓扑会执行函数来计算结果，并在拓扑的最后使用一个名为 ReturnResults 的 bolt 连接到 DRPC 服务器，根据函数调用的 id 来将函数调用的结果返回。

三、定义DRPC拓扑
方法1：
通过LinearDRPCTopologyBuilder （该方法已过期，不建议使用）
该方法会自动为我们设定Spout、将结果返回给DRPC Server等，我们只需要将Topology实现

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you 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.
 */
package com.sxt.storm.drpc;

import backtype.storm.Config;
import backtype.storm.LocalCluster;
import backtype.storm.LocalDRPC;
import backtype.storm.StormSubmitter;
import backtype.storm.drpc.LinearDRPCTopologyBuilder;
import backtype.storm.topology.BasicOutputCollector;
import backtype.storm.topology.OutputFieldsDeclarer;
import backtype.storm.topology.base.BaseBasicBolt;
import backtype.storm.tuple.Fields;
import backtype.storm.tuple.Tuple;
import backtype.storm.tuple.Values;

/**
 * This topology is a basic example of doing distributed RPC on top of Storm. It
 * implements a function that appends a "!" to any string you send the DRPC
 * function.
 * <p/>
 * See https://github.com/nathanmarz/storm/wiki/Distributed-RPC for more
 * information on doing distributed RPC on top of Storm.
 */
public class BasicDRPCTopology {
    public static class ExclaimBolt extends BaseBasicBolt {
        @Override
        public void execute(Tuple tuple, BasicOutputCollector collector) {
            String input = tuple.getString(1);
            collector.emit(new Values(tuple.getValue(0), input + "!"));
        }

        @Override
        public void declareOutputFields(OutputFieldsDeclarer declarer) {
            declarer.declare(new Fields("id", "result"));
        }

    }

    public static void main(String[] args) throws Exception {
        //线性创建拓扑 参数为函数名或drpc服务名
        //LinearDRPCTopologyBuilder封装了spout和返回结果的bolt
        LinearDRPCTopologyBuilder builder = new LinearDRPCTopologyBuilder("exclamation");
        //按照顺序添加业务计算单元
        builder.addBolt(new ExclaimBolt(), 3);

        Config conf = new Config();
        if (args == null || args.length == 0) {
            LocalDRPC drpc = new LocalDRPC();
            LocalCluster cluster = new LocalCluster();
            cluster.submitTopology("drpc-demo", conf, builder.createLocalTopology(drpc));
            for (String word : new String[] { "hello", "goodbye" }) {
                //执行函数或服务
                System.err.println("Result for "" + word + "": " + drpc.execute("exclamation", word));
            }
            //关闭集群
            cluster.shutdown();
            //关闭drpc
            drpc.shutdown();
        } else {
            conf.setNumWorkers(3);
            StormSubmitter.submitTopologyWithProgressBar(args[0], conf, builder.createRemoteTopology());
            //StormSubmitter.submitTopology(args[0], conf, builder.createTopology());
        }
    }
}

方法2：
直接通过普通的拓扑构造方法TopologyBuilder来创建DRPC拓扑
需要手动设定好开始的DRPCSpout以及结束的ReturnResults

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you 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.
 */
package com.sxt.storm.drpc;

import backtype.storm.Config;
import backtype.storm.LocalCluster;
import backtype.storm.LocalDRPC;
import backtype.storm.drpc.DRPCSpout;
import backtype.storm.drpc.ReturnResults;
import backtype.storm.topology.BasicOutputCollector;
import backtype.storm.topology.OutputFieldsDeclarer;
import backtype.storm.topology.TopologyBuilder;
import backtype.storm.topology.base.BaseBasicBolt;
import backtype.storm.tuple.Fields;
import backtype.storm.tuple.Tuple;
import backtype.storm.tuple.Values;

public class ManualDRPC {
    public static class ExclamationBolt extends BaseBasicBolt {

        @Override
        public void declareOutputFields(OutputFieldsDeclarer declarer) {
            declarer.declare(new Fields("result", "return-info"));
        }

        @Override
        public void execute(Tuple tuple, BasicOutputCollector collector) {
            String arg = tuple.getString(0);
            Object retInfo = tuple.getValue(1);
            collector.emit(new Values(arg + "!!!", retInfo));
        }

    }

    public static void main(String[] args) {
        TopologyBuilder builder = new TopologyBuilder();
        LocalDRPC drpc = new LocalDRPC();
        //自己定义spout和返回结果bolt-ReturnResults
        DRPCSpout spout = new DRPCSpout("exclamation", drpc);
        builder.setSpout("drpc", spout);
        builder.setBolt("exclaim", new ExclamationBolt(), 3).shuffleGrouping("drpc");
        builder.setBolt("return", new ReturnResults(), 3).shuffleGrouping("exclaim");

        LocalCluster cluster = new LocalCluster();
        Config conf = new Config();
        cluster.submitTopology("exclaim", conf, builder.createTopology());

        System.err.println(drpc.execute("exclamation", "aaa"));
        System.err.println(drpc.execute("exclamation", "bbb"));

    }
}

四、运行模式
1、本地模式

参考上述方法2.

2、集群模式
(1)修改配置文件conf/storm.yaml
drpc.servers:
- "node1"

(2)启动DRPC Server
bin/storm drpc &

(3)提交jar
./storm jar drpc.jar com.sxt.storm.drpc.BasicDRPCTopology drpc

(4)客户端调用DRPC

package com.sxt.storm.drpc;
import org.apache.thrift7.TException;
import backtype.storm.generated.DRPCExecutionException;
import backtype.storm.utils.DRPCClient;

public class MyDRPCclient {

    public static void main(String[] args) {
        //连接DRPC服务端端口3772通信
        DRPCClient client = new DRPCClient("node1", 3772);
        try {
            String result = client.execute("exclamation", "11,22");
            System.out.println(result);
        } catch (TException e) {
            e.printStackTrace();
        } catch (DRPCExecutionException e) {
            e.printStackTrace();
        } 
    }
}

五、案例
Twitter 中某个URL的受众人数统计(这篇twitter到底有多少人看到过)

 

分析：
首先看一下这篇文章被哪些人看到
1、这篇文章的发送者；
2、发送者的粉丝；
其次，不同的发送者粉丝有重复的，需要去重
最后，累加在一起count

 

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you 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.
 */
package com.sxt.storm.drpc;

import java.util.Arrays;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;

import backtype.storm.Config;
import backtype.storm.LocalCluster;
import backtype.storm.LocalDRPC;
import backtype.storm.StormSubmitter;
import backtype.storm.coordination.BatchOutputCollector;
import backtype.storm.drpc.LinearDRPCTopologyBuilder;
import backtype.storm.task.TopologyContext;
import backtype.storm.topology.BasicOutputCollector;
import backtype.storm.topology.OutputFieldsDeclarer;
import backtype.storm.topology.base.BaseBasicBolt;
import backtype.storm.topology.base.BaseBatchBolt;
import backtype.storm.tuple.Fields;
import backtype.storm.tuple.Tuple;
import backtype.storm.tuple.Values;

/**
 * This is a good example of doing complex Distributed RPC on top of Storm. This
 * program creates a topology that can compute the reach for any URL on Twitter
 * in realtime by parallelizing the whole computation.
 * <p/>
 * Reach is the number of unique people exposed to a URL on Twitter. To compute
 * reach, you have to get all the people who tweeted the URL, get all the
 * followers of all those people, unique that set of followers, and then count
 * the unique set. It's an intense computation that can involve thousands of
 * database calls and tens of millions of follower records.
 * <p/>
 * This Storm topology does every piece of that computation in parallel, turning
 * what would be a computation that takes minutes on a single machine into one
 * that takes just a couple seconds.
 * <p/>
 * For the purposes of demonstration, this topology replaces the use of actual
 * DBs with in-memory hashmaps.
 * <p/>
 * See https://github.com/nathanmarz/storm/wiki/Distributed-RPC for more
 * information on Distributed RPC.
 */
public class ReachTopology {
    //发tweeter的信息库
    public static Map<String, List<String>> TWEETERS_DB = new HashMap<String, List<String>>() {
        {
            put("foo.com/blog/1", Arrays.asList("sally", "bob", "tim", "george", "nathan"));
            put("engineering.twitter.com/blog/5", Arrays.asList("adam", "david", "sally", "nathan"));
            put("tech.backtype.com/blog/123", Arrays.asList("tim", "mike", "john"));
        }
    };
    //粉丝信息库
    public static Map<String, List<String>> FOLLOWERS_DB = new HashMap<String, List<String>>() {
        {
            put("sally", Arrays.asList("bob", "tim", "alice", "adam", "jim", "chris", "jai"));
            put("bob", Arrays.asList("sally", "nathan", "jim", "mary", "david", "vivian"));
            put("tim", Arrays.asList("alex"));
            put("nathan", Arrays.asList("sally", "bob", "adam", "harry", "chris", "vivian", "emily", "jordan"));
            put("adam", Arrays.asList("david", "carissa"));
            put("mike", Arrays.asList("john", "bob"));
            put("john", Arrays.asList("alice", "nathan", "jim", "mike", "bob"));
        }
    };
    
    //获取发微博人
    public static class GetTweeters extends BaseBasicBolt {
        @Override
        public void execute(Tuple tuple, BasicOutputCollector collector) {
            //第一个参数是request-id
            Object id = tuple.getValue(0);
            //第二个value是客户端请求的参数 url
            String url = tuple.getString(1);
            //根据请求url 获取发微博的人
            List<String> tweeters = TWEETERS_DB.get(url);
            if (tweeters != null) {
                for (String tweeter : tweeters) {
                    //向后推送发微博的人-博主
                    collector.emit(new Values(id, tweeter));
                }
            }
        }

        @Override
        public void declareOutputFields(OutputFieldsDeclarer declarer) {
            declarer.declare(new Fields("id", "tweeter"));
        }
    }
    
    //获取粉丝
    public static class GetFollowers extends BaseBasicBolt {
        @Override
        public void execute(Tuple tuple, BasicOutputCollector collector) {
            //request-id
            Object id = tuple.getValue(0);
            //第二个参数是博主
            String tweeter = tuple.getString(1);
            //根据博主获取对应粉丝
            List<String> followers = FOLLOWERS_DB.get(tweeter);
            if (followers != null) {
                for (String follower : followers) {
                    //将粉丝信息推送出去
                    collector.emit(new Values(id, follower));
                }
            }
        }

        @Override
        public void declareOutputFields(OutputFieldsDeclarer declarer) {
            declarer.declare(new Fields("id", "follower"));
        }
    }

    public static class PartialUniquer extends BaseBatchBolt {
        BatchOutputCollector _collector;
        Object _id;
        Set<String> _followers = new HashSet<String>();

        @Override
        public void prepare(Map conf, TopologyContext context, BatchOutputCollector collector, Object id) {
            _collector = collector;
            _id = id;
        }

        @Override
        public void execute(Tuple tuple) {
            //接收粉丝信息放进Set  达到去重的目的
            _followers.add(tuple.getString(1));
        }

        @Override
        public void finishBatch() {
            //等到这一批数据统计完成之后将这一波统计信息发送出去
            _collector.emit(new Values(_id, _followers.size()));
        }

        @Override
        public void declareOutputFields(OutputFieldsDeclarer declarer) {
            declarer.declare(new Fields("id", "partial-count"));
        }
    }

    public static class CountAggregator extends BaseBatchBolt {
        BatchOutputCollector _collector;
        Object _id;
        int _count = 0;

        @Override
        public void prepare(Map conf, TopologyContext context, BatchOutputCollector collector, Object id) {
            _collector = collector;
            _id = id;
        }

        @Override
        public void execute(Tuple tuple) {
            //累加
            _count += tuple.getInteger(1);
        }

        @Override
        public void finishBatch() {
            //将统计结果推送出去
            _collector.emit(new Values(_id, _count));
        }

        @Override
        public void declareOutputFields(OutputFieldsDeclarer declarer) {
            declarer.declare(new Fields("id", "reach"));
        }
    }

    public static LinearDRPCTopologyBuilder construct() {
        LinearDRPCTopologyBuilder builder = new LinearDRPCTopologyBuilder("reach");
        builder.addBolt(new GetTweeters(), 4);
        builder.addBolt(new GetFollowers(), 12).shuffleGrouping();
        builder.addBolt(new PartialUniquer(), 6).fieldsGrouping(new Fields("id", "follower"));
        builder.addBolt(new CountAggregator(), 3).fieldsGrouping(new Fields("id"));
        return builder;
    }

    public static void main(String[] args) throws Exception {
        LinearDRPCTopologyBuilder builder = construct();

        Config conf = new Config();

        if (args == null || args.length == 0) {
            conf.setMaxTaskParallelism(3);
            LocalDRPC drpc = new LocalDRPC();
            LocalCluster cluster = new LocalCluster();
            cluster.submitTopology("reach-drpc", conf, builder.createLocalTopology(drpc));

            String[] urlsToTry = new String[] { "foo.com/blog/1", "engineering.twitter.com/blog/5", "notaurl.com" };
            for (String url : urlsToTry) {
                System.err.println("Reach of " + url + ":   " + drpc.execute("reach", url));
            }

            cluster.shutdown();
            drpc.shutdown();
        } else {
            conf.setNumWorkers(6);
            StormSubmitter.submitTopologyWithProgressBar(args[0], conf, builder.createRemoteTopology());
        }
    }
}

备注：在实际应用中，storm异步统计分析用的多一些，实时统计分析用spark多一些。