一：介绍
1.说明
Storm里面引入DRPC主要是利用storm的实时计算能力来并行化CPU intensive的计算。DRPC的storm topology以函数的参数流作为输入，而把这些函数调用的返回值作为topology的输出流。
2.工作机制
Distributed RPC是由一个”DPRC Server”协调的(storm自带了一个实现)DRPC服务器协调
1) 接收一个RPC请求。
2) 发送请求到storm topology
3) 从storm topology接收结果。
4) 把结果发回给等待的客户端。从客户端的角度来看一个DRPC调用跟一个普通的RPC调用没有任何区别。
3.工作流程
客户端给DRPC服务器发送要执行的方法的名字，以及这个方法的参数。
实现了这个函数的topology使用 DRPCSpout 从DRPC服务器接收函数调用流。
每个函数调用被DRPC服务器标记了一个唯一的id。 这个topology然后计算结果，在topology的最后一个叫做 ReturnResults 的bolt会连接到DRPC服务器，并且把这个调用的结果发送给DRPC服务器(通过那个唯一的id标识)。DRPC服务器用那个唯一id来跟等待的客户端匹配上，唤醒这个客户端并且把结果发送给它。
二：本地DRPC
1.主驱动类
package com.jun.tridentWithHbase; import backtype.storm.Config;
import backtype.storm.LocalCluster;
import backtype.storm.LocalDRPC;
import backtype.storm.StormSubmitter;
import backtype.storm.generated.AlreadyAliveException;
import backtype.storm.generated.InvalidTopologyException;
import backtype.storm.tuple.Fields;
import backtype.storm.tuple.Values;
import org.apache.storm.hbase.trident.state.HBaseMapState;
import storm.trident.Stream;
import storm.trident.TridentState;
import storm.trident.TridentTopology;
import storm.trident.operation.builtin.Count;
import storm.trident.operation.builtin.MapGet;
import storm.trident.operation.builtin.Sum;
import storm.trident.state.OpaqueValue;
import storm.trident.state.StateFactory;
import storm.trident.testing.FixedBatchSpout;
import storm.trident.testing.MemoryMapState; public class TridentDemo {
public static void main(String[] args) throws AlreadyAliveException, InvalidTopologyException {
TridentTopology tridentTopology=new TridentTopology();
//模拟数据
Fields field=new Fields("log","flag");
FixedBatchSpout spout=new FixedBatchSpout(field,5,
new Values("168.214.187.214 - - [1481953616092] \"GET /view.php HTTP/1.1\" 200 0 \"http://cn.bing.com/search?q=spark mllib\" \"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1\" \"-\"","A"),
new Values("168.187.202.202 - - [1481953537038] \"GET /IBEIfeng.gif?order_id=1063&orderTime=1481953537038&memberId=4000012340500607&productInfos=10005-2099.48-B-1|10004-1886.62-A-2|10001-961.99-A-1&orderAmt=6834.70 HTTP/1.1\" 200 0 \"-\" \"Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2;Tident/6.0)\" \"-\"","A"),
new Values("61.30.167.187 - - [1481953539039] \"GET /IBEIfeng.gif?order_id=1064&orderTime=1481953539039&memberId=4000930409959999&productInfos=10007-3329.13-B-1|10009-2607.71-B-1|10002-390.62-A-1|10006-411.00-B-2&orderAmt=7149.46 HTTP/1.1\" 200 0 \"-\" \"Mozilla/5.0 (Linux; Android 4.2.1; Galaxy Nexus Build/JOP40D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Mobile Safari/535.19\" \"-\"","A"),
new Values("30.29.132.190 - - [1481953544042] \"GET /IBEIfeng.gif?order_id=1065&orderTime=1481953544043&memberId=1234568970080798&productInfos=10005-2099.48-B-1|10001-3242.40-C-2|10006-411.00-B-1&orderAmt=8995.28 HTTP/1.1\" 200 0 \"-\" \"Mozilla/5.0 (iPhone; CPU iPhone OS 7_)_3 like Mac OS X) AppleWebKit/537.51.1 (KHTML, like Gecko) Version/7.0 Mobile/11B511 Safari/9537.53\" \"-\"","B"),
new Values("222.190.187.201 - - [1481953578068] \"GET /IBEIfeng.gif?order_id=1066&orderTime=1481953578068&memberId=3488586887970809&productInfos=10005-2099.48-B-1|10001-2774.16-C-2&orderAmt=7647.80 HTTP/1.1\" 200 0 \"-\" \"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1\" \"-\"","B"),
new Values("72.202.43.53 - - [1481953579069] \"GET /IBEIfeng.gif?order_id=1067&orderTime=1481953579069&memberId=2084859896989877&productInfos=10007-3329.13-B-1|10001-961.99-A-2&orderAmt=5253.10 HTTP/1.1\" 200 0 \"-\" \"Mozilla/5.0 (Linux; Android 4.2.1; Galaxy Nexus Build/JOP40D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Mobile Safari/535.19\" \"-\"","B")
);
//多次循环
spout.setCycle(true);
//流处理
Stream stream=tridentTopology.newStream("orderAnalyse",spout)
//过滤
.each(new Fields("log"),new ValidLogFilter())
//解析
.each(new Fields("log"), new LogParserFunction(),new Fields("orderId","orderTime","orderAmtStr","memberId"))
//投影
.project(new Fields("orderId","orderTime","orderAmtStr","memberId"))
//时间解析
.each(new Fields("orderTime"),new DateTransFormerFunction(),new Fields("day","hour","minter"))
;
//分流
//1.基于minter统计订单数量，分组统计
TridentState state=stream.groupBy(new Fields("minter"))
//全局聚合，使用内存存储状态信息
.persistentAggregate(new MemoryMapState.Factory(),new Count(),new Fields("orderNumByMinter"));
// state.newValuesStream().each(new Fields("minter","orderNumByMinter"),new PrintFilter()); //2.另一个流,基于分钟的订单金额，局部聚合
Stream partitionStream=stream.each(new Fields("orderAmtStr"),new TransforAmtToDoubleFunction(),new Fields("orderAmt"))
.groupBy(new Fields("minter"))
//局部聚合
.chainedAgg() //聚合链
.partitionAggregate(new Fields("orderAmt"),new LocalSum(),new Fields("orderAmtSumOfLocal"))
.chainEnd(); //聚合链 //做一次全局聚合
TridentState partitionState=partitionStream.groupBy(new Fields("minter"))
//全局聚合
.persistentAggregate(new MemoryMapState.Factory(),new Fields("orderAmtSumOfLocal"),new Sum(),new Fields("totalOrderAmt"));
partitionState.newValuesStream().each(new Fields("minter","totalOrderAmt"),new PrintFilter()); //提交
Config config=new Config();
if(args==null || args.length<=0){
//应该是构建一个DRPC的服务器
LocalDRPC localDRPC=new LocalDRPC();
tridentTopology.newDRPCStream("orderDataServer",localDRPC)
//参数处理
.each(new Fields("args"),new RequestParamsParserFunction(),new Fields("date"))
//查询，重要的参数是上面的partitionState
.stateQuery(partitionState,new Fields("date"),new MapGet(),new Fields("totalAmtByMinter"))
//投影
.project(new Fields("date","totalAmtByMinter"));
//提交任务
LocalCluster localCluster=new LocalCluster();
localCluster.submitTopology("tridentDemo",config,tridentTopology.build());
//获取值
String jsonResult=localDRPC.execute("orderDataServer","201612171345 201612171345");
System.out.println("***"+jsonResult+"***"); }else {
config.setNumWorkers(2);
StormSubmitter.submitTopology(args[0],config,tridentTopology.build());
}
}
}
2.请求参数处理类
package com.jun.tridentWithHbase; import backtype.storm.tuple.Values;
import storm.trident.operation.Function;
import storm.trident.operation.TridentCollector;
import storm.trident.operation.TridentOperationContext;
import storm.trident.tuple.TridentTuple; import java.util.Map; public class RequestParamsParserFunction implements Function {
@Override
public void execute(TridentTuple tridentTuple, TridentCollector tridentCollector) {
String parameters=tridentTuple.getStringByField("args");
String[] params=parameters.split(" ");
for (String param:params){
tridentCollector.emit(new Values(param));
}
} @Override
public void prepare(Map map, TridentOperationContext tridentOperationContext) { } @Override
public void cleanup() { }
}
3.效果
三：集群模式的DRPC
1.主驱动类
config.setNumWorkers(2);
//集群上构建DRPC服务器
tridentTopology.newDRPCStream("orderDataServer")
//参数处理
.each(new Fields("args"),new RequestParamsParserFunction(),new Fields("date"))
//查询，重要的参数是上面的partitionState
.stateQuery(partitionState,new Fields("date"),new MapGet(),new Fields("totalAmtByMinter"))
//投影
.project(new Fields("date","totalAmtByMinter"));
StormSubmitter.submitTopology(args[0],config,tridentTopology.build());
2.配置DRPC服务和端口
3.启动storm
4.启动Drpc进程
在drpc.servers参数所指定的服务器上。
命令：nohup bin/storm drpc >>/dev/null 2>&1 &
查看端口是否正常打开：netstat -tlnup | grep 3772
5.将jar包提交到集群上
6.编写客户端
package com.jun.tridentWithKafka; import backtype.storm.generated.DRPCExecutionException;
import backtype.storm.utils.DRPCClient;
import org.apache.thrift7.TException; public class DrpcClientDemo {
public static void main(String[] args) {
DRPCClient drpcClient=new DRPCClient("linux-hadoop01.ibeifeng.com",3772);
try {
String jsonResult=drpcClient.execute("orderDataServer","201612171345 201612171345");
System.out.println("==="+jsonResult+"===");
} catch (TException e) {
e.printStackTrace();
} catch (DRPCExecutionException e) {
e.printStackTrace();
}
}
}