Hbase Endpoint Coprocessor

Endpoint Coprocessor比observer Coprocessor要复杂很多，这里不做具体解释了，大家慢慢看代码仔细琢磨。 另外此篇文章代码是从HBASE官方文档拷贝过来的。但是官方文档实际也没有给出很详细的解释。

1) 定义proto文件

// 定义常用选项option java_package = "com.isesol.mapreduce";   //指定生成Java代码的包名option java_outer_classname = "Sum";    //指定生成Java代码的外部类名称option java_generic_services = true;    //基于服务定义产生抽象服务代码option optimize_for = SPEED;    //指定优化级别// 定义请求包message SumRequest {        required string family = 1;     //列族        required string column = 2;     //列名}// 定义回复包message SumResponse {        required int64 sum = 1 [default = 0];   //求和结果}// 定义RPC服务service SumService {        //获取求和结果        rpc getSum(SumRequest)                returns (SumResponse);}

2) 通过proto命令生成Sum.java类, 并拷贝到项目中

protoc endpoint.proto --java_out=./

3)编写endpoint 类

package com.isesol.mapreduce;import java.io.IOException;import java.util.ArrayList;import java.util.List;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.hbase.Coprocessor;import org.apache.hadoop.hbase.CoprocessorEnvironment;import org.apache.hadoop.hbase.client.Durability;import org.apache.hadoop.hbase.client.Get;import org.apache.hadoop.hbase.client.HTable;import org.apache.hadoop.hbase.client.Put;import org.apache.hadoop.hbase.client.Scan;import org.apache.hadoop.hbase.coprocessor.BaseRegionObserver;import org.apache.hadoop.hbase.coprocessor.CoprocessorException;import org.apache.hadoop.hbase.coprocessor.CoprocessorService;import org.apache.hadoop.hbase.coprocessor.ObserverContext;import org.apache.hadoop.hbase.coprocessor.RegionCoprocessorEnvironment;import org.apache.hadoop.hbase.protobuf.ResponseConverter;import org.apache.hadoop.hbase.regionserver.InternalScanner;import org.apache.hadoop.hbase.regionserver.wal.WALEdit;import org.apache.hadoop.hbase.util.Bytes;import org.apache.hadoop.hbase.Cell;  import org.apache.hadoop.hbase.CellUtil;  import com.google.protobuf.RpcCallback;import com.google.protobuf.RpcController;import com.google.protobuf.Service;import com.isesol.mapreduce.Sum.SumRequest;import com.isesol.mapreduce.Sum.SumResponse;import com.isesol.mapreduce.Sum.SumService;public class endpointTrigger extends SumService implements Coprocessor, CoprocessorService {private RegionCoprocessorEnvironment env;@Overridepublic void getSum(RpcController controller, SumRequest request, RpcCallback<SumResponse> done) {// TODO Auto-generated method stubSumResponse response = null;InternalScanner scanner = null;Scan scan = new Scan();scan.addFamily(Bytes.toBytes(request.getFamily()));scan.addColumn(Bytes.toBytes(request.getFamily()), Bytes.toBytes(request.getColumn()));// 扫描每个region，取值后求和try {scanner = env.getRegion().getScanner(scan);List<Cell> results = new ArrayList<Cell>();boolean hasMore = false;Long sum = 0L;do {hasMore = scanner.next(results);for (Cell cell : results) {sum += Long.parseLong(new String(CellUtil.cloneValue(cell)));}results.clear();} while (hasMore);// 设置返回结果response = SumResponse.newBuilder().setSum(sum).build();} catch (IOException e) {ResponseConverter.setControllerException(controller, e);} finally {if (scanner != null) {try {scanner.close();} catch (IOException e) {e.printStackTrace();}}}done.run(response);}public Service getService() {// TODO Auto-generated method stubreturn this;}public void start(CoprocessorEnvironment env) throws IOException {// TODO Auto-generated method stubif (env instanceof RegionCoprocessorEnvironment) {this.env = (RegionCoprocessorEnvironment) env;} else {throw new CoprocessorException("can not start endpoint");}}public void stop(CoprocessorEnvironment env) throws IOException {// TODO Auto-generated method stub}}

4)编写客户端

package com.isesol.mapreduce;import java.io.IOException;import java.util.Map;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.hbase.HBaseConfiguration;import org.apache.hadoop.hbase.TableName;import org.apache.hadoop.hbase.client.Connection;import org.apache.hadoop.hbase.client.ConnectionFactory;import org.apache.hadoop.hbase.client.HTable;import org.apache.hadoop.hbase.client.coprocessor.Batch;import org.apache.hadoop.hbase.ipc.BlockingRpcCallback;import com.google.protobuf.ServiceException;import com.isesol.mapreduce.Sum.SumRequest;import com.isesol.mapreduce.Sum.SumResponse;import com.isesol.mapreduce.Sum.SumService;;/** * @author developer * 说明：hbase协处理器endpooint的客户端代码 * 功能：从服务端获取对hbase表指定列的数据的求和结果 */public class Sumclient {    public static void main(String[] args) throws ServiceException, Throwable {                long sum = 0L;                int count = 0;                // 配置HBse        Configuration conf = HBaseConfiguration.create();        conf.set("hbase.zookeeper.quorum","datanode01.isesol.com,datanode02.isesol.com,datanode03.isesol.com,datanode04.isesol.com,cmserver.isesol.com");        conf.set("hbase.zookeeper.property.clientPort", "2181");        // 建立一个数据库的连接        Connection conn = ConnectionFactory.createConnection(conf);        // 获取表        HTable table = (HTable) conn.getTable(TableName.valueOf("t_axes_feeding_status"));        table.setOperationTimeout(10);        // 设置请求对象        final SumRequest request = SumRequest.newBuilder().setFamily("cf").setColumn("AXABSFBPOS A").build();                        System.out.println("start to invoke result");                // 获得返回值        Map<byte[], Long> result = table.coprocessorService(Sum.SumService.class, null, null,                 new Batch.Call<Sum.SumService, Long>() {                    public Long call(SumService service) throws IOException {                        BlockingRpcCallback<SumResponse> rpcCallback = new BlockingRpcCallback<SumResponse>();                        service.getSum(null, request, rpcCallback);                        SumResponse response = (SumResponse) rpcCallback.get();                        return response.hasSum() ? response.getSum() : 0L;                    }        });                System.out.println("satrt to count the value");        // 将返回值进行迭代相加        for (Long v : result.values()) {                    count++;        }        // 结果输出        System.out.println("count: " + count);        // 关闭资源        table.close();        conn.close();    }}

5)加载协处理器

  alter 't_axes_feeding_status', METHOD => 'table_att', 'COPROCESSOR'=> 'hdfs://nameservice1/tmp/endpointTrigger.jar|com.isesol.mapreduce.endpointTrigger||'    alter  't_axes_feeding_status',   METHOD => 'table_att_unset', NAME => 'coprocessor$1'

6) 执行client代码，看看返回的数据是否正确。