HBase Client JAVA API

舊 的 HBase 接口邏輯與傳統 JDBC 方式很不相同，新的接口與傳統 JDBC 的邏輯更加相像，具有更加清晰的 Connection 管理方式。

同時，在舊的接口中，客戶端何時將 Put 寫到服務端也需要設置，一個 Put 馬上寫到服務端，還是攢到一批寫到服務端，新用戶往往對此不太清楚。

在新的接口中，引入了 BufferedMutator，可以提供更加高效清晰的寫操作。

HBase 0.98 與 HBase 1.0 接口名稱對比

舉一個例子，舊的 API 寫入操作的代碼：

新的 API 寫入操作的代碼：

可以看到，在操作前，首先建立連接，然后拿到一個對應表的句柄，之后再進行一系列操作。以上兩個是同步寫操作。

下面看一下批量異步寫入接口：

org.apache.hadoop.hbase.client.BufferedMutator主要用來對HBase的單個表進行操作。它和Put類的作用差不多，但是主要用來實現批量的異步寫操作。

BufferedMutator替換了HTable的setAutoFlush(false)的作用。

可以從Connection的實例中獲取BufferedMutator的實例。在使用完成后需要調用close()方法關閉連接。對BufferedMutator進行配置需要通過BufferedMutatorParams完成。

MapReduce Job的是BufferedMutator使用的典型場景。MapReduce作業需要批量寫入，但是無法找到恰當的點執行flush。

BufferedMutator接收MapReduce作業發送來的Put數據后，會根據某些因素（比如接收的Put數據的總量）啟發式地執行Batch Put操作，且會異步的提交Batch Put請求，這樣MapReduce作業的執行也不會被打斷。

BufferedMutator也可以用在一些特殊的情況上。MapReduce作業的每個線程將會擁有一個獨立的BufferedMutator對象。

一個獨立的BufferedMutator也可以用在大容量的在線系統上來執行批量Put操作，但是這時需要注意一些極端情況比如JVM異常或機器故障，此時有可能造成數據丟失。

官方源碼路徑：/hbase-2.0.4/hbase-examples/src/main/java/org/apache/hadoop/hbase/client/example/BufferedMutatorExample.java

/**
 *
 * 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 org.apache.hadoop.hbase.client.example;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.Callable;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import java.util.concurrent.Future;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.BufferedMutator;
import org.apache.hadoop.hbase.client.BufferedMutatorParams;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.RetriesExhaustedWithDetailsException;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.yetus.audience.InterfaceAudience;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
 * An example of using the {@link BufferedMutator} interface.
 */
@InterfaceAudience.Private
public class BufferedMutatorExample extends Configured implements Tool {

  private static final Logger LOG = LoggerFactory.getLogger(BufferedMutatorExample.class);

  private static final int POOL_SIZE = 10;
  private static final int TASK_COUNT = 100;
  private static final TableName TABLE = TableName.valueOf("foo");
  private static final byte[] FAMILY = Bytes.toBytes("f");

  @Override
  public int run(String[] args) throws InterruptedException, ExecutionException, TimeoutException {

    /** a callback invoked when an asynchronous write fails. */
    final BufferedMutator.ExceptionListener listener = new BufferedMutator.ExceptionListener() {
      @Override
      public void onException(RetriesExhaustedWithDetailsException e, BufferedMutator mutator) {
        for (int i = 0; i < e.getNumExceptions(); i++) {
          LOG.info("Failed to sent put " + e.getRow(i) + ".");
        }
      }
    };
    BufferedMutatorParams params = new BufferedMutatorParams(TABLE)
        .listener(listener);

    //
    // step 1: create a single Connection and a BufferedMutator, shared by all worker threads.
    //
    try (final Connection conn = ConnectionFactory.createConnection(getConf());
         final BufferedMutator mutator = conn.getBufferedMutator(params)) {

      /** worker pool that operates on BufferedTable instances */
      final ExecutorService workerPool = Executors.newFixedThreadPool(POOL_SIZE);
      List<Future<Void>> futures = new ArrayList<>(TASK_COUNT);

      for (int i = 0; i < TASK_COUNT; i++) {
        futures.add(workerPool.submit(new Callable<Void>() {
          @Override
          public Void call() throws Exception {
            //
            // step 2: each worker sends edits to the shared BufferedMutator instance. They all use
            // the same backing buffer, call-back "listener", and RPC executor pool.
            //
            Put p = new Put(Bytes.toBytes("someRow"));
            p.addColumn(FAMILY, Bytes.toBytes("someQualifier"), Bytes.toBytes("some value"));
            mutator.mutate(p);
            // do work... maybe you want to call mutator.flush() after many edits to ensure any of
            // this worker's edits are sent before exiting the Callable
            return null;
          }
        }));
      }

      //
      // step 3: clean up the worker pool, shut down.
      //
      for (Future<Void> f : futures) {
        f.get(5, TimeUnit.MINUTES);
      }
      workerPool.shutdown();
    } catch (IOException e) {
      // exception while creating/destroying Connection or BufferedMutator
      LOG.info("exception while creating/destroying Connection or BufferedMutator", e);
    } // BufferedMutator.close() ensures all work is flushed. Could be the custom listener is
      // invoked from here.
    return 0;
  }

  public static void main(String[] args) throws Exception {
    ToolRunner.run(new BufferedMutatorExample(), args);
  }
}