通过java api连接Hadoop集群时，如果集群支持HA方式，那么可以通过如下方式设置来自动切换到活动的master节点上。其中，ClusterName 是可以任意指定的，跟集群配置无关，dfs.ha.namenodes.ClusterName也可以任意指定名称，有几个master就写几个，后面根据相应的设置添加master节点地址即可。
private static String ClusterName = "nsstargate";
private static final String HADOOP_URL = "hdfs://"+ClusterName;
public static Configuration conf; static {
conf = new Configuration();
conf.set("fs.defaultFS", HADOOP_URL);
conf.set("dfs.nameservices", ClusterName);
conf.set("dfs.ha.namenodes."+ClusterName, "nn1,nn2");
conf.set("dfs.namenode.rpc-address."+ClusterName+".nn1", "172.16.50.24:8020");
conf.set("dfs.namenode.rpc-address."+ClusterName+".nn2", "172.16.50.21:8020");
//conf.setBoolean(name, value);
conf.set("dfs.client.failover.proxy.provider."+ClusterName,
"org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider");
}
上传文件到HDFS的代码如下，至于读取等其他操作，可以参考网络上其他文章。
/**
* 上传文件到HDFS上去
*/
private static void uploadToHdfs() throws IOException {
String localSrc = "E:\\test\\article01.txt";
String dst = "/user/test/article04.txt";
FileSystem fs = FileSystem.get(URI.create(HADOOP_URL), conf);
long start = new Date().getTime(); /* InputStream in = new FileInputStream(localSrc);
InputStreamReader isr = new InputStreamReader(in, "GBK");
OutputStream out = fs.create(new Path(HADOOP_URL+dst), true);
IOUtils.copy(isr, out, "UTF8");*/ //该方法更快
FSDataOutputStream outputStream=fs.create(new Path(dst));
String fileContent = FileUtils.readFileToString(new File(localSrc), "GBK");
outputStream.write(fileContent.getBytes());
outputStream.close(); long end = new Date().getTime();
System.out.println("use:"+(end-start)); }