Mapreduce 蜂巢查询HBase太慢了

我想使用配置单元查询HBase表中的数据，如：

100         column=cf1:val, timestamp=1379536809907, value=val_100

我在配置单元中键入以下命令：

select * from hbase_table where value = 'val_100';

我相信一切都安排好了。当我键入上述命令时，它显示如下：

Total MapReduce jobs = 1
Launching Job 1 out of 1
Number of reduce tasks is set to 0 since there's no reduce operator
Starting Job = job_201309031344_0024, Tracking URL =        http://namenode:50030/jobdetails.jsp?jobid=job_201309031344_0024
Kill Command = /usr/libexec/../bin/hadoop job  -kill job_201309031344_0024
Hadoop job information for Stage-1: number of mappers: 1; number of reducers: 0
2013-09-18 14:45:53,815 Stage-1 map = 0%,  reduce = 0%
2013-09-18 14:46:54,654 Stage-1 map = 0%,  reduce = 0%
2013-09-18 14:47:55,449 Stage-1 map = 0%,  reduce = 0%
2013-09-18 14:48:56,193 Stage-1 map = 0%,  reduce = 0%
2013-09-18 14:49:56,990 Stage-1 map = 0%,  reduce = 0%

为什么映射任务总是0%？怎么了？有没有我没有配置的地方

我在datanode日志文件中发现错误：

2013-09-18 15:18:27,415 INFO org.apache.zookeeper.ClientCnxn: 
Opening socket connection to server datanode2/192.168.1.97:2181. 
Will not attempt to authenticate using SASL (unknown error)

2013-09-18 15:18:27,417 WARN org.apache.zookeeper.ClientCnxn: 
Session 0x0 for server null, unexpected error, closing socket 
connection and attempting reconnect java.net.ConnectException: 
Connection refused at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method) 
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:692)
at org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:350) 
at org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1068)

---

是永远停止？还是运行太慢？您有多少数据和多少节点？它停止超过5分钟…所以我杀死了它。在Hbase中只有一行数据，如上图所示，实际上可能太慢了……因为它在某个时候一直显示map=0%……但一定是出了什么问题……只有一行数据才能处理TT日志中感兴趣的内容？