i config name node HA,but when i start data node ,i found the error info in
log
and here is my hdfs-site.xml file
<configuration>
<!--
<property>
<name>dfs.name.dir</name>
<value>/var/lib/hadoop-hdfs/cache/hdfs/dfs/name</value>
</property>
-->
<property>
<name>dfs.permissions.superusergroup</name>
<value>hadoop</value>
</property>
<!--
<property>
<name>dfs.namenode.name.dir</name>
<value>/data/hadoopnamespace</value>
</property>
-->
<property>
<name>dfs.datanode.data.dir</name>
<value>/data/hadoopdataspace</value>
</property>
<property>
<name>dfs.datanode.failed.volumes.tolerated</name>
<value>3</value>
</property>
<!-- HA -->
<property>
<name>dfs.nameservices</name>
<value>mycluster</value>
</property>
<property>
<name>dfs.ha.namenodes.mycluster</name>
<value>nn1,nn2</value>
</property>
<property>
<name>dfs.namenode.rpc-address.mycluster.nn1</name>
<value>node1:8020</value>
</property>
<property>
<name>dfs.namenode.rpc-address.mycluster.nn2</name>
<value>node2:8020</value>
</property>
<property>
<name>dfs.namenode.http-address.mycluster.nn1</name>
<value>node1:50070</value>
</property>
<property>
<name>dfs.namenode.http-address.mycluster.nn2</name>
<value>node2:50070</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://node1:8485;node2:8485;node3:8485/mycluster</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/data/1/dfs/jn</value>
</property>
<property>
<name>dfs.client.failover.proxy.provider.mycluster</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!-- HA end -->
<!-- ssh fence method -->
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/home/nodefence/.ssh/id_rsa</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
<description>
SSH connection timeout, in milliseconds, to use with the builtin
sshfence fencer.
</description>
</property>
<!-- enable web HDFS -->
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
</configuration>
2013-07-26 21:20:18,850 INFO
org.apache.hadoop.hdfs.server.datanode.DataNode: Setting up storage:
nsid=291409768;bpid=BP-771660648-192.168.142.129-1374837820241;lv=-40;nsInfo=lv
=-40;cid=CID-28365f0e-e4f1-45b0-a86a-bb37794b6672;nsid=291409768;c=0;bpid=BP-771660648-192.168.142.129-1374837820241
2013-07-26 21:20:18,870 INFO
org.apache.hadoop.hdfs.server.datanode.DataNode: Block pool
BP-771660648-192.168.142.129-1374837820241 (storage id
DS-713465905-192.168.142.131-5001
0-1374844418641) service to node1/192.168.142.129:8020 beginning handshake
with NN
2013-07-26 21:20:18,873 FATAL
org.apache.hadoop.hdfs.server.datanode.DataNode: Initialization failed for
block pool Block pool BP-771660648-192.168.142.129-1374837820241 (storag
e id DS-713465905-192.168.142.131-50010-1374844418641) service to node2/
192.168.142.130:8020
org.apache.hadoop.util.DiskChecker$DiskErrorException: Invalid volume
failure config value: 3
at
org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetImpl.<init>(FsDatasetImpl.java:183)
at
org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetFactory.newInstance(FsDatasetFactory.java:34)
at
org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetFactory.newInstance(FsDatasetFactory.java:30)
at
org.apache.hadoop.hdfs.server.datanode.DataNode.initStorage(DataNode.java:920)
at
org.apache.hadoop.hdfs.server.datanode.DataNode.initBlockPool(DataNode.java:882)
at
org.apache.hadoop.hdfs.server.datanode.BPOfferService.verifyAndSetNamespaceInfo(BPOfferService.java:308)
at
org.apache.hadoop.hdfs.server.datanode.BPServiceActor.connectToNNAndHandshake(BPServiceActor.java:218)
at
org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:660)
at java.lang.Thread.run(Thread.java:722)
2013-07-26 21:20:18,874 WARN
org.apache.hadoop.hdfs.server.datanode.DataNode: En
ding block pool service for: Block pool
BP-771660648-192.168.142.129-1374837820241 (storage id
DS-713465905-192.168.142.131-50010-1374844418641) service to node2/
192.168.142.130:8020
2013-07-26 21:20:18,886 INFO
org.apache.hadoop.hdfs.server.datanode.DataNode: Block pool Block pool
BP-771660648-192.168.142.129-1374837820241 (storage id
DS-713465905-192.168.142.131-50010-1374844418641) service to node1/
192.168.142.129:8020 successfully registered with NN
2013-07-26 21:20:18,887 INFO
org.apache.hadoop.hdfs.server.datanode.DataNode: For namenode node1/
192.168.142.129:8020 using DELETEREPORT_INTERVAL of 300000 msec
BLOCKREPORT_INTERVAL of 21600000msec Initial delay: 0msec;
heartBeatInterval=3000
2013-07-26 21:20:18,887 ERROR
org.apache.hadoop.hdfs.server.datanode.DataNode: Exception in
BPOfferService for Block pool BP-771660648-192.168.142.129-1374837820241
(storage id DS-713465905-192.168.142.131-50010-1374844418641) service to
node1/192.168.142.129:8020
java.lang.NullPointerException
at
org.apache.hadoop.hdfs.server.datanode.BPServiceActor.sendHeartBeat(BPServiceActor.java:435)
at
org.apache.hadoop.hdfs.server.datanode.BPServiceActor.offerService(BPServiceActor.java:521)
at
org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:673)
at java.lang.Thread.run(Thread.java:722)
~
