Hi all,
I seem to get this error far too frequently:
2010-08-09 09:54:03,685 INFO org.apache.hadoop.hbase.regionserver.Store: Started compaction
of 1 file(s) in annotations of doc,293817e024ed1d54a11e9e7c9b836dd837badbbc,1281372823189,
hasReferences=true, into /hbase/doc/compaction.dir/237345967, seqid=1182913218
2010-08-09 09:54:03,784 WARN org.apache.hadoop.hdfs.DFSClient: DFSOutputStream ResponseProcessor
exception for block blk_-4556852958383799371_431518java.net.SocketTimeoutException: 6000
millis timeout while waiting for channel to be ready for read. ch : java.nio.channels.SocketChannel[connected
local=/10.220.5.35:49924 remote=/10.220.5.14:50010]
at org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:164)
at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:155)
at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:128)
at java.io.DataInputStream.readFully(DataInputStream.java:178)
at java.io.DataInputStream.readLong(DataInputStream.java:399)
at org.apache.hadoop.hdfs.protocol.DataTransferProtocol$PipelineAck.readFields(DataTransferProtocol.java:119)
at org.apache.hadoop.hdfs.DFSClient$DFSOutputStream$ResponseProcessor.run(DFSClient.java:2424)
This basically is taking one of clusters down consistently. Is there an obvious thing I can
do about this?
I have seen this across three different clusters with radically different hardware, leading
me to believe that I have misconfigured something in either hbase or hdfs
Any ideas of where to look?
Thanks,
Dave
|