This is 0.19.0.
Grepping around, it appears that message for this block has been
printed 1-5 Hz throughout all our logs (oldest logs are 12-3). Has
happened about .5 million times. If I grep for the
"nextGenerationStamp" error message, it's happened .4M times.
Anything else I can provide?
Brian
On Dec 5, 2008, at 8:31 PM, Tsz Wo (Nicholas), Sze wrote:
Which version are you using?
Calling commitBlockSynchronization(...) with newgenerationstamp=0,
newlength=0, newtargets=[] does not look normal. You may check the
namenode log and the client log about the block
blk_-4236881263392665762.
Nicholas Sze
----- Original Message ----
From: Brian Bockelman <[EMAIL PROTECTED]>
To: core-user@hadoop.apache.org
Sent: Friday, December 5, 2008 5:22:03 PM
Subject: Block not found during commitBlockSynchronization
Hey,
I'm seeing this message repeated over and over in my logs:
2008-12-05 19:20:00,534 INFO
org.apache.hadoop.hdfs.server.namenode.FSNamesystem:
commitBlockSynchronization(lastblock=blk_-4236881263392665762_88597,
newgenerationstamp=0, newlength=0, newtargets=[])
2008-12-05 19:20:00,534 INFO org.apache.hadoop.ipc.Server: IPC
Server handler 29
on 9000, call
commitBlockSynchronization(blk_-4236881263392665762_88597, 0, 0,
false, true,
[Lorg.apache.hadoop.hdfs.protocol.DatanodeID;@67537412) from
172.16.1.184:57586: error: java.io.IOException: Block
(=blk_-4236881263392665762_88597) not found
java.io.IOException: Block (=blk_-4236881263392665762_88597) not
found
at
org
.apache
.hadoop
.hdfs
.server
.namenode.FSNamesystem.commitBlockSynchronization(FSNamesystem.java:
1898)
at
org
.apache
.hadoop
.hdfs
.server.namenode.NameNode.commitBlockSynchronization(NameNode.java:
410)
at sun.reflect.GeneratedMethodAccessor21.invoke(Unknown Source)
at
sun
.reflect
.DelegatingMethodAccessorImpl
.invoke(DelegatingMethodAccessorImpl.java:25)
at java.lang.reflect.Method.invoke(Method.java:597)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:452)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:892)
What can I do to debug?
Brian
