[prev in list] [next in list] [prev in thread] [next in thread] 

List:       hadoop-user
Subject:    Seeing DiskErrorException, but no real error appears to be happening
From:       John Lee <j.benlin.lee () gmail ! com>
Date:       2009-01-30 17:27:08
Message-ID: 1c24ea390901300927i7512bd5ai5c0e96d511bd035 () mail ! gmail ! com
[Download RAW message or body]

Folks,

I'm seeing a lot of the following exceptions in my Hadoop logs when I
run jobs under Hadoop 0.19. I dont recall seeing this in Hadoop 0.18:

org.apache.hadoop.mapred.TaskTracker:
org.apache.hadoop.util.DiskChecker$DiskErrorException: Could not find
taskTracker/jobcache/job_200901131804_0215/attempt_200901131804_0215_r_000009_0/output/file.out
in any of the configured local directories

My understanding is that this means the reduce outputs can't be found
for some reason. However, the jobs seem to complete successfully and
the output is fine. I've double checked my configuration and can't
find any errors or problems. Is this pretty normal behavior? Is there
anything that might cause this other than misconfiguration? I'm trying
to decide if a bug needs to be filed.

Thanks,
John
[prev in list] [next in list] [prev in thread] [next in thread]