I submitted a map reduce job that had 9 tasks killed out of 139. But I
don't see any errors in the admin page. The entire job however has
SUCCEDED. How can I track down the reason?

Also, how do I determine if this is something to worry about?

You probably have speculative execution enabled. That¹s normal for job
tracker to launch multiple tasks and take result of the ones that
complited first.

Regards,
Serge

On 2/27/12 11:55 AM, "Mohit Anchlia" <[EMAIL PROTECTED]> wrote:

>I submitted a map reduce job that had 9 tasks killed out of 139. But I
>don't see any errors in the admin page. The entire job however has
>SUCCEDED. How can I track down the reason?
>
>Also, how do I determine if this is something to worry about?

On 2/27/2012 1:55 PM, Mohit Anchlia wrote:
> I submitted a map reduce job that had 9 tasks killed out of 139. But I
> don't see any errors in the admin page. The entire job however has
> SUCCEDED. How can I track down the reason?
>
> Also, how do I determine if this is something to worry about?
>
Hi,

You should go to the data nodes and check /logs/userlogs/ directories
there.

Though I am not either very clear about this case:  If you are working
on the administrated cluster and you don't have access to the data
nodes, how to check the error logs.  For me I have to ask administrator
forward me the error log sometimes.  The logs in jobtracker and namenode
are very limited.  And the datanode info in admin web page is blocked
because of security reasons? I didn't follow up the new releases about
this issue.  Maybe in 1.0.x they have improved methods about this?

Shi