[GE users] Nodes going 'au'

Jack Neely jjneely at pams.ncsu.edu
Fri Nov 12 17:52:43 GMT 2004


Folks,

I'm not sure if this is related or not but I'm still trying to track
down why nodes randomly go into the au state.  I've found the following
in SGE's message file on one of the clients.  What does this mean in
regards to the unknown job part?

Mon Oct 18 14:15:04 2004|execd|compute-0-6|I|starting up 5.3p3 (sge)
Mon Oct 18 21:00:30 2004|execd|compute-0-6|E|acknowledge for unknown job
26814.1/master
Mon Oct 18 21:00:30 2004|execd|compute-0-6|E|can't find active jobs
directory "active_jobs/26814.1" for reaping job 26814
Mon Oct 18 21:00:30 2004|execd|compute-0-6|E|ERROR: unlinking
"jobs/00/0002/6814.1": No such file or directory
Mon Oct 18 21:00:30 2004|execd|compute-0-6|E|can not remove job spool
file: jobs/00/0002/6814.1
Mon Oct 18 21:00:30 2004|execd|compute-0-6|E|can't remove directory
"active_jobs/26814.1": opendir(active_jobs/26814.1) failed: No such file
or directory
Mon Oct 18 21:00:30 2004|execd|compute-0-6|E|ja-task "26814.1" is
unknown - reporting it to qmaster
Mon Oct 18 21:01:00 2004|execd|compute-0-6|E|acknowledge for unknown job
26814.1/master
Mon Oct 18 21:01:00 2004|execd|compute-0-6|E|can't find active jobs
directory "active_jobs/26814.1" for reaping job 26814
Mon Oct 18 21:01:00 2004|execd|compute-0-6|E|ERROR: unlinking
"jobs/00/0002/6814.1": No such file or directory
Mon Oct 18 21:01:00 2004|execd|compute-0-6|E|can not remove job spool
file: jobs/00/0002/6814.1
Mon Oct 18 21:01:00 2004|execd|compute-0-6|E|can't remove directory
"active_jobs/26814.1": opendir(active_jobs/26814.1) failed: No such file
or directory

Jack
-- 
Jack Neely <slack at quackmaster.net>
Realm Linux Administration and Development
PAMS Computer Operations at NC State University
GPG Fingerprint: 1917 5AC1 E828 9337 7AA4  EA6B 213B 765F 3B6A 5B89

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list