[GE users] SGE6.2u5 - sge_execd on windows node not responding after period of time

jching jching at bbn.com
Tue Oct 26 22:03:27 BST 2010


I have a strange problem with sge 6.2u5 where everything works fine for a windows node but it will randomly (could be a few hours to a few days) go into au state BUT on the machine, sge_execd and qloadsensor.exe are both still running.  If I start sge_execd again on the windows node which will then cause duplicate processes (sge_execd and qloadsensor.exe), the au state will go away... any thoughts on what might cause this and how I may be able to debug on the client side?

All logs have been checked but on qmaster and on client, nothing suspicious...

Thanks for any direction!

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=290278

To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].



More information about the gridengine-users mailing list