[GE users] Restarting sge_execd on all nodes

fx d.love at liverpool.ac.uk
Wed Mar 11 15:29:55 GMT 2009


reuti <reuti at staff.uni-marburg.de> writes:

> a hard mount is fine. Normally the OS should just wait, until the  
> hard mount becomes available again. Was the file server rebooted? For  
> this to survive, you might need to supply "file system id"s in /etc/ 
> exports like:
>
> /usr/sge                        @nodes 
> (rw,root_squash,anonuid=63,anongid=58,sync,fsid=1004,subtree_check)

Under what circumstances might that be necessary?  It's something I've
never used, and we generally have no problem rebooting the head or the
NFS home directory server with hard mounts to the compute nodes.  (A
recent problem with a Panasas system serving home directories did
require a general re-boot of the compute nodes for reasons that weren't
clear, but that wasn't an SGE issue.)

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=127662

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



More information about the gridengine-users mailing list