Jake Carroll <[email protected]> writes: > Hi. > > Interesting. > > From /opt/gridengine/default/spool/compute-0-4/messages, we are seeing > some unusual stuff (or, maybe it is entirely run of the mill?):
I'm not sure whether it's the same as https://arc.liv.ac.uk/trac/SGE/ticket/1418, which I haven't tried to debug. It might be relevant, what operating system it is. > 01/16/2013 18:05:50| main|compute-0-4|W|reaping job "1350379" ptf > complains: Job does not exist > 01/16/2013 18:07:56| main|compute-0-4|E|removing unreferenced job > 1350379.4111 without job report from ptf > At this point, we're scratching our heads and considering a reboot of the > head node on Friday, as we really aren't understanding what is going wrong > here. I'd restart the execd on the node, if anything, and possibly the qmaster. I can't think rebooting the head would be useful. -- Community Grid Engine: http://arc.liv.ac.uk/SGE/ _______________________________________________ users mailing list [email protected] https://gridengine.org/mailman/listinfo/users
