Adam Brenner <[email protected]> writes: > In our case, it is very helpful for our users to directly SSH into the > nodes to determine what is wrong with their qsub scripts, etc. This is > a follow up the following thread by Joseph and Harry: > https://gridengine.org/pipermail/users/2013-February/005585.html
The question seems to have been answered adequately in that thread. I'd say (a) don't allow over-subscription of SGE resources (perhaps with core binding/cpusets), though it's not uncommon for ssh to be clobbered when something goes wild, (b) deal with the antisocial job submission, (c) check system logs before asking here, especially as something like that has to be a local issue. -- Community Grid Engine: http://arc.liv.ac.uk/SGE/ _______________________________________________ users mailing list [email protected] https://gridengine.org/mailman/listinfo/users
