[Swift-devel] process hogging memory on ranger login

Mihael Hategan hategan at mcs.anl.gov
Wed Nov 25 13:24:52 CST 2009


On Wed, 2009-11-25 at 11:50 -0600, skenny at uchicago.edu wrote:
> >> 
> >>
> /ci/projects/cnari/logs/skenny/importDTI-20091124-1655-agj0mze1.log
> >> 
> >> let me know if you need the coaster log as well.
> >
> >That may occur at times, such as when the service runs out of
> memory. So
> >yes, I do need the coaster log.
> >
> >Regardless of the exact reason, I think that there needs to
> be extra
> >logic in there to ensure liveness. In other words a lost
> state should
> >not be interpreted as "still in last state" but "failure".
> 
> ok, just added the coasters.log to that same dir:
> 
> /ci/projects/cnari/logs/skenny/coasters.log

Looks like the jobs go way over their walltime and that causes badness.
I'll investigate.

In the mean time, you could try to figure out why the jobs take much
longer than expected or adjust the expectation (walltime) accordingly.




More information about the Swift-devel mailing list