On Mon, 2007-02-05 at 10:33 +0000, Burke, S (Stephen) wrote:
> LHC Computer Grid - Rollout
> > [mailto:[log in to unmask]] On Behalf Of John R. Hover
> said:
> > I understand that for many values, there are signal flags
> > that need to
> > be set as the default ( e.g., 4444 for WaitingJobs ). I just
> > wanted to double check that the other fields, e.g.
> > "GlueCEStateTotalJobs: 0", are supposed to have a 0 default.
>
> In general TotalJobs = RunningJobs + WaitingJobs, so possibly TotalJobs
> should also default to 4444 - on the other hand, publishing values that
> violate the constraint is maybe another signal that the info is invalid
> ... but in general it would probably be better to have it default to a
> large value, the principle is for the defaults to make a broken CE look
> as unattractive as possible.
I don't remeber if i have complained about this before so here goes.
Having a valid value (4444) as a marker for invalid data is stupid.
Our cluster have a varying degree of jobs in the system, sometimes as
many as 12-16000!!
This happens when some of the local users start submitting LOTS of
medium sized jobs.
--
Ake Sandgren, HPC2N, Umea University, S-90187 Umea, Sweden
Internet: [log in to unmask] Phone: +46 90 7866134 Fax: +46 90 7866126
Mobile: +46 70 7716134 WWW: http://www.hpc2n.umu.se
|