[torqueusers] Who Has the most users?
dbeer at adaptivecomputing.com
Wed Aug 28 12:07:53 MDT 2013
On Wed, Aug 28, 2013 at 12:03 PM, Michael Jennings <mej at lbl.gov> wrote:
> On Wednesday, 28 August 2013, at 11:54:57 (-0600),
> David Beer wrote:
> > We are asking because we're just curious how many users sites
> > have. Someone was asked me how many users the biggest sites had, so
> > I just wanted to ask to find out. I believe the person was asking me
> > to find out where we are in order to gauge how much work it'll be to
> > support more users going forward.
> Fair enough. Though I suspect the support burden is more accurately
> defined in terms of nodes and jobs; I'm not sure simultaneous users is
> really a significant factor...is it? Is there an appreciable
> difference in TORQUE between 1 user with 30,000 jobs and 300 users
> with 100 jobs each?
There are only minor considerations for having different users. In general,
I agree with what you're saying.
> > As a note on establishing limits in the code - our goal is to remove
> > from the code. A big part of moving to C++ is the desire to more readily
> > support resizing containers and data structures, and I hope people see
> > we're trying to remove static limits on quantities in our code.
> Yay! I hope the Moab engineers are following suit! ;-)
I know not everyone here uses Moab, but I can tell you that Moab and TORQUE
are in lockstep in this effort and that in general you can expect to see
them more in lockstep as we move forward.
> Michael Jennings <mej at lbl.gov>
> Senior HPC Systems Engineer
> High-Performance Computing Services
> Lawrence Berkeley National Laboratory
> Bldg 50B-3209E W: 510-495-2687
> MS 050B-3209 F: 510-486-8615
> torqueusers mailing list
> torqueusers at supercluster.org
David Beer | Senior Software Engineer
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the torqueusers