[torquedev] nodes, procs, tpn and ncpus
siegert at sfu.ca
Fri Jun 11 12:43:02 MDT 2010
On Fri, Jun 11, 2010 at 08:19:39PM +0200, "Mgr. Šimon Tóth" wrote:
> On 11.6.2010 18:41, Martin Siegert wrote:
> > On Fri, Jun 11, 2010 at 09:59:47AM -0600, Ken Nielson wrote:
> >> On 06/10/2010 09:36 PM, Christopher Samuel wrote:
> >> -----BEGIN PGP SIGNED MESSAGE-----
> >> Hash: SHA1
> >> On 11/06/10 04:47, Glen Beane wrote:
> >> > In my opinion, I think nodes=X,procx=Y should generate
> >> > a syntax error...
> >> Agreed.
> >> I am not swayed one way or another yet. What if a user makes a request
> >> like the following
> >> -l nodes=4:ppn=2+procs=6
> >> The user wants four nodes with two processors each and then 6
> >> processors anywhere they are available.
> >> -l nodes=4+procs=4
> >> The user wants 4 nodes plus 4 processors anywhere. This one makes less
> >> sense than the first, but if we allow the first we need to allow this
> >> as well.
> >> Thoughts anyone?
> > It all depends on whether we want to break the meaning of nodes=N being
> > totally equivalent to nodes=N:ppn=1.
> > 1) if we stick to the meaning of nodes=N just being a shorthand for
> > nodes=N:ppn=1 then -l nodes=4+procs=4 makes just as much sense as
> > nodes=4:ppn=2+procs=6, i.e., there is no problem.
> > 2) if we change the meaning of nodes=N to become "give me exclusive
> > access to N nodes" then we need to define what -l nodes=N+procs=M
> > means.
> > I actually vote for (1). E.g., what is the default if neither nodes nor
> > procs is specified? Currently that is nodes=1:ppn=1, i.e., the default
> > for nodes is 1 and the default for ppn is one. That logical extension is
> > that if only nodes is specified then the default value for ppn should be
> > used. I.e., nodes=N means nodes=N:ppn=1.
> > But that leaves us with the problem of how to specify exclusive access
> > to a node. What about a keyword ALL as in nodes=4:ppn=ALL ? It is a
> > logical extension of the current syntax and is easy to understand.
> > And then things like -l nodes=1:ppn=ALL+procs=42 make total sense
> > (at least to me).
> That's not good enough. How do you tell Torque that you want at least a
> 4 CPU node, but when you get it, then you want all the CPUs?
Right (I am too much used to homogeneous clusters).
What about the -l naccesspolicy=singlejob specification?
Is this only understood by moab? And if that's the case, could this
get implemented within torque? E.g.,
More information about the torquedev