[torquedev] cpuset support
prakash.velayutham at cchmc.org
Tue Nov 13 11:27:24 MST 2007
Can I ask a stupid question like, what does the current cpuset code in
On Nov 12, 2007, at 7:17 PM, Garrick Staples wrote:
> I just bumped into Chris Samuel at his (rather barren) booth here at
> SC07 and I think we just designed cpuset support.
> Here's what we came up with...
> On startup, pbs_mom will create /dev/cpuset/torque (with all cpus)
> if it
> doesn't already exist and move itself to it. This allows the admin
> to stuff
> pbs_mom inside a smaller cpuset if desired by creating it in the
> We will call this the "torqueset".
> When a job starts, pbs_mom will create a per-job cpuset under the
> with the correct cpus called the "jobset". It will do this after
> which allows the admin to pre-create it if desired. This happens on
> all nodes.
> Also, per-vnode cpusets will also be created under the jobset at job
> pbs_mom will run the batch script inside of the jobset and all TM
> requests will run in the vnodeset.
> You end up with cpusets that look like:
> Job exit will consist of ensuring the cpusets are empty (killing
> before removing them.
> Exclusive cpusets can't be used because of suspended jobs.
> All mems will be added to all cpusets unless someone comes up with
> another idea.
> This seems pretty simple to implement, doesn't require any build
> deps, and
> makes sense to me. Any thoughts?
More information about the torquedev