"[email protected]" <[email protected]> writes:

> Exactly. But sometimes it is appropriate to reconfigure in other
> situations, like when priorities change (regression C starts and is more
> important), or when Regression B is finished and the machines can start
> working on Regression A.

If you must re-provision, I'd guess you could handle the policy and
priorities via normal GE mechanisms (with a load sensor and complexes to
figure out whether you need a new configuration).  Maybe it's
appropriate to use something like SDM to manage the installations,
though.  It sounds squarely in Univa's consultancy area.

>> One solution could be to run 3 VMs per exechost (and each exechost appears
>> triple in SGE), but only one VM at a time might receive jobs?

[That would be much more convenient if you could do mutual suspension
between hosts, as we've said before.]

> That's unfortunately not possible, partly because we need all the power
> from the servers to run the application without timing issues.

If it must run on bare metal, and can't run stateless (when booting
might be faster than re-provisioning), is there some reason not to have
multiple configurations installed, and chroot into them for the job
concerned?
_______________________________________________
users mailing list
[email protected]
https://gridengine.org/mailman/listinfo/users

Reply via email to