[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-users] whether xen scheduler supports preemption

On mer, 2013-06-26 at 10:09 +0200, Christy Business wrote:
> Hello

> Please, i want to continue in this topic!
I'd be happy to help, but unfortunately, I did never get to look deeply
on how capping works. :-(

> How does the xen schedule ensures that the cap(not null) value  of a
> VM is respected? Firstly in a case of a single VCPU VM and in the case
> of the multiple  VPCU VM?
What I know is and, basing on that, what I suggest is:
 - credit1 has the capping capability, credit2 does not have anything
   like hat yet. SEDF has something like that, although I wouldn't call
   it a cap. Therefore, for learning how it works, concentrate on
 - the mechanism has been designed, and got the most of his serious
   testing, for single VCPU VMs. It is not that it does not work with
   SMP guests, actually, it behaved just fine all the time I had the
   chance to try it, even in that scenario, but bear this in mind when
   you investigate the algorithm.
 - it is all based on keeping track on how much credit a VM can consume
   before needing to be 'parked', to avoid overrunning the cap itself.
   Look for what happens to variables called 'cap', 'credit_cap', and of
   course 'credit'. Most of the math to make it work seems to reside in
   the csched_acct() (in sched_credit.c, of course) function.

And this is all I can say about it, I'm afraid.


<<This happens because I choose it to happen!>> (Raistlin Majere)
Dario Faggioli, Ph.D, http://about.me/dario.faggioli
Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK)

Attachment: signature.asc
Description: This is a digitally signed message part

Xen-users mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.