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

[Dario Faggioli <dario.faggioli@xxxxxxxxxx>]

Ok, you're still failing at using plain text... Could you please try
harder? :-)

On dom, 2013-06-30 at 23:00 +0800, åä wrote:
> At first, I have a wrong understanding for xen scheduler preemption. I 
> thought it did not support preemption. Last week, my advisor  corrects my 
> thought. 
>
Ok, so you're "just" studying scheduling in OSes/hypervisors, with
particular focus on how preemption works and is implemented.. Or you're
also aiming at envisioning/introducing some new functionality, perhaps,
for research/coursework (since you mentioned an 'advisor')?

> So I want to know if a system supports preemption, the code which key part 
> need to do the modification. At first, I add something in xen scheduler(only 
> simple). 
>
Ok, so you added something... What for? What was the final purpose?
"Just" understanding, or are you modifying the behavior?

You know, the reason I'm asking is because, whatever you're doing, we
might be able to help you better if we know what you are aiming at, not
to mention that what you're trying to achieve, might be interesting
and/or beneficial for other Xen users as well! :-)

> My modification will bring some virtual machines starvation. Now I want to 
> decrease the starvation. 
>
Oh... And the purpose was to actually introduce starvation? EhEh, I
don't think so! :-P If not, what was it?

> I need to add some other things. I meet a serious problem, in the schedule() 
> or csched_schedule() function, if access the variable csched_dom structure, 
> the system will automatically reboot. Eg, if add  the printk("The domain 
> weight is %d", sdom->weight); in the csched_schedule() or schedule(), the 
> system will automatically reboot and can not enter the system. Do you know 
> why? It is very strange. In these two functions, I can successfully access 
> the variable of csched_vcpu structure and csched_private.
>
I cannot comment on the specific 'access the variable' without seeing
the code. However, the behavior you're reporting is a clear symptom of
the hypervisor crashing. For better investigating the reason, you need
to be able to see what it says _before_ rebooting.

You'll most likely need the 'noreboot' boot parameter and a serial
console... Do you already have those? Follow some tips on how to do that
here on how to put yourself in a more debugging friendly situation:

http://wiki.debian.org/Xen#dom0_automatic_reboots
http://wiki.xen.org/wiki/Xen_Serial_Console
http://wiki.xen.org/wiki/Debugging_Xen

Regards,
Dario

-- 
<<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
Xen-users@xxxxxxxxxxxxx
http://lists.xen.org/xen-users