Re: [Xen-users] Does Xen's Dom0 hypervisor based cpufreq support 'schedutil' governor?

["Austin S. Hemmelgarn" <ahferroin7@xxxxxxxxx>]

On 2016-08-23 14:43, lists@xxxxxxxxxxxx wrote:
> > xenpm set-scaling-governor command is used to set what governor Xen uses when 
> > cpufreq=xen
> Right, and that's what I've set
>
> But here
>
>   https://wiki.xenproject.org/wiki/Xen_power_management#Hypervisor_based_cpufreq
>
> the picture seems to suggest that Hypervisor based cpufreq 'builds' on top of the Dom0's 
> "registered cpufreq governor"
>
> and it says
>
>         Xen currently has four governors:
>                 ondemand: choose the best frequency which best fit the
>                 userspace: choose the frequency that specified by user.
>                 performance: select the highest frequency
>                 powersave: select the lowest frequency
>
> which are the same as the usual kernel governors.
>
> Or are they just NAMED the same, but are different implementations, unique to 
> Xen?  If that's the case, is there a 'schedutil' equivalent? or one that's 
> planned?
As far as I understand it, they are independent of the Domain-0 cpufreq 
governors (or if they aren't, then Linux and NetBSD have identical 
behavior in their CPU frequency governors, which would not surprise me 
all that much).
Assuming that's the case, 'ondemand' is the closest to 'schedutil', as 
schedutil in Linux is just a smarter version of the ondemand governor. 
Ondemand takes only the processor utilization and the current frequency 
into account, while schedutil also factors in a bunch of other things.
I'm not a Xen developer myself, but based on my very limited knowledge 
of the internals of Xen and my marginally greater knowledge of the 
internals of Linux, I'd say it's not likely that a governor equivalent 
to schedutil is even possible on Xen without all the domains 
co-operating (a lot of the stats that schedutil looks at are derived 
from parts of the process state which would translate to guest kernel 
internal state in the context of Xen).
_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxx
https://lists.xen.org/xen-users