[pve-devel] qemu-server : cgroups implementation through systemd-run

Alexandre DERUMIER aderumier at odiso.com
Sun May 31 18:47:10 CEST 2015


>>I though it apply globally, but I am unsure now. 

Just tested, you are right, it's globally for the number of cpus in the groups (default all cpus).

so , with 20cores host, and cpus limit 2, 

you can indeed use 2 cpu full, or split the load accross all cpus.

(It's just a counter with limit after a number of cpu cycles used, but can be used on any cpu)


>>Anyway, I guess I will rename 'cpus' into 'cpulimit', and we can then add further 
>>cpu restrictions in future.

I agree with that, it's more clear to understand.


----- Mail original -----
De: "dietmar" <dietmar at proxmox.com>
À: "aderumier" <aderumier at odiso.com>
Cc: "pve-devel" <pve-devel at pve.proxmox.com>
Envoyé: Samedi 30 Mai 2015 19:26:54
Objet: Re: [pve-devel] qemu-server : cgroups implementation through systemd-run

> But maybe I'm wrong, 
> 
> I don't know if cfs_quota_us value apply globally on all cpus , or 
> individually on each cpu. 

I though it apply globally, but I am unsure now. 

Anyway, I guess I will rename 'cpus' into 'cpulimit', and we can then add 
further 
cpu restrictions in future. 


More information about the pve-devel mailing list