[pve-devel] cgroups implementation proposal for kvm (cpuunits support for kvm)

[Alexandre DERUMIER]

Hi,

I have do some tests,

and I don't know why, but cpu.shares cgroup values is working fine, but only with openvz containers ....

With kvm process, it does'nt work, and with other host process it doesn't work too ....

So, maybe openvz patches made changes to cgroups ..?.. 

I'll try to do more test with a redhat stock kernel (it's working fine on rhel 6.2), maybe after proxmox 2.0 release.

The main idea was to have a working fairuse scheduling with kvm and virtio devices, without patching qemu.

I'll keep you in touch ...

- Alexandre








----- Mail original ----- 

De: "Dietmar Maurer" <dietmar at proxmox.com> 
À: "Dietmar Maurer" <dietmar at proxmox.com>, "Alexandre DERUMIER" <aderumier at odiso.com> 
Cc: pve-devel at pve.proxmox.com 
Envoyé: Lundi 19 Décembre 2011 20:01:49 
Objet: RE: [pve-devel] cgroups implementation proposal for kvm (cpuunits support for kvm) 

> > cpu.share is working like cpuunits, it's not limiting the cpu, only 
> > give priorities between process when the host cpus are 100% 
> 
> Sure, but why do you want different priorities? 

Anyways, pve-qemu-kvm with fairsched patch should exactly do that. 

- Dietmar 




-- 

-- 




	
	Alexandre Derumier 
Ingénieur système 
e-mail : aderumier at odiso.com 
Tél : +33 (0)3 20 68 88 90 
Fax : +33 (0)3 20 68 90 81 
45 Bvd du Général Leclerc 
59100 ROUBAIX - FRANCE 













-------------- next part --------------
A non-text attachment was scrubbed...
Name: aderumier.vcf
Type: text/x-vcard
Size: 183 bytes
Desc: not available
URL: <http://lists.proxmox.com/pipermail/pve-devel/attachments/20111220/8988e0a6/attachment.vcf>