openstack team mailing list archive

[John Garbutt <John.Garbutt@xxxxxxxxxx>]

I have seen this issue myself when I had a clock skew between the compute nodes.
The scheduler assumed one of my nodes was dead because it was so long since it reported, because the compute clock was behind the schedulers clock.
I think that was using Cactus, can't 100% remember now.

Cheers,
John

From: openstack-bounces+john.garbutt=eu.citrix.com@xxxxxxxxxxxxxxxxxxx [mailto:openstack-bounces+john.garbutt=eu.citrix.com@xxxxxxxxxxxxxxxxxxx] On Behalf Of Sateesh Chodapuneedi
Sent: 09 November 2011 12:03
To: Razique Mahroua; openstack (openstack@xxxxxxxxxxxxxxxxxxx)
Subject: Re: [Openstack] Fwd: Four compute-node, everytime the 1st and 2nd are choosen

Hi Razique,

Which scheduler are you using?
And what is the underlying hypervisor?

Regards,
Sateesh

----------------------------------------------------------------------------------------------------------------------------
"This e-mail message is for the sole use of the intended recipient(s) and may contain confidential and/or privileged information. Any unauthorized review, use, disclosure, or distribution is prohibited. If you are not the intended recipient, please contact the sender by reply e-mail and destroy all copies of the original message."


From: openstack-bounces+sateesh.chodapuneedi=citrix.com@xxxxxxxxxxxxxxxxxxx [mailto:openstack-bounces+sateesh.chodapuneedi=citrix.com@xxxxxxxxxxxxxxxxxxx] On Behalf Of Razique Mahroua
Sent: Wednesday, November 09, 2011 3:22 PM
To: openstack (openstack@xxxxxxxxxxxxxxxxxxx)
Subject: [Openstack] Fwd: Four compute-node, everytime the 1st and 2nd are choosen

I confirm that issue,
since I've disabled the nova-compute service on the first 3 nodes, and when I spawn a new instance, now it goes to the last one, so the scheduler would have been able to choose them I've now a disbalanced farm :

Host 1 : High load (11 instances)
Host2 : Middel load (9 instance)
Host 3 : null load (0 instances)
Host 4 : null load (1 instance)

I use nova 2011.2 (Cactus stable)

Thanks

Début du message réexpédié :

De : Razique Mahroua <razique.mahroua@xxxxxxxxx<mailto:razique.mahroua@xxxxxxxxx>>
Objet : Four compute-node, everytime the 1st and 2nd are choosen
Date : 9 novembre 2011 10:39:17 HNEC
À : "openstack (openstack@xxxxxxxxxxxxxxxxxxx<mailto:openstack@xxxxxxxxxxxxxxxxxxx>)" <openstack@xxxxxxxxxxxxxxxxxxx<mailto:openstack@xxxxxxxxxxxxxxxxxxx>>

Hl all,
I've four compute-nodes, around 20 instances runing.
I've four nodes registered to nova-scheduler (nova-manage shows them)
but everytime I spawn a new instance, the 3rd an 4th node are never choosen for the instances.
the ressources are the same on the nodes (around 24gb of ram), they are idle, and available.
Can I force the scheduler to use them for an instance ?
Thanks
Razique - doc team -