[PVE-User] 100% CPU usage after live migration onheterogeneouscluster (Xeon E5345 and Xeon 5405)

[Alexandre DERUMIER]

Hi,

Try with pve-kernel 3.10 , I have seen some similar bugs but with opteron.

Some flags are not always filtered by kvm module in 2.6.32.




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

De: "Gilberto Nunes" <gilberto.nunes32 at gmail.com> 
À: "Chris Murray" <chrismurray84 at gmail.com> 
Cc: pve-user at pve.proxmox.com 
Envoyé: Vendredi 5 Septembre 2014 15:35:34 
Objet: Re: [PVE-User] 100% CPU usage after live migration onheterogeneouscluster (Xeon E5345 and Xeon 5405) 


Just to complete this subject: Is it a recommendation that we used the same hardware or not necessarily?? 




2014-09-05 10:23 GMT-03:00 Chris Murray < chrismurray84 at gmail.com > : 





Of course the typical thing has happened; as soon as I ask for help, I’ve resolved it myself. 

I enabled No Execute in the BIOS of host ‘B’. VMs will now migrate back and forth without complaint. 



From: pve-user [mailto: pve-user-bounces at pve.proxmox.com ] On Behalf Of Chris Murray 
Sent: 05 September 2014 14:08 
To: pve-user at pve.proxmox.com 
Subject: Re: [PVE-User] 100% CPU usage after live migration onheterogeneouscluster (Xeon E5345 and Xeon 5405) 



Also if it helps: 

'A' 

cat /proc/cpuinfo | grep flags | uniq 
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_good aperfmperf pni dtes64 monitor ds_cpl vmx tm2 ssse3 cx16 xtpr pdcm dca sse4_1 lahf_lm dts tpr_shadow vnmi flexpriority 


'B' 

cat /proc/cpuinfo | grep flags | uniq 
flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall lm constant_tsc arch_perfmon pebs bts rep_good aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm dca lahf_lm dts tpr_shadow 


I can already see ‘nx’ in there, which has got me wondering. 

Thanks again. 



From: pve-user [ mailto:pve-user-bounces at pve.proxmox.com ] On Behalf Of Chris Murray 
Sent: 05 September 2014 14:03 
To: pve-user at pve.proxmox.com 
Subject: [PVE-User] 100% CPU usage after live migration on heterogeneouscluster (Xeon E5345 and Xeon 5405) 

Hi all, 

I'm experiencing the same issue as the following post, but I can't register to ask if there was ever a solution as the Image Verification section of the registration page tells me "Input error: Invalid Referer" 
http://188.165.151.221/threads/16171-PX-3-0-live-migration-(node-to-node)-freeze-VM-on-different-hardware 

I'm on 3.2 and this particular cluster has two nodes. I'll call them 'A' and 'B' 

'A' has an Intel Xeon E5405. 
'B' has two Intel Xeon E5345 (the same as the post. Interestingly, the issue is in migrating * to * this node, as it is in the forum post) 

Start a VM on node B. 
Migrate to A. 
This works fine. 
Migrate to B. 
This is also fine. 

Power down the VM, start it up from node A 
Migrate to B. 
100% CPU. VM unresponsive. 
Migrate to A: 
VM comes back to life again 

I’m guessing this is related to the capability of the two CPUs being different. I've set the VM's CPU to Conroe (to oldest Xeon?) and qemu64, neither of which made any difference. It’s now back to the default of KVM64. 

Any ideas? 

Thanks, 
Chris 



Node 'A' 

proxmox-ve-2.6.32: 3.2-136 (running kernel: 2.6.32-32-pve) 
pve-manager: 3.2-30 (running version: 3.2-30/1d095287) 
pve-kernel-2.6.32-32-pve: 2.6.32-136 
pve-kernel-2.6.32-29-pve: 2.6.32-126 
lvm2: 2.02.98-pve4 
clvm: 2.02.98-pve4 
corosync-pve: 1.4.7-1 
openais-pve: 1.1.4-3 
libqb0: 0.11.1-2 
redhat-cluster-pve: 3.2.0-2 
resource-agents-pve: 3.9.2-4 
fence-agents-pve: 4.0.10-1 
pve-cluster: 3.0-14 
qemu-server: 3.1-34 
pve-firmware: 1.1-3 
libpve-common-perl: 3.0-19 
libpve-access-control: 3.0-15 
libpve-storage-perl: 3.0-22 
pve-libspice-server1: 0.12.4-3 
vncterm: 1.1-8 
vzctl: 4.0-1pve6 
vzprocps: 2.0.11-2 
vzquota: 3.1-2 
pve-qemu-kvm: 2.1-5 
ksm-control-daemon: 1.1-1 
glusterfs-client: 3.5.2-1 


Node 'B' 

proxmox-ve-2.6.32: 3.2-136 (running kernel: 2.6.32-32-pve) 
pve-manager: 3.2-30 (running version: 3.2-30/1d095287) 
pve-kernel-2.6.32-32-pve: 2.6.32-136 
pve-kernel-2.6.32-29-pve: 2.6.32-126 
lvm2: 2.02.98-pve4 
clvm: 2.02.98-pve4 
corosync-pve: 1.4.7-1 
openais-pve: 1.1.4-3 
libqb0: 0.11.1-2 
redhat-cluster-pve: 3.2.0-2 
resource-agents-pve: 3.9.2-4 
fence-agents-pve: 4.0.10-1 
pve-cluster: 3.0-14 
qemu-server: 3.1-34 
pve-firmware: 1.1-3 
libpve-common-perl: 3.0-19 
libpve-access-control: 3.0-15 
libpve-storage-perl: 3.0-22 
pve-libspice-server1: 0.12.4-3 
vncterm: 1.1-8 
vzctl: 4.0-1pve6 
vzprocps: 2.0.11-2 
vzquota: 3.1-2 
pve-qemu-kvm: 2.1-5 
ksm-control-daemon: 1.1-1 
glusterfs-client: 3.5.2-1 
_______________________________________________ 
pve-user mailing list 
pve-user at pve.proxmox.com 
http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-user 







-- 


Obrigado 


Cordialmente 


Gilberto Ferreira 



Konnecta TI Tecnologia - Sistemas de Virtualização, Soluções de Armazenamento de Dados, Criação de SAN/NAS, Zimbra Mail Server, Implantação de Linux e Windows server. 



Fundação Softville 
Rua Otto Boehm, 48 



(47) 9676-7530 


Skype: gilberto.nunes36 


www.konnectati.com.br 
blog.konnectati.com.br 
_______________________________________________ 
pve-user mailing list 
pve-user at pve.proxmox.com 
http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-user