> On 28 Mar 2017, at 14:54, Gianluca Cecchi <[email protected]> wrote: > > On Tue, Mar 28, 2017 at 1:50 PM, Michal Skrivanek > <[email protected] <mailto:[email protected]>> wrote: > > > On 28 Mar 2017, at 13:41, Jiří Sléžka <[email protected] > > <mailto:[email protected]>> wrote: > > > > On 03/28/2017 12:34 AM, Jiří Sléžka wrote: > >> Hi all, > >> > >> I have just upgraded ovirt manager from 4.1.0 to 4.1.1, then I have > >> upgraded one host. After reboot and activation of this host some vms > >> started to migrate here. > >> > >> Some time after migration CPU of this vms go to 100% and vms become > >> unreachable. > >> > >> There is /var/log/libvirt/qemu/hypnos.log (hypnos is one of this vms) > >> https://pastebin.com/U30xfBMJ <https://pastebin.com/U30xfBMJ> > >> > >> Powering off and starting again solve this but I would like to have a > >> glue what is happening. > >> > >> I suspect this line > >> > >> 2017-03-27T22:09:23.746710Z qemu-kvm: warning: TSC frequency mismatch > >> between VM (2600031 kHz) and host (2100024 kHz), and TSC scaling > >> unavailable > >> > >> Original host uses "AMD Opteron(TM) Processor 6238" with "cpu MHz: > >> 2600.113" and upgraded host uses "AMD Opteron(tm) Processor 6172" with > >> "cpu MHz: 2100.097". > > > > It looks like it isn't problem with 4.1.1 at all. > > > > There is just missing tsc_scale cpu flag on our older AMD CPUs... > > > > http://unix.stackexchange.com/questions/296636/100-cpu-utilisation-and-hang-after-virsh-migrate > > > > <http://unix.stackexchange.com/questions/296636/100-cpu-utilisation-and-hang-after-virsh-migrate> > > > > This is probably unsolvable hw problem, right? > > And this is without host-model CPU type? > That 6172 should be Opteron G3…is that what you have set in your Cluster? > > Thanks, > michal > > > > Should I care about it too? > In my case on my AMD hypervisors: > > [g.cecchi@ovmsrv06 ~]$ cat /proc/cpuinfo | grep tsc_ > [g.cecchi@ovmsrv06 ~]$ > > model name : Dual-Core AMD Opteron(tm) Processor 8222 > flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov > pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt rdtscp lm > 3dnowext 3dnow art rep_good nopl extd_apicid pni cx16 lahf_lm cmp_legacy svm > extapic cr8_legacy > > The related cluster is set as "AMD Opteron G2”
I suppose not unless you have newer Opterons. And if you do it’s a matter of testing it I guess, whether the enforced “AMD Opteron G2” on a newer Opteron works correctly. Thanks, michal > > Thanks in advance, > Gianluca
_______________________________________________ Users mailing list [email protected] http://lists.ovirt.org/mailman/listinfo/users
