Re: [Qemu-devel] [pve-devel] QEMU LIve Migration - swap_free: Bad swap file entry

[Alexandre DERUMIER]

do you use xbzrle for live migration ?



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

De: "Stefan Priebe" <address@hidden>
À: "Dr. David Alan Gilbert" <address@hidden>
Cc: "Alexandre DERUMIER" <address@hidden>, "qemu-devel" <address@hidden>
Envoyé: Jeudi 6 Février 2014 21:00:27
Objet: Re: [Qemu-devel] [pve-devel] QEMU LIve Migration - swap_free: Bad swap 
file entry

Hi,
Am 06.02.2014 20:51, schrieb Dr. David Alan Gilbert:
> * Stefan Priebe - Profihost AG (address@hidden) wrote:
>> some more things which happen during migration:
>>
>> php5.2[20258]: segfault at a0 ip 0000000000740656 sp 00007fff53b694a0
>> error 4 in php-cgi[400000+6d7000]
>>
>> php5.2[20249]: segfault at c ip 00007f1fb8ecb2b8 sp 00007fff642d9c20
>> error 4 in ZendOptimizer.so[7f1fb8e71000+147000]
>>
>> cron[3154]: segfault at 7f0008a70ed4 ip 00007fc890b9d440 sp
>> 00007fff08a6f9b0 error 4 in libc-2.13.so[7fc890b67000+182000]
>
> OK, so lets just assume some part of memory (or CPU state, or memory
> loaded off disk...)
>
> You said before that it was happening on a 32GB image - is it *only*
> happening on a 32GB or bigger VM, or is it just more likely?

Not image, memory. I've only seen this with vms having more than 16GB or
32GB memory. But maybe this also indicates that just the migration takes
longer.

> I think you also said you were using 1.7; have you tried an older
> version - i.e. is this a regression in 1.7 or don't we know?
Don't know. Sadly i cannot reproduce this with test VMs only with
production ones.

Stefan

> Dave
> --
> Dr. David Alan Gilbert / address@hidden / Manchester, UK
>