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

[Stefan Priebe - Profihost AG]

Am 07.02.2014 10:15, schrieb Dr. David Alan Gilbert:
> * Stefan Priebe - Profihost AG (address@hidden) wrote:
>> Am 07.02.2014 09:15, schrieb Alexandre DERUMIER:
>>>
>>> do you use xbzrle for live migration ?
>>
>> no - i'm really stucked right now with this. Biggest problem i can't
>> reproduce with test machines ;-(
> 
> Only being able to test on your production VMs isn't fun;
> is it possible or you to run an extra program on these VMs - e.g.
> if we came up with a simple (userland) memory test?

You mean to reproduce?

I already tried https://code.google.com/p/stressapptest/ while migrating
on a test VM but this works fine.

I also tried running mysql bench while migrating on a test vm and this
works too ;-(

Stefan

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