Re: [kvm-devel] [ANNOUNCE] kvm-51 release

[Avi K. <av...@qu...>]

Farkas Levente wrote:
> Avi Kivity wrote:
>   
>> Farkas Levente wrote:
>>     
>>> Avi Kivity wrote:
>>>  
>>>       
>>>> If you're having trouble on AMD systems, please try this out.
>>>>     
>>>>         
>>> this version worse than kvm-50:-(
>>> setup:
>>> - host:
>>>   - Intel(R) Core(TM)2 Quad CPU Q6600  @ 2.40GHz
>>>   - Intel S3000AHV
>>>   - 8GB RAM
>>>   - CentOS-5
>>>   - kernel-2.6.18-8.1.14.el5 x86_64 64bit
>>> - guest-1:
>>>   - CentOS-5
>>>   - kernel-2.6.18-8.1.14.el5 i386 32bit
>>> - guest-2:
>>>   - CentOS-5
>>>   - kernel-2.6.18-8.1.14.el5 x86_64 64bit
>>> - guest-3:
>>>   - Mandrake-9
>>>   - kernel-2.4.19.16mdk-1-1mdk 32bit
>>> - guest-4:
>>>   - Windows XP Professional 32bit
>>> smp not working on any centos guest (guests are hang during boot). even
>>> the host crash. the worst thing is the host crash during boot with
>>> another stack trace which i was not able to log.
>>> i really would like to see some kind of stable version other then
>>> kvm-36. i see there is a huge ongoing work on ia64, virtio, libkmv and
>>> arch rearrange, but wouldn't it be better to fix these basic issues
>>> first? like running two smp guest (32 and 64) on 64 smp host, just to
>>> boot until the login screen.
>>> this is when the guest stop and the host dump it:
>>>   
>>>       
>> [...]
>>
>>     
>>> Call Trace:
>>>  <IRQ>  [<ffffffff800b2cd7>] softlockup_tick+0xdb/0xed
>>>  [<ffffffff80093493>] update_process_times+0x42/0x68
>>>  [<ffffffff80073e08>] smp_local_timer_interrupt+0x23/0x47
>>>  [<ffffffff800744ca>] smp_apic_timer_interrupt+0x41/0x47
>>>  [<ffffffff8005bd4a>] apic_timer_interrupt+0x66/0x6c
>>>  <EOI>  [<ffffffff88201d8b>] :kvm:kvm_flush_remote_tlbs+0x16e/0x188
>>>  [<ffffffff88201d78>] :kvm:kvm_flush_remote_tlbs+0x15b/0x188
>>>  [<ffffffff8820101b>] :kvm:ack_flush+0x0/0x1
>>>   
>>>       
>> Are you sure this is a regression relative to kvm-50?  Please recheck.
>>     
>
> i', not sure this's a regression since kvm-50 was so terrible slow that
> we switch back to kvm-46. but i can't catch any stack trace with kvm-50.
> anyway even if it's not a regression it's currently not working with smp.
>
>   

I can't reproduce this on a centos system here running 2.6.18-8.el5 with 
a 4-way FC6 x86_64 as guest.  It appears to survive a kernel compile.

What does one need to do in order to reproduce this?

-- 
error compiling committee.c: too many arguments to function