kvm-devel

Re: [kvm-devel] [RFC] fix VMX TSC synchronicity

[Will T. <wi...@tr...>]

Hello,

Just thought i'd mention that this patch caused disk corruption in my
virtual machines, particularly when using scsi emulation.

I got few errors like this as well:

lsi_scsi: error: ORDERED queue not implemented
lsi_scsi: error: IO with unknown tag 65577

Regards,

Will

Re: [kvm-devel] [RFC] fix VMX TSC synchronicity

[Marcelo T. <ma...@kv...>]

On Sat, Jan 12, 2008 at 02:11:30PM +1100, Will Trives wrote:
> Hello,
> 
> Just thought i'd mention that this patch caused disk corruption in my
> virtual machines, particularly when using scsi emulation.
> 
> I got few errors like this as well:
> 
> lsi_scsi: error: ORDERED queue not implemented
> lsi_scsi: error: IO with unknown tag 65577

Hi Will,

Can you please be more descriptive of your environment? What guest OS  ?
How many CPU's do you have assigned to it                              ?

Are you sure you're talking about the "VMX TSC" patch in the Subject:
line?

Thanks

Re: [kvm-devel] [RFC] fix VMX TSC synchronicity

[Will T. <wi...@tr...>]

Hello,

64 bit environment Intel Q6600 processor.

I did hand apply the patch so I might have got something wrong.

Guest was a 32 bit kubuntu 7.10.

Basically I just mounted a few disk images with " -drive
file=/whatever,if=scsi " and used gparted to copy a partition from one
to the other.

It's probably something I have done wrong, i'll test it again in a few
more days.

Regards,

Will

On Sat, 2008-01-12 at 10:28 -0200, Marcelo Tosatti wrote:
> On Sat, Jan 12, 2008 at 02:11:30PM +1100, Will Trives wrote:
> > Hello,
> > 
> > Just thought i'd mention that this patch caused disk corruption in my
> > virtual machines, particularly when using scsi emulation.
> > 
> > I got few errors like this as well:
> > 
> > lsi_scsi: error: ORDERED queue not implemented
> > lsi_scsi: error: IO with unknown tag 65577
> 
> Hi Will,
> 
> Can you please be more descriptive of your environment? What guest OS  ?
> How many CPU's do you have assigned to it                              ?
> 
> Are you sure you're talking about the "VMX TSC" patch in the Subject:
> line?
> 
> Thanks

Re: [kvm-devel] [RFC] fix VMX TSC synchronicity

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

Will Trives wrote:
> Hello,
>
> 64 bit environment Intel Q6600 processor.
>
> I did hand apply the patch so I might have got something wrong.
>
> Guest was a 32 bit kubuntu 7.10.
>
> Basically I just mounted a few disk images with " -drive
> file=/whatever,if=scsi " and used gparted to copy a partition from one
> to the other.
>
> It's probably something I have done wrong, i'll test it again in a few
> more days.
>
>   

I've trashed more than one image by running multiple guests with the 
same image, can this be the case here?

-- 
Any sufficiently difficult bug is indistinguishable from a feature.

Re: [kvm-devel] [PATCH] kvm: qemu: remove SIGUSR2 from io_sigset

[Will T. <wi...@tr...>]

Hello,

This patch :

kvm: qemu: remove SIGUSR2 from io_sigset

Applied 15th Jan 2008 looks to kill I/O performance for me. As soon as I
revert it my VMs are much faster. I don't really use SMP for my guests,
perhaps this patch made uniprocessor VMs slower ?


Regards,

Will Trives

Re: [kvm-devel] [PATCH] kvm: qemu: remove SIGUSR2 from io_sigset

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

Will Trives wrote:
> Hello,
>
> This patch :
>
> kvm: qemu: remove SIGUSR2 from io_sigset
>
> Applied 15th Jan 2008 looks to kill I/O performance for me. As soon as I
> revert it my VMs are much faster. I don't really use SMP for my guests,
> perhaps this patch made uniprocessor VMs slower ?
>
>
>   

How are you measuring performance?

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

Re: [kvm-devel] [PATCH] kvm: qemu: remove SIGUSR2 from io_sigset

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

Avi Kivity wrote:
> Will Trives wrote:
>> Hello,
>>
>> This patch :
>>
>> kvm: qemu: remove SIGUSR2 from io_sigset
>>
>> Applied 15th Jan 2008 looks to kill I/O performance for me. As soon as I
>> revert it my VMs are much faster. I don't really use SMP for my guests,
>> perhaps this patch made uniprocessor VMs slower ?
>>
>>
>>   
>
> How are you measuring performance?
>

Never mind, fio shows it.

Will investigate.

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