On Sun, 2017-03-26 at 22:12 +0100, Patrick O'Callaghan wrote:
> No-one has commented on the keyboard overrun issue I asked about.
> That's really more noticeable at this stage than file I/O. I moved the
> wireless hub to a USB-3 port and again it may have made a slight
> difference, but some stutte
On Sun, 2017-03-26 at 19:41 -0700, Nick S wrote:
> Do you pass your USB keyboard or do you use emulated keyboard and one of
> QXL windows to grab/release focus?
The latter.
> I use the second option and I had to
> follow the steps from the following link to deal with performance proplems
> with k
Do you pass your USB keyboard or do you use emulated keyboard and one of
QXL windows to grab/release focus? I use the second option and I had to
follow the steps from the following link to deal with performance proplems
with key repeats:
http://serverfault.com/questions/624690/windows-guest-on-kvm-
On Sun, 2017-03-26 at 17:04 -0500, Zachary Boley wrote:
> Also some source:
> https://access.redhat.com/documentation/en-US/Red_Hat_Enterprise_Linux/6/html/Virtualization_Tuning_and_Optimization_Guide/chap-Virtualization_Tuning_Optimization_Guide-BlockIO.html
>
OK thanks.
(BTW the top-posting is
Also some source:
https://access.redhat.com/documentation/en-US/Red_Hat_Enterprise_Linux/6/html/Virtualization_Tuning_and_Optimization_Guide/chap-Virtualization_Tuning_Optimization_Guide-BlockIO.html
I really couldnt find the exact one i read but it basically says to do Raw
with what i said above.
Just normal virtio, I have it set to that, don't know how I would go about
setting virtio scsi or if I would need too
On Mar 26, 2017 12:45 PM, "Nick Sarnie" wrote:
> Sorry, is that a SCSI controller set to virtio type, or the virtio option
> selected for the disk instead of SCSI? I've seen both
On Sun, 2017-03-26 at 08:31 -0600, Alex Williamson wrote:
> On Sun, Mar 26, 2017 at 4:33 AM, Patrick O'Callaghan wrote:
>
> > On Sun, 2017-03-26 at 10:58 +0100, Bronek Kozicki wrote:
> > > Assuming you use libvirt, make sure to use vCPU pinning. For disk
> >
> > access, try cache='writeback' io=
On Sun, 2017-03-26 at 11:58 -0500, Zachary Boley wrote:
> From what I've read Red Hat recommends virtio with raw on no cache with io
> thread due to the reasons listed above. Not sure about LVM but they did
> also say (or someone did) do not use BTRFS for keeping the image.
Can you give a referenc
On Sun, 2017-03-26 at 13:45 -0400, Nick Sarnie wrote:
> Sorry, is that a SCSI controller set to virtio type, or the virtio option
> selected for the disk instead of SCSI? I've seen both recommended.
>
The latter. I'd be interested in knowing if virtio-scsi has any
advantages.
poc
__
Sorry, is that a SCSI controller set to virtio type, or the virtio option
selected for the disk instead of SCSI? I've seen both recommended.
Thanks,
Sarnex
On Sun, Mar 26, 2017 at 12:58 PM, Zachary Boley wrote:
> From what I've read Red Hat recommends virtio with raw on no cache with io
> threa
>From what I've read Red Hat recommends virtio with raw on no cache with io
thread due to the reasons listed above. Not sure about LVM but they did
also say (or someone did) do not use BTRFS for keeping the image.
The only optimization I would immediately recommended is to do
host-passthrough as t
On 26/03/2017 15:31, Alex Williamson wrote:
On Sun, Mar 26, 2017 at 4:33 AM, Patrick O'Callaghan mailto:p...@usb.ve>> wrote:
On Sun, 2017-03-26 at 10:58 +0100, Bronek Kozicki wrote:
> Assuming you use libvirt, make sure to use vCPU pinning. For disk access,
try cache='writeback' io='thr
On Sun, Mar 26, 2017 at 4:33 AM, Patrick O'Callaghan wrote:
> On Sun, 2017-03-26 at 10:58 +0100, Bronek Kozicki wrote:
> > Assuming you use libvirt, make sure to use vCPU pinning. For disk
> access, try cache='writeback' io='threads'. If you switch to scsio-vfio,
> this will give you the ability
On Sun, 2017-03-26 at 09:17 -0400, Joshua Lee wrote:
> On Sun, Mar 26, 2017 at 6:33 AM, Patrick O'Callaghan wrote:
>
> > On Sun, 2017-03-26 at 10:58 +0100, Bronek Kozicki wrote:
> > > Assuming you use libvirt, make sure to use vCPU pinning. For disk
> >
> > access, try cache='writeback' io='thre
On Sun, Mar 26, 2017 at 6:33 AM, Patrick O'Callaghan wrote:
> On Sun, 2017-03-26 at 10:58 +0100, Bronek Kozicki wrote:
> > Assuming you use libvirt, make sure to use vCPU pinning. For disk
> access, try cache='writeback' io='threads'. If you switch to scsio-vfio,
> this will give you the ability
On Sun, 2017-03-26 at 10:58 +0100, Bronek Kozicki wrote:
> Assuming you use libvirt, make sure to use vCPU pinning. For disk access, try
> cache='writeback' io='threads'. If you switch to scsio-vfio, this will give
> you the ability to define queue length which might additionally improve IO.
> A
it might enable some additional optimizations.
However given you host seem to have little spare capacity, YMMV
B.
Original Message
From: Patrick O'Callaghan
Sent: Sunday, 26 March 2017 09:25
To: vfio-users@redhat.com
Subject: [vfio-users] Speed tips requested
I'm running Windows 10 in
I'm running Windows 10 in a KVM/QEMU VM under Fedora 25. The host is a
16GB i3770 and I have 4 threads (2 cores) dedicated to the VM with CPU
pinning and 8GB hugepages. The passthrough GPU is an Nvidia Geforce GTX
1050.
The guest disk is a 100GB raw file under vfio. The host disk is a 1TB
Toshiba
18 matches
Mail list logo
