<div dir="auto">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</div><div class="gmail_extra"><br><div class="gmail_quote">On Mar 26, 2017 12:45 PM, "Nick Sarnie" <<a href="mailto:commendsarnex@gmail.com">commendsarnex@gmail.com</a>> wrote:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div>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.<br><br></div>Thanks,<br></div>Sarnex<br></div><div class="gmail_extra"><br><div class="gmail_quote">On Sun, Mar 26, 2017 at 12:58 PM, Zachary Boley <span dir="ltr"><<a href="mailto:zboley00@gmail.com" target="_blank">zboley00@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="auto">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. <div dir="auto"><br></div><div dir="auto">The only optimization I would immediately recommended is to do host-passthrough as the CPU option in your guests xml. It's noticeably different assuming you haven't already done it</div></div><div class="m_7673045077105815381HOEnZb"><div class="m_7673045077105815381h5"><div class="gmail_extra"><br><div class="gmail_quote">On Mar 26, 2017 11:13 AM, "Bronek Kozicki" <<a href="mailto:brok@spamcop.net" target="_blank">brok@spamcop.net</a>> wrote:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">On 26/03/2017 15:31, Alex Williamson wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
On Sun, Mar 26, 2017 at 4:33 AM, Patrick O'Callaghan <<a href="mailto:poc@usb.ve" target="_blank">poc@usb.ve</a><br>
<mailto:<a href="mailto:poc@usb.ve" target="_blank">poc@usb.ve</a>>> wrote:<br>
<br>
On Sun, 2017-03-26 at 10:58 +0100, Bronek Kozicki wrote:<br>
> 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. Also, try QCOW2 format for guest disk, it might enable some additional optimizations. However given you host seem to have little spare capacity, YMMV<br>
<br>
Thanks. I'm already using CPU pinning as I said. The disk options are<br>
both set to "hypervisor default" so I'll try changing them. I'd<br>
configured the guest disk as 'raw' assuming that would be faster than<br>
QCOW2 but I'll look into it.<br>
<br>
<br>
<br>
Generally the recommendation is to use raw (not sparse), LVM, or a block<br>
device for the best performance. QCOW is never going to be as fast as<br>
these at writing unused blocks since it needs to go out and allocate new<br>
blocks from the underlying file system when this happens.<br>
</blockquote>
<br>
I am not going to argue with your experience here, only wanted to note that QCOW2 can be created with preallcation=falloc (or full, which is not very useful) which means there will no extra allocations in the rutime. Everything will be allocated at the moment of disk creation with qemu-img create -f qcow2 -o preallcation=falloc ....<br>
<br>
<br>
<br>
B.<br>
<br>
______________________________<wbr>_________________<br>
vfio-users mailing list<br>
<a href="mailto:vfio-users@redhat.com" target="_blank">vfio-users@redhat.com</a><br>
<a href="https://www.redhat.com/mailman/listinfo/vfio-users" rel="noreferrer" target="_blank">https://www.redhat.com/mailman<wbr>/listinfo/vfio-users</a><br>
</blockquote></div></div>
</div></div><br>______________________________<wbr>_________________<br>
vfio-users mailing list<br>
<a href="mailto:vfio-users@redhat.com" target="_blank">vfio-users@redhat.com</a><br>
<a href="https://www.redhat.com/mailman/listinfo/vfio-users" rel="noreferrer" target="_blank">https://www.redhat.com/mailman<wbr>/listinfo/vfio-users</a><br>
<br></blockquote></div><br></div>
</blockquote></div></div>