[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH] hw/virtio: enable common virtio feature for mmi
From: |
Ming Lei |
Subject: |
Re: [Qemu-devel] [PATCH] hw/virtio: enable common virtio feature for mmio device |
Date: |
Wed, 2 Jul 2014 20:36:58 +0800 |
On Wed, Jul 2, 2014 at 8:34 PM, Michael S. Tsirkin <address@hidden> wrote:
> On Wed, Jun 04, 2014 at 10:05:55AM +0800, Ming Lei wrote:
>> Both 'indirect_desc' and 'event_idx' are bus independent features,
>> and they should be enabled for mmio devices too.
>>
>> On arm64 quad core VM(qemu-kvm), the patch can increase block I/O
>> performance a lot with latest linux tree:
>> - without the patch: 14K IOPS
>> - with the patch: 34K IOPS
>>
>> fio script:
>> [global]
>> direct=1
>> bsrange=4k-4k
>> timeout=10
>> numjobs=4
>> ioengine=libaio
>> iodepth=64
>>
>> filename=/dev/vdc
>> group_reporting=1
>>
>> [f1]
>> rw=randread
>>
>> Cc: Peter Maydell <address@hidden>
>> Signed-off-by: Ming Lei <address@hidden>
>
> Applied, thanks!
> I'm guessing this doesn't affect cross-version
> migration since virtio-mmio isn't used on
> a PC and that's the only versioned machine.
Yes, I think so.
Even ARM/ARM64 will use virtio-pci if kernel support is
ready because virtio-pci has better support than virtio-mmio.
Thanks,