Re: [Qemu-devel] [PATCH v4 00/13] aio: experimental virtio-blk polling mode

2016-12-06 Thread Stefan Hajnoczi
On Mon, Dec 05, 2016 at 10:40:49AM -0600, Karl Rister wrote: > On 12/05/2016 08:56 AM, Stefan Hajnoczi wrote: > > > > Karl: do you have time to run a bigger suite of benchmarks to identify a > > reasonable default poll-max-ns value? Both aio=native and aio=threads > > are important. > > > > If

Re: [Qemu-devel] [PATCH v4 00/13] aio: experimental virtio-blk polling mode

2016-12-05 Thread Karl Rister
On 12/05/2016 08:56 AM, Stefan Hajnoczi wrote: > Karl: do you have time to run a bigger suite of benchmarks to identify a > reasonable default poll-max-ns value? Both aio=native and aio=threads > are important. > > If there is a sweet spot that improves performance without pathological > cases

Re: [Qemu-devel] [PATCH v4 00/13] aio: experimental virtio-blk polling mode

2016-12-05 Thread Stefan Hajnoczi
On Mon, Dec 05, 2016 at 06:25:49PM +0800, Fam Zheng wrote: > On Thu, 12/01 19:26, Stefan Hajnoczi wrote: > > One way to avoid the costly exit is to use polling instead of notification. > > Testing with fio on virtio-blk backed by NVMe device, I can see significant > performance improvement with

Re: [Qemu-devel] [PATCH v4 00/13] aio: experimental virtio-blk polling mode

2016-12-05 Thread Christian Borntraeger
On 12/01/2016 08:26 PM, Stefan Hajnoczi wrote: > v4: > * Added poll time self-tuning algorithm [Christian and Paolo] > * Try a single iteration of polling to avoid non-blocking > ppoll(2)/epoll_wait(2) [Paolo] > * Reordered patches to make performance analysis easier - see below This looks

Re: [Qemu-devel] [PATCH v4 00/13] aio: experimental virtio-blk polling mode

2016-12-05 Thread Fam Zheng
On Thu, 12/01 19:26, Stefan Hajnoczi wrote: > One way to avoid the costly exit is to use polling instead of notification. Testing with fio on virtio-blk backed by NVMe device, I can see significant performance improvement with this series: poll-max-nsiodepth=1iodepth=32

Re: [Qemu-devel] [PATCH v4 00/13] aio: experimental virtio-blk polling mode

2016-12-02 Thread Stefan Hajnoczi
On Thu, Dec 01, 2016 at 07:26:39PM +, Stefan Hajnoczi wrote: > v4: > * Added poll time self-tuning algorithm [Christian and Paolo] > * Try a single iteration of polling to avoid non-blocking > ppoll(2)/epoll_wait(2) [Paolo] > * Reordered patches to make performance analysis easier - see

Re: [Qemu-devel] [PATCH v4 00/13] aio: experimental virtio-blk polling mode

2016-12-02 Thread Paolo Bonzini
> v4: > * Added poll time self-tuning algorithm [Christian and Paolo] > * Try a single iteration of polling to avoid non-blocking > ppoll(2)/epoll_wait(2) [Paolo] > * Reordered patches to make performance analysis easier - see below Reviewed-by: Paolo Bonzini > v3: >

[Qemu-devel] [PATCH v4 00/13] aio: experimental virtio-blk polling mode

2016-12-01 Thread Stefan Hajnoczi
v4: * Added poll time self-tuning algorithm [Christian and Paolo] * Try a single iteration of polling to avoid non-blocking ppoll(2)/epoll_wait(2) [Paolo] * Reordered patches to make performance analysis easier - see below v3: * Avoid ppoll(2)/epoll_wait(2) if polling succeeded [Paolo] *