Re: [PATCH] kvm:virtio-net: Run TX from the I/O thread

[Mark McLoughlin <markmc@redhat.com>]

Hi Alex,

On Wed, 2009-01-21 at 16:08 -0700, Alex Williamson wrote:
> This is an attempt to improve the latency of virtio-net while not hurting
> throughput.  I wanted to try moving packet TX into a different thread
> so we can quickly return to the guest after it kicks us to send packets
> out.  I also switched the order of when the tx_timer comes into play, so
> we can get an inital burst of packets out, then wait for the timer to
> fire and notify us if there's more to do.  Here's what it does for me
> (average of 5 runs each, testing to a remote system on a 1Gb network):
> 
> netperf TCP_STREAM: 939.22Mb/s -> 935.24Mb/s =  99.58%
> netperf TCP_RR:      2028.72/s -> 3927.99/s  = 193.62%
> tbench:              92.99MB/s -> 99.97MB/s  = 107.51%
> 
> I'd be interested to hear if it helps or hurts anyone else.  Thanks,

Avi and I went back and forth on this one in great detail before:

  http://www.mail-archive.com/kvm@vger.kernel.org/msg06431.html

Avi's arguments make a lot of sense, but looking over those patches
again now, I still think that applying them would be a better approach
than what we have right now.

Cheers,
Mark.