On Mon, Jun 4, 2012 at 6:40 PM, Asias He <asias.hejun@xxxxxxxxx> wrote:
> All blk requests are processed in notify_vq() which is in the context of
> ioeventfd thread: ioeventfd__thread(). The processing in notify_vq() may
> take a long time to complete and all devices share the single ioeventfd
> thead, so this might block other device's notify_vq() being called and
> starve other devices.
>
> This patch makes virtio blk's notify_vq() just notify the blk thread
> instead of doing the real hard read/write work. Tests show that the
> overhead of the notification operations is small.
>
> The reasons for using dedicated thead instead of using thead pool
> follow:
>
> 1) In thread pool model, each job handling operation:
> thread_pool__do_job() takes about 6 or 7 mutex_{lock,unlock} ops. Most
> of the mutex are global (job_mutex) which are contented by the threads
> in the pool. It's fine for the non performance critical virtio devices,
> such as console, rng, etc. But it's not optimal for net and blk devices.
>
> 2) Using dedicated threads to handle blk requests opens the door for
> user to set different IO priority for the blk threads.
>
> 3) It also reduces the contentions between net and blk devices if they
> do not share the thead pool.
>
> Signed-off-by: Asias He <asias.hejun@xxxxxxxxx>
You wouldn't happen to have any performance numbers for this? ;-)
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
