On 2016年05月30日 23:55, Michael S. Tsirkin wrote:
On Mon, May 30, 2016 at 02:47:54AM -0400, Jason Wang wrote:
We always poll tx for socket, this is sub optimal since:
- it will be only used when we exceed the sndbuf of the socket.
- since we use two independent polls for tx and vq, this will
On 2016年05月30日 23:47, Michael S. Tsirkin wrote:
On Mon, May 30, 2016 at 02:47:53AM -0400, Jason Wang wrote:
We don't stop rx polling socket during rx processing, this will lead
unnecessary wakeups from under layer net devices (E.g
sock_def_readable() form tun). Rx will be slowed down in this
Per Vlastimi's review comment.
Thanks for the detail review, Vlastimi!
If you have another concern, feel free to say.
After I resolve all thing, I will send v7 rebased on recent mmotm.
>From b14aab2d3ac0702c7b2eec36409d74406d43 Mon Sep 17 00:00:00 2001
From: Minchan Kim
On Mon, May 30, 2016 at 11:36:07AM +0200, Vlastimil Babka wrote:
> On 05/30/2016 03:39 AM, Minchan Kim wrote:
> >After isolation, VM calls migratepage of driver with isolated page.
> >The function of migratepage is to move content of the old page to new page
> >and set up fields of struct page
On Mon, May 30, 2016 at 02:47:54AM -0400, Jason Wang wrote:
> We always poll tx for socket, this is sub optimal since:
>
> - it will be only used when we exceed the sndbuf of the socket.
> - since we use two independent polls for tx and vq, this will slightly
> increase the waitqueue traversing
On Mon, May 30, 2016 at 02:47:53AM -0400, Jason Wang wrote:
> We don't stop rx polling socket during rx processing, this will lead
> unnecessary wakeups from under layer net devices (E.g
> sock_def_readable() form tun). Rx will be slowed down in this
> way. This patch avoids this by stop polling
On Mon, May 30, 2016 at 02:03:26PM +0200, Gerd Hoffmann wrote:
> Needed for multihead setups where we can have disabled
> outputs and therefore plane->crtc can be NULL.
>
> Signed-off-by: Gerd Hoffmann
See my reply in the other thread, but I think you have a more fundamental
On Mon, May 30, 2016 at 02:06:50PM +0200, Gerd Hoffmann wrote:
> Hi,
>
> > > But I'll take you up on the implied offer to help out and test ;-)
> >
> > git://people.freedesktop.org/~danvet/drm stuff
>
> Tried that branch.
>
> > Would be really awesome if you could test this on virtio. Note
Hi,
> - add a small core function to registerr HOT_X/HOT_Y for a (cursor) plane,
> e.g. drm_plane_register_hotspot(). That should allocate the properties
> (if they don't exist yet) and then attach those props to the cursor. We
> don't want those props everywhere, but only on drivers that
On 05/20/2016 04:23 PM, Minchan Kim wrote:
Now, VM has a feature to migrate non-lru movable pages so
balloon doesn't need custom migration hooks in migrate.c
and compaction.c. Instead, this patch implements
page->mapping->a_ops->{isolate|migrate|putback} functions.
With that, we could remove
Hi,
> > But I'll take you up on the implied offer to help out and test ;-)
>
> git://people.freedesktop.org/~danvet/drm stuff
Tried that branch.
> Would be really awesome if you could test this on virtio. Note that the
> new nonblocking helpers require that your atomic backend gets the drm
>
On 05/30/2016 03:39 AM, Minchan Kim wrote:
After isolation, VM calls migratepage of driver with isolated page.
The function of migratepage is to move content of the old page to new page
and set up fields of struct page newpage. Keep in mind that you should
clear PG_movable of oldpage via
On 05/30/2016 03:33 AM, Minchan Kim wrote:
+ page->mapping = (void *)((unsigned long)page->mapping &
+ PAGE_MAPPING_MOVABLE);
This should be negated to clear... use ~PAGE_MAPPING_MOVABLE ?
No.
The intention is to clear only mapping value but
On Fri, May 27, 2016 at 09:50:27AM +0200, Daniel Vetter wrote:
> On Fri, May 27, 2016 at 09:46:03AM +0200, Gerd Hoffmann wrote:
> > On Mi, 2016-05-25 at 18:37 +0200, Daniel Vetter wrote:
> > > On Fri, Oct 2, 2015 at 1:58 PM, Gerd Hoffmann wrote:
> > > > Signed-off-by: Gerd
We always poll tx for socket, this is sub optimal since:
- it will be only used when we exceed the sndbuf of the socket.
- since we use two independent polls for tx and vq, this will slightly
increase the waitqueue traversing time and more important, vhost
could not benefit from commit
We don't stop rx polling socket during rx processing, this will lead
unnecessary wakeups from under layer net devices (E.g
sock_def_readable() form tun). Rx will be slowed down in this
way. This patch avoids this by stop polling socket during rx
processing. A small drawback is that this introduces
Hi:
This series tries to optimize vhost_net polling at two points:
- Stop rx polling for reduicng the unnecessary wakeups during
handle_rx().
- Conditonally enable tx polling for reducing the unnecessary
traversing and spinlock touching.
Test shows about 17% improvement on rx pps.
Please
17 matches
Mail list logo