[lkml]   [2012]   [Aug]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH v9 0/5] make balloon pages movable by compaction
On 08/26/2012 03:58 AM, Michael S. Tsirkin wrote:
> On Sat, Aug 25, 2012 at 02:24:55AM -0300, Rafael Aquini wrote:
>> Memory fragmentation introduced by ballooning might reduce significantly
>> the number of 2MB contiguous memory blocks that can be used within a guest,
>> thus imposing performance penalties associated with the reduced number of
>> transparent huge pages that could be used by the guest workload.
>> This patch-set follows the main idea discussed at 2012 LSFMMS session:
>> "Ballooning for transparent huge pages" --
>> to introduce the required changes to the virtio_balloon driver, as well as
>> the changes to the core compaction & migration bits, in order to make those
>> subsystems aware of ballooned pages and allow memory balloon pages become
>> movable within a guest, thus avoiding the aforementioned fragmentation issue
> Meta-question: are there any numbers showing gain from this patchset?
> The reason I ask, on migration we notify host about each page
> individually. If this is rare maybe the patchset does not help much.
> If this is common we would be better off building up a list of multiple
> pages and passing them in one go.

The gain is in getting a better THP allocation rate inside the
guest, allowing applications to run faster.

The rarer it is for this code to run, the better - it means we
are getting the benefits without the overhead :)

All rights reversed

 \ /
  Last update: 2012-08-26 17:21    [W:0.063 / U:19.032 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site