<div dir="ltr"><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Wed, Jan 16, 2019 at 9:43 AM Christian König <<a href="mailto:ckoenig.leichtzumerken@gmail.com">ckoenig.leichtzumerken@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div bgcolor="#FFFFFF">
<div class="gmail-m_1079118432294564707moz-cite-prefix">Am 16.01.19 um 15:39 schrieb Marek
Olšák:<br>
</div>
<blockquote type="cite">
<div dir="auto">
<div><br>
<br>
<div class="gmail_quote">
<div dir="ltr">On Wed, Jan 16, 2019, 9:34 AM Koenig,
Christian <<a href="mailto:Christian.Koenig@amd.com" target="_blank">Christian.Koenig@amd.com</a>
wrote:<br>
</div>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div bgcolor="#FFFFFF">
<div class="gmail-m_1079118432294564707m_3799249069402976776moz-cite-prefix">Am
16.01.19 um 15:31 schrieb Marek Olšák:<br>
</div>
<blockquote type="cite">
<div dir="auto">
<div><br>
<br>
<div class="gmail_quote">
<div dir="ltr">On Wed, Jan 16, 2019, 7:55 AM
Christian König <<a href="mailto:ckoenig.leichtzumerken@gmail.com" rel="noreferrer" target="_blank">ckoenig.leichtzumerken@gmail.com</a>
wrote:<br>
</div>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
Well if you ask me we should have the
following interface for <br>
negotiating memory management with the kernel:<br>
<br>
1. We have per process BOs which can't be
shared between processes.<br>
<br>
Those are always valid and don't need to be
mentioned in any BO list <br>
whatsoever.<br>
<br>
If we knew that a per process BO is currently
not in use we can <br>
optionally tell that to the kernel to make
memory management more efficient.<br>
<br>
In other words instead of a list of stuff
which is used we send down to <br>
the kernel a list of stuff which is not used
any more and that only when <br>
we know that it is necessary, e.g. when a game
or application overcommits.<br>
</blockquote>
</div>
</div>
<div dir="auto"><br>
</div>
<div dir="auto">Radeonsi doesn't use this because
this approach caused performance degradation and
also drops BO priorities.</div>
</div>
</blockquote>
<br>
The performance degradation where mostly shortcomings
with the LRU which by now have been fixed.<br>
<br>
BO priorities are a different topic, but could be added
to per VM BOs as well.<br>
</div>
</blockquote>
</div>
</div>
<div dir="auto"><br>
</div>
<div dir="auto">What's the minimum drm version that contains the
fixes?</div>
</div>
</blockquote>
<br>
I've pushed the last optimization this morning. No idea when it
really became useful, but the numbers from the closed source clients
now look much better.<br>
<br>
We should probably test and bump the drm version when we are sure
that this now works as expected.<br></div></blockquote><div><br></div><div>We should, but AMD Mesa guys don't have any time.</div><div><br></div><div>Marek</div></div></div>