From mboxrd@z Thu Jan 1 00:00:00 1970 From: bugzilla-daemon@freedesktop.org Subject: [Bug 110781] Radeon: heavy r300 performance drop regression between 11.x and 19.x Date: Wed, 05 Jun 2019 20:50:09 +0000 Message-ID: References: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1271762817==" Return-path: Received: from culpepper.freedesktop.org (culpepper.freedesktop.org [IPv6:2610:10:20:722:a800:ff:fe98:4b55]) by gabe.freedesktop.org (Postfix) with ESMTP id 8EA74896C7 for ; Wed, 5 Jun 2019 20:50:09 +0000 (UTC) In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" To: dri-devel@lists.freedesktop.org List-Id: dri-devel@lists.freedesktop.org --===============1271762817== Content-Type: multipart/alternative; boundary="15597678093.6499.17524" Content-Transfer-Encoding: 7bit --15597678093.6499.17524 Date: Wed, 5 Jun 2019 20:50:09 +0000 MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.freedesktop.org/ Auto-Submitted: auto-generated https://bugs.freedesktop.org/show_bug.cgi?id=3D110781 --- Comment #39 from Richard Thier --- First I went on to strace a bit and measure directly... 10 sec glxgears - lastfast 17.x: - 2105 ioctl calls - 6 DRM_IOCTL_RADEON_GEM_CREATE - 7 DRM_IOCTL_GEM_CLOSE 10 sec glxgears - patched 19.x: - 2916 ioctl calls - 712 DRM_IOCTL_RADEON_GEM_CREATE - 713 DRM_IOCTL_GEM_CLOSE In comparison this is the unpatched 19.x originally (10 sec): -> 12466 (any) ioctl calls -> 3111 DRM_IOCTL_RADEON_GEM_CREATE -> 3112 DRM_IOCTL_GEM_CLOSE Surely it is already an order of magnitude better now, but maybe still not = as best as it should be. As I told you, when bisecting there was a point I saw this happening and it was hinting there are two issues - but one is much smaller. glxgears however runs roughly the same FPS now. Maybe things start to slow = down if I run out of CPU power as glxgears don't run out now - neither tuxracer,= but will try heavy things like mount&blade: warband... it was working well befo= re.. --=20 You are receiving this mail because: You are the assignee for the bug.= --15597678093.6499.17524 Date: Wed, 5 Jun 2019 20:50:09 +0000 MIME-Version: 1.0 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.freedesktop.org/ Auto-Submitted: auto-generated

Comme= nt # 39 on bug 11078= 1 from = Richard Thier 
First I went on to strace a bit and measure directly...

10 sec glxgears - lastfast 17.x:

- 2105 ioctl calls
- 6 DRM_IOCTL_RADEON_GEM_CREATE
- 7 DRM_IOCTL_GEM_CLOSE

10 sec glxgears - patched 19.x:

- 2916 ioctl calls
- 712 DRM_IOCTL_RADEON_GEM_CREATE
- 713 DRM_IOCTL_GEM_CLOSE

In comparison this is the unpatched 19.x originally (10 sec):

-> 12466 (any) ioctl calls
-> 3111 DRM_IOCTL_RADEON_GEM_CREATE
-> 3112 DRM_IOCTL_GEM_CLOSE

Surely it is already an order of magnitude better now, but maybe still not =
as
best as it should be. As I told you, when bisecting there was a point I saw
this happening and it was hinting there are two issues - but one is much
smaller.

glxgears however runs roughly the same FPS now. Maybe things start to slow =
down
if I run out of CPU power as glxgears don't run out now - neither tuxracer,=
 but
will try heavy things like mount&blade: warband... it was working well =
before..

You are receiving this mail because:
  • You are the assignee for the bug.
= --15597678093.6499.17524-- --===============1271762817== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZHJpLWRldmVs IG1haWxpbmcgbGlzdApkcmktZGV2ZWxAbGlzdHMuZnJlZWRlc2t0b3Aub3JnCmh0dHBzOi8vbGlz dHMuZnJlZWRlc2t0b3Aub3JnL21haWxtYW4vbGlzdGluZm8vZHJpLWRldmVs --===============1271762817==--