<html> <head> <base href="https://bugs.freedesktop.org/"> </head> <body> <div> <a class="bz_bug_link bz_status_NEW " title="NEW - Radeon: heavy r300 performance drop regression between 11.x and 19.x" href="https://bugs.freedesktop.org/show_bug.cgi?id=110781#c39">Comment # 39</a> on <a class="bz_bug_link bz_status_NEW " title="NEW - Radeon: heavy r300 performance drop regression between 11.x and 19.x" href="https://bugs.freedesktop.org/show_bug.cgi?id=110781">bug 110781</a> from <a class="email" href="mailto:u9vata@gmail.com" title="Richard Thier <u9vata@gmail.com>"> Richard Thier</a> <pre>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..</pre> </div> <hr> You are receiving this mail because: <ul> <li>You are the assignee for the bug.</li> </ul> </body> </html>