/srv/irclogs.ubuntu.com/2016/04/08/#ubuntu-x.txt

furkanhas anybody noticed this text corruption in LibreOffice? https://www.dropbox.com/s/ypr3q8si3br2kze/libreoffice2.png?dl=003:22
furkani wonder if it's X-related03:22
furkani'm guessing probably not, but figure it doesn't hurt to ask03:22
furkanthis is with 16.0403:23
tjaaltonnot here on intel04:13
alkisgHi, I'm trying to use glxgears in order to benchmark various window managers, compiz, metacity, xcompmgr etc.05:12
alkisgBut in one case I'm getting very weird results: http://paste.ubuntu.com/15682185/05:12
alkisgI.e. 472 FPS for one minute, then dang, 572 FPS the next minute05:13
alkisgNothing running on the client, no cron jobs or dmesg or xorg messages etc etc05:13
alkisgIt's even somewhat reproducible05:13
alkisg...what can possibly boost glxgears to have an additional 100 FPS after 1 minute of it running?!05:13
alkisg(intel 855 graphics)05:17
alkisg(ubuntu 16.04, plain xinit xterm)05:18
tjaaltonglxgears is not a benchmark05:24
alkisgI've seen everyone saying that, and then offering no alternatives :)05:24
alkisgBut the numbers I care about are e.g. metacity --no-composite=500 fps, --composite=200 fps05:25
tjaaltonglmark2?05:25
alkisgSo it's some indicator. The performance difference in e.g. youtube is visible with the naked eye, I just want some hard numbers to get the developers interested in addressing them05:25
alkisgThanks, let me check that...05:25
tjaaltonalso very good at hanging intel in the past..05:26
tjaaltonskylake at least05:26
alkisgError: Glmark2 needs OpenGL(ES) version >= 2.0 to run (but version string is: '1.3 Mesa 11.2.0')!05:26
tjaaltontoo bad05:29
* alkisg will try it with some newer client05:29
alkisgBut any idea what could cause such a big performance difference in glxgears from one minute to the next, though?05:29
tjaaltonno05:29
alkisgThanks for the glmark2 hint, tjaalton :)05:29
tjaaltonsounds like it's running asynchronously, unlike on modern hw where it reports fps ~= vert refresh05:30
alkisgI'm running it with vblank_mode=005:31
alkisgOtherwise yeah I'm getting a constant 60 fps05:31
tjaaltonsince you have obsolete hw just benchmark using gtkperf or such05:32
tjaaltonnot that the wm matters there05:32
alkisgIt appears to matter a whole lot, metacity --composite has 1/3 of the performance of metacity --no-composite05:34
alkisg...in gtkperf, x11perf and glxgears05:35
alkisg...so I'm trying to convince them to put back --no-composite as the default (they changed it in 16.04)05:35
tjaaltonok then05:36
alkisghttps://bugs.launchpad.net/ubuntu/+source/metacity/+bug/156615705:36
ubottuLaunchpad bug 1566157 in metacity (Ubuntu) "Metacity's compositing is too slow" [Undecided,New]05:36
tjaaltonI don't think anyone cares, really :)05:40
alkisgWell, it makes the difference of "usable" vs "unusable" in thousands of pcs here... 5 fps in youtube vs 15 is a very big difference05:40
tjaaltonthen change the default there05:41
alkisgThey replied that --no-composite is unsupported05:41
alkisgSo I'm evaluating different DEs currently, Mate seems to fare much better...05:41
alkisgglmark2 score without wm: 2058, marco --no-composite: 1894, compiz : 1878, metacity --no-composite: 742, marco --composite: 708, metacity --composite: 44106:45
=== darkxst_ is now known as darkxst
tseliotricotz, mamarley: I've just uploaded 364.15 with KMS enabled, the initrd hook, and without the gfx blacklist. This is for 16.04, 15.10, 14.0415:47
mamarleytseliot: Yay, thanks!16:32
tseliot:)17:35
* tseliot -> EOW17:35
mamarleyHave a good weekend!17:38
=== darkness is now known as darkxst

Generated by irclog2html.py 2.7 by Marius Gedminas - find it at mg.pov.lt!