[glxgears]I think is the update of Xorg

Drake · 2010-06-21 21:10:54

i have this

xf86-video-intel

00:02.0 VGA compatible controller: Intel Corporation Mobile 945GM/GMS, 943/940GML Express Integrated Graphics Controller (rev 03)
00:02.1 Display controller: Intel Corporation Mobile 945GM/GMS/GME, 943/940GML Express Integrated Graphics Controller (rev 03)

that's ok?

[user@equipo ~]$ glxgears
Running synchronized to the vertical refresh. The framerate should be
approximately the same as the monitor refresh rate.
298 frames in 5.0 seconds = 59.442 FPS
311 frames in 5.0 seconds = 62.111 FPS
311 frames in 5.0 seconds = 61.973 FPS
311 frames in 5.0 seconds = 62.064 FPS
311 frames in 5.0 seconds = 62.026 FPS
311 frames in 5.0 seconds = 62.063 FPS
311 frames in 5.0 seconds = 61.988 FPS

Last edited by Drake (2010-06-21 21:16:56)

Woofie · 2010-06-21 21:18:31

You're not alone

http://bbs.archlinux.org/viewtopic.php?id=99488

Seems that last update did something with performance.

enihcam · 2010-06-22 01:14:54

https://wiki.ubuntu.com/X/Troubleshooti … ce#Problem: glxgears has low FPS

Problem: glxgears has low FPS
It is important to note and remember that glxgears is *not* a benchmark tool. It simply measures how fast the driver writes images to the screen, whereas most 3D applications are limited by render speed, not merely blit speed. Instead use a 3D game (flightgear, tremulous, etc.) that has a real rendering workload to make comparisons.
glxgears is installed by default, easy to run, and generates results that are easy to read, so users like to utilize it as a rough measure of performance, and thus the question of why these numbers change comes up quite a bit.
For discussion we can categorize the fps changes into four groups:
1. glxgears drops from XXXX to YYY
This is generally nothing to worry about. High glxgears numbers generally indicate excessively high screen repainting, so if this drops from say 1500 fps to 500 fps, it should not produce any noticeable performance impact.
2. glxgears drops from XXX to YYY
As in #1, these drops are *usually* nothing to worry about, especially if you haven't noticed any change in performance. In *some* cases if you notice a performance drop, glxgears numbers may drop as well, and there may indeed be a correlation. However, glxgears isn't a benchmark, so it does little good to post the numbers (indeed, if anything it flags your post as ill-informed on the subject!)
Instead, get before and after FPS measurements using a 3D game, such as sauerbraten, tuxracer, tremulous, or the like.
3. glxgears drops from XXX to YY (e.g. usually around ~50-60fps)
This may indicate that you have vblank syncing turned on. Is the glxgears fps roughly equal to the refresh rate of your monitor? (LCDs tend to operate at 60Hz, so 50-60fps is common in these cases)
If so, see the previous section for a discussion of vblank settings. Normally vblank is a GOOD thing, but it can cause side-effects. If you are experiencing performance impacts, try disabling vblank.
4. glxgears drops to 30fps or below
Any time glxgears returns fps less than your monitor's refresh rate, it definitely indicates a performance problem.
If the fps seems to hit at about half your monitor refresh rate, it indicates the graphics card is not synchronizing properly, and is missing every other frame request by the monitor.

Solution:

Via driconf: 'Synchronization with vertical refresh (swap intervals)' -> set to 'Never synchronize with vertical refresh'.

Last edited by enihcam (2010-06-22 01:16:18)

Skripka · 2010-06-22 01:22:09

Woofie wrote:

You're not alone
http://bbs.archlinux.org/viewtopic.php?id=99488
Seems that last update did something with performance.

Rly? Probably only on Intel, as Nvidia is still fine.

[marcus@ARCH ~]$ glxgears
34977 frames in 5.0 seconds = 6995.329 FPS
42650 frames in 5.0 seconds = 8529.744 FPS
43771 frames in 5.0 seconds = 8750.448 FPS
45666 frames in 5.0 seconds = 9133.074 FPS
45401 frames in 5.0 seconds = 9080.127 FPS

Last edited by Skripka (2010-06-22 01:23:36)

madek · 2010-06-22 02:36:31

same thing here

[madek@bender ~]$ glxgears
Running synchronized to the vertical refresh. The framerate should be
approximately the same as the monitor refresh rate.
204 frames in 5.0 seconds = 40.695 FPS
300 frames in 5.0 seconds = 59.804 FPS
240 frames in 5.0 seconds = 47.980 FPS
247 frames in 5.0 seconds = 49.326 FPS
301 frames in 5.0 seconds = 60.029 FPS

dmz · 2010-06-22 04:03:04

Looks like I am the only one with a 965 chipset, but I'm having bad performance as well (and had with the previous Xorg too), around 150 fps and simple games like pacman lags.

dmz · 2010-06-22 05:02:17

Forget what I just wrote, I fixed it.

Check what glxinfo|grep -i opengl tells you, it should NOT say it's using software.
Then check my patch here: http://github.com/trapd00r/configs/comm … c6edc658b7

Now I'm going back to Street Fighter again, this time with full resolution and all options turned UP!

ijanos · 2010-06-22 08:14:54

[user@equipo ~]$ glxgears
Running synchronized to the vertical refresh. The framerate should be
approximately the same as the monitor refresh rate.
298 frames in 5.0 seconds = 59.442 FPS

Guess what, your monitor runs on 60Hz which is perfectly normal. When will people finally stop using glxgears as a benchmark?

ChemBro · 2010-06-22 11:20:40

Try extreme tuxracer as a "benchmark". It's better (and funnier).

ijanos · 2010-06-22 11:28:21

Not that, because of vsync, everything will top at 60fps. To really benchmark your HW try something that rendering around 20 to 50 fps.

Labello · 2010-06-22 12:09:47

ijanos wrote:

Not that, because of vsync, everything will top at 60fps. To really benchmark your HW try something that rendering around 20 to 50 fps.

like nexuiz on highest settings

ijanos · 2010-06-22 12:14:29

Labello wrote:

ijanos wrote:
Not that, because of vsync, everything will top at 60fps. To really benchmark your HW try something that rendering around 20 to 50 fps.
like nexuiz on highest settings

Exactly it is even better if it has a "demo" mode so it plays the same everytime, so you can compare fps.

Drake · 2010-06-22 16:54:51

glxgears is not a type of bechmark?

Last edited by Drake (2010-06-22 17:01:06)

ijanos · 2010-06-22 17:02:35

Drake wrote:

glxgears is not a type of bechmark?

no and it never was.

Drake · 2010-06-22 17:04:29

ijanos wrote:

Drake wrote:
glxgears is not a type of bechmark?
no and it never was.

so, my video driver it's fine ??

Last edited by Drake (2010-06-22 17:04:45)

ijanos · 2010-06-22 17:07:19

Drake wrote:

ijanos wrote:
Drake wrote:
glxgears is not a type of bechmark?
no and it never was.
so, my video driver it's fine ??

You cannot tell from the output of glxgears. Try something that using 3D like a game or google earth. If it works without aritfacts and lag (low fps) you are good.

Drake · 2010-06-22 17:23:27

ijanos wrote:

Drake wrote:
ijanos wrote:
no and it never was.
so, my video driver it's fine ??
You cannot tell from the output of glxgears. Try something that using 3D like a game or google earth. If it works without aritfacts and lag (low fps) you are good.

i tested tuxrace and worked fine for me.. the max of fps in the game was 30 fps.. i don't have lag and stucks..
thanks everyone by the attention

bananabrain · 2010-06-24 11:13:41

ijanos wrote:

Drake wrote:
glxgears is not a type of bechmark?
no and it never was.

Quite, but in spite of people endlessly telling us this for years, no distribution has ever thought it a good idea to remove the mesa utilities from their repos

Let's put it another way. Suppose I'm a weird dude who gets his jollies by looking at glxgears for three hours a day. Last week I was in heaven, but under this week's xorg update those sexy gears look crap. How do I fix it?

whaevr · 2010-06-24 20:47:42

bananabrain wrote:

ijanos wrote:
Drake wrote:
glxgears is not a type of bechmark?
no and it never was.
Quite, but in spite of people endlessly telling us this for years, no distribution has ever thought it a good idea to remove the mesa utilities from their repos
Let's put it another way. Suppose I'm a weird dude who gets his jollies by looking at glxgears for three hours a day. Last week I was in heaven, but under this week's xorg update those sexy gears look crap. How do I fix it?

Tacos to this man.

Or you could simply say you enjoy using compiz as a window manager (as opposed to metacity ugh) without your system forgetting to update parts of the screen. Whatever gets the point across theres a problem

Drake · 2010-07-02 03:08:13

Uhmm i believe my driver video is not fine,sees not as fluid as before(drivers old)..
Desktop:Kde 4.4.5

JohnVV · 2010-07-02 03:55:40

and i thought that my GeForce 2 mx 400 card was slow with

4305 frames in 5.0 seconds = 860.951 FPS
3677 frames in 5.0 seconds = 735.335 FPS

still on the old x11 no driver yet

Last edited by JohnVV (2010-07-02 03:56:24)

cantabile · 2010-07-02 05:07:28

I googled around for a way to disable sync to vblank, and found two things:
1. that ubuntu wiki page, which says driconf can fix it - didn't have any effect
2. some page saying xvattr can fix it - didn't have any effect

Maybe you guys will have more luck with these?

Video card is

00:02.0 VGA compatible controller: Intel Corporation Mobile GME965/GLE960 Integrated Graphics Controller (rev 0c)

dmz · 2010-07-02 05:43:04

Did anyone read my post? Maybe I wasnt affected and just fucked up?

cantabile · 2010-07-02 06:07:22

dmz wrote:

Did anyone read my post?

What sort of response did you expect?

dmz · 2010-07-02 08:16:44

cantabile wrote:

dmz wrote:
Did anyone read my post?
What sort of response did you expect?

Haha, something along the lines 'Yes, that was it, now it works'. Guess it was just me then.

Arch Linux

#1 2010-06-21 21:10:54

[glxgears]I think is the update of Xorg

#2 2010-06-21 21:18:31

Re: [glxgears]I think is the update of Xorg

#3 2010-06-22 01:14:54

Re: [glxgears]I think is the update of Xorg

#4 2010-06-22 01:22:09

Re: [glxgears]I think is the update of Xorg

#5 2010-06-22 02:36:31

Re: [glxgears]I think is the update of Xorg

#6 2010-06-22 04:03:04

Re: [glxgears]I think is the update of Xorg

#7 2010-06-22 05:02:17

Re: [glxgears]I think is the update of Xorg

#8 2010-06-22 08:14:54

Re: [glxgears]I think is the update of Xorg

#9 2010-06-22 11:20:40

Re: [glxgears]I think is the update of Xorg

#10 2010-06-22 11:28:21

Re: [glxgears]I think is the update of Xorg

#11 2010-06-22 12:09:47

Re: [glxgears]I think is the update of Xorg

#12 2010-06-22 12:14:29

Re: [glxgears]I think is the update of Xorg

#13 2010-06-22 16:54:51

Re: [glxgears]I think is the update of Xorg

#14 2010-06-22 17:02:35

Re: [glxgears]I think is the update of Xorg

#15 2010-06-22 17:04:29

Re: [glxgears]I think is the update of Xorg

#16 2010-06-22 17:07:19

Re: [glxgears]I think is the update of Xorg

#17 2010-06-22 17:23:27

Re: [glxgears]I think is the update of Xorg

#18 2010-06-24 11:13:41

Re: [glxgears]I think is the update of Xorg

#19 2010-06-24 20:47:42

Re: [glxgears]I think is the update of Xorg

#20 2010-07-02 03:08:13

Re: [glxgears]I think is the update of Xorg

#21 2010-07-02 03:55:40

Re: [glxgears]I think is the update of Xorg

#22 2010-07-02 05:07:28

Re: [glxgears]I think is the update of Xorg

#23 2010-07-02 05:43:04

Re: [glxgears]I think is the update of Xorg

#24 2010-07-02 06:07:22

Re: [glxgears]I think is the update of Xorg

#25 2010-07-02 08:16:44

Re: [glxgears]I think is the update of Xorg

Board footer