crappy performance with 100.xx.xx series.

[linux23dragon]

I too get a performance hit with the Nvidia 100.*.*.*.* drivers using my 8800-GTX.
A good test to check this performance issue out, is to play UT2004 (Map to use:- DM_TokaraForest)

I'm not sure if a Nvidia bug report is going to help here ATM.


I'm using non-official Nvidia kernel driver (module option) hacks to fix the old Beryl issues. Are they really needed now? http://www.nvnews.net/vbulletin/show...&postcount=329

EDIT: Does this performance issue happen if you upgrade the kernel to 2.6.22-rc6, or is it due to the Linux kernel (in my case) 2.6.21.xx ?

Also, could this issue be due to the games getting a bit old and/or are no longer being maintained?

Oh, yea. One last thing. Don't be worried about this warning (When playing UT2004). Its been around since the dawn of time :-

Xlib:  extension "XiG-SUNDRY-NONSTANDARD" missing on display ":0.0".

Here is the info in the README.linux file (found in your installed UT2004 folder):-

Q: I get the following text on my console when I run the game:
Xlib: extension "XiG-SUNDRY-NONSTANDARD" missing on display ":0.0".
Is this a problem?
A: No. This means you aren't using an X server from Xi Graphics.
That message means we're looking for the X11 extension they use to
change screen resolutions, and having a non-XiG X server, you
don't have it. THIS IS NOT A UT2004 BUG. It's not a bug at all.
Xlib prints that "error", but we handle it gracefully.

[netllama]

gbil, I'm not really clear on what more you'd like me to comment upon, as your results look clear to me.

[gbil]

Originally Posted by netllama

gbil, I'm not really clear on what more you'd like me to comment upon, as your results look clear to me.

So according to the following I've posted you acknowledge the performance drop on 100.14.11 drivers. Nice, when you expect a fix for this performance drop? Maybe next release?

--------------------------------------------------------------------------
9755:

WoW fps: between 90 to 130 , around 115fps most of the time measured inside IF with no other people around.

100.14.11:

WoW fps: between 70 to 110, around 85 most of the time in the same place again with no people around.

This numbers of course, in both cases, are much smaller around 35fps in busy areas etc again with 9755 driver giving around 10fps more but I can't create a test-bed to report fps since the environment is busy places changes all the time (more - less people around).

I don't want to report glxgears numbers since this is no real benchmark but just for the record 9755 gives 4000 more fps.

I also installed pprace (old tuxracer I think) which reports about 250-280 for 100.14.11 driver and about 270-300 for the 9755 driver, again though I don't think this is a 'serious' benchmarking tool.

[linuxgameprogra]

Im on kernel 2.6.21. Ill try 2.6.20. Maybe thats the problem.

edit: NOPE.

[linuxgameprogra]

Bump Bump. Biggadi, bump bump.

Could it be SMP?

[zander]

We identified one problem with 100.14.11 that could explain performance regressions since 1.0-97xx with GeForce 8 series GPUs; this problem should be resolved in future NVIDIA Linux graphics driver releases. For any other performance regressions (e.g. due to Linux kernel or system upgrades), please check if other users have reported similar problems, else start new threads.

[gbil]

Originally Posted by zander

We identified one problem with 100.14.11 that could explain performance regressions since 1.0-97xx with GeForce 8 series GPUs; this problem should be resolved in future NVIDIA Linux graphics driver releases. For any other performance regressions (e.g. due to Linux kernel or system upgrades), please check if other users have reported similar problems, else start new threads.

Great

This answers also another post I've made when I changed from my 6600 to 8800GTS were I was expressing my feeling that the 8800GTS wasn't so much faster than the 6600 as I would expect.

Thanks zander

[linuxgameprogra]

Phoronix seems to look into this issue.

http://www.phoronix.com/scan.php?pag...item=781&num=1

[gilboa]

Does this problem efects GF7xxxs?
(I've got a 8800GTS/640 on pre-order)

- Gilboa

[linuxgameprogra]

I dont think it would affect the G70 chips, but I sold my 7900 GT when I got the 8800, so I cant test the differance in drivers. I would still order your new 8800, and just use the 9755 driver until the new one comes out, assuming that will fix the performance issues.

[gilboa]

Originally Posted by linuxgameprogra

I dont think it would affect the G70 chips, but I sold my 7900 GT when I got the 8800, so I cant test the differance in drivers. I would still order your new 8800, and just use the 9755 driver until the new one comes out, assuming that will fix the performance issues.

Never the less phoronix seem to suggest that the performance problem is not limited to 100.xx drivers.
Am I wrong?

If the problem is long-standing, I'll get a used/cheap/etc GF7800 now, and wait for the problem to clear before upgrading.

- Gilboa

[babalouj]

Any word when the drivers will be out to fix the performance issues documented in the article?