Ubuntu
xserver-xorg-video-ati package

[RV200] ATI Radeon Mobility KMS modeset=1 22% slower than vesa

Bug #399559 reported by jerrylamos
20
This bug affects 2 people
Affects Status Importance Assigned to Milestone
xserver-xorg-driver-ati
Invalid
High
xserver-xorg-video-ati (Ubuntu)
Expired
Low
Unassigned

Bug Description

Binary package hint: xorg

The bug is KMS modeset=1 measured 22% slower than vesa with video intensive GtkPerf is from Ubuntu synaptic, and 12% slower than modeset=0. At least for this benchmark ubuntu is faster with vesa than with the specific ati drivers.

Does anyone know how to get launchpad to handle columnar data?
There are 5 columns of data here.

Measurements are from IBM Thinkpad T40 with ATI Radeon Mobility 7500.
Col 1 is measurements with xorg driver vesa.
Col 2 is nomodeset no KMS xorg ati driver 6.12.99+git.....
Col 3 is modeset=1 KMS xorg ati driver 6.12.99+git.....

jaunty.Mobility7500
karmic.mode0.Mobility7500.6.12.99+git20090629.f39cafc5-0ubuntu1
karmic.mode1.Mobility7500.6.12.99+git20090629.f39cafc-0ubuntu1
GtkPerf from Ubuntu Synaptic
Thinkpad T40 Mobility 7500 vesa karmicmode0 karmicmode1 Mode0:vesa Mode1:vesa
GtkEntrytime:_____________ 0.08 0.06 0.05 -25% -38%
GtkComboBoxtime:________ 2.15 2.41 3.08 12% 43%
GtkComboBoxEntrytime:____ 1.39 1.78 1.75 28% 26%
GtkSpinButtontime:________ 0.35 0.37 0.96 6% 174%
GtkProgressBartime:_______ 0.34 0.34 0.74 0% 118%
GtkToggleButtontime:______ 0.45 0.46 0.72 2% 60%
GtkCheckButtontime:_______ 0.27 0.29 0.29 7% 7%
GtkRadioButtontime:_______ 0.43 0.48 0.4 12% -7%
GtkTextViewAddtexttime:___ 1.62 1.94 1.36 20% -16%
GtkTextViewScrolltime:_____ 0.55 0.65 0.47 18% -15%
GtkDrawingAreaLinestime:__ 1.47 1.71 1.87 16% 27%
GtkDrawingAreaCirclestime: 2.12 2.18 1.86 3% -12%
GtkDrawingAreaTexttime:___ 1.51 1.52 1.51 1% 0%
GtkDrawingAreaPixbufstime: 0.16 0.26 0.69 63% 331%

Total time:________________ 12.90 14.46 15.76 12% 22%

Will attach lspi, Xorg.0.log, ... tomorrow. It's late now.

[lspci]
00:00.0 Host bridge [0600]: Intel Corporation 82855PM Processor to I/O Controller [8086:3340] (rev 03)
     Subsystem: IBM Device [1014:0529]
01:00.0 VGA compatible controller [0300]: ATI Technologies Inc Radeon Mobility M7 LW [Radeon Mobility 7500] [1002:4c57]
     Subsystem: IBM Device [1014:0530]

See original description
Revision history for this message
Bryce Harrington (bryce) wrote :

> Does anyone know how to get launchpad to handle columnar data?

It doesn't. Probably simplest solution is to attach a txt file. Spreadsheets work fine too.

lspci -vvnn, Xorg.0.log, and dmesg would be helpful in order to permit upstreaming this bug.

affects: xorg (Ubuntu) → xserver-xorg-video-ati (Ubuntu)
Changed in xserver-xorg-video-ati (Ubuntu):
importance: Undecided → High
status: New → Incomplete
Revision history for this message
jerrylamos (jerrylamos) wrote :

Attached is spreadsheet giving results from Radeon Mobility 7500 GtkPerf from
Jaunty, Vesa, default (no modeset), radeon.modeset=1.

The modeset=1 was re-run with yesterday's updates. Modeset=1 was 24% slower than Vesa. Will try today's updates when time permits. Since I'm just a user (customer) seems to me Vesa would be better to use than the driver with "accelerations".

Today's karmic update might be 2.6.31-3 however boot hangs after samba on the i845 ThinkCentre so I'm not sure the update is ready yet.

Subsequent attachments will be lspci -vvnn, Xorg.0.log, dmesg.

Thanks, Jerry

Revision history for this message
jerrylamos (jerrylamos) wrote :

dmesg after GtkPerf latest run

Revision history for this message
jerrylamos (jerrylamos) wrote :

lspci -vvnn from the Thinkpad T40

Revision history for this message
jerrylamos (jerrylamos) wrote :

Xorg.0.log after GtkPerf run

Revision history for this message
jerrylamos (jerrylamos) wrote :

.xsession-errors. I'm not knowledgeable enough to see any problems but here's the file anyway.

Jerry

Revision history for this message
Timo Aaltonen (tjaalton) wrote :

known issue, the userland driver doesn't support KMS yet, so you get no DRI as you can see from the logfile..

Changed in xserver-xorg-video-ati (Ubuntu):
importance: High → Low
Revision history for this message
In , Bryce Harrington (bryce) wrote :

Created an attachment (id=28531)
results.html

Forwarding this bug report from Ubuntu reporter Jerry Lamos.

[Problem]
Performance regression when using the KMS -ati driver corresponding to version 1:6.12.99+git20090805.bd03977e along with kernel, mesa, and libdrm from the kms ppa: https://edge.launchpad.net/~ubuntu-x-swat/+archive/kms.

[Original Report]
Performance is actually worse than -vesa on this system.

Measurements are from IBM Thinkpad T40 with ATI Radeon Mobility 7500. See attached file for specific data.

Col 1 is measurements with xorg driver vesa.
Col 2 is nomodeset no KMS xorg ati driver 6.12.99+git.....
Col 3 is modeset=1 KMS xorg ati driver 6.12.99+git.....

Revision history for this message
In , Bryce Harrington (bryce) wrote :

Created an attachment (id=28532)
Xorg.0.log.mode1

I understand this is a known issue, so haven't forwarded other performance bugs, however this one has some crunchy data to go with it, so am forwarding for tracking purposes.

Revision history for this message
In , Bryce Harrington (bryce) wrote :

Created an attachment (id=28533)
dmesg

Revision history for this message
In , Bryce Harrington (bryce) wrote :

Created an attachment (id=28534)
lspci-vvnn

Revision history for this message
In , Michel Dänzer (michel-daenzer) wrote :

The log file shows that the X driver lacks KMS support, so it fails to enable the DRI (and uses the hardware behind KMS' back...). If there is a problem when the X driver actually uses KMS (and higher AGP transfer rates don't help), please reopen with the corresponding log file.

Revision history for this message
Bryce Harrington (bryce) wrote : Re: ATI Radeon Mobility KMS modeset=1 22% slower than vesa

Results from Jerry testing against the ATI KMS PPA.

Changed in xserver-xorg-video-ati (Ubuntu):
status: Incomplete → New
Revision history for this message
Bryce Harrington (bryce) wrote :

Thanks Jerry, I've forwarded this bug upstream to https://bugs.freedesktop.org/show_bug.cgi?id=23262 - please subscribe there in case upstream needs further information or wishes you to test something. Thanks ahead of time!

Changed in xserver-xorg-video-ati (Ubuntu):
status: New → Triaged
Revision history for this message
Bryce Harrington (bryce) wrote :

Jerry, please provide a fresh dmesg and Xorg.0.log from the tests with kms enabled. Upstream won't accept the test results without that.

Changed in xserver-xorg-video-ati (Ubuntu):
status: Triaged → Incomplete
Revision history for this message
In , jerrylamos (jerrylamos) wrote :

Created an attachment (id=28574)
Xorg.0.log from modeset=1

Revision history for this message
In , jerrylamos (jerrylamos) wrote :

Results from GtkPerf on IBM Thinkpad T40 1.5 gHz P4 ati radeon mobility 7500
All times are in seconds with higher number being slower.

GtkPerf0.40Aug1117:35:092009
karmic.A3.radeon.Mobility7500.1:6.12.99+git20090805.bd03977e-0ubuntu2
[CODE]
      jaunty A3_mode0 Modeset=1
GtkEntrytime:____________ 0.13 0.07 0.10
GtkComboBoxtime:_______ 1.78 2.33 8.87
GtkComboBoxEntrytime:___ 1.08 1.56 4.86
GtkSpinButtontime:_______ 0.32 0.37 2.96
GtkProgressBartime:______ 0.86 0.36 5.12
GtkToggleButtontime:_____ 0.35 0.46 3.05
GtkCheckButtontime:______ 0.31 0.26 0.97
GtkRadioButtontime:______ 0.60 0.40 1.31
GtkTextViewAddtexttime:__ 1.29 1.64 1.75
GtkTextViewScrolltime:____ 0.51 0.49 1.60
GtkDrawingAreaLinestime:__ 1.74 1.01 2.67
GtkDrawingAreaCirclestime: 1.34 1.31 2.55
GtkDrawingAreaTexttime:__ 1.78 8.00 1.89
GtkDrawingAreaPixbufstime: 0.44 0.77 3.01

Total time: 12.54 19.04 40.72
[/CODE]

Revision history for this message
In , jerrylamos (jerrylamos) wrote :

Created an attachment (id=28575)
dmesg from the T40

Revision history for this message
In , jerrylamos (jerrylamos) wrote :

Ctrl-Alt-F1 switches quickly to the typical modeset=1 small font 48 line screen on this 1024x768 lcd, and lots of characters per line? Then pressing Ctr-Alt-F7 switches quickly right back to this graphics screen. There doesn't appear to be any reset. It's almost like flipping windows. Yes there are some complaints in syslog but isn't that always the case with linux.

Jerry

Revision history for this message
jerrylamos (jerrylamos) wrote : Re: ATI Radeon Mobility KMS modeset=1 22% slower than vesa

Bryce,

Latest update as of today 20090812 results over three times slower than jaunty....will attach dmesg, Xorg.0.log, dpkg, lspci -vvnn. Last 2 lines in apt.sources.list are:
deb http://ppa.launchpad.net/ubuntu-x-swat/kms/ubuntu karmic main
deb-src http://ppa.launchpad.net/ubuntu-x-swat/kms/ubuntu karmic main

 GtkPerf0.40Aug1117:35:092009
 karmic.A3.radeon.Mobility7500.1:6.12.99+git20090805.bd03977e-0ubuntu2
 [CODE]
       jaunty A3_mode0 Modeset=1
 GtkEntrytime:____________ 0.13 0.07 0.10
 GtkComboBoxtime:_______ 1.78 2.33 8.87
 GtkComboBoxEntrytime:___ 1.08 1.56 4.86
 GtkSpinButtontime:_______ 0.32 0.37 2.96
 GtkProgressBartime:______ 0.86 0.36 5.12
 GtkToggleButtontime:_____ 0.35 0.46 3.05
 GtkCheckButtontime:______ 0.31 0.26 0.97
 GtkRadioButtontime:______ 0.60 0.40 1.31
 GtkTextViewAddtexttime:__ 1.29 1.64 1.75
 GtkTextViewScrolltime:____ 0.51 0.49 1.60
 GtkDrawingAreaLinestime:__ 1.74 1.01 2.67
 GtkDrawingAreaCirclestime: 1.34 1.31 2.55
 GtkDrawingAreaTexttime:__ 1.78 8.00 1.89
 GtkDrawingAreaPixbufstime: 0.44 0.77 3.01

 Total time: 12.54 19.04 40.72
 [/CODE]

Anything else?

Jerry

Revision history for this message
jerrylamos (jerrylamos) wrote :

dmesg from T40

Revision history for this message
jerrylamos (jerrylamos) wrote :

lspci -vvnn from T40

Revision history for this message
jerrylamos (jerrylamos) wrote :

dpkg -l xserver-xorg-video-radeon

Revision history for this message
In , Bryce Harrington (bryce) wrote :

[Jerry has attached the log files from his more recent tests with kms, showing the regression.]

Revision history for this message
jerrylamos (jerrylamos) wrote : Re: ATI Radeon Mobility KMS modeset=1 22% slower than vesa

Bryce,

I provided the logs requested here and in https://bugs.freedesktop.org/show_bug.cgi?id=23262. Someone decided the bug was "invalid" and "resolved" but on my pc's it's still slow and getting slower.

What do I do now?

Thanks, Jerry

Revision history for this message
Bryce Harrington (bryce) wrote :

Thanks for adding those files. The next thing to do is re-open the upstream bug, which I've just done. Beyond this, work with upstream as they may suggest or provide patches or branches to test.

Changed in xserver-xorg-video-ati (Ubuntu):
status: Incomplete → Triaged
Bryce Harrington (bryce)
tags: added: karmic
Bug Watch Updater (bug-watch-updater)
Changed in xserver-xorg-driver-ati:
status: Unknown → Confirmed
Bryce Harrington (bryce)
description: updated
Robert Hooker (sarvatt)
summary: - ATI Radeon Mobility KMS modeset=1 22% slower than vesa
+ [RV200] ATI Radeon Mobility KMS modeset=1 22% slower than vesa
Revision history for this message
Bryce Harrington (bryce) wrote :

[This is an automatic notification.]

Hi jerrylamos,

This bug was reported against an earlier version of Ubuntu, can you
test if it still occurs on Lucid?

Please note we also provide technical support for older versions of
Ubuntu, but not in the bug tracker. Instead, to raise the issue through
normal support channels, please see:

    http://www.ubuntu.com/support

If you are the original reporter and can still reproduce the issue on
Lucid, please run the following command to refresh the report:

  apport-collect 399559

If you are not the original reporter, please file a new bug report, so
we can work with you as the original reporter instead (you can reference
bug 399559 in your report if you think it may be related):

  ubuntu-bug xorg

If by chance you can no longer reproduce the issue on Lucid or if you
feel it is no longer relevant, please mark the bug report 'Fix Released'
or 'Invalid' as appropriate, at the following URL:

  https://bugs.launchpad.net/ubuntu/+bug/399559

Changed in xserver-xorg-video-ati (Ubuntu):
status: Triaged → Incomplete
tags: added: needs-retested-on-lucid-by-june
Bryce Harrington (bryce)
tags: added: hardy
Bug Watch Updater (bug-watch-updater)
Changed in xserver-xorg-driver-ati:
importance: Unknown → High
Bug Watch Updater (bug-watch-updater)
Changed in xserver-xorg-driver-ati:
importance: High → Unknown
Bug Watch Updater (bug-watch-updater)
Changed in xserver-xorg-driver-ati:
importance: Unknown → High
Brian Murray (brian-murray)
Changed in xserver-xorg-video-ati (Ubuntu):
status: Incomplete → Expired
Revision history for this message
In , penalvch (penalvch) wrote :

Jerry Lamos, Ubuntu Karmic reached EOL on April 30, 2011. For more on this, please see https://wiki.ubuntu.com/Releases .

If this is reproducible on a supported release, it will help immensely if you filed a new report with Ubuntu by ensuring you have the package xdiagnose installed, and that you click the Yes button for attaching additional debugging information running the following from a terminal:
ubuntu-bug xorg

Also, please feel free to subscribe me to it.

For more on why this is helpful, please see https://wiki.ubuntu.com/ReportingBugs.

Bug Watch Updater (bug-watch-updater)
Changed in xserver-xorg-driver-ati:
status: Confirmed → Invalid
To post a comment you must log in.
This report contains Public information  
Everyone can see this information.
Subscribing...

Other bug subscribers

Remote bug watches

Bug watches keep track of this bug in other bug trackers.