ubuntu-x-swat team mailing list archive
-
ubuntu-x-swat team
-
Mailing list archive
-
Message #67923
[Bug 574746] [NEW] serve Xorg performance regression (fullscreen flash)
Public bug reported:
Binary package hint: xorg
Hi,
I am the owner of a Samsung NC20 netbook with a Via Nano CPU and a Via
VX800 chipset. With karmic I was able to play most fullscreen flash
videos fluently. After the upgrade to lucid, this it no more possible. I
already found and fixed a bug for me (Launchpad Bug #574733) and the
performance got measurably better, but there is still a major regressen
and fullscreen flash is like a dia show.
I think I got a way to show/measure the problem with x11perf -shmputxy10
-shmputxy100 -shmputxy500:
1: x11perf_exa_karmic.log
2: x11perf_xaa_karmic.log
3: x11perf_exa_lucid_patched.log
4: x11perf_xaa_lucid_patched.log
1 2 3 4 Operation
-------- ----------------- ----------------- ----------------- -----------------
152000.0 109000.0 ( 0.72) 159000.0 ( 1.05) 121000.0 ( 0.80) ShmPutImage 10x10 square
22300.0 1890.0 ( 0.085) 22900.0 ( 1.03) 1940.0 ( 0.087) ShmPutImage 100x100 square
1020.0 76.0 ( 0.075) 1020.0 ( 1.00) 76.7 ( 0.075) ShmPutImage 500x500 square
157000.0 108000.0 ( 0.69) 18600.0 ( 0.12) 19800.0 ( 0.13) ShmPutImage XY 10x10 square
22200.0 1920.0 ( 0.086) 324.0 ( 0.015) 278.0 ( 0.013) ShmPutImage XY 100x100 square
996.0 76.0 ( 0.076) 11.3 ( 0.011) 9.2 ( 0.009) ShmPutImage XY 500x500 square
As you can see, EXA is better than XAA, but more important, lucid is
much worse than karmic for the ShmPutImage XY test. As these numbers
relate very good to my fullscreen flash experience, I think this may be
related.
Kind regards,
Thomas
---
Architecture: i386
DistroRelease: Ubuntu 10.04
DkmsStatus:
virtualbox-ose, 3.1.6, 2.6.31-21-generic, i686: built
virtualbox-ose, 3.1.6, 2.6.32-21-generic, i686: installed
MachineType: SAMSUNG ELECTRONICS CO., LTD. NC20/NB20
Package: xorg 1:7.5+5ubuntu1
PackageArchitecture: i386
ProcCmdLine: BOOT_IMAGE=/boot/vmlinuz-2.6.32-21-generic root=UUID=28a00041-0781-44a2-8a24-684926bf9ea9 ro video=uvesafb:vbemode=0x230 quiet splash
ProcEnviron:
LANGUAGE=de_DE:de:en_GB:en
LANG=de_DE.UTF-8
SHELL=/bin/bash
ProcVersionSignature: Ubuntu 2.6.32-21.32-generic 2.6.32.11+drm33.2
Tags: lucid lucid
Uname: Linux 2.6.32-21-generic i686
UserGroups: adm admin cdrom dialout lpadmin plugdev sambashare
dmi.bios.date: 11/25/2009
dmi.bios.vendor: Phoenix Technologies Ltd.
dmi.bios.version: 10MQ
dmi.board.name: NC20/NB20
dmi.board.vendor: SAMSUNG ELECTRONICS CO., LTD.
dmi.chassis.asset.tag: No Asset Tag
dmi.chassis.type: 10
dmi.chassis.vendor: SAMSUNG ELECTRONICS CO., LTD.
dmi.chassis.version: N/A
dmi.modalias: dmi:bvnPhoenixTechnologiesLtd.:bvr10MQ:bd11/25/2009:svnSAMSUNGELECTRONICSCO.,LTD.:pnNC20/NB20:pvr04MQ:rvnSAMSUNGELECTRONICSCO.,LTD.:rnNC20/NB20:rvr:cvnSAMSUNGELECTRONICSCO.,LTD.:ct10:cvrN/A:
dmi.product.name: NC20/NB20
dmi.product.version: 04MQ
dmi.sys.vendor: SAMSUNG ELECTRONICS CO., LTD.
system:
distro: Ubuntu
codename: lucid
architecture: i686
kernel: 2.6.32-21-generic
** Affects: xorg (Ubuntu)
Importance: Undecided
Status: New
** Tags: apport-collected
** Tags added: apport-collected
** Description changed:
Binary package hint: xorg
Hi,
I am the owner of a Samsung NC20 netbook with a Via Nano CPU and a Via
VX800 chipset. With karmic I was able to play most fullscreen flash
videos fluently. After the upgrade to lucid, this it no more possible. I
already found and fixed a bug for me (Launchpad Bug #574733) and the
performance got measurably better, but there is still a major regressen
and fullscreen flash is like a dia show.
I think I got a way to show/measure the problem with x11perf -shmputxy10
-shmputxy100 -shmputxy500:
1: x11perf_exa_karmic.log
2: x11perf_xaa_karmic.log
3: x11perf_exa_lucid_patched.log
4: x11perf_xaa_lucid_patched.log
1 2 3 4 Operation
-------- ----------------- ----------------- ----------------- -----------------
152000.0 109000.0 ( 0.72) 159000.0 ( 1.05) 121000.0 ( 0.80) ShmPutImage 10x10 square
22300.0 1890.0 ( 0.085) 22900.0 ( 1.03) 1940.0 ( 0.087) ShmPutImage 100x100 square
1020.0 76.0 ( 0.075) 1020.0 ( 1.00) 76.7 ( 0.075) ShmPutImage 500x500 square
157000.0 108000.0 ( 0.69) 18600.0 ( 0.12) 19800.0 ( 0.13) ShmPutImage XY 10x10 square
22200.0 1920.0 ( 0.086) 324.0 ( 0.015) 278.0 ( 0.013) ShmPutImage XY 100x100 square
996.0 76.0 ( 0.076) 11.3 ( 0.011) 9.2 ( 0.009) ShmPutImage XY 500x500 square
As you can see, EXA is better than XAA, but more important, lucid is
much worse than karmic for the ShmPutImage XY test. As these numbers
relate very good to my fullscreen flash experience, I think this may be
related.
Kind regards,
Thomas
+ ---
+ Architecture: i386
+ DistroRelease: Ubuntu 10.04
+ DkmsStatus:
+ virtualbox-ose, 3.1.6, 2.6.31-21-generic, i686: built
+ virtualbox-ose, 3.1.6, 2.6.32-21-generic, i686: installed
+ MachineType: SAMSUNG ELECTRONICS CO., LTD. NC20/NB20
+ Package: xorg 1:7.5+5ubuntu1
+ PackageArchitecture: i386
+ ProcCmdLine: BOOT_IMAGE=/boot/vmlinuz-2.6.32-21-generic root=UUID=28a00041-0781-44a2-8a24-684926bf9ea9 ro video=uvesafb:vbemode=0x230 quiet splash
+ ProcEnviron:
+ LANGUAGE=de_DE:de:en_GB:en
+ LANG=de_DE.UTF-8
+ SHELL=/bin/bash
+ ProcVersionSignature: Ubuntu 2.6.32-21.32-generic 2.6.32.11+drm33.2
+ Tags: lucid lucid
+ Uname: Linux 2.6.32-21-generic i686
+ UserGroups: adm admin cdrom dialout lpadmin plugdev sambashare
+ dmi.bios.date: 11/25/2009
+ dmi.bios.vendor: Phoenix Technologies Ltd.
+ dmi.bios.version: 10MQ
+ dmi.board.name: NC20/NB20
+ dmi.board.vendor: SAMSUNG ELECTRONICS CO., LTD.
+ dmi.chassis.asset.tag: No Asset Tag
+ dmi.chassis.type: 10
+ dmi.chassis.vendor: SAMSUNG ELECTRONICS CO., LTD.
+ dmi.chassis.version: N/A
+ dmi.modalias: dmi:bvnPhoenixTechnologiesLtd.:bvr10MQ:bd11/25/2009:svnSAMSUNGELECTRONICSCO.,LTD.:pnNC20/NB20:pvr04MQ:rvnSAMSUNGELECTRONICSCO.,LTD.:rnNC20/NB20:rvr:cvnSAMSUNGELECTRONICSCO.,LTD.:ct10:cvrN/A:
+ dmi.product.name: NC20/NB20
+ dmi.product.version: 04MQ
+ dmi.sys.vendor: SAMSUNG ELECTRONICS CO., LTD.
+ system:
+ distro: Ubuntu
+ codename: lucid
+ architecture: i686
+ kernel: 2.6.32-21-generic
--
serve Xorg performance regression (fullscreen flash)
https://bugs.launchpad.net/bugs/574746
You received this bug notification because you are a member of Ubuntu-X,
which is subscribed to xorg in ubuntu.
Follow ups
-
[Bug 574746] Re: [VX800] serve Xorg performance regression (fullscreen flash)
From: Bartosz, 2010-05-10
-
[Bug 574746] Re: [VX800] serve Xorg performance regression (fullscreen flash)
From: Thomas Schlichter, 2010-05-09
-
[Bug 574746] Re: [VX800] serve Xorg performance regression (fullscreen flash)
From: Thomas Schlichter, 2010-05-04
-
[Bug 574746] Re: [VX800] serve Xorg performance regression (fullscreen flash)
From: Thomas Schlichter, 2010-05-04
-
[Bug 574746] Re: [VX800] serve Xorg performance regression (fullscreen flash)
From: Thomas Schlichter, 2010-05-04
-
[Bug 574746] Re: serve Xorg performance regression (fullscreen flash)
From: Bryce Harrington, 2010-05-04
-
[Bug 574746] Re: serve Xorg performance regression (fullscreen flash)
From: Bartosz, 2010-05-04
-
[Bug 574746] xkbcomp.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] xdpyinfo.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] setxkbmap.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] glxinfo.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] Xrandr.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] XorgLogOld.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] XorgLog.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] UdevLog.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] UdevDb.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] RelatedPackageVersions.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] ProcModules.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] ProcInterrupts.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] ProcCpuinfo.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] PciDisplay.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] Lsusb.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] Lspci.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] Dependencies.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] CurrentDmesg.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] BootDmesg.txt
From: Thomas Schlichter, 2010-05-03
-
[Bug 574746] [NEW] serve Xorg performance regression (fullscreen flash)
From: Thomas Schlichter, 2010-05-03
References