[drm/mgag200] e44e907dd8: phoronix-test-suite.glmark2.800x600.score -64.9% regression

Thomas Zimmermann tzimmermann at suse.de
Tue Jun 16 13:49:53 UTC 2020


Hi

Am 16.06.20 um 05:10 schrieb Rong Chen:
> 
> 
> On 6/16/20 4:58 AM, Emil Velikov wrote:
>> Hi all,
>>
>> On Thu, 4 Jun 2020 at 08:11, kernel test robot <rong.a.chen at intel.com>
>> wrote:
>>> Greeting,
>>>
>>> FYI, we noticed a -64.9% regression of
>>> phoronix-test-suite.glmark2.800x600.score due to commit:
>>>
>> On one hand, I'm really happy to see performance testing happening
>> although this report is missing various crucial pieces of information.
>>
>>> commit: e44e907dd8f937313d35615d799d54162c56d173 ("[PATCH v3 05/15]
>>> drm/mgag200: Split MISC register update into PLL selection, SYNC and
>>> I/O")
>>> url:
>>> https://github.com/0day-ci/linux/commits/Thomas-Zimmermann/drm-mgag200-Convert-to-atomic-modesetting/20200515-163744
>>>
>>> base: git://anongit.freedesktop.org/drm/drm-tip drm-tip
>>>
>>> in testcase: phoronix-test-suite
>>> on test machine: 16 threads Intel(R) Xeon(R) CPU X5570 @ 2.93GHz with
>>> 48G memory
>>> with following parameters:
>>>
>>>          need_x: true
>> Replace "need_x" with the Xorg version as seen in `Xorg -version'.
> 
> # Xorg -version
> /bin/sh: warning: setlocale: LC_ALL: cannot change locale (en_US.UTF-8)
> 
> X.Org X Server 1.20.4
> X Protocol Version 11, Revision 0
> Build Operating System: Linux 4.9.0-8-amd64 x86_64 Debian
> Current Operating System: Linux lkp-nhm-2ep1
> 5.7.0-rc5-01428-ge44e907dd8f937 #1 SMP Tue Jun 2 19:51:38 CST 2020 x86_64
> Kernel command line:  ip=::::lkp-nhm-2ep1::dhcp
> root=/dev/disk/by-id/wwn-0x55cd2e4123123127-part2
> rootflags=subvol=debian-x86_64-phoronix
> remote_rootfs=internal-lkp-server:/osimage/debian/debian-x86_64-phoronix
> user=lkp
> job=/lkp/jobs/scheduled/lkp-nhm-2ep1/phoronix-test-suite-performance-true-glmark2-1.1.0-ucode=0x1d-debian-x86_64-phoronix-e44e907dd8f937313d35615d799d54162c56d173-20200616-56456-1kgmjzm-0.yaml
> ARCH=x86_64 kconfig=x86_64-rhel-7.6
> branch=linux-devel/devel-hourly-2020051600
> commit=e44e907dd8f937313d35615d799d54162c56d173
> BOOT_IMAGE=/pkg/linux/x86_64-rhel-7.6/gcc-7/e44e907dd8f937313d35615d799d54162c56d173/vmlinuz-5.7.0-rc5-01428-ge44e907dd8f937
> console=ttyS1,115200 console=tty0 max_uptime=3600
> RESULT_ROOT=/result/phoronix-test-suite/performance-true-glmark2-1.1.0-ucode=0x1d/lkp-nhm-2ep1/debian-x86_64-phoronix/x86_64-rhel-7.6/gcc-7/e44e907dd8f937313d35615d799d54162c56d173/4
> LKP_SERVER=inn nokaslr selinux=0 debug apic=debug sysrq_always_enabled
> rcupdate.rcu_cpu_stall_timeout=100 net.ifnames=0 printk.devkmsg=on
> panic=-1 softlockup_panic=1 nmi_watchdog=panic oops=panic load_ramdisk=2
> prompt_ramdisk=0 drbd.minor_count=8 systemd.log_level=err
> ignore_loglevel console=tty0 earlyprintk=ttyS0,115200
> console=ttyS0,115200 vga=normal rw
> Build Date: 05 March 2019  08:11:12PM
> xorg-server 2:1.20.4-1 (https://www.debian.org/support)
> Current version of pixman: 0.36.0
>         Before reporting problems, check http://wiki.x.org
>         to make sure that you have the latest version.
> 
>>
>>>          test: glmark2-1.1.0
>>>          cpufreq_governor: performance
>>>          ucode: 0x1d
>>>
>>> test-description: The Phoronix Test Suite is the most comprehensive
>>> testing and benchmarking platform available that provides an
>>> extensible framework for which new tests can be easily added.
>>> test-url: http://www.phoronix-test-suite.com/
>>>
>> Please remove the test description and url. They don't add any value.
>>
>> Mention which Mesa version is used as well as on what GPU. The output
>> of lspci and glxinfo will help here.
> 
> Attached please find the outputs of lspci and glxinfo
> 
>>
>> For this particular test - there is no Mesa/upstream driver for this
>> GPU, so I imagine one of the swrast drivers was used. Which one -
>> swrast (classic, softpipe, llvmpipe, swr) or kms_swrast.
>> The output of `LD_DEBUG=libs glxinfo  |& grep _dri.so` will help here.
> 
> # LD_DEBUG=libs glxinfo  |& grep _dri.so
>       2132:     calling init: /usr/lib/i386-linux-gnu/dri/swrast_dri.so
>       2132:     calling fini: /usr/lib/i386-linux-gnu/dri/swrast_dri.so [0]
> 
> Best Regards,
> Rong Chen

Thanks for testing. If I send out a patch, could you try it?

Best regards
Thomas

> 
>>
>>> commit:
>>>    bef2303526 ("drm/mgag200: Move mode-setting code into separate
>>> helper function")
>>>    e44e907dd8 ("drm/mgag200: Split MISC register update into PLL
>>> selection, SYNC and I/O")
>>>
>> Actually the offending commit has a subtle change of behaviour - it
>> adds an extra MGAREG_MISC_RAMMAPEN.
>> That is not documented and I've failed to spot it during review.
>>
>> Thomas - shall we revert that line in itself or at least add an inline
>> comment why it is needed?
>>
>>>    100
>>> +---------------------------------------------------------------------+
>>>     90 |-+    +      +   +.+      +    +     +    +      +  
>>> :               |
>>>        | :    :      :   : :      :    :     :    :      :  
>>> :               |
>>>     80 |-:    :      :   : :      :    :     :    :      :  
>>> :               |
>>>     70 |-::   :     ::   :  :     :   ::     ::   :     :: 
>>> :                |
>>>        |: :  : :    : : :   :    : :  : :   : :  : :    : :
>>> :                |
>>>     60 |:+:  : :    : : :   :    : :  : :   : :  : :    : :
>>> :                |
>>>     50 |:+:  : :    : : :   :    : :  : :   : :  : :    : :
>>> :                |
>>>     40 |:+ : : :   :  : :    :   : : :  :   :  : : :   :  :
>>> :                |
>>>        |:  : : :   :  : :    :   : : :  :   :  : : :   :  : :O      O
>>> O O  O |
>>>     30 |:+ : : :   :  : :    :   : : :  :   :  : : :   :  :
>>> :                |
>>>     20 |-+ ::   :  :   :     :  :   ::   : :   ::   :  : O
>>> :                 |
>>>        |    :   : :    :      : :   :    : :    :   : :   
>>> :                 |
>>>     10 |-+  :   : :    :      : :   :    : :    :   : :   
>>> :                 |
>>>      0
>>> +---------------------------------------------------------------------+
>>>
>>>
>>>                     phoronix-test-suite.glmark2.1024x768.score
>>>
>>>    70
>>> +----------------------------------------------------------------------+
>>>       | +    +      +   +..+     +    +      +    +     +   
>>> +.+             |
>>>    60 |-:    :      :   :  :     :    :      :    :     :   
>>> :               |
>>>       | :    :      :   :  :     :    :      :    :     :   
>>> :               |
>>>    50 |-::   :     ::   :  :     ::   :      :   ::     ::  
>>> :               |
>>>       |: :  : :    : : :    :   : :  : :    : :  : :   : : 
>>> :                |
>>>    40 |:+:  : :    : : :    :   : :  : :    : :  : :   : : 
>>> :                |
>>>       |: :  : :    : : :    :   : :  : :    : :  : :   : :  :        
>>> O      |
>>>    30 |:+ : : :   :  : :    :   :  : : :    : : :  :   :  : :O     
>>> O   O  O |
>>>       |:  : : :   :  : :    :   :  : : :    : : :  :   :  :
>>> :                |
>>>    20 |:+ : : :   :  : :    :   :  : : :    : : :  :   :  :
>>> :                |
>>>       |   ::   :  :   :      : :   ::   :  :   ::   : : O
>>> ::                 |
>>>    10 |-+  :   : :    :      : :    :   :  :   :    : :   
>>> :                 |
>>>       |    :   : :  O :    O : : O  :   :  : O :    : :   
>>> :                 |
>>>     0
>>> +----------------------------------------------------------------------+
>>>
>>>
>>> [*] bisect-good sample
>>> [O] bisect-bad  sample
>>>
>> Hmm I must be going blind - there isn't even a single * in either of
>> the graphs.
>> Or perhaps my eyesight is fine and the legend or the graphs need fixing.
>>
>> HTH
>> -Emil
> 

-- 
Thomas Zimmermann
Graphics Driver Developer
SUSE Software Solutions Germany GmbH
Maxfeldstr. 5, 90409 Nürnberg, Germany
(HRB 36809, AG Nürnberg)
Geschäftsführer: Felix Imendörffer

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 488 bytes
Desc: OpenPGP digital signature
URL: <https://lists.freedesktop.org/archives/dri-devel/attachments/20200616/2e205d24/attachment-0001.sig>


More information about the dri-devel mailing list