Re: [drm/mgag200] 913ec479bb: vm-scalability.throughput 26.2% improvement

[Mike Kravetz]

On 8/27/20 2:16 AM, Thomas Zimmermann wrote:
> Hi
> 
> Am 26.08.20 um 10:58 schrieb kernel test robot:
>> Greeting,
>>
>> FYI, we noticed a 26.2% improvement of vm-scalability.throughput due to commit:
> 
> I guess this resolves the once-measured performance penalty of similar
> magnitude. But do we really understand these tests? When I sent out
> patches to resolve the problem, nothing changed. And suddenly the
> performance is back to normal.
> 
> Best regards
> Thomas
> 
>>
>>
>> commit: 913ec479bb5cc27f99f24d5fd111b3ef29a4deb9 ("drm/mgag200: Replace VRAM helpers with SHMEM helpers")
>> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
>>
>>
>> in testcase: vm-scalability
>> on test machine: 288 threads Intel(R) Xeon Phi(TM) CPU 7295 @ 1.50GHz with 80G memory
>> with following parameters:
>>
>> 	runtime: 300s
>> 	size: 8T
>> 	test: anon-cow-seq-hugetlb
>> 	cpufreq_governor: performance
>> 	ucode: 0x11

Hello Thomas,

Did drm changes really impact anon-cow-seq-hugetlb performance?

My change c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing
synchronization") caused a -33.4% regression of anon-cow-seq-hugetlb.  A
recent change 34ae204f185 (hugetlbfs: remove call to huge_pte_alloc without
i_mmap_rwsem) was tested by Zhengjun Xing and improved performance by 20
something percent.  That seems in line with this report/improvement.

Perhaps the tooling is not always accurate in determining the commit which
causes the performance changes?
Perhaps I am misreading information in the reports?
-- 
Mike Kravetz