On 12/28/18 6:26 AM, kernel test robot wrote:
> Greeting,
>
> FYI, we noticed a -4.3% regression of vm-scalability.throughput due to commit:
>
>
> commit: 9c83282117778856d647ffc461c4aede2abb6742 ("[PATCH v3 1/2] hugetlbfs:
> use i_mmap_rwsem for more pmd sharing synchronization")
> url:
> https://github.com/0day-ci/linux/commits/Mike-Kravetz/hugetlbfs-use-i_mmap_rwsem-for-better-synchronization/20181223-095226
>
>
> in testcase: vm-scalability
> on test machine: 104 threads Intel(R) Xeon(R) Platinum 8170 CPU @ 2.10GHz
> with 64G memory
> with following parameters:
>
> runtime: 300s
> size: 8T
> test: anon-cow-seq-hugetlb
> cpufreq_governor: performance
> ucode: 0x200004d
I'll take a closer look.
The patch does introduce longer i_mmap_rwsem hold times for the sake of
correctness. Need to more fully understand the test and results to determine
if this is expected.
--
Mike Kravetz
