Re: kernel BUG at mm/huge_memory.c:2736(linux 5.10.29)

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hi,

> And I'm not sure if khugepaged may have race condition with split, it
> sounds unlikely, but collapsing PTE-mapped THP support was added in
> v5.8, so you may try to reproduce this on v5.7 to narrow it down.

This is the test result on linux 5.7.17/5.8.18/5.9.16 with
CONFIG_DEBUG_VM=y and
CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y,
but without the debug patch from Yang Shi 

linux 5.7.17: this problem yet not happan after 6 tests.

linux 5.8.18: this problem yet not happan after 6 tests.

linux 5.19.16: this problem yet not happen ater 5 tests,
	but triggered a new problem, see dmesg-5.9.16.txt

we also noticed that the btrfs filesystem performance improvement in
5.10.x, that maybe change the memory reclaim frequency too.

Best Regards
Wang Yugui (wangyugui@xxxxxxxxxxxx)
2021/04/27

Attachment: dmesg-5.9.16.txt
Description: Binary data


[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux