16 Feb
2022
16 Feb
'22
4:35 p.m.
On 2022/2/16 3:32 下午, Huang, Ying wrote:
zhongjiang-ali
<zhongjiang-ali(a)linux.alibaba.com> writes:
benchmark test will produce lots of read and write, but the data comes
from pmem node and dram node
is not enough in current situation. hence promote will be triggered
frequently, a lot of hots page is promoted
frequently is not expected, we need to ajust the promote threshold to
decrease the hot page is demoted.
Mysql benchmark will produce too mnay promotion
due to DRAM node is not
enough,
I don't understand this. Why promotion will be too many if free pages
in DRAM node aren't enough?
Best Regards,
Huang, Ying
> but promotion frequently will result in performance decrease.
> hence, we perfer to remote access rather than demote/promote traffic
> frequently.
>
> Huang Ying (3):
> mm, migrate: use flags parameter for remove_migration_ptes()
> memory tiering: measure whether demoted pages are hot
> memory tiering: adjust promotion threshold based on hot pages demoted
>
> include/linux/mmzone.h | 3 ++
> include/linux/page-flags.h | 9 ++++++
> include/linux/page_ext.h | 3 ++
> include/linux/rmap.h | 8 ++++-
> include/linux/sched/numa_balancing.h | 62 ++++++++++++++++++++++++++++++++++++
> include/linux/sched/sysctl.h | 3 ++
> include/trace/events/mmflags.h | 8 ++++-
> kernel/sched/fair.c | 27 +++++++++++++---
> kernel/sysctl.c | 16 ++++++++++
> mm/huge_memory.c | 6 ++--
> mm/mempolicy.c | 2 ++
> mm/migrate.c | 60 ++++++++++++++++++++++++++++------
> mm/vmstat.c | 1 +
> 13 files changed, 189 insertions(+), 19 deletions(-)