Re: [PATCH v3] mm: swap: properly update readahead statistics in unuse_pte_range()

From: Andrea Righi
Date: Sat Apr 18 2020 - 04:51:51 EST


On Fri, Apr 17, 2020 at 01:18:37PM +0800, Huang, Ying wrote:
> Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> writes:
>
> > On Fri, 17 Apr 2020 11:01:22 +0800 "Huang\, Ying" <ying.huang@xxxxxxxxx> wrote:
> >
> >> Andrea Righi <andrea.righi@xxxxxxxxxxxxx> writes:
> >>
> >> > In unuse_pte_range() we blindly swap-in pages without checking if the
> >> > swap entry is already present in the swap cache.
> >> >
> >> > By doing this, the hit/miss ratio used by the swap readahead heuristic
> >> > is not properly updated and this leads to non-optimal performance during
> >> > swapoff.
> >>
> >> It's more important to describe why we need this patch in the patch
> >> description. So, please add some information about your use case. And
> >> please focus on the technical part instead of the business part.
> >
> > Confused. I thought the changelog was quite good. If "business part"
> > means "end user effect of the patch" then that's a very important
> > thing.
>
> Previously, Andrea has described their use case in the cloud environment
> to hiberate the guest and swapoff after resuming. So swapoff
> performance is important for them. I think that should be included.
> For the business part, I mean something like "Ubuntu used in AWS EC2", I
> think that isn't important for the patch description.

I just sent a v4 of this patch adding "conclusion" section in the
description to better explain the purpose of this patch. Let me know if
you have any comment on that.

Thanks,
-Andrea