[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-Id: <20220321133825.6f003c62381edbab361a8d96@linux-foundation.org>
Date: Mon, 21 Mar 2022 13:38:25 -0700
From: Andrew Morton <akpm@...ux-foundation.org>
To: Sean Anderson <seanga2@...il.com>
Cc: Yinan Zhang <zhangyinan2019@...il.szu.edu.cn>,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] tools/vm/page_owner_sort.c: add switch between culling
by stacktrace and txt
These comments were not responded to:
On Mon, 29 Nov 2021 21:23:41 -0500 Sean Anderson <seanga2@...il.com> wrote:
>
> This is working as designed. IMO there's no point in separating
> allocations like this which differ only in PID and timestamp, since you
> will get no grouping at all.
>
> > The info of second block missed. So, add -c to turn on culling
> > by stacktrace. By default, it will cull by txt.
>
> Please keep the default to actually do something in the cull step.
>
> ...
>
> > @@ -162,6 +171,9 @@ int main(int argc, char **argv)
> > case 't':
> > cmp = compare_num;
> > break;
> > + case 'c':
> > + cull_st = 1;
> > + break;
>
> Can we set a "cull_cmp" variable like cmp?
>
> Looking forward, I think something like
>
> page_owner_sort --cull=stacktrace --sort=times foo bar
>
> would be nice.
>
Which is unfortunate.
I'll send the patch in to Linus anyway, as many other patches
syntactically depend on it. Please work with Sean to address these
issues and lets get this resolved over the next few weeks.
Also, please cc linux-mm@...ck.org on changes to page_owner.
Powered by blists - more mailing lists