linux-kernel - Re: [PATCH 2/2] zsmalloc: fine-grained inuse ratio based fullness grouping

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 9 Feb 2023 21:15:58 -0800
From:   Yosry Ahmed <yosryahmed@...gle.com>
To:     Sergey Senozhatsky <senozhatsky@...omium.org>
Cc:     Minchan Kim <minchan@...nel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCH 2/2] zsmalloc: fine-grained inuse ratio based fullness grouping

On Thu, Feb 9, 2023 at 8:30 PM Sergey Senozhatsky
<senozhatsky@...omium.org> wrote:
>
> On (23/02/09 20:25), Yosry Ahmed wrote:
> > > On (23/02/07 10:47), Sergey Senozhatsky wrote:
> [..]
> > > Forgot to mention, I was also thinking about extending zsmalloc stats
> > > file and providing values for each fullness group per class, as opposed
> > > to current ALMOST_EMPTY and ALMOST_FULL stats, which don't tell much.
> >
> > Makes sense.
> >
> > >
> > > I can get rid of static const arrays and pass "begin / end" group IDs to
> > > functions that iterate fullness lists and pick the first head page, but
> > > I think that enum values will stay.
> >
> > Do they have to stay for a technical reason or just to make reviews simpler?
>
> We need to be able to do zs_stat_get(class, CLASS_USAGE_70) or
> zs_stat_get(class, CLASS_USAGE_10) in zs_stats_size_show() to
> show class's fullness stats.

If we use #define FULLNESS_GROUPS 10 for example, we can break down
struct zs_size_stat from a single array to two arrays, one of the for
fullness groups and the other one for the rest of the stats (e.g.
OBJ_USED). We can have different helpers to update each, the former
taking in a fullness value (0 to FULLNESS_GROUPS-1), and the latter an
enum. WDYT?