[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CALvZod7uzDuWAMnnxubv7=vx5Qktmw5o=2ivS-tUa2YA+5QzzA@mail.gmail.com>
Date: Tue, 22 Jun 2021 07:59:35 -0700
From: Shakeel Butt <shakeelb@...gle.com>
To: SeongJae Park <sj38.park@...il.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
SeongJae Park <sjpark@...zon.de>, Jonathan.Cameron@...wei.com,
acme@...nel.org, alexander.shishkin@...ux.intel.com,
amit@...nel.org, benh@...nel.crashing.org,
Brendan Higgins <brendanhiggins@...gle.com>,
Jonathan Corbet <corbet@....net>,
David Hildenbrand <david@...hat.com>, dwmw@...zon.com,
Marco Elver <elver@...gle.com>, "Du, Fan" <fan.du@...el.com>,
foersleo@...zon.de, greg@...ah.com,
Greg Thelen <gthelen@...gle.com>, guoju.fgj@...baba-inc.com,
jgowans@...zon.com, Mel Gorman <mgorman@...e.de>, mheyne@...zon.de,
Minchan Kim <minchan@...nel.org>,
Ingo Molnar <mingo@...hat.com>, namhyung@...nel.org,
"Peter Zijlstra (Intel)" <peterz@...radead.org>,
Rik van Riel <riel@...riel.com>,
David Rientjes <rientjes@...gle.com>,
Steven Rostedt <rostedt@...dmis.org>,
Mike Rapoport <rppt@...nel.org>, Shuah Khan <shuah@...nel.org>,
sieberf@...zon.com, snu@...le79.org,
Vlastimil Babka <vbabka@...e.cz>,
Vladimir Davydov <vdavydov.dev@...il.com>,
zgf574564920@...il.com, linux-damon@...zon.com,
Linux MM <linux-mm@...ck.org>, linux-doc@...r.kernel.org,
LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v31 03/13] mm/damon: Adaptively adjust regions
On Mon, Jun 21, 2021 at 1:31 AM SeongJae Park <sj38.park@...il.com> wrote:
>
> From: SeongJae Park <sjpark@...zon.de>
>
> Even somehow the initial monitoring target regions are well constructed
> to fulfill the assumption (pages in same region have similar access
> frequencies), the data access pattern can be dynamically changed. This
> will result in low monitoring quality. To keep the assumption as much
> as possible, DAMON adaptively merges and splits each region based on
> their access frequency.
>
> For each ``aggregation interval``, it compares the access frequencies of
> adjacent regions and merges those if the frequency difference is small.
> Then, after it reports and clears the aggregated access frequency of
> each region, it splits each region into two or three regions if the
> total number of regions will not exceed the user-specified maximum
> number of regions after the split.
>
> In this way, DAMON provides its best-effort quality and minimal overhead
> while keeping the upper-bound overhead that users set.
>
> Signed-off-by: SeongJae Park <sjpark@...zon.de>
> Reviewed-by: Leonard Foerster <foersleo@...zon.de>
> Reviewed-by: Fernand Sieber <sieberf@...zon.com>
[...]
>
> +unsigned int damon_nr_regions(struct damon_target *t)
> +{
> + struct damon_region *r;
> + unsigned int nr_regions = 0;
> +
> + damon_for_each_region(r, t)
> + nr_regions++;
This bugs me everytime. Please just have nr_regions field in the
damon_target instead of traversing the list to count the number of
regions.
Other than that, it looks good to me.
Powered by blists - more mailing lists