[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201126121226.18883-1-sjpark@amazon.com>
Date: Thu, 26 Nov 2020 13:12:26 +0100
From: SeongJae Park <sjpark@...zon.com>
To: Shakeel Butt <shakeelb@...gle.com>
CC: SeongJae Park <sjpark@...zon.com>,
SeongJae Park <sjpark@...zon.de>,
<Jonathan.Cameron@...wei.com>,
Andrea Arcangeli <aarcange@...hat.com>, <acme@...nel.org>,
<alexander.shishkin@...ux.intel.com>, <amit@...nel.org>,
<benh@...nel.crashing.org>, <brendan.d.gregg@...il.com>,
Brendan Higgins <brendanhiggins@...gle.com>,
Qian Cai <cai@....pw>,
Colin Ian King <colin.king@...onical.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 Thelen" <gthelen@...gle.com>,
Ian Rogers <irogers@...gle.com>, <jolsa@...hat.com>,
"Kirill A. Shutemov" <kirill@...temov.name>,
Mark Rutland <mark.rutland@....com>,
Mel Gorman <mgorman@...e.de>, Minchan Kim <minchan@...nel.org>,
Ingo Molnar <mingo@...hat.com>, <namhyung@...nel.org>,
"Peter Zijlstra (Intel)" <peterz@...radead.org>,
Randy Dunlap <rdunlap@...radead.org>,
Rik van Riel <riel@...riel.com>,
David Rientjes <rientjes@...gle.com>,
Steven Rostedt <rostedt@...dmis.org>,
Mike Rapoport <rppt@...nel.org>, <sblbir@...zon.com>,
Shuah Khan <shuah@...nel.org>, <sj38.park@...il.com>,
<snu@...zon.de>, Vlastimil Babka <vbabka@...e.cz>,
Vladimir Davydov <vdavydov.dev@...il.com>,
Yang Shi <yang.shi@...ux.alibaba.com>,
Huang Ying <ying.huang@...el.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 v22 03/18] mm/damon: Adaptively adjust regions
On Wed, 25 Nov 2020 07:29:41 -0800 Shakeel Butt <shakeelb@...gle.com> wrote:
> On Tue, Oct 20, 2020 at 2:01 AM SeongJae Park <sjpark@...zon.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>
>
> The high level comment I have is that kdamond_[merge|split]_regions
> should be part of the abstraction of the target instead of the damon
> context.
Agreed in a high level. Please refer to my answer to your second suggestion at
https://lore.kernel.org/linux-mm/20201126115157.6888-1-sjpark@amazon.com/
Thanks,
SeongJae Park
Powered by blists - more mailing lists