linux-kernel - Re: [PATCH v1 0/3] per-process reclaim

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]

Message-ID: <575E9DE8.4050200@hisilicon.com>
Date:	Mon, 13 Jun 2016 19:50:00 +0800
From:	Chen Feng <puck.chen@...ilicon.com>
To:	Minchan Kim <minchan@...nel.org>,
	Andrew Morton <akpm@...ux-foundation.org>
CC:	<linux-kernel@...r.kernel.org>, <linux-mm@...ck.org>,
	Rik van Riel <riel@...hat.com>,
	Redmond <u93410091@...il.com>,
	"ZhaoJunmin Zhao(Junmin)" <zhaojunmin@...wei.com>,
	Vinayak Menon <vinmenon@...eaurora.org>,
	Juneho Choi <juno.choi@....com>,
	Sangwoo Park <sangwoo2.park@....com>,
	Chan Gyun Jeong <chan.jeong@....com>
Subject: Re: [PATCH v1 0/3] per-process reclaim

Hi Minchan,

On 2016/6/13 15:50, Minchan Kim wrote:
> Hi all,
> 
> http://thread.gmane.org/gmane.linux.kernel/1480728
> 
> I sent per-process reclaim patchset three years ago. Then, last
> feedback from akpm was that he want to know real usecase scenario.
> 
> Since then, I got question from several embedded people of various
> company "why it's not merged into mainline" and heard they have used
> the feature as in-house patch and recenlty, I noticed android from
> Qualcomm started to use it.
> 
> Of course, our product have used it and released it in real procuct.
> 
> Quote from Sangwoo Park <angwoo2.park@....com>
> Thanks for the data, Sangwoo!
> "
> - Test scenaro
>   - platform: android
>   - target: MSM8952, 2G DDR, 16G eMMC
>   - scenario
>     retry app launch and Back Home with 16 apps and 16 turns
>     (total app launch count is 256)
>   - result:
> 			  resume count   |  cold launching count
> -----------------------------------------------------------------
>  vanilla           |           85        |          171
>  perproc reclaim   |           184       |           72
> "
> 
> Higher resume count is better because cold launching needs loading
> lots of resource data which takes above 15 ~ 20 seconds for some
> games while successful resume just takes 1~5 second.
> 
> As perproc reclaim way with new management policy, we could reduce
> cold launching a lot(i.e., 171-72) so that it reduces app startup
> a lot.
> 
> Another useful function from this feature is to make swapout easily
> which is useful for testing swapout stress and workloads.
> 
Thanks Minchan.

Yes, this is useful interface when there are memory pressure and let the userspace(Android)
to pick process for reclaim. We also take there series into our platform.

But I have a question on the reduce app startup time. Can you also share your
theory(management policy) on how can the app reduce it's startup time?


> Thanks.
> 
> Cc: Redmond <u93410091@...il.com>
> Cc: ZhaoJunmin Zhao(Junmin) <zhaojunmin@...wei.com>
> Cc: Vinayak Menon <vinmenon@...eaurora.org>
> Cc: Juneho Choi <juno.choi@....com>
> Cc: Sangwoo Park <sangwoo2.park@....com>
> Cc: Chan Gyun Jeong <chan.jeong@....com>
> 
> Minchan Kim (3):
>   mm: vmscan: refactoring force_reclaim
>   mm: vmscan: shrink_page_list with multiple zones
>   mm: per-process reclaim
> 
>  Documentation/filesystems/proc.txt |  15 ++++
>  fs/proc/base.c                     |   1 +
>  fs/proc/internal.h                 |   1 +
>  fs/proc/task_mmu.c                 | 149 +++++++++++++++++++++++++++++++++++++
>  include/linux/rmap.h               |   4 +
>  mm/vmscan.c                        |  85 ++++++++++++++++-----
>  6 files changed, 235 insertions(+), 20 deletions(-)
>