From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pg0-f70.google.com (mail-pg0-f70.google.com [74.125.83.70]) by kanga.kvack.org (Postfix) with ESMTP id AFCBD6B0038 for ; Mon, 15 May 2017 03:25:34 -0400 (EDT) Received: by mail-pg0-f70.google.com with SMTP id s62so105797915pgc.2 for ; Mon, 15 May 2017 00:25:34 -0700 (PDT) Received: from tyimss.htc.com (tyimss.htc.com. [220.128.71.150]) by mx.google.com with ESMTPS id x3si9687104pls.24.2017.05.15.00.25.33 for (version=TLS1 cipher=AES128-SHA bits=128/128); Mon, 15 May 2017 00:25:33 -0700 (PDT) From: Subject: RE: Low memory killer problem Date: Mon, 15 May 2017 07:25:20 +0000 Message-ID: References: In-Reply-To: Content-Language: en-US Content-Type: multipart/alternative; boundary="_000_AF7C0ADF1FEABA4DABABB97411952A2EDD0A4F06CNMBX03HTCCOMTW_" MIME-Version: 1.0 Sender: owner-linux-mm@kvack.org List-ID: To: vinmenon@codeaurora.org, linux-mm@kvack.org, skhiani@codeaurora.org, gregkh@linuxfoundation.org Cc: torvalds@linux-foundation.org --_000_AF7C0ADF1FEABA4DABABB97411952A2EDD0A4F06CNMBX03HTCCOMTW_ Content-Type: text/plain; charset="iso-2022-jp" Content-Transfer-Encoding: quoted-printable Loop MM maintainers, Dear All, Who can talk about this problem? Thanks. Maybe this is lowmemory killer=1B$B!G=1B(Bs bug ? ION memory is complex now, we need to have a breakdown for them, I think. Thanks a lot Zhiyuan zhu From: Zhiyuan Zhu(=1B$B<3.=1B(B); Zhiyuan Zhu(=1B$B

Loop MM maintainers,

 

Dear All,

 

Who can talk about this problem? Thanks.

Maybe this is lowmemory killer=1B$B!G=1B(Bs bug ?

ION memory is complex now, we need to have a breakdown for them, I thi= nk.

 

Thanks a lot

Zhiyuan zhu

From: Zhiyuan = Zhu(=1B$B)
Sent: Friday, May 12, 2017 4:56 PM
To: vinmenon@codeaurora.org
Cc: Kyle Lin(=1B$BNS><3.=1B(B); Zhiyuan Zhu(=1B$B)
Subject: Low memory killer problem

 

Dear Vinmenon,

 

I found a part of ION memory will be return to syste= m in android platform,

But these memorys  can=1B$B!G=1B(Bt accounted i= n low-memory-killer strategy.

=1B$B!D=1B(B

And I also found ION memory comes from, kmalloc/vmal= loc/alloc pages/reserved memory.

What affect if account these memorys for free?<= /o:p>

Many thanks.

 

=1B$B!D=1B(B

Lowmemory killer strategy

af6c02b83 (Vinayak Menon    &nbs= p; 2015-08-27 16:29:37 +0530 418)      &n= bsp;     global_page_state(NR_FILE_PAGES) + zcache_= pages())

af6c02b83 (Vinayak Menon    &nbs= p; 2015-08-27 16:29:37 +0530 419)      &n= bsp;     other_file =3D global_page_state(NR_FILE_PAGES= ) + zcache_pages() -

058dbde92 (Vinayak Menon    &nbs= p; 2014-02-27 00:36:22 +0530 420)      &n= bsp;            = ;            &n= bsp;            glob= al_page_state(NR_SHMEM) -

5c4698e38 (kyle_lin     &nb= sp;     2015-04-16 16:04:22 +0800 421)  &= nbsp;           &nbs= p;            &= nbsp;           &nbs= p;    global_page_state(NR_MLOCK) -

058dbde92 (Vinayak Menon    &nbs= p; 2014-02-27 00:36:22 +0530 422)      &n= bsp;            = ;            &n= bsp;            tota= l_swapcache_pages();

 

 

Meminfo example

$ adb shell cat /proc/meminfo

MemTotal:        = 3805312 kB

MemFree:       &n= bsp; 1446220 kB

MemAvailable:    2388384 kB

Buffers:       &n= bsp;   16796 kB

Cached:       &nb= sp;  1190868 kB

=1B$B!D=1B(B

IonTotal:       &= nbsp; 224252 kB

IonInUse:       &= nbsp; 199108 kB

 

 

Thanks

BR

Zhiyuan zhu

--_000_AF7C0ADF1FEABA4DABABB97411952A2EDD0A4F06CNMBX03HTCCOMTW_-- -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org