From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
To: Ying Han <yinghan@google.com>
Cc: kosaki.motohiro@jp.fujitsu.com, riel@redhat.com,
minchan.kim@gmail.com, hugh.dickins@tiscali.co.uk,
kamezawa.hiroyu@jp.fujitsu.com, fengguang.wu@intel.com,
mel@csn.ul.ie, npiggin@suse.de, akpm@linux-foundation.org,
linux-mm@kvack.org
Subject: Re: [PATCH] [RFC]Dirty page accounting on lru basis.
Date: Fri, 3 Sep 2010 16:50:29 +0900 (JST) [thread overview]
Message-ID: <20100903164142.2F23.A69D9226@jp.fujitsu.com> (raw)
In-Reply-To: <1283488982-19361-1-git-send-email-yinghan@google.com>
> For each active, inactive and unevictable lru list, we would like to count the
> number of dirty file pages. This becomes useful when we start monitoring and
> tracking the efficiency of page reclaim path while doing some heavy IO workloads.
>
> We export the new accounting now through global proc/meminfo as well as per-node
> meminfo. Ideally, the accounting should work as:
linux/Documentation/vm/page-types.c ?
% sudo ~/bin/page-types
flags page-count MB symbolic-flags long-symbolic-flags
0x0000000000000000 76660 299 __________________________________
0x0000000000000024 33920 132 __R__l____________________________ referenced,lru
0x0000000000000028 23774 92 ___U_l____________________________ uptodate,lru
0x0001000000000028 378 1 ___U_l________________________I___ uptodate,lru,readahead
0x000000000000002c 160474 626 __RU_l____________________________ referenced,uptodate,lru
0x0000000000004038 21 0 ___UDl________b___________________ uptodate,dirty,lru,swapbacked
0x000000000000003c 124491 486 __RUDl____________________________ referenced,uptodate,dirty,lru
0x000000000000403c 7 0 __RUDl________b___________________ referenced,uptodate,dirty,lru,swapbacked
0x0000000000000060 3521 13 _____lA___________________________ lru,active
0x0000000000000064 12681 49 __R__lA___________________________ referenced,lru,active
0x0000000000000068 5309 20 ___U_lA___________________________ uptodate,lru,active
0x000000000000006c 22840 89 __RU_lA___________________________ referenced,uptodate,lru,active
0x0000000000000074 60 0 __R_DlA___________________________ referenced,dirty,lru,active
0x000000000000007c 3 0 __RUDlA___________________________ referenced,uptodate,dirty,lru,active
0x0000000000000080 33810 132 _______S__________________________ slab
0x0004000000000080 179 0 _______S________________________A_ slab,slub_frozen
0x000000000000012c 7463 29 __RU_l__W_________________________ referenced,uptodate,lru,writeback
0x000000000000012d 2 0 L_RU_l__W_________________________ locked,referenced,uptodate,lru,writeback
0x0000000000000400 683 2 __________B_______________________ buddy
0x0000000000000800 16 0 ___________M______________________ mmap
0x0000000000000804 1 0 __R________M______________________ referenced,mmap
0x0000000000000828 42 0 ___U_l_____M______________________ uptodate,lru,mmap
0x000000000000082c 959 3 __RU_l_____M______________________ referenced,uptodate,lru,mmap
0x0000000000004838 4 0 ___UDl_____M__b___________________ uptodate,dirty,lru,mmap,swapbacked
0x0000000000000868 158 0 ___U_lA____M______________________ uptodate,lru,active,mmap
0x000000000000086c 3091 12 __RU_lA____M______________________ referenced,uptodate,lru,active,mmap
0x0000000000005808 2 0 ___U_______Ma_b___________________ uptodate,mmap,anonymous,swapbacked
0x0000000000005828 2702 10 ___U_l_____Ma_b___________________ uptodate,lru,mmap,anonymous,swapbacked
0x000000000000582c 22 0 __RU_l_____Ma_b___________________ referenced,uptodate,lru,mmap,anonymous,swapbacked
0x0000000000005868 8342 32 ___U_lA____Ma_b___________________ uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c 17 0 __RU_lA____Ma_b___________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked
total 521632 2037
That said,
ActiveDirty(file): 240KB
InactiveDirty(file): 486MB
--
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: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
prev parent reply other threads:[~2010-09-03 7:50 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-09-03 4:43 Ying Han
2010-09-03 7:50 ` KOSAKI Motohiro [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20100903164142.2F23.A69D9226@jp.fujitsu.com \
--to=kosaki.motohiro@jp.fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=fengguang.wu@intel.com \
--cc=hugh.dickins@tiscali.co.uk \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--cc=minchan.kim@gmail.com \
--cc=npiggin@suse.de \
--cc=riel@redhat.com \
--cc=yinghan@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox