From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
To: "nishimura@mxp.nes.nec.co.jp" <nishimura@mxp.nes.nec.co.jp>
Cc: "kamezawa.hiroyu@jp.fujitsu.com" <kamezawa.hiroyu@jp.fujitsu.com>,
"balbir@linux.vnet.ibm.com" <balbir@linux.vnet.ibm.com>,
"hugh@veritas.com" <hugh@veritas.com>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
"menage@google.com" <menage@google.com>,
Andrew Morton <akpm@linux-foundation.org>
Subject: memo: mem+swap controller
Date: Thu, 31 Jul 2008 10:15:33 +0900 [thread overview]
Message-ID: <20080731101533.c82357b7.kamezawa.hiroyu@jp.fujitsu.com> (raw)
Hi, mem+swap controller is suggested by Hugh Dickins and I think it's a great
idea. Its concept is having 2 limits. (please point out if I misunderstand.)
- memory.limit_in_bytes .... limit memory usage.
- memory.total_limit_in_bytes .... limit memory+swap usage.
By this, we can avoid excessive use of swap under a cgroup without any bad effect
to global LRU. (in page selection algorithm...overhead will be added, of course)
Following is state transition and counter handling design memo.
This uses "3" counters to handle above conrrectly. If you have other logic,
please teach me. (and blame me if my diagram is broken.)
A point is how to handle swap-cache, I think.
(Maybe we need a _big_ change in memcg.)
==
state definition
new alloc .... an object is newly allocated
no_swap .... an object with page without swp_entry
swap_cache .... an object with page with swp_entry
disk_swap .... an object without page with swp_entry
freed .... an object is freed (by munmap)
(*) an object is an enitity which is accoutned, page or swap.
new alloc -> no_swap <=> swap_cache <=> disk_swap
| | |
freed. <-----------<-------------<-----------
use 3 counters, no_swap, swap_cache, disk_swap.
on_memory = no_swap + swap_cache.
total = no_swap + swap_cache + disk_swap
on_memory is limited by memory.limit_in_bytes
total is limtied by memory.total_limit_in_bytes.
no_swap swap_cache disk_swap on_memory total
new alloc->no_swap +1 - - +1 +1
no_swap->swap_cache -1 +1 - - -
swap_cache->no_swap +1 -1 - - -
swap_cache->disk_swap - -1 +1 -1 -
disk_swap->swap_cache - +1 -1 +1 -
no_swap->freed -1 - - -1 -1
swap_cache->freed - -1 - -1 -1
disk_swap->freed - - -1 - -1
any comments are welcome.
Regards,
-Kame
--
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>
next reply other threads:[~2008-07-31 1:15 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-07-31 1:15 KAMEZAWA Hiroyuki [this message]
2008-07-31 6:18 ` KOSAKI Motohiro
2008-07-31 6:25 ` Daisuke Nishimura
2008-07-31 6:51 ` KAMEZAWA Hiroyuki
2008-07-31 13:03 ` Daisuke Nishimura
2008-07-31 16:31 ` kamezawa.hiroyu
2008-08-01 3:05 ` Daisuke Nishimura
2008-08-01 3:28 ` Balbir Singh
2008-08-01 4:02 ` Daisuke Nishimura
2008-08-01 4:13 ` Balbir Singh
2008-08-01 4:57 ` Daisuke Nishimura
2008-08-01 5:07 ` memcg swappiness (Re: memo: mem+swap controller) YAMAMOTO Takashi
2008-08-01 5:25 ` Balbir Singh
2008-08-01 6:37 ` YAMAMOTO Takashi
2008-08-01 6:46 ` Balbir Singh
2008-09-09 9:17 ` YAMAMOTO Takashi
2008-09-09 14:07 ` Balbir Singh
2008-08-01 3:20 ` memo: mem+swap controller Balbir Singh
2008-08-01 3:45 ` KAMEZAWA Hiroyuki
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=20080731101533.c82357b7.kamezawa.hiroyu@jp.fujitsu.com \
--to=kamezawa.hiroyu@jp.fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=balbir@linux.vnet.ibm.com \
--cc=hugh@veritas.com \
--cc=linux-mm@kvack.org \
--cc=menage@google.com \
--cc=nishimura@mxp.nes.nec.co.jp \
/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