From: Minchan Kim <minchan.kim@gmail.com>
To: Mel Gorman <mel@csn.ul.ie>
Cc: Wu Fengguang <fengguang.wu@intel.com>,
Iram Shahzad <iram.shahzad@jp.fujitsu.com>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Subject: Re: compaction: trying to understand the code
Date: Fri, 20 Aug 2010 19:22:16 +0900 [thread overview]
Message-ID: <AANLkTimVmoomDjGMCfKvNrS+v-mMnfeq6JDZzx7fjZi+@mail.gmail.com> (raw)
In-Reply-To: <20100820093558.GG19797@csn.ul.ie>
On Fri, Aug 20, 2010 at 6:35 PM, Mel Gorman <mel@csn.ul.ie> wrote:
> On Fri, Aug 20, 2010 at 01:34:47PM +0800, Wu Fengguang wrote:
>> You do run lots of tasks: kernel_stack=1880kB.
>>
>> And you have lots of free memory, page reclaim has never run, so
>> inactive_anon=0. This is where compaction is different from vmscan.
>> In vmscan, inactive_anon is reasonably large, and will only be
>> compared directly with isolated_anon.
>>
>
> True, the key observation here was that compaction is being run via the
> proc trigger. Normally it would be run as part of the direct reclaim
> path when kswapd would already be awake. too_many_isolated() needs to be
> different for compaction to take the whole system into account. What
> would be the best alternative? Here is one possibility. A reasonable
> alternative would be that when inactive < active that isolated can't be
> more than num_online_cpus() * 2 (i.e. one compactor per online cpu).
>
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 94cce51..1e000b7 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -215,14 +215,16 @@ static void acct_isolated(struct zone *zone, struct compact_control *cc)
> static bool too_many_isolated(struct zone *zone)
> {
>
> - unsigned long inactive, isolated;
> + unsigned long active, inactive, isolated;
>
> + active = zone_page_state(zone, NR_ACTIVE_FILE) +
> + zone_page_state(zone, NR_INACTIVE_ANON);
> inactive = zone_page_state(zone, NR_INACTIVE_FILE) +
> zone_page_state(zone, NR_INACTIVE_ANON);
> isolated = zone_page_state(zone, NR_ISOLATED_FILE) +
> zone_page_state(zone, NR_ISOLATED_ANON);
>
> - return isolated > inactive;
> + return (inactive > active) ? isolated > inactive : false;
> }
>
> /*
>
1. active : 1000 inactive : 1000
2. parallel reclaiming -> active : 1000 inactive : 500 isolated : 500
3. too_many_isolated return false.
But in this case, there are already many isolated pages. So it should
return true.
How about this?
too_many_isolated()
{
return (isolated > nr_zones * nr_nodes * nr_online_cpu *
SWAP_CLUSTER_MAX);
}
--
Kind regards,
Minchan Kim
--
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 prev parent reply other threads:[~2010-08-20 10:30 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-08-17 11:08 compaction: trying to understand the code Iram Shahzad
2010-08-17 11:10 ` Mel Gorman
2010-08-18 8:19 ` Iram Shahzad
2010-08-18 15:41 ` Wu Fengguang
2010-08-19 7:09 ` Iram Shahzad
2010-08-19 7:45 ` Wu Fengguang
2010-08-19 7:46 ` Mel Gorman
2010-08-19 8:08 ` Wu Fengguang
2010-08-19 8:15 ` Mel Gorman
2010-08-19 8:29 ` Wu Fengguang
2010-08-20 5:45 ` Iram Shahzad
2010-08-20 5:50 ` Wu Fengguang
2010-08-20 6:13 ` Iram Shahzad
2010-08-19 16:00 ` Minchan Kim
2010-08-20 5:31 ` Iram Shahzad
2010-08-20 5:34 ` Wu Fengguang
2010-08-20 9:35 ` Mel Gorman
2010-08-20 10:22 ` Minchan Kim [this message]
2010-08-22 15:31 ` Minchan Kim
2010-08-22 23:23 ` Wu Fengguang
2010-08-23 1:58 ` Minchan Kim
2010-08-23 3:03 ` Iram Shahzad
2010-08-23 9:10 ` Minchan Kim
2010-08-26 8:51 ` Mel Gorman
2010-08-23 7:18 ` Mel Gorman
2010-08-23 17:14 ` Minchan Kim
2010-08-24 0:27 ` Wu Fengguang
2010-08-24 5:07 ` Iram Shahzad
2010-08-24 6:52 ` Minchan Kim
2010-08-26 8:05 ` Iram Shahzad
2010-08-23 7:16 ` Mel Gorman
2010-08-23 9:07 ` Minchan Kim
2010-08-20 10:23 ` Wu Fengguang
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=AANLkTimVmoomDjGMCfKvNrS+v-mMnfeq6JDZzx7fjZi+@mail.gmail.com \
--to=minchan.kim@gmail.com \
--cc=fengguang.wu@intel.com \
--cc=iram.shahzad@jp.fujitsu.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.