linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
To: Minchan Kim <minchan.kim@gmail.com>
Cc: kosaki.motohiro@jp.fujitsu.com, Shaohua Li <shaohua.li@intel.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm <linux-mm@kvack.org>, Andi Kleen <andi@firstfloor.org>,
	Rik van Riel <riel@redhat.com>, mel <mel@csn.ul.ie>,
	Johannes Weiner <hannes@cmpxchg.org>
Subject: Re: [PATCH 2/2 v3]mm: batch activate_page() to reduce lock contention
Date: Tue,  8 Mar 2011 15:10:37 +0900 (JST)	[thread overview]
Message-ID: <20110308150937.7EC5.A69D9226@jp.fujitsu.com> (raw)
In-Reply-To: <AANLkTikBKemiS1aJB-MrHXwefHxKs2gGX6w=J1oQqJd-@mail.gmail.com>

> On Tue, Mar 8, 2011 at 1:47 PM, KOSAKI Motohiro
> <kosaki.motohiro@jp.fujitsu.com> wrote:
> >> > > +#ifdef CONFIG_SMP
> >> > > +static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
> >> >
> >> > Why do we have to handle SMP and !SMP?
> >> > We have been not separated in case of pagevec using in swap.c.
> >> > If you have a special reason, please write it down.
> >> this is to reduce memory footprint as suggested by akpm.
> >>
> >> Thanks,
> >> Shaohua
> >
> > Hi Shaouhua,
> >
> > I agree with you. But, please please avoid full quote. I don't think
> > it is so much difficult work. ;-)
> 
> I didn't want to add new comment in the code but want to know why we
> have to care of activate_page_pvecs specially. I think it's not a
> matter of difficult work or easy work. If new thing is different with
> existing things, at least some comment in description makes review
> easy.
> 
> If it's memory footprint issue, should we care of other pagevec to
> reduce memory footprint in non-smp? If it is, it would be a TODO list
> for consistency and memory footprint.

Yeah. indeed.
Shaoua, If my remember is correct, your previous version has code size
comparision result. could you resurrect it?


--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2011-03-08  6:10 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-03-07  8:36 Shaohua Li
2011-03-07  9:13 ` KOSAKI Motohiro
2011-03-07 15:57 ` Minchan Kim
2011-03-08  4:44   ` Shaohua Li
2011-03-08  4:47     ` KOSAKI Motohiro
2011-03-08  5:17       ` Minchan Kim
2011-03-08  6:10         ` KOSAKI Motohiro [this message]
2011-03-08  6:52           ` Shaohua Li

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=20110308150937.7EC5.A69D9226@jp.fujitsu.com \
    --to=kosaki.motohiro@jp.fujitsu.com \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-mm@kvack.org \
    --cc=mel@csn.ul.ie \
    --cc=minchan.kim@gmail.com \
    --cc=riel@redhat.com \
    --cc=shaohua.li@intel.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