From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: kosaki.motohiro@jp.fujitsu.com,
Andrew Morton <akpm@linux-foundation.org>,
"Rafael J. Wysocki" <rjw@sisk.pl>, Rik van Riel <riel@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH 3/3][RFC] swsusp: shrink file cache first
Date: Fri, 6 Feb 2009 14:59:35 +0900 (JST) [thread overview]
Message-ID: <20090206135302.628E.KOSAKI.MOTOHIRO@jp.fujitsu.com> (raw)
In-Reply-To: <20090206044907.GA18467@cmpxchg.org>
Hi
> > if we think suspend performance, we should consider swap device and file-backed device
> > are different block device.
> > the interleave of file-backed page out and swap out can improve total write out performce.
>
> Hm, good point. We could probably improve that but I don't think it's
> too pressing because at least on my test boxen, actual shrinking time
> is really short compared to the total of suspending to disk.
ok.
only remain problem is mesurement result posting :)
> > if we think resume performance, we shold how think the on-disk contenious of the swap consist
> > process's virtual address contenious.
> > it cause to reduce unnecessary seek.
> > but your patch doesn't this.
> >
> > Could you explain this patch benefit?
>
> The patch tries to shrink those pages first that are most unlikely to
> be needed again after resume. It assumes that active anon pages are
> immediately needed after resume while inactive file pages are not. So
> it defers shrinking anon pages after file cache.
hmm, I'm confusing.
I agree active anon is important than inactive file.
but I don't understand why scanning order at suspend change resume order.
> But I just noticed that the old behaviour defers it as well, because
> even if it does scan anon pages from the beginning, it allows writing
> only starting from pass 3.
Ah, I see.
it's obiously wrong.
> I couldn't quite understand what you wrote about on-disk
> contiguousness, but that claim still stands: faulting in contiguous
> pages from swap can be much slower than faulting file pages. And my
> patch prefers mapped file pages over anon pages. This is probably
> where I have seen the improvements after resume in my tests.
sorry, I don't understand yet.
Why "prefers mapped file pages over anon pages" makes large improvement?
> So assuming that we can not save the whole working set, it's better to
> preserve as much as possible of those pages that are the most
> expensive ones to refault.
>
> > and, I think you should mesure performence result.
>
> Yes, I'm still thinking about ideas how to quantify it properly. I
> have not yet found a reliable way to check for whether the working set
> is intact besides seeing whether the resumed applications are
> responsive right away or if they first have to swap in their pages
> again.
thanks.
I'm looking for this :)
> > > @@ -2134,17 +2144,17 @@ unsigned long shrink_all_memory(unsigned
> > >
> > > /*
> > > * We try to shrink LRUs in 5 passes:
> > > - * 0 = Reclaim from inactive_list only
> > > - * 1 = Reclaim from active list but don't reclaim mapped
> > > - * 2 = 2nd pass of type 1
> > > - * 3 = Reclaim mapped (normal reclaim)
> > > - * 4 = 2nd pass of type 3
> > > + * 0 = Reclaim unmapped inactive file pages
> > > + * 1 = Reclaim unmapped file pages
> >
> > I think your patch reclaim mapped file at priority 0 and 1 too.
>
> Doesn't the following check in shrink_page_list prevent this:
>
> if (!sc->may_swap && page_mapped(page))
> goto keep_locked;
>
> ?
Grr, you are right.
I agree, currently may_swap doesn't control swap out or not.
so I think we should change it correct name ;)
next prev parent reply other threads:[~2009-02-06 5:59 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-02-06 3:11 [PATCH 0/3] [PATCH 0/3] swsusp: shrink file cache first Johannes Weiner
2009-02-06 3:11 ` [PATCH 1/3] swsusp: clean up shrink_all_zones() Johannes Weiner
2009-02-06 3:20 ` KOSAKI Motohiro
2009-02-06 3:11 ` [PATCH 2/3] swsusp: dont fiddle with swappiness Johannes Weiner
2009-02-06 3:21 ` KOSAKI Motohiro
2009-02-06 3:11 ` [PATCH 3/3][RFC] swsusp: shrink file cache first Johannes Weiner
2009-02-06 3:39 ` KOSAKI Motohiro
2009-02-06 4:49 ` Johannes Weiner
2009-02-06 5:59 ` KOSAKI Motohiro [this message]
2009-02-06 12:24 ` Johannes Weiner
2009-02-06 13:35 ` MinChan Kim
2009-02-06 17:15 ` MinChan Kim
2009-02-06 23:37 ` Johannes Weiner
2009-02-09 19:43 ` [patch] vmscan: rename sc.may_swap to may_unmap Johannes Weiner
2009-02-09 23:02 ` MinChan Kim
2009-02-10 10:00 ` KOSAKI Motohiro
2009-03-27 6:19 ` [PATCH] vmscan: memcg needs may_swap (Re: [patch] vmscan: rename sc.may_swap to may_unmap) Daisuke Nishimura
2009-03-27 6:30 ` KAMEZAWA Hiroyuki
2009-03-29 23:45 ` KOSAKI Motohiro
2009-03-31 0:18 ` Daisuke Nishimura
2009-03-31 1:26 ` Minchan Kim
2009-03-31 1:42 ` KAMEZAWA Hiroyuki
2009-03-31 1:48 ` KOSAKI Motohiro
2009-04-01 4:09 ` Johannes Weiner
2009-04-01 5:08 ` Daisuke Nishimura
2009-04-01 9:04 ` KAMEZAWA Hiroyuki
2009-04-01 9:11 ` KOSAKI Motohiro
2009-04-01 9:49 ` Johannes Weiner
2009-04-01 9:55 ` KOSAKI Motohiro
2009-04-01 16:03 ` Johannes Weiner
2009-03-31 1:52 ` Daisuke Nishimura
2009-02-06 21:00 ` [PATCH 3/3][RFC] swsusp: shrink file cache first Andrew Morton
2009-02-06 23:27 ` Johannes Weiner
2009-02-07 17:23 ` Rafael J. Wysocki
2009-02-08 20:56 ` Johannes Weiner
2009-02-07 4:41 ` Nigel Cunningham
2009-02-07 16:51 ` KOSAKI Motohiro
2009-02-07 21:20 ` Nigel Cunningham
2009-02-27 13:27 ` Pavel Machek
2009-03-01 10:37 ` KOSAKI Motohiro
2009-02-06 8:03 ` MinChan Kim
2009-02-06 10:06 ` MinChan Kim
2009-02-06 11:50 ` Johannes Weiner
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=20090206135302.628E.KOSAKI.MOTOHIRO@jp.fujitsu.com \
--to=kosaki.motohiro@jp.fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=riel@redhat.com \
--cc=rjw@sisk.pl \
/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;
as well as URLs for NNTP newsgroup(s).