From: Simon Kirby <sim@hostway.ca>
To: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>, Mel Gorman <mel@csn.ul.ie>,
Shaohua Li <shaohua.li@intel.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-mm <linux-mm@kvack.org>,
"Chen, Tim C" <tim.c.chen@intel.com>
Subject: Re: too big min_free_kbytes
Date: Fri, 11 Feb 2011 17:28:50 -0800 [thread overview]
Message-ID: <20110212012850.GA4179@hostway.ca> (raw)
In-Reply-To: <20110203191157.GN5843@random.random>
On Thu, Feb 03, 2011 at 08:11:57PM +0100, Andrea Arcangeli wrote:
> On Thu, Feb 03, 2011 at 09:36:47AM -0500, Rik van Riel wrote:
> > On 02/02/2011 09:58 PM, Andrea Arcangeli wrote:
> >
> > >> Subject: vmscan: kswapd must not free more than high_wmark pages
> >
> > NAK
> >
> > I believe we need a little bit of slack above high_wmark_pages,
> > to be able to even out memory pressure between zones.
> >
> > Maybe free up to high_wmark_pages + min_wmark_pages ?
>
> If this can only go in with high+min that's still better than *8, but
> in prev email on this thread I explained why I think it's not
> beneficial for lru balancing and this level can't affect kswapd wakeup
> times either, so I personally prefer just "high". I don't think out of
> memory has anything to do with this the "min" level is all about the
> PF_MEMALLOC and OOM levels. The zone balancing as well has nothing to
> do with this and the only "hard" thing that guarantees balancing is
> the lowmem reserve ratio (high ptes allocated in lowmem zones aren't
> relocatable etc..).
I was proposing before that the allocator fast path should use a weighted
(by zone size) round robin approach to the available zones, rather than
allocating from top down, so that reclaim would be fair rather than small
zones reclaiming stuff earlier than larger zones.
Riel pointed out that this 8*high_wmark_pages thing helped free a
proportional amount of stuff from the zone once the high_wmark was
breached, eventually causing allocation rates for each zone to end up
being close to the actual size of the zone. This happens because the
watermark values are set based on the size of the zone.
I still think this approach is a bit odd, since when kswapd first wakes
up, systems with multiple zones will reclaim things that aren't as old as
the stuff in the highest zone, until the system runs for a while and this
watermark thing balances the allocation rates. OTOH, changing the
allocator increases the possibility of some high-order DMA zone
allocation failing during boot that otherwise wouldn't.
Simon-
--
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>
next prev parent reply other threads:[~2011-02-12 1:28 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-01-24 3:56 too big min_free_kbytes Shaohua Li
2011-01-24 15:00 ` Andrea Arcangeli
2011-01-25 14:35 ` Mel Gorman
2011-01-26 14:17 ` Mel Gorman
2011-01-26 15:23 ` Mel Gorman
2011-01-26 15:42 ` Andrea Arcangeli
2011-01-26 16:36 ` Mel Gorman
2011-01-26 17:42 ` Mel Gorman
2011-01-27 13:40 ` Mel Gorman
2011-01-27 15:27 ` Andrea Arcangeli
2011-01-27 16:03 ` Mel Gorman
2011-01-27 18:52 ` Andrea Arcangeli
2011-01-27 20:33 ` Rik van Riel
2011-01-27 21:31 ` Mel Gorman
2011-01-27 23:18 ` Rik van Riel
2011-01-28 10:35 ` Mel Gorman
2011-01-28 16:28 ` Andrea Arcangeli
2011-01-28 16:46 ` Mel Gorman
2011-01-28 17:16 ` Rik van Riel
2011-01-28 17:46 ` Andrea Arcangeli
2011-01-28 18:03 ` Rik van Riel
2011-01-28 18:24 ` Andrea Arcangeli
2011-01-28 19:34 ` Rik van Riel
2011-01-28 19:45 ` Andrea Arcangeli
2011-01-28 20:55 ` Rik van Riel
2011-01-29 19:45 ` Andrea Arcangeli
2011-01-28 17:34 ` Andrea Arcangeli
2011-01-28 17:10 ` Rik van Riel
2011-02-03 2:58 ` Andrea Arcangeli
2011-02-03 13:15 ` Mel Gorman
2011-02-03 18:59 ` Andrea Arcangeli
2011-02-03 14:36 ` Rik van Riel
2011-02-03 19:11 ` Andrea Arcangeli
2011-02-12 1:28 ` Simon Kirby [this message]
2011-02-14 2:25 ` Shaohua Li
2011-02-22 14:25 ` Mel Gorman
2011-02-22 14:42 ` Andrea Arcangeli
2011-02-22 14:50 ` Mel Gorman
2011-02-22 14:54 ` Andrea Arcangeli
2011-02-22 16:04 ` Mel Gorman
2011-02-22 16:40 ` Rik van Riel
2011-02-23 5:29 ` Shaohua Li
2011-02-23 14:45 ` Andrea Arcangeli
2011-02-24 8:08 ` Shaohua Li
2011-02-24 9:52 ` Mel Gorman
2011-02-24 9:57 ` Mel Gorman
2011-02-24 14:27 ` Andrea Arcangeli
2011-02-24 14:04 ` Andrea Arcangeli
2011-02-25 0:51 ` Shaohua Li
2011-02-25 12:13 ` Mel Gorman
2011-02-12 9:48 ` alex shi
2011-02-22 14:24 ` Mel Gorman
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=20110212012850.GA4179@hostway.ca \
--to=sim@hostway.ca \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--cc=riel@redhat.com \
--cc=shaohua.li@intel.com \
--cc=tim.c.chen@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;
as well as URLs for NNTP newsgroup(s).