All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mel Gorman <mel@csn.ul.ie>
To: Minchan Kim <minchan.kim@gmail.com>
Cc: Simon Kirby <sim@hostway.ca>,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	Shaohua Li <shaohua.li@intel.com>,
	Dave Hansen <dave@linux.vnet.ibm.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm <linux-mm@kvack.org>,
	linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 4/6] mm: kswapd: Reset kswapd_max_order and classzone_idx after reading
Date: Fri, 10 Dec 2010 10:42:54 +0000	[thread overview]
Message-ID: <20101210104254.GL20133@csn.ul.ie> (raw)
In-Reply-To: <AANLkTimKVZjfVtZ_Rz0p0xKbE76Uoa1rDrYmN9EC4wLU@mail.gmail.com>

On Fri, Dec 10, 2010 at 01:03:01AM +0900, Minchan Kim wrote:
> On Fri, Dec 10, 2010 at 12:59 AM, Minchan Kim <minchan.kim@gmail.com> wrote:
> > On Thu, Dec 09, 2010 at 11:18:18AM +0000, Mel Gorman wrote:
> >> When kswapd wakes up, it reads its order and classzone from pgdat and
> >> calls balance_pgdat. While its awake, it potentially reclaimes at a high
> >> order and a low classzone index. This might have been a once-off that
> >> was not required by subsequent callers. However, because the pgdat
> >> values were not reset, they remain artifically high while
> >> balance_pgdat() is running and potentially kswapd enters a second
> >> unnecessary reclaim cycle. Reset the pgdat order and classzone index
> >> after reading.
> >>
> >> Signed-off-by: Mel Gorman <mel@csn.ul.ie>
> > Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
> 
> Nitpick.
> Shouldn't this patch be merged with 1/6?
> 

I don't think so as it's a standalone fix. For example, if this was
merged on its own, the "order" should still be reset after reading.

-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab

WARNING: multiple messages have this Message-ID (diff)
From: Mel Gorman <mel@csn.ul.ie>
To: Minchan Kim <minchan.kim@gmail.com>
Cc: Simon Kirby <sim@hostway.ca>,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	Shaohua Li <shaohua.li@intel.com>,
	Dave Hansen <dave@linux.vnet.ibm.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm <linux-mm@kvack.org>,
	linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 4/6] mm: kswapd: Reset kswapd_max_order and classzone_idx after reading
Date: Fri, 10 Dec 2010 10:42:54 +0000	[thread overview]
Message-ID: <20101210104254.GL20133@csn.ul.ie> (raw)
In-Reply-To: <AANLkTimKVZjfVtZ_Rz0p0xKbE76Uoa1rDrYmN9EC4wLU@mail.gmail.com>

On Fri, Dec 10, 2010 at 01:03:01AM +0900, Minchan Kim wrote:
> On Fri, Dec 10, 2010 at 12:59 AM, Minchan Kim <minchan.kim@gmail.com> wrote:
> > On Thu, Dec 09, 2010 at 11:18:18AM +0000, Mel Gorman wrote:
> >> When kswapd wakes up, it reads its order and classzone from pgdat and
> >> calls balance_pgdat. While its awake, it potentially reclaimes at a high
> >> order and a low classzone index. This might have been a once-off that
> >> was not required by subsequent callers. However, because the pgdat
> >> values were not reset, they remain artifically high while
> >> balance_pgdat() is running and potentially kswapd enters a second
> >> unnecessary reclaim cycle. Reset the pgdat order and classzone index
> >> after reading.
> >>
> >> Signed-off-by: Mel Gorman <mel@csn.ul.ie>
> > Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
> 
> Nitpick.
> Shouldn't this patch be merged with 1/6?
> 

I don't think so as it's a standalone fix. For example, if this was
merged on its own, the "order" should still be reset after reading.

-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab

--
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 policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2010-12-10 10:43 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-12-09 11:18 [PATCH 0/5] Prevent kswapd dumping excessive amounts of memory in response to high-order allocations V3 Mel Gorman
2010-12-09 11:18 ` Mel Gorman
2010-12-09 11:18 ` [PATCH 1/6] mm: kswapd: Stop high-order balancing when any suitable zone is balanced Mel Gorman
2010-12-09 11:18   ` Mel Gorman
2010-12-09 15:21   ` Minchan Kim
2010-12-09 15:21     ` Minchan Kim
2010-12-10  1:06   ` KAMEZAWA Hiroyuki
2010-12-10  1:06     ` KAMEZAWA Hiroyuki
2010-12-13 16:54   ` Eric B Munson
2010-12-09 11:18 ` [PATCH 2/6] mm: kswapd: Keep kswapd awake for high-order allocations until a percentage of the node " Mel Gorman
2010-12-09 11:18   ` Mel Gorman
2010-12-09 15:42   ` Minchan Kim
2010-12-09 15:42     ` Minchan Kim
2010-12-10 10:19     ` Mel Gorman
2010-12-10 10:19       ` Mel Gorman
2010-12-10  1:16   ` KAMEZAWA Hiroyuki
2010-12-10  1:16     ` KAMEZAWA Hiroyuki
2010-12-10 10:25     ` Mel Gorman
2010-12-10 10:25       ` Mel Gorman
2010-12-13 17:00   ` Eric B Munson
2010-12-09 11:18 ` [PATCH 3/6] mm: kswapd: Use the order that kswapd was reclaiming at for sleeping_prematurely() Mel Gorman
2010-12-09 11:18   ` Mel Gorman
2010-12-10  1:16   ` Minchan Kim
2010-12-10  1:16     ` Minchan Kim
2010-12-10 10:36     ` Mel Gorman
2010-12-10 10:36       ` Mel Gorman
2010-12-10  1:18   ` KAMEZAWA Hiroyuki
2010-12-10  1:18     ` KAMEZAWA Hiroyuki
2010-12-09 11:18 ` [PATCH 4/6] mm: kswapd: Reset kswapd_max_order and classzone_idx after reading Mel Gorman
2010-12-09 11:18   ` Mel Gorman
2010-12-09 15:59   ` Minchan Kim
2010-12-09 15:59     ` Minchan Kim
2010-12-09 16:03     ` Minchan Kim
2010-12-09 16:03       ` Minchan Kim
2010-12-10 10:42       ` Mel Gorman [this message]
2010-12-10 10:42         ` Mel Gorman
2010-12-10  1:19   ` KAMEZAWA Hiroyuki
2010-12-10  1:19     ` KAMEZAWA Hiroyuki
2010-12-09 11:18 ` [PATCH 5/6] mm: kswapd: Treat zone->all_unreclaimable in sleeping_prematurely similar to balance_pgdat() Mel Gorman
2010-12-09 11:18   ` Mel Gorman
2010-12-10  1:23   ` KAMEZAWA Hiroyuki
2010-12-10  1:23     ` KAMEZAWA Hiroyuki
2010-12-10 10:55     ` Mel Gorman
2010-12-10 10:55       ` Mel Gorman
2010-12-12 23:58       ` KAMEZAWA Hiroyuki
2010-12-12 23:58         ` KAMEZAWA Hiroyuki
2010-12-09 11:18 ` [PATCH 6/6] mm: kswapd: Use the classzone idx that kswapd was using for sleeping_prematurely() Mel Gorman
2010-12-09 11:18   ` Mel Gorman
2010-12-10  2:38   ` Minchan Kim
2010-12-10  2:38     ` Minchan Kim
2010-12-09 11:19 ` [PATCH 0/5] Prevent kswapd dumping excessive amounts of memory in response to high-order allocations V3 Mel Gorman
2010-12-09 11:19   ` Mel Gorman
  -- strict thread matches above, loose matches on Subject: below --
2010-12-10 15:46 [PATCH 0/6] Prevent kswapd dumping excessive amounts of memory in response to high-order allocations V4 Mel Gorman
2010-12-10 15:46 ` [PATCH 4/6] mm: kswapd: Reset kswapd_max_order and classzone_idx after reading Mel Gorman
2010-12-10 15:46   ` Mel Gorman
2010-12-13 19:39   ` Eric B Munson

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=20101210104254.GL20133@csn.ul.ie \
    --to=mel@csn.ul.ie \
    --cc=akpm@linux-foundation.org \
    --cc=dave@linux.vnet.ibm.com \
    --cc=hannes@cmpxchg.org \
    --cc=kosaki.motohiro@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=minchan.kim@gmail.com \
    --cc=shaohua.li@intel.com \
    --cc=sim@hostway.ca \
    /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.