From: Mel Gorman <mgorman@suse.de>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Linux Kernel <linux-kernel@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>,
Linux-FSDevel <linux-fsdevel@vger.kernel.org>
Subject: Re: [PATCH 5/6] mm: page_alloc: Abort fair zone allocation policy when remotes nodes are encountered
Date: Thu, 10 Jul 2014 13:44:07 +0100 [thread overview]
Message-ID: <20140710124407.GH10819@suse.de> (raw)
In-Reply-To: <20140710121419.GM29639@cmpxchg.org>
On Thu, Jul 10, 2014 at 08:14:19AM -0400, Johannes Weiner wrote:
> On Wed, Jul 09, 2014 at 09:13:07AM +0100, Mel Gorman wrote:
> > The purpose of numa_zonelist_order=zone is to preserve lower zones
> > for use with 32-bit devices. If locality is preferred then the
> > numa_zonelist_order=node policy should be used. Unfortunately, the fair
> > zone allocation policy overrides this by skipping zones on remote nodes
> > until the lower one is found. While this makes sense from a page aging
> > and performance perspective, it breaks the expected zonelist policy. This
> > patch restores the expected behaviour for zone-list ordering.
> >
> > Signed-off-by: Mel Gorman <mgorman@suse.de>
>
> 32-bit NUMA? :-)
I'm tempted to just say "it can go on fire" but realistically speaking
they should be configured to use node ordering. I was very tempted to
always force node ordering but I didn't have good data on how often lowmem
allocations are required on NUMA machines.
> Anyway, this change also cuts down the fair pass
> overhead on bigger NUMA machines, so I'm all for it.
>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Thanks for the reviews!
--
Mel Gorman
SUSE Labs
next prev parent reply other threads:[~2014-07-10 12:44 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-09 8:13 [PATCH 0/5] Reduce sequential read overhead Mel Gorman
2014-07-09 8:13 ` [PATCH 1/6] mm: pagemap: Avoid unnecessary overhead when tracepoints are deactivated Mel Gorman
2014-07-10 12:01 ` Johannes Weiner
2014-07-09 8:13 ` [PATCH 2/6] mm: Rearrange zone fields into read-only, page alloc, statistics and page reclaim lines Mel Gorman
2014-07-10 12:06 ` Johannes Weiner
2014-07-09 8:13 ` [PATCH 3/6] mm: Move zone->pages_scanned into a vmstat counter Mel Gorman
2014-07-10 12:08 ` Johannes Weiner
2014-07-09 8:13 ` [PATCH 4/6] mm: vmscan: Only update per-cpu thresholds for online CPU Mel Gorman
2014-07-10 12:09 ` Johannes Weiner
2014-07-09 8:13 ` [PATCH 5/6] mm: page_alloc: Abort fair zone allocation policy when remotes nodes are encountered Mel Gorman
2014-07-10 12:14 ` Johannes Weiner
2014-07-10 12:44 ` Mel Gorman [this message]
2014-07-09 8:13 ` [PATCH 6/6] mm: page_alloc: Reduce cost of the fair zone allocation policy Mel Gorman
2014-07-10 12:18 ` Johannes Weiner
2014-08-08 15:27 ` Vlastimil Babka
2014-08-11 12:12 ` Mel Gorman
2014-08-11 12:34 ` Vlastimil Babka
2014-09-02 14:01 ` Johannes Weiner
2014-09-05 10:14 ` [PATCH] mm: page_alloc: Fix setting of ZONE_FAIR_DEPLETED on UP Mel Gorman
2014-09-07 6:32 ` Leon Romanovsky
2014-09-08 11:57 ` [PATCH] mm: page_alloc: Fix setting of ZONE_FAIR_DEPLETED on UP v2 Mel Gorman
2014-09-09 19:53 ` Andrew Morton
2014-09-10 9:16 ` Mel Gorman
2014-09-10 20:32 ` 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=20140710124407.GH10819@suse.de \
--to=mgorman@suse.de \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/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).