From: Jeremy Harris <jgh@redhat.com>
Cc: Linux-MM <linux-mm@kvack.org>, LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 0/2] Disable zone_reclaim_mode by default
Date: Thu, 10 Apr 2014 11:26:35 +0100 [thread overview]
Message-ID: <534671DB.50802@redhat.com> (raw)
In-Reply-To: <alpine.DEB.2.10.1404081752390.16708@nuc>
On 08/04/14 23:58, Christoph Lameter wrote:
> The reason that zone reclaim is on by default is that off node accesses
> are a big performance hit on large scale NUMA systems (like ScaleMP and
> SGI). Zone reclaim was written *because* those system experienced severe
> performance degradation.
>
> On the tightly coupled 4 and 8 node systems there does not seem to
> be a benefit from what I hear.
In principle, is this difference in distance something the kernel
could measure?
--
Cheers,
Jeremy
--
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/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Jeremy Harris <jgh@redhat.com>
To: unlisted-recipients:; (no To-header on input)
Cc: Linux-MM <linux-mm@kvack.org>, LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 0/2] Disable zone_reclaim_mode by default
Date: Thu, 10 Apr 2014 11:26:35 +0100 [thread overview]
Message-ID: <534671DB.50802@redhat.com> (raw)
In-Reply-To: <alpine.DEB.2.10.1404081752390.16708@nuc>
On 08/04/14 23:58, Christoph Lameter wrote:
> The reason that zone reclaim is on by default is that off node accesses
> are a big performance hit on large scale NUMA systems (like ScaleMP and
> SGI). Zone reclaim was written *because* those system experienced severe
> performance degradation.
>
> On the tightly coupled 4 and 8 node systems there does not seem to
> be a benefit from what I hear.
In principle, is this difference in distance something the kernel
could measure?
--
Cheers,
Jeremy
next prev parent reply other threads:[~2014-04-10 10:26 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-04-07 22:34 [PATCH 0/2] Disable zone_reclaim_mode by default Mel Gorman
2014-04-07 22:34 ` Mel Gorman
2014-04-07 22:34 ` [PATCH 1/2] mm: " Mel Gorman
2014-04-07 22:34 ` Mel Gorman
2014-04-07 23:35 ` Johannes Weiner
2014-04-07 23:35 ` Johannes Weiner
2014-04-08 1:17 ` Zhang Yanfei
2014-04-08 1:17 ` Zhang Yanfei
2014-04-08 7:14 ` Andres Freund
2014-04-08 7:14 ` Andres Freund
2014-04-08 14:14 ` Christoph Lameter
2014-04-08 14:14 ` Christoph Lameter
2014-04-08 14:47 ` Mel Gorman
2014-04-08 14:47 ` Mel Gorman
2014-04-07 22:34 ` [PATCH 2/2] mm: page_alloc: Do not cache reclaim distances Mel Gorman
2014-04-07 22:34 ` Mel Gorman
2014-04-07 23:36 ` Johannes Weiner
2014-04-07 23:36 ` Johannes Weiner
2014-04-08 1:17 ` Zhang Yanfei
2014-04-08 1:17 ` Zhang Yanfei
2014-04-08 7:26 ` [PATCH 0/2] Disable zone_reclaim_mode by default Vlastimil Babka
2014-04-08 7:26 ` Vlastimil Babka
2014-04-08 14:17 ` Christoph Lameter
2014-04-08 14:17 ` Christoph Lameter
2014-04-08 14:26 ` Andres Freund
2014-04-08 14:26 ` Andres Freund
[not found] ` <WM!ea1193ee171854a74828ee30c859d97ff2ce66405ffa3a0b8c31a1233c6a0b55530cdf3cbfcd989c0ec18fef1d533f81!@asav-3.01.com>
2014-04-08 14:46 ` Josh Berkus
2014-04-08 14:46 ` Josh Berkus
2014-04-08 19:53 ` Robert Haas
2014-04-08 19:53 ` Robert Haas
[not found] ` <WM!55d2a092da9f6180473043487a4eb612ae8195f78d2ffdd83f673ed5cb2cb9659cf61e0c8d5bae23f5c914057bcd2ee4!@asav-3.01.com>
2014-04-08 19:56 ` Josh Berkus
2014-04-08 19:56 ` Josh Berkus
2014-04-09 13:08 ` Mel Gorman
2014-04-09 13:08 ` Mel Gorman
2014-04-08 22:58 ` Christoph Lameter
2014-04-08 22:58 ` Christoph Lameter
2014-04-08 23:26 ` Mel Gorman
2014-04-08 23:26 ` Mel Gorman
2014-04-10 10:26 ` Jeremy Harris [this message]
2014-04-10 10:26 ` Jeremy Harris
2014-04-18 15:49 ` Michal Hocko
2014-04-18 15:49 ` Michal Hocko
2014-04-18 16:44 ` Christoph Lameter
2014-04-18 16:44 ` Christoph Lameter
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=534671DB.50802@redhat.com \
--to=jgh@redhat.com \
--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 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.