From: William Lee Irwin III <wli@holomorphy.com>
To: Daniel Phillips <phillips@arcor.de>
Cc: Andrew Morton <akpm@digeo.com>, Dave Hansen <haveblue@us.ibm.com>,
"Martin J. Bligh" <Martin.Bligh@us.ibm.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH] per-zone kswapd process
Date: Mon, 16 Sep 2002 00:46:02 -0700 [thread overview]
Message-ID: <20020916074602.GK3530@holomorphy.com> (raw)
In-Reply-To: <E17qogR-0000HR-00@starship>
On Thu, Sep 12, 2002 at 09:06:20PM -0700, Andrew Morton wrote:
>>> I still don't see why it's per zone and not per node. It seems strange
>>> that a wee little laptop would be running two kswapds?
>>> kswapd can get a ton of work done in the development VM and one per
>>> node would, I expect, suffice?
On Friday 13 September 2002 06:59, William Lee Irwin III wrote:
>> Machines without observable NUMA effects can benefit from it if it's
>> per-zone.
On Mon, Sep 16, 2002 at 07:44:30AM +0200, Daniel Phillips wrote:
> How?
The notion was that some level of parallelism would be bestowed on the
single-node case by using separate worker threads on a per-zone basis,
as they won't have more than one node to spawn worker threads for at all.
This notion apparently got shot down somewhere, and I don't care to rise
to its defense. I've lost enough debates this release to know better than
to try.
Bill
WARNING: multiple messages have this Message-ID (diff)
From: William Lee Irwin III <wli@holomorphy.com>
To: Daniel Phillips <phillips@arcor.de>
Cc: Andrew Morton <akpm@digeo.com>, Dave Hansen <haveblue@us.ibm.com>,
"Martin J. Bligh" <Martin.Bligh@us.ibm.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH] per-zone kswapd process
Date: Mon, 16 Sep 2002 00:46:02 -0700 [thread overview]
Message-ID: <20020916074602.GK3530@holomorphy.com> (raw)
In-Reply-To: <E17qogR-0000HR-00@starship>
On Thu, Sep 12, 2002 at 09:06:20PM -0700, Andrew Morton wrote:
>>> I still don't see why it's per zone and not per node. It seems strange
>>> that a wee little laptop would be running two kswapds?
>>> kswapd can get a ton of work done in the development VM and one per
>>> node would, I expect, suffice?
On Friday 13 September 2002 06:59, William Lee Irwin III wrote:
>> Machines without observable NUMA effects can benefit from it if it's
>> per-zone.
On Mon, Sep 16, 2002 at 07:44:30AM +0200, Daniel Phillips wrote:
> How?
The notion was that some level of parallelism would be bestowed on the
single-node case by using separate worker threads on a per-zone basis,
as they won't have more than one node to spawn worker threads for at all.
This notion apparently got shot down somewhere, and I don't care to rise
to its defense. I've lost enough debates this release to know better than
to try.
Bill
--
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/
next prev parent reply other threads:[~2002-09-16 7:46 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-09-13 3:33 [PATCH] per-zone kswapd process Dave Hansen
2002-09-13 4:06 ` Andrew Morton
2002-09-13 4:06 ` Andrew Morton
2002-09-13 4:59 ` William Lee Irwin III
2002-09-13 4:59 ` William Lee Irwin III
2002-09-13 5:10 ` Martin J. Bligh
2002-09-13 5:10 ` Martin J. Bligh
[not found] ` <3D8232DE.9090000@us.ibm.com>
[not found] ` <3D823702.8E29AB4F@digeo.com>
[not found] ` <3D8251D6.3060704@us.ibm.com>
[not found] ` <3D82566B.EB2939D5@digeo.com>
2002-09-13 22:52 ` [PATCH] per-zone^Wnode " Dave Hansen
2002-09-13 23:24 ` Matthew Dobson
2002-09-13 23:29 ` Matthew Dobson
2002-09-13 23:46 ` William Lee Irwin III
2002-09-14 0:02 ` Andrew Morton
2002-09-14 0:12 ` William Lee Irwin III
2002-09-14 1:19 ` Andrew Morton
2002-09-13 5:46 ` [PATCH] per-zone " Andrew Morton
2002-09-13 5:46 ` Andrew Morton
2002-09-13 5:38 ` Martin J. Bligh
2002-09-13 5:38 ` Martin J. Bligh
2002-09-13 6:03 ` Andrew Morton
2002-09-13 6:03 ` Andrew Morton
2002-09-13 13:05 ` Alan Cox
2002-09-13 13:05 ` Alan Cox
2002-09-13 21:30 ` William Lee Irwin III
2002-09-13 21:30 ` William Lee Irwin III
2002-09-18 16:07 ` [PATCH] recognize MAP_LOCKED in mmap() call Hubertus Franke
2002-09-18 16:29 ` Andrew Morton
2002-09-18 16:29 ` Andrew Morton
2002-09-16 5:44 ` [PATCH] per-zone kswapd process Daniel Phillips
2002-09-16 5:44 ` Daniel Phillips
2002-09-16 7:46 ` William Lee Irwin III [this message]
2002-09-16 7:46 ` William Lee Irwin III
2002-09-16 15:12 ` Rik van Riel
2002-09-16 15:12 ` Rik van Riel
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=20020916074602.GK3530@holomorphy.com \
--to=wli@holomorphy.com \
--cc=Martin.Bligh@us.ibm.com \
--cc=akpm@digeo.com \
--cc=haveblue@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=phillips@arcor.de \
/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.