From: Yasunori Goto <y-goto@jp.fujitsu.com>
To: Andi Kleen <ak@suse.de>
Cc: keith <kmannth@us.ibm.com>,
"Tolentino, Matthew E" <matthew.e.tolentino@intel.com>,
Matt Tolentino <metolent@cs.vt.edu>,
akpm@osdl.org, discuss@x86-64.org,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [patch 2/2] add x86-64 support for memory hot-add
Date: Wed, 11 Jan 2006 10:49:11 +0900 [thread overview]
Message-ID: <20060111103557.BCA6.Y-GOTO@jp.fujitsu.com> (raw)
In-Reply-To: <200601101348.17322.ak@suse.de>
> On Tuesday 10 January 2006 13:43, Yasunori Goto wrote:
> > > IIRC, SRAT is just for booting time. So, when hotplug occured,
> > > it is not reliable. DSDT should be used for it in order to SRAT
> > > like following 2 patches.
> > > First is to get pxm from physical address.
> > > I'll post the second patch after this post.
> >
> > Second one is here.
> > This is map/unmap between pxm to nid. This is just for ia64.
> > But I guess for x86-64 is not so difference.
>
> It probably is. The x86-64 NUMA setup is quite different from IA64.
Ah... Ok.
I wish my patch would be good example for x86-64.
But, hmm. I feel it is a bit strange.
Why there is a difference among x86-64 and ia64 about mapping
pxm to nid? (in addition i386.)
PXM is defined by ACPI. ACPI is used on all of them.
Node id is used on Linux generically.
So, ia64 and i386 has pxm_to_nid_map[], and x86-64 has pxm2node[] too.
Why are these arrays and codes are defined on each arch?
Does anyone know it?
Its code might be able to be common on driver/acpi/numa.c...
--
Yasunori Goto
next prev parent reply other threads:[~2006-01-11 1:50 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-01-09 19:55 Tolentino, Matthew E
2006-01-09 20:09 ` keith
2006-01-10 12:34 ` Yasunori Goto
2006-01-10 12:43 ` Yasunori Goto
2006-01-10 12:48 ` Andi Kleen
2006-01-11 1:49 ` Yasunori Goto [this message]
2006-01-09 20:27 ` Andi Kleen
-- strict thread matches above, loose matches on Subject: below --
2006-01-09 19:58 Tolentino, Matthew E
2006-01-09 19:29 Lu, Yinghai
2006-01-09 19:28 Lu, Yinghai
2006-01-09 19:37 ` Andi Kleen
2006-01-09 15:21 Matt Tolentino
2006-01-09 15:36 ` Andi Kleen
2006-01-09 18:51 ` Yinghai Lu
2006-01-09 19:24 ` keith
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=20060111103557.BCA6.Y-GOTO@jp.fujitsu.com \
--to=y-goto@jp.fujitsu.com \
--cc=ak@suse.de \
--cc=akpm@osdl.org \
--cc=discuss@x86-64.org \
--cc=kmannth@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=matthew.e.tolentino@intel.com \
--cc=metolent@cs.vt.edu \
/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
all inboxes | Powered by JetHome®