From: Jack Steiner <steiner@sgi.com>
To: "Randy.Dunlap" <rddunlap@osdl.org>
Cc: linux-kernel@vger.kernel.org
Subject: Re: [PATCH] - Externel SLIT table information thru sysfs
Date: Thu, 25 Nov 2004 08:00:15 -0600 [thread overview]
Message-ID: <20041125140015.GA2750@sgi.com> (raw)
In-Reply-To: <41A53D93.5070005@osdl.org>
On Wed, Nov 24, 2004 at 06:04:03PM -0800, Randy.Dunlap wrote:
> Jack Steiner wrote:
> >The ACPI SLIT table provides useful information on internode distances.
> >Here is a patch to externalize the SLIT information.
> >
> >For example:
> >
> > # cd /sys/devices/system
> > # find .
> > ./node
> > ./node/node5
> > ./node/node5/distance
> > ./node/node5/numastat
> > ./node/node5/meminfo
> > ./node/node5/cpumap
> >
> > # cat ./node/node0/distance
> > 10 20 64 42 42 22
> >
> > # cat node/*/distance
> > 10 20 64 42 42 22
> > 20 10 42 22 64 84
> > 64 42 10 20 22 42
> > 42 22 20 10 42 62
> > 42 64 22 42 10 20
> > 22 84 42 62 20 10
>
> Apparently I'm easily confused, but node_distance() {near end}
> seems to evaluate to either 10 or 20 (only), so what are
> all of these other numbers here?
On systems that provide the ACPI SLIT table, the distances come from
the SLIT table. (See the ACPI spec for the full definition).
The example above is from the ACPI SLIT table of a 6-node SGI Altix
system and the table is provided by the BIOS.
If the BIOS does not provide a SLIT table, the default distance is 10 for
local & 20 for remote. The value of 10 conforms to the spec for
local distance, 20 is arbitrary but indicates further than local.
>
> And how many nodes are in this example?
> Maybe 6, numbered 0 thru 5? Plz correct this guess....
Good guess.
>
> >Index: linux/drivers/base/node.c
> >===================================================================
> >--- linux.orig/drivers/base/node.c 2004-11-05 08:34:42.461312000 -0600
> >+++ linux/drivers/base/node.c 2004-11-05 15:56:23.345662000 -0600
> >@@ -111,6 +111,24 @@ static ssize_t node_read_numastat(struct
> > }
> > static SYSDEV_ATTR(numastat, S_IRUGO, node_read_numastat, NULL);
> >
> >+static ssize_t node_read_distance(struct sys_device * dev, char * buf)
> >+{
> >+ int nid = dev->id;
> >+ int len = 0;
> >+ int i;
> >+
> >+ /* buf currently PAGE_SIZE, need ~4 chars per node */
> >+ BUILD_BUG_ON(NR_NODES*4 > PAGE_SIZE/2);
> >+
> >+ for (i = 0; i < numnodes; i++)
> >+ len += sprintf(buf + len, "%s%d", i ? " " : "",
> >node_distance(nid, i));
> >+
> >+ len += sprintf(buf + len, "\n");
> >+ return len;
> >+}
> >+static SYSDEV_ATTR(distance, S_IRUGO, node_read_distance, NULL);
> >+
> >+
> >Index: linux/include/linux/topology.h
> >===================================================================
> >--- linux.orig/include/linux/topology.h 2004-11-05
> >08:34:57.492932000 -0600
> >+++ linux/include/linux/topology.h 2004-11-23 10:03:26.700821978 -0600
> >@@ -55,7 +55,10 @@ static inline int __next_node_with_cpus(
> > for (node = 0; node < numnodes; node = __next_node_with_cpus(node))
> >
> > #ifndef node_distance
> >-#define node_distance(from,to) ((from) != (to))
> >+/* Conform to ACPI 2.0 SLIT distance definitions */
> >+#define LOCAL_DISTANCE 10
> >+#define REMOTE_DISTANCE 20
> >+#define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE :
> >REMOTE_DISTANCE)
> Please add a space after "from,".
>
> > #endif
>
> --
> ~Randy
--
Thanks
Jack Steiner (steiner@sgi.com) 651-683-5302
Principal Engineer SGI - Silicon Graphics, Inc.
next prev parent reply other threads:[~2004-11-27 1:24 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-11-24 16:57 [PATCH] - Externel SLIT table information thru sysfs Jack Steiner
2004-11-25 2:04 ` Randy.Dunlap
2004-11-25 3:39 ` Greg KH
2004-11-26 3:54 ` Jack Steiner
2004-11-25 14:00 ` Jack Steiner [this message]
[not found] <34a45-4B7-9@gated-at.bofh.it>
[not found] ` <34hyB-2nd-21@gated-at.bofh.it>
[not found] ` <34iNY-3nm-27@gated-at.bofh.it>
2004-11-25 11:12 ` Andi Kleen
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=20041125140015.GA2750@sgi.com \
--to=steiner@sgi.com \
--cc=linux-kernel@vger.kernel.org \
--cc=rddunlap@osdl.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