DPDK patches and discussions
 help / color / mirror / Atom feed
From: Damien Millescamps <damien.millescamps@6wind.com>
To: dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH 0/7] Vyatta patches
Date: Fri, 31 May 2013 11:29:09 +0200	[thread overview]
Message-ID: <51A86D65.2090003@6wind.com> (raw)
In-Reply-To: <20130530171234.301927271@vyatta.com>

On 05/30/2013 07:12 PM, Stephen Hemminger wrote:
> One fix not included is the NUMA cpu assignment. The original Intel code
> in 1.2 incorrectly used /proc/cpuinfo to try and assign CPU's to NUMA socket.
> The problem is that /proc/cpuinfo physical_id corresponds to what the BIOS
> tells the kernel and is intended for messages only. For example, on our
> Dell boxes the first CPU and only CPU is reported as physical_id 1!
> The fix is to use sysfs instead,
Hi Stephen,

Are you using the
/sys/devices/system/node/nodeX/cpuX/topology/physical_package_id special
file ?

If so, then it is only usable starting from Kernel 3.3 according to this
fix:
http://git.kernel.org/cgit/linux/kernel/git/tip/tip.git/commit/?id=64be4c1c2428e148de6081af235e2418e6a66dda

The value returned for kernel prior to 3.3 is really not better than the
one from /proc/cpuinfo, so that's kind of a robbing Peter to pay Paul
example...

There is obviously a problem with the NUMA node ID detection right now
since both /proc/cpuinfo and /sys can return incorrect values, however
the node and cpu numbering is always good in the kernel boot log from
what I know. So there might be a better way to find the real node ID
whatever the kernel version used.

Cheers,
-- 
Damien Millescamps

  parent reply	other threads:[~2013-05-31  9:29 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-05-30 17:12 Stephen Hemminger
2013-05-30 17:12 ` [dpdk-dev] [PATCH 1/7] [PATCH 4/8] igb: workaround errata with wthresh on 82576 Stephen Hemminger
2013-06-05 14:22   ` Vincent JARDIN
2013-06-12 10:06     ` [dpdk-dev] [PATCH 1/7] " Thomas Monjalon
2013-05-30 17:12 ` [dpdk-dev] [PATCH 2/7] rte_timer: optimize for empty case Stephen Hemminger
2013-06-05 14:25   ` Vincent JARDIN
2013-06-12 10:07     ` Thomas Monjalon
2013-05-30 17:12 ` [dpdk-dev] [PATCH 3/7] optimize log/panic Stephen Hemminger
2013-06-05 14:34   ` Vincent JARDIN
2013-06-12 10:09     ` Thomas Monjalon
2013-05-30 17:12 ` [dpdk-dev] [PATCH 4/7] eal: support different modules Stephen Hemminger
2013-06-03  8:58   ` Damien Millescamps
2013-06-03 15:41     ` Stephen Hemminger
2013-06-03 16:36       ` Thomas Monjalon
2013-06-03 17:26         ` Stephen Hemminger
2013-06-04  9:17           ` Damien Millescamps
2013-06-03 16:08     ` Antti Kantee
2013-06-03 16:29       ` Thomas Monjalon
2013-06-03 17:25         ` Stephen Hemminger
2013-06-03 18:40         ` Antti Kantee
2013-05-30 17:12 ` [dpdk-dev] [PATCH 5/7] pci: support multiple PCI regions per device Stephen Hemminger
2013-06-03 16:41   ` Thomas Monjalon
2013-06-05 14:50   ` Damien Millescamps
2013-06-05 15:49     ` Stephen Hemminger
2013-06-05 18:05       ` Damien Millescamps
2013-06-05 21:33         ` Stephen Hemminger
2013-06-18  1:28           ` somnath kotur
2013-07-16  8:53             ` Thomas Monjalon
2013-07-19 16:44               ` Stephen Hemminger
2013-05-30 17:12 ` [dpdk-dev] [PATCH 6/7] igb_uio: pci_block_user_cfg_access is unsafe, remove it Stephen Hemminger
2013-05-30 17:12 ` [dpdk-dev] [PATCH 7/7] eal: add ability to override DPDK syslog parameters Stephen Hemminger
2013-06-05 14:36   ` Vincent JARDIN
2013-06-12 10:18     ` Thomas Monjalon
2013-05-30 22:20 ` [dpdk-dev] [PATCH 0/7] Vyatta patches Thomas Monjalon
2013-05-31  9:29 ` Damien Millescamps [this message]
2013-05-31 15:45   ` Stephen Hemminger
2013-05-31 16:44     ` Damien Millescamps
2013-05-31 17:00       ` Stephen Hemminger
2013-06-03 15:22 ` Thomas Monjalon

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=51A86D65.2090003@6wind.com \
    --to=damien.millescamps@6wind.com \
    --cc=dev@dpdk.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).