From: Oliver Hartkopp <socketcan@hartkopp.net>
To: netdev@vger.kernel.org, therbert.google.com@vger.kernel.org
Cc: "linux-can@vger.kernel.org" <linux-can@vger.kernel.org>,
sunil.kovvuri@gmail.com, jonathon.reinhart@gmail.com
Subject: Fighting out-of-order reception with RPS?
Date: Wed, 08 Jul 2015 19:49:00 +0200 [thread overview]
Message-ID: <559D628C.5020100@hartkopp.net> (raw)
I'm picking up the request 'Setting RPS affinities from network driver' from
Sunil Kovvuri http://marc.info/?t=142424023500001&r=1&w=2 as I assume to have
the same issue here.
When receiving CAN frames from a specific CAN network interface (e.g. can0)
the frames are sporadically out-of-order on SMP systems like my Core i7 laptop
with 4 CPUs. This out-of-order reception kills reliable communication e.g. for
CAN transport protocols.
First approach was to set the smp_affinity for the USB adapter on irq 28 with:
echo 1 > /proc/irq/28/smp_affinity
This worked in my case but it looks wrong to pin the USB host adapter to a
single CPU and has to be done by hand depending on where the CAN interfaces
are attached to the system.
Next idea was to use RPS after reading Documentation/networking/scaling.txt
As the only relevant flow identifiction is the number of the incoming CAN
interface I added
skb_set_hash(skb, dev->ifindex, PKT_HASH_TYPE_L2);
when creating CAN skbs with alloc_can_skb() in drivers/net/can/dev.c
After enabling RPS for my four CPUs with
echo f > /sys/class/net/can0/queues/rx-0/rps_cpus
I had no more out-of-order frames in my system :-)
My two questions:
1. Is there any better solution to meet the described requirements?
2. If not: How can enable this RPS solution by default for CAN interfaces?
Best regards,
Oliver
next reply other threads:[~2015-07-08 17:49 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-08 17:49 Oliver Hartkopp [this message]
2015-07-08 21:17 ` Fighting out-of-order reception with RPS? Tom Herbert
2015-07-09 5:55 ` Oliver Hartkopp
2015-07-10 2:48 ` Tom Herbert
2015-07-10 20:36 ` Oliver Hartkopp
2015-07-11 4:35 ` Eric Dumazet
2015-07-12 19:15 ` Oliver Hartkopp
2015-07-13 3:22 ` David Miller
2015-07-13 4:57 ` Eric Dumazet
2015-07-14 17:09 ` Oliver Hartkopp
2015-07-14 18:02 ` Tom Herbert
2015-07-14 19:03 ` David Miller
2015-07-14 19:05 ` Oliver Hartkopp
2015-07-13 19:08 ` Tom Herbert
2015-07-09 6:34 ` Holger Schurig
2015-07-09 8:48 ` Oliver Hartkopp
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=559D628C.5020100@hartkopp.net \
--to=socketcan@hartkopp.net \
--cc=jonathon.reinhart@gmail.com \
--cc=linux-can@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=sunil.kovvuri@gmail.com \
--cc=therbert.google.com@vger.kernel.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).