All of lore.kernel.org
 help / color / mirror / Atom feed
From: Simon Thelen <urday@student.kit.edu>
To: <linux-rt-users@vger.kernel.org>
Subject: Low USB polling frequency with RT-PREEMPT
Date: Tue, 5 Sep 2017 17:05:39 +0200	[thread overview]
Message-ID: <20170905150539.GF2607@anonymous> (raw)

Hello,

We have some Dynamixel robitic actuators hooked up via USB to an Ubuntu
14.04 system running the 4.4.79-rt92 kernel. When using a kernel built
without the realtime patches (CONFIG_PREEMPT not set) we can query the
bus at 1000Hz (2 devices at 500Hz each) whereas with the realtime kernel
(CONFIG_PREEMPT=y, CONFIG_PREEMPT_RT_FULL=y) we only get 62.5Hz per
device. The USB device requests Ivl=0ms in both cases and the issue
isn't related to load etc. The polling rate is always 62.5Hz (It takes
~15ms for every read()).


Is this a known limitation of USB with the CONFIG_PREEMPT_RT patches and
is there any method to improve the polling rate?

-- 
Simon Thelen

             reply	other threads:[~2017-09-05 15:24 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-09-05 15:05 Simon Thelen [this message]
2017-09-05 17:53 ` Low USB polling frequency with RT-PREEMPT Niels Kolthoff

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=20170905150539.GF2607@anonymous \
    --to=urday@student.kit.edu \
    --cc=linux-rt-users@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 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.