Linux CAN drivers development
 help / color / mirror / Atom feed
From: Alexander Stein <alexander.stein@systec-electronic.com>
To: David Jander <david@protonic.nl>
Cc: "Marc Kleine-Budde" <mkl@pengutronix.de>,
	linux-can@vger.kernel.org,
	"Martin Däumler" <martin.daeumler@systec-electronic.com>,
	"Daniel Krüger" <daniel.krueger@systec-electronic.com>
Subject: Re: [PATCH v2 00/12] can: rx-offload: add implmentation and switch flexcan driver to use it
Date: Wed, 05 Oct 2016 14:37:20 +0200	[thread overview]
Message-ID: <1506116.7yduGgf9eG@ws-stein> (raw)
In-Reply-To: <20161004143315.23423e56@erd980>

Hi David,

On Tuesday 04 October 2016 14:33:15, David Jander wrote:
> > In summary the non-RT case seems fine now, but I wonder what causes the
> > delays on RT to the CAN-IRQ-Thread which seem to be about 500us (bus time
> > of 6 4Byte CAN frames).
> 
> Thanks for testing!
> Well, in -RT I guess anything with a higher priority than the CAN-IRQ can
> cause a delay... but since going from -rt13 to -rt14 improved the situation,
> this sounds like bugs in the -rt code. Are you running any code in
> SCHED_FIFO that you don't run in the non-RT case?

AFAIK no userspace process is put into SCHED_FIFO and only the priority of 
CAN-IRQ-Thread is increased to 91. Userspace runs with unchanged priority. So 
yes I guess there is still problem in -rt code.

> It's nevertheless very nice to see that for non-RT, you got from losing
> messages to not losing any message with this patchset, even on a lowly
> i.MX35 at 1Mbit/s! This proves that the patchset is certainly worth it.

I would expect the same from running with RT enabled, especially as the CAN-
IRQ-Thread has SCHED_FIFO wuth priority 91. There shouldn't be much code which 
can delay that thread.

Best regards,
Alexander


  reply	other threads:[~2016-10-05 12:37 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-04 18:32 [PATCH v2 00/12] can: rx-offload: add implmentation and switch flexcan driver to use it Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 01/12] can: rx-offload: Add support for HW fifo based irq offloading Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 02/12] can: rx-offload: Add support for timestamp " Marc Kleine-Budde
2016-07-04 18:49   ` Andri Yngvason
2016-07-04 20:59     ` Marc Kleine-Budde
2016-07-04 22:30       ` Marc Kleine-Budde
2016-07-05 11:58         ` Andri Yngvason
2016-07-05 12:40           ` Marc Kleine-Budde
2016-07-05  5:46   ` Alexander Stein
2016-07-05  6:19     ` Marc Kleine-Budde
2016-07-05  6:31       ` David Jander
2016-07-05  7:21         ` Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 03/12] can: flexcan: remove write-only member pdata of struct flexcan_priv Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 04/12] can: flexcan: make declaration of devtype_data const Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 05/12] can: flexcan: calculate default value for imask1 during runtime Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 06/12] can: flexcan: make TX mailbox selectable " Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 07/12] can: flexcan: make use of rx-offload's irq_offload_fifo Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 08/12] can: flexcan: add missing register definitions Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 09/12] can: flexcan: activate individual RX masking and initialize reg_rximr Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 10/12] can: flexcan: add quirk FLEXCAN_QUIRK_ENABLE_EACEN_RRS Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 11/12] can: flexcan: add support for timestamp based rx-offload Marc Kleine-Budde
2016-07-04 18:32 ` [PATCH v2 12/12] can: flexcan: switch imx6 and vf610 to timestamp based offloading Marc Kleine-Budde
2016-07-13  7:28 ` [PATCH v2 00/12] can: rx-offload: add implmentation and switch flexcan driver to use it Mirza Krak
2016-07-13  7:46   ` Marc Kleine-Budde
2016-09-07  6:33 ` Holger Schurig
2016-10-04  6:32   ` Holger Schurig
2016-10-04 11:57 ` Alexander Stein
2016-10-04 12:33   ` David Jander
2016-10-05 12:37     ` Alexander Stein [this message]
2016-11-30 14:22 ` Alexander Stein

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=1506116.7yduGgf9eG@ws-stein \
    --to=alexander.stein@systec-electronic.com \
    --cc=daniel.krueger@systec-electronic.com \
    --cc=david@protonic.nl \
    --cc=linux-can@vger.kernel.org \
    --cc=martin.daeumler@systec-electronic.com \
    --cc=mkl@pengutronix.de \
    /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