[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210510074555.ufojb42u5cyrmomb@pengutronix.de>
Date: Mon, 10 May 2021 09:45:55 +0200
From: Marc Kleine-Budde <mkl@...gutronix.de>
To: Patrick Menschel <menschel.p@...teo.de>
Cc: Drew Fustini <drew@...gleboard.org>, netdev@...r.kernel.org,
linux-can@...r.kernel.org, Will C <will@...china.cc>
Subject: Re: [net-next 6/6] can: mcp251xfd: mcp251xfd_regmap_crc_read(): work
around broken CRC on TBC register
On 09.05.2021 07:46:20, Patrick Menschel wrote:
> > Do I have to change my test?
>
> I changed my test to 1 hour and removed the sleep statement.
> Still no measurable difference for performance and no CRC Errors with
> both kernels.
See other mail about my thoughts about performance and CRC.
> Apparently the test is hard on the CPU, I have two pytest processes
> listed in htop one with 80%CPU and one with 60% CPU, approx 30% ram
> usage of 512MB. I have no clue how it reaches the CPU values, there
> should be only one CPU on the pi0w.
Interesting :)
> ### 5.10.17+ on pi0w ###
>
> 2021-05-09 08:02:56 [ INFO] 725649 frames in 1:00:00
> (test_socketcan.py:890)
>
> ### 5.10.31-performance-backports+ on pi0w ###
>
> 2021-05-09 09:13:32 [ INFO] 715936 frames in 1:00:00
> (test_socketcan.py:890)
>
> I'll switch boards to a pi3b and test again with these settings.
Marc
--
Pengutronix e.K. | Marc Kleine-Budde |
Embedded Linux | https://www.pengutronix.de |
Vertretung West/Dortmund | Phone: +49-231-2826-924 |
Amtsgericht Hildesheim, HRA 2686 | Fax: +49-5121-206917-5555 |
Download attachment "signature.asc" of type "application/pgp-signature" (489 bytes)
Powered by blists - more mailing lists