linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: joerg.krause@embedded.rocks (Jörg Krause)
To: linux-arm-kernel@lists.infradead.org
Subject: Low network throughput on i.MX28
Date: Fri, 04 Nov 2016 23:42:39 +0100	[thread overview]
Message-ID: <1478299359.26659.5.camel@embedded.rocks> (raw)
In-Reply-To: <1783642995.185945.5e54a2af-ba2c-4901-93f6-1967dd432939.open-xchange@email.1und1.de>

Hi Stefan,

sorry, I forget the link in the previous mail.

On Fri, 2016-11-04 at 20:30 +0100, Stefan Wahren wrote:
> Hi J?rg,
> 
> > J?rg Krause <joerg.krause@embedded.rocks> hat am 4. November 2016
> > um 19:44
> > geschrieben:
> > 
> > 
> > Hi Shawn,
> > 
> > On Wed, 2016-11-02 at 09:24 +0100, Stefan Wahren wrote:
> > > Am 02.11.2016 um 09:14 schrieb J?rg Krause:
> > > > On Sat, 2016-10-29 at 11:08 +0200, Stefan Wahren wrote:
> > > > > > J?rg Krause <joerg.krause@embedded.rocks> hat am 29.
> > > > > > Oktober
> > > > > > 2016
> > > > > > um 01:07
> > > > > > geschrieben:
> > > > > > 
> > > > > > 
> > > > > > You mentioned [1] an optimization in the Freescale vendor
> > > > > > Linux
> > > > > > kernel
> > > > > > [2]. I would really like to see this optimization in the
> > > > > > mainline
> > > > > > kernel.
> > > > > > 
> > > > > > Did you ever tried to port this code from Freescale to
> > > > > > mainline?
> > > > > 
> > > > > Yes, i tried once but i was frustrated soon because of the
> > > > > lot of
> > > > > required
> > > > > changes and resulting issues.
> > > > 
> > > > I got the PIO mode working for the mxs-mmc driver. For this I
> > > > ported
> > > > the PIO code from the vendor kernel and removed the usage of
> > > > the
> > > > DMA
> > > > engine entirely.
> > > 
> > > Good job
> > > 
> > > > 
> > > > Testing network bandwidth with iperf, I get about ~10Mbit/sec
> > > > with
> > > > PIO
> > > > mode compared to ~6.5Mbit/sec with DMA mode for UDP and about
> > > > ~6.5Mbit/sec compared to ~4.5Mbit/sec with DMA mode for TCP.
> > > 
> > > And how about MMC / sd card performance?
> > 
> > I noticed poor performance with the i.MX28 MMC and/or DMA driver
> > using
> > the mainline kernel compared to the vendor Freescale kernel 2.6.35.
> > I've seen that hou have added the drivers to mainline some years
> > ago.
> > 
> > My custom i.MX28 board has a wifi chip attached to the SSP2
> > interface.
> > Comparing the bandwith with iperf I get >20Mbits/sec on the vendor
> > kernel and <5Mbits/sec on the mainline kernel.
> 
> there is one thing about the clock handling. I noticed that the
> Vendor Kernel
> round up the clock frequency and the Mainline Kernel round down the
> clock
> frequency [1]. So don't trust the clock ratings from DT / board code.
> Better
> verify the register settings or check it with an osci.
> 
> [1] - http://www.spinics.net/lists/linux-mmc/msg09132.html

I checked the clock rate setting by reading the register 0x80014070
(HW_SSP2_TIMING). CLOCK_DIVIDE is 0x2 and CLOCK_RATE is 0x0. As SSP CLK
is 96MHz this makes a clock rate of 48MHz.

There was a discussion on the mailing list [1] about that tasklets
might be slow.

[1] http://lists.infradead.org/pipermail/linux-arm-kernel/2011-February
/043395.html

J?rg

  parent reply	other threads:[~2016-11-04 22:42 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-10-12 23:09 Low network throughput on i.MX28 Jörg Krause
2016-10-13  6:48 ` Lothar Waßmann
2016-10-13 19:43   ` Jörg Krause
2016-10-13 20:42     ` Uwe Kleine-König
2016-10-14  6:13     ` Lothar Waßmann
2016-10-15  8:46       ` Jörg Krause
2016-10-15  8:59         ` Stefan Wahren
2016-10-15  9:41           ` Jörg Krause
2016-10-15 16:16             ` Stefan Wahren
2016-10-28 23:07               ` Jörg Krause
2016-10-29  9:08                 ` Stefan Wahren
2016-10-29 13:08                   ` Jörg Krause
2016-11-02  8:14                   ` Jörg Krause
2016-11-02  8:24                     ` Stefan Wahren
2016-11-02  8:30                       ` Jörg Krause
2016-11-04 18:44                       ` Jörg Krause
2016-11-04 19:30                         ` Stefan Wahren
2016-11-04 20:56                           ` Jörg Krause
2016-11-04 22:42                           ` Jörg Krause [this message]
2016-11-05 11:33                             ` Stefan Wahren
2016-11-05 12:06                               ` Jörg Krause
2016-11-05 12:39                                 ` Koul, Vinod
2016-11-05 12:47                                   ` Jörg Krause
2016-11-05 12:48                                   ` Fabio Estevam
2016-11-05 13:14                                   ` Jörg Krause
2016-11-05 15:45                                     ` Koul, Vinod
2016-11-05 22:37                                       ` Jörg Krause
2016-11-18 23:49                                       ` Jörg Krause
2016-11-19 11:36                                         ` Stefan Wahren
2016-11-20  9:14                                           ` Jörg Krause
2016-10-15 11:18           ` Jörg Krause

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=1478299359.26659.5.camel@embedded.rocks \
    --to=joerg.krause@embedded.rocks \
    --cc=linux-arm-kernel@lists.infradead.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).