All of lore.kernel.org
 help / color / mirror / Atom feed
From: CAMUS Benoit <benoit.camus@domain.hid>
To: xenomai@xenomai.org
Subject: [Xenomai-help] Latencies while ethernet access
Date: Fri, 04 May 2007 10:40:43 +0200	[thread overview]
Message-ID: <1178268043.5391.47.camel@domain.hid> (raw)

Hi,

I'm using Xenomai 2.3.1 with a 2.6.19.2 kernel (from ELDK) on a custom
board based on Xscale PXA processor and with smc91c111 ethernet chip. 
I did modifications on Linux kernel to port it on board and then just
applied Adeos's patch following Xenomai's proceedings.
Http and telnet servers are running on and i notice that latencies get
really worse while i access any of them (see traces below).

I understood that Adeos might avoid that kind of behavior due to its
architecture. So i infer that the ethernet driver might access the
hardware by-passing Adeos ?
In this way and before modificate the driver, i decided to try RT driver
thanks to Rtnet project and get an oops error at device probing due to
memory mapping wich i still don't resolve.
I don't have experience with Xenomai and would apreciate any advice on
that phenomenum.

I'm a bit surprised too about gap between best and worst latencies so
i'm asking question to myself about my porting, does this gap seam
strange for you  too?

Thanks in advance and sorry for my english

Ben



/ # latency -p 10000
== Sampling period: 10000 us
== Test mode: periodic user-mode task
== All results in microseconds
warming up...
RTT|  00:00:01  (periodic user-mode task, 10000 us period, priority 99)
RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat
worst
RTD|      24.685|      25.227|      55.609|       0|      24.685|
55.609
RTD|      24.685|      25.499|      60.763|       0|      24.685|
60.763
RTD|      24.142|      26.584|      91.417|       0|      24.142|
91.417
RTD|      24.685|     204.806|     332.845|       0|      24.142|
332.845
RTD|     153.537|     230.034|     324.435|       0|      24.142|
332.845
RTD|      24.685|      68.359|     235.188|       0|      24.142|
332.845
RTD|      24.685|      25.499|      69.173|       0|      24.142|
332.845
RTD|      24.685|      24.956|      65.646|       0|      24.142|
332.845
RTD|      24.685|      26.041|      82.194|       0|      24.142|
332.845
---|------------|------------|------------|--------|-------------------------
RTS|      24.142|      72.970|     332.845|       0|
00:00:10/00:00:10

/ # latency -p 10000 -t 1
== Sampling period: 10000 us
== Test mode: in-kernel periodic task
== All results in microseconds
warming up...
RTT|  00:00:01  (in-kernel periodic task, 10000 us period, priority 99)
RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat
worst
RTD|      14.269|      15.226|      44.108|       0|      14.269|
44.108
RTD|      14.269|      15.388|      44.108|       0|      14.269|
44.108
RTD|      14.269|      15.549|      37.326|       0|      14.269|
44.108
RTD|      13.997|      47.365|     134.169|       0|      13.997|
134.169 
RTD|      60.927|      94.029|     187.337|       0|      13.997|
187.337
RTD|      14.269|      25.187|     108.127|       0|      13.997|
187.337
RTD|      14.269|      16.482|      94.292|       0|      13.997|
187.337
RTD|      14.269|      15.058|      51.975|       0|      13.997|
187.337
RTD|      14.269|      15.066|      30.816|       0|      13.997|
187.337
---|------------|------------|------------|--------|-------------------------
RTS|      13.997|      28.816|     187.337|       0|
00:00:10/00:00:10

/ # latency -p 10000 -t 2
== Sampling period: 10000 us
== Test mode: in-kernel timer handler
== All results in microseconds
warming up...
RTT|  00:00:01  (in-kernel timer handler, 10000 us period, priority 99)
RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat
worst
RTD|       3.960|       4.144|      12.912|       0|       3.960|
12.912
RTD|       3.960|       4.369|      13.183|       0|       3.960|
13.183
RTD|       3.960|       4.404|      23.491|       0|       3.960|
23.491
RTD|       3.960|      25.707|      92.393|       0|       3.960|
92.393
RTD|       4.231|      46.546|      82.628|       0|       3.960|
92.393
RTD|       3.960|       4.204|      11.827|       0|       3.960|
92.393
RTD|       3.960|       4.391|      21.321|       0|       3.960|
92.393
---|------------|------------|------------|--------|-------------------------
RTS|       3.960|      13.395|      92.393|       0|
00:00:09/00:00:09






             reply	other threads:[~2007-05-04  8:40 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-05-04  8:40 CAMUS Benoit [this message]
2007-05-04 10:18 ` [Xenomai-help] Latencies while ethernet access Gilles Chanteperdrix
2007-05-04 16:24   ` Jan Kiszka
2007-05-14 10:09     ` CAMUS Benoit
2007-05-14 10:28       ` Jan Kiszka
2007-05-14 16:03         ` Jan Kiszka
2007-05-14 16:12           ` Gilles Chanteperdrix
2007-05-04 10:26 ` Gilles Chanteperdrix
     [not found]   ` <1178287470.22169.9.camel@domain.hid>
2007-05-04 16:06     ` Gilles Chanteperdrix
2007-05-04 16:12       ` Jan Kiszka

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=1178268043.5391.47.camel@domain.hid \
    --to=benoit.camus@domain.hid \
    --cc=xenomai@xenomai.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.