From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <45F6AFE5.20700@domain.hid> Date: Tue, 13 Mar 2007 15:06:29 +0100 From: Wolfgang Grandegger MIME-Version: 1.0 References: <45F68258.5040603@domain.hid> <45F6A44A.2030000@domain.hid> <45F6A73C.8030301@domain.hid> <45F6AA11.40707@domain.hid> In-Reply-To: <45F6AA11.40707@domain.hid> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: [Xenomai-help] Re: Latencies due to RT-Socket-CAN register accesses List-Id: Help regarding installation and common use of Xenomai List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: rolandtollenaar@domain.hid Cc: xenomai-help Roland Tollenaar wrote: > HI Wolfgang, > >> It was the IXXAT PCI card currently plugged into my test PC but I >> actually recommand the PEAK PCI card. It's also much cheaper, I guess. >> Tomorrow I'm going to repeat the tests with this card ... stay tuned. > Clear. Thanks for the advice. > >> >>> I will continue development on my laptop with the dongle for the time >>> being. It would be interesting to see what happens to the latency >>> after your proposed changes are in effect. >> >> BTW, what are the latencies you measure on your system under load >> (without RT-Socket-CAN). > Off the top of my head 25us average 30us to 35us max. I am not sure I am > "loading" the system though. How do I measure this load that is always > talked about? While the latency test is running execute in other windows: - while ls; do ls; done - ping -f " - dd if=/dev/zero of=/dev/null and let it run for a few hours. And also search the file TROUBLESHOOTING for "stress". Wolfgang.