Most daq boards can sample faster and buffer some number of samples. Your best bet might be to set up your daq board like that (if it's capable) and read the buffered data out of it several samples at a time at some period less than 10 uS. The 10 uS is probably a limit because of what RTLinux has to do to reprogram the timer and stuff. That 8254 is on the ISA bus and it's 1.3 uS for every port op. (somebody correct me if I'm wrong here.)
If your DAQ board can't do that, you could try bombarding it with high fields of radiation. There's a finite probability that the radiation could trigger just the right physical changes on the silicon in the board's various ICs to do what you want. :) Steve >-----Original Message----- >From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]]On Behalf Of >Miguel Saiz Arnedo >Sent: Wednesday, June 05, 2002 2:02 AM >To: [EMAIL PROTECTED] >Subject: [rtl] rtlinux 10us limit > > > >Hello. > >I installed RTLinux on my AMDk6 430 MHZ with 128 Mb RAM and up >to now I've just >been probing with the example programs. >I have tried the hello.c with various thread periods and >observed that when I >try periods of less than 10us my system crashes. Is this a >normal limit? Is it >a >hardware limit or is it an RTLinux limit? >If I can't schedule periodic threads with less than 10us >period that will mean >that if the thread is used to aquire samples from a DAQ board >I will have a >100KHz sampling rate limit, which I find a bit low for my >needs.Is it possible >to achieve higher sampling rates with RTLinux? > >Thanks in advance and best regards. > >Miguel. -- [rtl] --- To unsubscribe: echo "unsubscribe rtl" | mail [EMAIL PROTECTED] OR echo "unsubscribe rtl <Your_email>" | mail [EMAIL PROTECTED] -- For more information on Real-Time Linux see: http://www.rtlinux.org/
