I'd suggest you wander over to http://www.rtlinux.org/rtlinux/ and get
yourself subscribed on the RTLinux list there then ask the question again.
There are people from both RT-Linux and Realtimelinux.org on that list (as
can be seen in the archives from the occassional flame wars), so you could
get some pointers/guidance/suggestions/death threats from there.
Unfortunately I'm no expert on real time Linux but I do have more than a
passing interest in RTOSs and I've been lurking on that list for quite a
There are a lot of people doing serious stuff with what's currently
available but there are considerably more people having serious difficulty
just getting started, which suggests to me that there's a lot of work still
to be done in the field.
Straight Forward Solutions Ltd
Maynooth Road, Prosperous,
Naas, Co.Kildare, Ireland
Phone : +353 (0)45 892739
Fax : +353 (0)45 893880
Mobile : +353 (0)86 8179683
email : geoffm at straight-forward.com
> -----Original Message-----
> From: ilug-admin at linux.ie [mailto:ilug-admin at linux.ie]On Behalf Of Mel
> Sent: 20 March 2001 07:04
> To: ilug at linux.ie> Subject: [ILUG] Realtime Linux
>>> About this time last year, I posted up saying I was considering starting a
> Masters on implementing a POSIX real time implementation for Linux.
> Against the odds, I started it a month ago. After a month of reading
> through docs, kernel list archives, various real time documentats and the
> implementations out there, I'm wondering have I started a lemon masters.
> Prehaps someone out there could shed some light?
>> Linux appears to already provide all the POSIX compliant services required
> for soft real time through interfaces such as sched_setscheduler and
> memory locking. It is shady if they are fully implemented but it is
> looking like it. However, I can not find somewhere that explicetly says
> that stock linux kernel will provide soft real time reasonably well. By
> reasonably I mean, it falls just short of hard real time. Could someone
> tell me for definite, that all work for soft real time linux is completed
> to satisfaction or is there some secret list out there of all the failures
> that I'm missing?
>> Hard real time seems to be headed up by RT-Linux and Realtimelinux.org.
> RT-Linux looks like short cut so I'm not interested in how it does things.
> Realtimelinux.org appears to have a good and nifty approach but never got
> near the stable kernel tree and the docs doesn't say why. Does anyone in
> the loop know why hard real time services never made it to the stable
> kernel branch? If at all possible, if I do work on a hard real time
> system, I would like to get it near the stable branch if possible. For
> that matter, if the course of the Master changes, I would like to get as
> much of the work into the stable tree as possible.
>> If implementing a real time system is meaningless (which I think it might
> possibly be), my options are drop out of college or find something new
> dealing with real time and linux. If people know of some magical TODO list
> that is out there that is evading me, I would appreciate it if it was
> passed on.
>> The Final Solution: grep -vi mel life > sanity
> Irish Linux Users' Group: ilug at linux.ie>http://www.linux.ie/mailman/listinfo/ilug for (un)subscription
> List maintainer: listmaster at linux.ie>>
Maintained by the ILUG website team. The aim of Linux.ie is to
support and help commercial and private users of Linux in Ireland. You can
display ILUG news in your own webpages, read backend
information to find out how. Networking services kindly provided by HEAnet, server kindly donated by
Dell. Linux is a trademark of Linus Torvalds,
used with permission. No penguins were harmed in the production or maintenance
of this highly praised website. Looking for the
Indian Linux Users' Group? Try here. If you've read all this and aren't a lawyer: you should be!