[ILUG] Realtime Linux

[Geoff Moore]

Hi Mel

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
while.

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.

Good luck!

Geoff Moore
====================================
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.
>
> cheers
>
> --
> 		Mel
>
> 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
> information.
> List maintainer: listmaster at linux.ie
>
>