Re: preempt rt in commercial use

[David Kastrup <dak@gnu.org>]

Armin Steinhoff <armin@steinhoff.de> writes:

>  Robert Schwebel wrote:
>> On Tue, Sep 14, 2010 at 11:24:21AM +0200, Raz wrote:
>>> anyone can say preempt rt is hard real time?
>> Hard realtime has something to do with how you define "missing the
>> deadline". If somebody cuts the cable of your roboter controller in the
>> factory hall, the system misses the deadline. So it is all about
>> probabilities: hard realtime systems have a very, very low probability
>> of missing the deadline. However, in real life systems, it is>  0%.
>>
>> So yes, if you talk about real world, it is hard realtime.
>>
> Hm, and what do think about that statement from FSMLabs:
>
> "Linux “PREEMPT” real-time is a continuing experiment aimed at audio
> and video playing with unreliable results and a detrimental affect on
> “enterprise” performance"

Kernel preemption is a complex thing.  Letting the kernel be a
low-priority realtime task (which is what most "enterprise" solutions do
instead) still preempts the kernel, though only with realtime tasks, not
competing tasks.  Treating the kernel as a black box does not give you
finer-grained control over device drivers etc unless you move the device
drivers into the realtime realm.

When a failure to service a device in a given time frame will result in
hardware damage, you don't want a system as complex as the whole kernel
involved.  A realtime control system around that is more secure, but a
dedicated, physically separate controller for meeting the hard
constraints might be the safer choice.

-- 
David Kastrup

--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html