On Sun, 02 Jul 2000, Khimenko Victor wrote:
>
> > BUT THE LATENCY GRAPHS DO NOT SHOW UP A SPIKE OVER 1.5msecs or so.
>
> > So your "My guess is you'll be digging yourself in deeper and deeper" statement
> > makes no sense to me.
>
> > The load I created is certainly bigger than the average load of a desktop
> > system, thus even if the lowlatency patch can not called "hard realtime",
> > it is SUITABLE for realtime multimedia.
>
> If it's good for you then use it ! What's the problem here ? If you want it
> to be included in kernel... It's COMPLETELY other story.
Of course I don't want THIS patch included (which solves the problem in an
unelegant/ hard to mantian way).
But it would be nice if Linux could deliver these latencies (of course
implemented in a clean way) before the next century. :-)
And this will be one of the few hurdles remaining which currently hinder desktop
users to get rid of M$ ware.
>
> > (Immagine that if the P133 can deliver these latencies, what a 1GHz PIII can
> > do ...)
>
> I dunno. If latencies were due to some PCI bus interation then you'll get
> the same 1.5ms or EVEN WORSE (PCI bus on 1GHz PIII can be slower in some
> [rare] situations). That's the point: you find that patch works great to
> you. You STILL have any proof that it'll do the same for millions of other
> boxes out there.
then try it and let us know :-)
the more people , the better .....
I agree that all my tests are "only" empirical, I have it tested only on 4 boxes
but I did not encounter problems (except that an asus motherboard with APM
turned on caused latency spikes at regular intervals, but after turining APM
off, the diagrams looked ok.
>
> > tons of songs were created using a windows or a Mac box (both
> > FAR away from an RTOS) so I don't see why Linux should be unsuitable for this
> > task.
>
> > the risk that we could loose 1msec of audio during the next 50 days because
> > lowlatency is not hardrealtime is not worth to switch to RTLinux.
>
> > ... just like saying better not take the plane, it might crash
> > such is life
> > :-)
>
> > (we live in a statistical world)
>
> You - may be. Linus - not :-) That's why Linus works (unlike some other OSes).
to quote Richard "My guess is you'll be digging yourself in deeper and deeper
..."
I see RTLinux vs lowlatency kernel like
solving f(x)=0 in an exact and aproximate way (for example Newton's xn+1 =
xn -f(x)/f'(x) )
RTLinux is the "exact" solution but is "expensive"
low-latency kernel is the "aproximate solution" which is less expensive
aproximate = does not try to get down to 10-50usec latencies (HW limits),
plus no one is forced to supply a written guarantee that the latencies will
never be bigger than X msecs.
if you wish you can call lowlatency = soft-realtime, where empirical tests under
extreme conditions have shown to not exceed 2ms on Pentium+ hardware.
I think most multimedia people are happy with the above definition,
since not even BeOS claims to be realtime but it's a so called "Media OS".
Benno.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Fri Jul 07 2000 - 21:00:11 EST