Re: [alsa-devel] Re: [patch] `cp /dev/zero /tmp' (patch against 2.2.9)

Benno Senoner (sbenno@gardena.net)
Thu, 17 Jun 1999 14:45:40 +0200


On Wed, 16 Jun 1999, Alan Cox wrote:
> > Do you think that we could archieve similar low scheduling latencies
> > as with microkerneled OSes (like BeOS) , or is this a design implementation
> > of monolithic kernels ?
>
> Low scheduling latencies has nothing to do with micro/monolithic kernels
>
> > >From what I heard IRIX is able to handle RT scheuled processes
> > with deadlines of 1ms even under high load, and IRIX is monolithic.
> > (correct me if I'm wrong)
>
> The Linux limitation is very much that our file system is not designed to
> provide real time guarantees but to get maximum work done. Irix XFS actually
> has the notion of being able to open a file and reserve bandwidth on it.
>
> Being able to open a file and say "guarantee me 2Mbits/second" is a very
> powerful facility.

Alan,
I agree that this is a nice feature of IRIX, but in my benchmark I make no
use of disk access in the process itself,
The process does only sit in a loop and write() data from RAM to /dev/dsp
( RT FIFO scheduled),
and in background I call scripts which write / copy / read from/to large files,
trying to disturb the RT thread.
Obviously my disk I/O processes are scheduled without realtime priority.

The scheduling latencies on Linux go up to 70-130ms on pretty high end HW.

The thing which I wanted to say, was that runnning these benchmarks on IRIX,
(playing audio from RAM using a small audiobuffer ( <20ms) and doing
while other processes perform heavy disk I/O, would not cause such
long lasting process stalls.

regards,
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/