Re: [patch] Real-Time Preemption, -RT-2.6.10-rc2-mm2-V0.7.30-2

[Ingo Molnar]

* Paul Davis <paul@xxxxxxxxxxxxxxxxxxxxx> wrote:

> >also, the problem is that jackd uses _named_ fifos, which are tied to
> >the raw FS and might trigger journalling activities. Normal pipes
> >(unnamed fifos) would not cause such problems. Would it be possible to
> >change jackd to use a pair of pipes, instead of a fifo?
> 
> i.e. pipe(2) rather than mkfifo(2) ?
> 
> it would be a complete pain because the pipes have to be
> "discoverable" across processes. we would have to do fd passing, which
> is still really quite ugly in linux (and other *nix systems). it would
> quite difficult, though not impossible.

yeah. And i think mkfifo(2) objects ought to behave atomically as well,
it's an unfortunate side-effect of atime/mtime inode semantics that they
can block.

your point is correct, the best way to have a system-wide namespace for
synchronization objects is ... the filesystem hierarchy. If you create a
unix domain socket then you can distribute your pipe fds, but that's
indeed somewhat painful.

	Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/