Re: Thread implementations...

Richard Gooch (Richard.Gooch@atnf.CSIRO.AU)
Sun, 28 Jun 1998 02:21:17 +1000


Raul Miller writes:
> Richard Gooch <Richard.Gooch@atnf.CSIRO.AU> wrote:
> > Really, glibc is not the solution.
>
> Of course. And, of course, it's a way of packaging the solution
> (provided it's a decent solution).

Maybe my point is still being missed. Glibc is neither the solution,
nor is its packaging of new solutions into standard interfaces of any
relevance *when those interfaces are not explicitely scalable*.

The aio_*() interface is not explicitely scalable. Since
implementations are free to emulate using threads, aio_*() is not
scalable across POSIX.4 systems. POSIX.4 says nothing about the cost
(or reasonableness) of submitting thousands of aio_*() requests. That
means it could be good or bad, depending on which OS you are using.

Let me say it another way: I want a solution that will scale well on
any vanilla POSIX.4 system (i.e. installing glibc is not an option).

Regards,

Richard....

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu