Re: SCO: "thread creation is about a thousand times faster than on

From: dean gaudet (dean-list-linux-kernel@arctic.org)
Date: Sat Aug 26 2000 - 00:52:54 EST


On Fri, 25 Aug 2000, John Kacur wrote:

> Alan Cox wrote:
> >
> > > > No major Java vendor currently uses Posix threads either.
> > >
> > > Of course they do, why would you think they don't?
> >
> > Because I talked to their engineers and asked them as part of finding out about
> > stuff for the LSB.
> >
> > Alan
> >
> > -
> > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> > the body of a message to majordomo@vger.kernel.org
> > Please read the FAQ at http://www.tux.org/lkml/
>
> Ahh, maybe I should have identified myself, I develop the jit compiler
> for IBM as part of the ia32 team, and I'm their Linux person, and I can
> ensure you that we are using posix threads. (met you on the bus at OLS)

is this a portability decision? 'cause i can't imagine it being a
performance decision :) pthread semantics just aren't required by java
threads.

back when IBM's java/linux threading performance results became known i
wrote up a proposal for a m:n JVM ... i'll include it again below.

-dean



This archive was generated by hypermail 2b29 : Thu Aug 31 2000 - 21:00:17 EST