Subject: Re: libpthread
To: None <firstname.lastname@example.org>
From: William Henny <email@example.com>
Date: 06/24/2003 19:00:53
In article <OF671BD924.D59CE0D8-ON65256D4E.0029DCD6-80256D4E.0042ABBE@in.ibm.com>, Kamal R Prasad wrote:
> Frank van der Linden <firstname.lastname@example.org>
> Sent by: email@example.com
> 06/21/2003 01:49 AM
> To: Matthias Buelow <firstname.lastname@example.org>
> cc: email@example.com, firstname.lastname@example.org
> Subject: Re: libpthread
> On Sat, Jun 21, 2003 at 02:47:08AM +0200, Matthias Buelow wrote:
>> But are there solid plans underway to give NetBSD 1x1
>> and MxN kernel threading
>>MxN is what the SA code does, so NetBSD currently does that. The issue
>>is that it's not release quality yet. 1x1 has been possible for a while
>>with the clone(2) system call. It's Linux compatible, so you could
>>compile linuxthreads on NetBSD with some minor adjustments.
> If you have MxN support, then thats good news.
> Linux 2.4.1 assigns a single thread to each thread/process created in
> user-space. The code in Linux is release-quality, but the design is awful.
Why the specific reference to Linux 2.4.1? LinuxThreads predates that kernel
by two or three years.
> and like all things linux, there is a major overhaul underway to fix that
Overhaul? LinuxThreads is being discarded.
An interesting article on the development of posix threading in Linux:
I believe the latest offerings from Red Hat already uses NPTL, while all of
the distributions will be using it come 2.6.
As for the fate of NGPT:
I think it says something when two programmers at Red Hat came up with an
implementation around the 1:1 model that greatly outperformed the M:N
implementation of the IBM/Intel folks, and in much shorter time.
And then there's Solaris' move from a M:N to a 1:1 model, as the former
proved very difficult to debug, and the 1:1 implementation they came up with
performed better anyway.