lkml.org 
[lkml]   [2000]   [Aug]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: SCO: "thread creation is about a thousand times faster than on
From
Date
Linus Torvalds <torvalds@transmeta.com> writes:
> Well, CLONE_PARENT is already there. And has been for a long time.

And it works fine. I've modified LinuxThreads in glibc-2.1.3 to use
it (patch at <http://www.doc.ic.ac.uk/~dpw/linux/dc/>). The remaining
loose end I have to address is to do with the setting the scheduling
parameters for the newly created thread specified in the call the
pthread_create(). (The scheduling parameters need to be set by the
time pthread_create() returns, and also by the time the new thread's
start function gets called. This can be solved by calling
sched_setscheduler() both in the parent thread and the child thread,
but then both threads need to wait until the other one has finished
making the call, and the two sched_setscheduler() syscalls tend to
contend with each other on SMP, so the performance isn't wonderful.)

> The CLONE_WAITPID patches I don't remember, so please refresh my memory
> about what they look like, and why they were needed in the first place..

POSIX says that any thread can do a wait() et al. for a child process.
But Linux currently thinks that a child processes is a child of a
particular thread, and so only that thread can wait() for it.


David Wragg

-
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/

\
 
 \ /
  Last update: 2005-03-22 12:38    [W:0.196 / U:0.280 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site