Messages in this thread | | | Date | Mon, 3 Jul 2000 12:09:49 -0600 | From | Richard Gooch <> | Subject | Re: a joint letter on low latency and Linux |
| |
David Schleef writes: > On Fri, Jun 30, 2000 at 03:29:46PM -0600, Richard Gooch wrote: > > > > I don't like that at all. Adding a pile of extra "fast" syscalls is > > just too hackish. Just say: "if you go into the kernel, you lose RT". > > It's the thin edge of the wedge. Soon you'll be getting people to say > > "we need read(2) to keep RT priority". > > They wouldn't technically be Linux system calls, but LXRT system > calls. They also don't tend to be any faster; they just happen > to be RT-safe. > > The nice thing about RT-safe is that means it is thread-safe and > lock-free. So an RT-safe version of gettimeofday() could easily > be a replacement for the current gettimeofday. But that would > require real-time support in the kernel.
I don't really see the point to adding LXRT system calls. If all you want is a RT-safe gettimeofday, then wait for the user-space implementation based on the global code page scheme.
Regards,
Richard.... Permanent: rgooch@atnf.csiro.au Current: rgooch@ras.ucalgary.ca
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |