Messages in this thread | | | Date | Thu, 29 Jul 2004 20:30:09 +0300 | From | Avi Kivity <> | Subject | Re: [PATCH 20/22] AIO poll |
| |
William Lee Irwin III wrote:
>William Lee Irwin III wrote: > > >>>I just did it for OLS. The answer is busywait. i.e. 100% cpu. This is >>>because you can't use timeouts unless they're unified. >>> >>> > >On Thu, Jul 29, 2004 at 08:24:18PM +0300, Avi Kivity wrote: > > >>That's not a server. >> >> > >It accepted enough client connections and did enough work on behalf of >its clients to qualify as such. > >Perhaps you have in mind that such a "solution" is inferior (which it is)? > > > > Yes. Sorry for being so terse. But busy-waiting isn't acceptable for anything more than a demonstration, or (extermely) special-purpose servers, like maybe embedded stuff.
-- Do not meddle in the internals of kernels, for they are subtle and quick to panic.
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |