Messages in this thread | | | From | "Stephen C. Tweedie" <> | Date | Wed, 15 Sep 1999 16:37:12 +0100 (BST) | Subject | Re: POSIX aio vs completion ports |
| |
Hi,
On Tue, 14 Sep 1999 14:31:47 -0400 (EDT), Chuck Lever <cel@monkey.org> said:
>> As far as I know, on a queue overflow, SIGIO is raised and you can >> select() or poll() on your fds. This of course is going to be >> exceptionally slow on a large number of descriptors, but it >> shouldn't happen often.
> i think that kind of design is completely unrealistic. you are most > likely to run out of queue space when the server is overloaded. why then > would you want to use a recovery mechanism that would just make the > overload worse?
Because you fall back to a poll mechanism which lets the application deal with a larger chunk of work at once.
> the server is better off ignoring queue overflow.
If the net result of ignoring a signal is to completely freeze one or more network connections, then I beg to differ.
--Stephen
- 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/
| |