Re: Timings for optimised poll(2)

Theodore Y. Ts'o (tytso@MIT.EDU)
Tue, 26 Aug 1997 12:32:35 -0400


Date: Tue, 26 Aug 1997 17:40:10 +1000
From: Richard Gooch <rgooch@atnf.CSIRO.AU>

I agree: poll(2) is more scalable than select(2), even if select(2)
has some advantages over poll(2) (like shifting less bits around).

However, what do you think of my idea to add a poll_event field to the
file struct so we can avoid calling those damn indirect poll
functions? Will people accept yet another change to the polling
interface? I'd consider starting to code up a patch to provide the
basics if I knew the idea would not be rejected :-)

I'd certainly be in favor of it. It's an internal change; we're in the
middle of the 2.1 development cycle; and it appears to have a
significant performance impact.

- Ted