"Darren Smith" <[EMAIL PROTECTED]> writes:
> I mean I added a usleep() before the poll in s_bsd.c for the undernet
> 2.10.10 code.
>
> timeout = (IRCD_MIN(delay2, delay)) * 1000;
> + usleep(10); <- New Line
> nfds = poll(poll_fds, pfd_count, timeout);
>
> And now we're using 1/8th the cp
Aaron Sethman <[EMAIL PROTECTED]> writes:
> On Mon, 4 Feb 2002, Darren Smith wrote:
>
> > I mean I added a usleep() before the poll in s_bsd.c for the undernet
> > 2.10.10 code.
> Why not just add the additional delay into the poll() timeout? It just
> seems like you were not doing enough of a
Darren.
-Original Message-
From: Aaron Sethman [mailto:[EMAIL PROTECTED]]
Sent: 04 February 2002 17:41
To: Darren Smith
Cc: 'Andrew Morton'; 'Dan Kegel'; 'Vincent Sweeney';
[EMAIL PROTECTED]; [EMAIL PROTECTED]; 'Kevin L.
Mitchell'
Subject: RE: [Coder-Com] R
> > I mean I added a usleep() before the poll in s_bsd.c for the undernet
> > 2.10.10 code.
> >
> > timeout = (IRCD_MIN(delay2, delay)) * 1000;
> > + usleep(10); <- New Line
> > nfds = poll(poll_fds, pfd_count, timeout);
> Why not just add the additional delay into the poll() timeout? It j
Hi
I've been testing the modified Undernet (2.10.10) code with Vincent
Sweeney based on the simple usleep(10) addition to s_bsd.c
PRI NICE SIZERES STATE C TIME WCPUCPU | # USERS
2 0 96348K 96144K poll 0 29.0H 39.01% 39.01% | 1700 <- Without
Patch
10 0 77584K 77336K na
>
>
>So I dunno if I'm going to go ahead and do that myself, but at least I've
>scoped out the situation. Before I did any work, I'd measure CPU
>usage under a simulated load of 2000 clients, just to verify that
>poll() was indeed a bottleneck (ok, can't imagine it not being a
>bottleneck, but i
