Date: Sun, 01 Oct 2006 09:16:01 -0400 From: Randall Stewart <rrs@cisco.com> To: =?ISO-8859-1?Q?Dag-Erling_Sm=F8rgrav?= <des@des.no> Cc: Peter Lei <peterlei@cisco.com>, Michael Tuexen <tuexen@fh-muenster.de>, Robert Watson <rwatson@freebsd.org>, "George V. Neville-Neil" <gnn@neville-neil.com>, freebsd-current@freebsd.org Subject: Re: Some interesting plots Message-ID: <451FBF91.5070205@cisco.com> In-Reply-To: <86r6xtjv6t.fsf@dwp.des.no> References: <451D5801.8030504@cisco.com> <86r6xtjv6t.fsf@dwp.des.no>
next in thread | previous in thread | raw e-mail | index | archive | help
Dag-Erling Smørgrav wrote: > Randall Stewart <rrs@cisco.com> writes: > >>As you all may know I have been working on getting SCTP >>into Current.. >> >>I have been, of late, trying to tweak things to get >>the BEST performance out of the implementation... > > > the first rule of software optimization: don't do it > > the second rule of software opimization (for experts only): don't do it yet > > DES When I started optimizing a couple of years ago.. (this is probably the 3rd or 4th pass of it) the SCTP implementation would not get more than 300M on the current configuration I illustrated... I am now up to 750M ... along the way I have fixed numerous bugs ... having been in this business almost 25 years now I humbly disagree :-) R -- Randall Stewart NSSTG - Cisco Systems Inc. 803-345-0369 <or> 815-342-5222 (cell)
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?451FBF91.5070205>