Date: Fri, 25 Jan 2008 09:21:53 +0100 From: =?utf-8?Q?Dag-Erling_Sm=C3=B8rgrav?= <des@des.no> To: "william wong" <beijing.liangjie@gmail.com> Cc: freebsd-hackers@freebsd.org Subject: Re: FreeBSD hacker 101 Message-ID: <86sl0m5n8e.fsf@ds4.des.no> In-Reply-To: <84a208a0801242158q632314dfpd370a2fee2f87390@mail.gmail.com> (william wong's message of "Fri\, 25 Jan 2008 13\:58\:51 %2B0800") References: <84a208a0801232306k6a34134aqd549a1ba2160fe41@mail.gmail.com> <86bq7bwlot.fsf@ds4.des.no> <84a208a0801240456q3154de92me73e846df84d587a@mail.gmail.com> <86prvrv0b1.fsf@ds4.des.no> <84a208a0801240711j979874apad2d17c9afdbd6e@mail.gmail.com> <86fxwn877v.fsf@ds4.des.no> <84a208a0801242158q632314dfpd370a2fee2f87390@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
"william wong" <beijing.liangjie@gmail.com> writes: > That brings me to another ponder: why juniper and cisco are using > FreeBSD and not Linux even Linux performs better in an UP environment? Who said Linux performs better in a UP environment? UP performance is close to irrelevant these days anyway; there are still many UP machines (especially in the embedded world), but application code is increasingly dependent on multithreading, and the kind of things you have to do to your kernel to get good multithreading performance are pretty much the same things you have to do to get good SMP performance. In any case, I doubt UP or SMP performance was the biggest factor in the decision. The licensing model, the stability of the code base (between major releases) and possibly the quality of the network stack are likely to have played a larger role. This is all speculation, however; I don't work at Juniper or Cisco. DES --=20 Dag-Erling Sm=C3=B8rgrav - des@des.no
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?86sl0m5n8e.fsf>