Dag Richards wrote:
Makes possible? Erm by magic? Will running that kernel ... well
Um I'd like to buy another clue please Vanna.
Ok. There you go.
src/sys/arch/i386/conf/GENERIC.MP
# $OpenBSD: GENERIC.MP,v 1.5 2005/05/01 07:54:42 david Exp $
#
# GENERIC.MP - sample multiprocessor kernel
#
include "arch/i386/conf/GENERIC"
option MULTIPROCESSOR # Multiple processor support
cpu* at mainbus?
ioapic* at mainbus?
^^^^^^^^^^^^^^^^^^^^^^^^^^^
^-> Fantastic... Isn't it?
Any hints on who to go to for the ultra secrets?
That's what happens in Linux world, some developer creates a so-called
magical patch but the dictator never let's it in kernel. The patch
becomes a myth and circulates between communities.
Generally this is not a case in OpenBSD world.
It's irony man... Literature... Fine arts...
I am currently trying to connect to DC's over a leased gigaMAN
connection. I am getting only 41 MB/s on the bsd routers without ipsec
running 7 Mbs with ipsec running. These are Sunfire x2100's running on
3.9 i386 kernels.....
I have so far just found Henning's paper on perf tunning, it seems to
tell me that I am very CPU bound when running ipsec. I can buy
accelerator cards for crypto, but the performance is nowhere near what I
would expect just machine to machine on a x-over cable, or switch
between the broadcom cards.
Instead of an accelerator card, buying a cheap VIA C7 powered small box
can be cost effective and painless. [EMAIL PROTECTED] or [EMAIL PROTECTED] will be
sufficient for many routing, filtering, monitoring with crypto
acceleration scenarios. You can achieve very high numbers with AES128 +
SHA-1. BTW, AES-256 + SHA256 is also possible with nearly same
performance timings.
Good luck.
