DragonFly BSD
DragonFly users List (threaded) for 2005-03
[Date Prev][Date Next]  [Thread Prev][Thread Next]  [Date Index][Thread Index]

Re: Fwd: Re: Differences between constructive and destructive criticism


From: EM1897@xxxxxxx
Date: Sat, 12 Mar 2005 14:02:26 -0500

> Chris Pressey babbled:

>On Sat, 12 Mar 2005 13:20:20> EM1897@xxxxxxx wrote:
>
>> The purpose of an O/S is to utilize hardware. If you think
>> that hardware is irrelevant, then you really aren't paying
>> attention. The entire point of FreeBSD 5 and dragonfly is
>> that uniprocessor has hit a wall, and the freebsd 4.x
>> design is not multiprocessor friendly, so it needs to be
>> redesigned to utilize multi-core, MP architectures. Its
>> always about performance, and the hardware available is
>> the entire point.
>
>How do you reconcile this with your earlier, clearly non-MP view?
>
>"If you learn to read english you'll know that uniprocessor is a basic
>premise."

There are currently no MP O/S implementations that run faster
than FreeBSD 4.x on a uniprocessor system, so thats what
I use. There is no point in investing in expensive hardware
that is slower than a uniprocessor solution. That WAS
the point of the thread, at least initially. That investing
in expensive AMD hardware is not currently worthwhile 
because much less expensive uniprocessor solutions are
at least equal in performance.

>
>"It seems almost comical that teams of engineers are rewriting an OS
>trying to squeeze some cycles out of _a_ CPU without any understanding
>of the main bottleneck to networking performance." [emphasis mine]

The point was that enhancing MP performance is a waste of
time if you're going to run things on bus-limited hardware.
A uniprocessor system with a PCI-X bus will blow the doors
off of even a well-implemented MP system with standard PCI,
because the CPU is not the limiting factor.



[Date Prev][Date Next]  [Thread Prev][Thread Next]  [Date Index][Thread Index]