Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 08 Nov 2005 23:20:53 +0100
From:      David Landgren <david@landgren.net>
To:        freebsd-smp@freebsd.org
Subject:   Re: Multi CPU support in 6.0
Message-ID:  <437124C5.7050008@landgren.net>
In-Reply-To: <43711067.2010500@elischer.org>
References:  <01d301c5e3ae$b2461840$b3db87d4@multiplay.co.uk>	<20051107152718.GA4743@tara.freenix.org>	<10EFEEF4-D1D4-45FC-991C-60A4E60FB391@bnc.net>	<20051108164520.GA81940@xor.obsecurity.org> <4370E4C3.5000204@landgren.net> <43711067.2010500@elischer.org>

next in thread | previous in thread | raw e-mail | index | archive | help
And Julian Elischer did write:

> David Landgren wrote:
> 
>> And Kris Kennaway did write:
>>
>>> On Mon, Nov 07, 2005 at 05:15:55PM +0100, Achim Patzner wrote:
>>>
>>>> Am 07.11.2005 um 16:27 schrieb Ollivier Robert:
>>>>
>>
>> [...]
>>
>>>> I remember someone writing that the intermediate state of -CURRENT  
>>>> while removing the giant lock around the kernel wasn't viable with  
>>>> more than four CPUs as it would completely deadlock from time to  
>>>> time. I guess we're a bit further down the road...
>>>
>>>
>>>
>>>
>>> That certainly seems to be the case.  You want to use FreeBSD 6.0,
>>> which has excellent performance and stability on SMP in my testing,
>>> even with 14 CPUs.  FreeBSD 5.4 is definitely not up to it, since VFS
>>> is under Giant.
>>
>>
>>
>> Well I'm going to take the plunge and bring an HP Netserver LT 6000 
>> with 6 CPUs up from 5.4-STABLE to 6.
> 
> 
> 
> do some benchmarks before and after :-)

Ah... wise words. I'll try a couple of things out then.

Thanks,
David





Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?437124C5.7050008>