Date: Sat, 30 May 2009 19:59:32 -0700 (PDT) From: bf <bf2006a@yahoo.com> To: freebsd-current@FreeBSD.org Cc: attilio@FreeBSD.org, ohartman@mail.zedat.fu-berlin.de Subject: Re: signifanctly slowdown of FreeBSD 8.0-CURRENT/amd64 Message-ID: <951233.95131.qm@web39108.mail.mud.yahoo.com>
next in thread | raw e-mail | index | archive | help
>2009/5/30 Attilio Rao <attilio at freebsd.org>:
>> 2009/5/30 O. Hartmann <ohartman at mail.zedat.fu-berlin.de>:
>>> Attilio Rao wrote:
>>>> 2009/5/30 O. Hartmann <ohartman at mail.zedat.fu-berlin.de>:
>>>>
>>>>> Hello.
>>>>> I realized a significant slowdown of FreeBSD 8.0-CURRENT/amd64 on every
>>>>> box I run. I have the most recent FreeBSD 8.0-CURRENT/amd64 with custom
>>>>> kernel and switched off every debugging. I see a drastic slowdown
>>>>> whenever heavy I/O on UFS2 and ZFS partitions is performed and whenever
>>>>> some compilation is done (compiling world and kernel).
...
>Also, did you compile the single-core athlon64 without the option SMP?
>
>Thanks,
>Attilio
I'm running the r193133 amd64 with a custom kernel and all debugging off
on an AMD Athlon64 3400+ single-core, and I haven't noticed any significant
slowing, although I haven't been doing any systematic benchmarking.
What would be the penalties of running an SMP -CURRENT kernel on
single-core hardware with no hyperthreading? Can anyone quantify the
typical added overhead? Or, counterintuitively, would an SMP kernel
be better in some ways?
Regards,
b.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?951233.95131.qm>