RE: Why HZ on i386 is 100 ?

Cabaniols, Sebastien (Sebastien.Cabaniols@Compaq.com)
Tue, 16 Apr 2002 12:41:43 +0200


>> -----Original Message-----
>> From: Olaf Fraczyk [mailto:olaf@navi.pl]
>> Sent: mardi 16 avril 2002 12:02
>> To: Liam Girdwood
>> Cc: BALBIR SINGH; William Lee Irwin III; linux-kernel@vger.kernel.org
>> Subject: Re: Why HZ on i386 is 100 ?
>>
>>
>> On 2002.04.16 12:29 Liam Girdwood wrote:
>> > On Tue, 2002-04-16 at 09:18, BALBIR SINGH wrote:
>> > > I remember seeing somewhere unix system VII used to have
>> HZ set to
>> > 60
>> > > for the machines built in the 70's. I wonder if todays
>> pentium iiis
>> > and ivs
>> > > should still use HZ of 100, though their internal clock
>> is in GHz.
>> > >
>> > > I think somethings in the kernel may be tuned for the
>> value of HZ,
>> > these
>> > > things would be arch specific.
>> > >
>> > > Increasing the HZ on your system should change the scheduling
>> > behaviour,
>> > > it could lead to more aggresive scheduling and could affect the
>> > > behaviour of the VM subsystem if scheduling happens more
>> frequently.
>> > I am
>> > > just guessing, I do not know.
>> > >
>> >
>> > I remember reading that a higher HZ value will make your
>> machine more
>> > responsive, but will also mean that each running process
>> will have a
>> > smaller CPU time slice and that the kernel will spend more CPU time
>> > scheduling at the expense of processes.
>> >
>> Has anyone measured this?
>> This shouldn't be a big problem, because some architectures
>> use value
>> 1024, eg. Alpha, ia-64.
>> And todays Intel/AMD 32-bit processors are as fast as Alpha was 1-2
>> years ago.

Anyone knows if this would be interesting to decrease this value
for computationnal farms and CPU/memory bound tasks ?

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/