Subject: Re: MP panic on p4p800
To: Manuel Bouyer <firstname.lastname@example.org>
From: Paul Ripke <email@example.com>
Date: 07/24/2004 11:37:05
On Saturday, Jul 24, 2004, at 00:24 Australia/Sydney, Manuel Bouyer
> On Fri, Jul 23, 2004 at 08:39:56PM +1000, Paul Ripke wrote:
>> Is this current or 2.0beta? I picked one of these up a week and a bit
>> ago, currently running a custom ACPI-MP+ioapic kernel from 2.0beta.
> Yes, a 2.0 with ACPI-MP+ioapic runs fine. Thanks !
> Now lets see if HT is really usefull :)
My only bit of benchmarking thus far is timing a kernel build. HT
reliably increased the time from 116s to 119s. Warm cache, multiple
runs, with -pipe. Guessing this is due to increase in various kernel
overheads (locking, IPIs, etc).
Knowing what I know about HT, I can see it isn't always going to be a
benefit... unless maybe you're talking IBM Power5 chips? Those I'm
curious to see.