[prev in list] [next in list] [prev in thread] [next in thread] 

List:       linux-smp
Subject:    Re: Athlon-MP problems ...
From:       Alan Cox <alan () lxorguk ! ukuu ! org ! uk>
Date:       2003-05-17 20:04:15
[Download RAW message or body]

On Sad, 2003-05-17 at 20:50, vincent blondel wrote:
> Adaptec SCSI RAID 5400s Family BIOS (version 1.0-0 build 5262)
> RAID-5 with 4 x SEAGATE Hard Drive Cheetah 15k.3 18.4gb U320

I've a very similiar set up as it happens (Dell Obsidian rather than
the 5400, and my disks suck)

> First of all, I always had some latencies with lots of basic commands ( clear, 
> ls ... ). So I recompiled kernel with a gcc 2.95.3 (instead of a gcc 3.2.2 as 
> it was the case for the first time) as it seems this latency is disappeared 

This still all sounds like an overheating machine, or other hardware
problems. ACPI will mask some of it by power saving the CPU's of course.

> Is that normal I received these messages in dmesg ???
> 
>     mtrr: your CPUs had inconsistent fixed MTRR settings
>     BIOS failed to enable PCI standards compliance, fixing this error.

Older BIOSes have this bug, newer ones fix the PCI compliance and latest
ones seem to fix the need for a PS/2 mouse to avoid IDE hangs

> How is that possible dmesg sees a AMD-760 MP device ??? ( when I look at the 
> website of TYAN, they say it is a 760 MPX)

760MP/MPX are all very much of the same thing.

>     amd76x_pm: Initializing northbridge Advanced Micro Devices [AMD] AMD-760 
> MP [IGD4-2P] System Controller

Ah - don't run both ACPI and amd76x_pm. They fall over each other

> Is that normal I got two different processors in /proc/cpuinfo ???
> 
>     model name	: AMD Athlon(tm) MP 1800+
>     model name	: AMD Athlon(tm) Processor

BIOS again but harmless in itself

-
To unsubscribe from this list: send the line "unsubscribe linux-smp" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
[prev in list] [next in list] [prev in thread] [next in thread]