Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 14 May 2003 10:32:05 +0300
From:      Vallo Kallaste <kalts@estpak.ee>
To:        Peter Wemm <peter@wemm.org>
Cc:        current@FreeBSD.org
Subject:   Re: 5.1-RELEASE TODO
Message-ID:  <20030514073205.GA1324@kevad.internal>
In-Reply-To: <20030513221637.3B7422A8AC@canning.wemm.org>
References:  <200305132101.h4DL1QM7051267@gw.catspoiler.org> <20030513221637.3B7422A8AC@canning.wemm.org>

next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, May 13, 2003 at 03:16:37PM -0700, Peter Wemm <peter@wemm.org> wrote:

> Also of note:  I recently saw a brand new P4 system with a genuine intel
> motherboard, for a RELENG_4 system.  It had shocking data corruption
> problems. The memory was swapped - no change.  The motherboard and CPU were
> swapped (same motherboard model, much newer P4 cpu stepping) - no change.
> It was simply unreliable.  Backporting DISABLE_PG_G to RELENG_4 and turning
> on it and DISABLE_PSE greatly reduced the problem, but it still happened.
> In the end, the Intel motherboard was replaced with a P4 Xeon system
> motherboard and the problem instantly went away.  The trouble appeared
> to be a generic problem the Intel 845 chipset motherboard.
> 
> Remember, this was RELENG_4 as of a few months ago.  It isn't a 5.x-only
> problem.

Peter, this sounds very suspiciously similar to my P4 system, do you
remember the mobo model? Mine is:

FreeBSD 5.0-CURRENT #0: Fri Mar 14 13:08:38 EET 2003
    root@vallo.internal:/usr/home/vallo/Vallo-5.0
Preloaded elf kernel "/boot/kernel/kernel" at 0xc04ff000.
Preloaded elf module "/boot/kernel/aout.ko" at 0xc04ff0a8.
Preloaded elf module "/boot/kernel/acpi.ko" at 0xc04ff154.
Timecounter "i8254"  frequency 1193182 Hz
Timecounter "TSC"  frequency 1699952048 Hz
CPU: Intel(R) Celeron(R) CPU 1.70GHz (1699.95-MHz 686-class CPU)
  Origin = "GenuineIntel"  Id = 0xf13  Stepping = 3
  Features=0x3febfbff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,C
MOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM>
real memory  = 132382720 (126 MB)
avail memory = 123236352 (117 MB)
Allocating major#253 to "net"
Allocating major#252 to "pci"
Pentium Pro MTRR support enabled
VESA: v3.0, 832k memory, flags:0x1, mode table:0xc0429d80 (1000040)
VESA: Brookdale-G Graphics Chip Accelerated VGA BIOS
npx0: <math processor> on motherboard
npx0: INT 16 interface
acpi0: <INTEL  D845GLLY> on motherboard         <<<<<<<<<<<<<<<<
    ACPI-0625: *** Info: GPE Block0 defined as GPE0 to GPE31
pcibios: BIOS version 2.10
Using $PIR table, 9 entries at 0xc00f3d20
acpi0: power button is handled as a fixed feature programming model.
Timecounter "ACPI-fast"  frequency 3579545 Hz
acpi_timer0: <24-bit timer at 3.579545MHz> port 0x408-0x40b on acpi0
acpi_cpu0: <CPU> port 0x530-0x537 on acpi0
------------------------------------------------------------

This is headless machine, has serial console and most of the work is
done via ssh. No X, no drm, agp driver compiled in, network card:

fxp0: <Intel 82801DB (ICH4) Pro/100 VE Ethernet> port 0xdc00-0xdc3f mem 0xff8ff0
00-0xff8fffff irq 11 at device 8.0 on pci1
fxp0: Ethernet address 00:03:47:29:85:a5
inphy0: <i82562ET 10/100 media interface> on miibus0
inphy0:  10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto
------------------------------------------------------------

I haven't tried builds absolutely without network interface (it's
onboard), but it doesn't matter will the ssh session be up or not.
Memory is non-ECC and I haven't swapped any components because of
restrictions we have here at work.

Have you guys considered setting up some webpage with clear and firm
instructions for testing, with some kind of feedback submit form.
I'm very concerned about data integrity and willing to do any
testing necessary on the systems I have here, but this is going to
nowhere if anyone will do their own set of tests and the initial
testing environment differs from case-to-case. If we need to prove
something, the very thing we need is the base; firm instructions for
testing and feedback data in the one format. Only after that we can
correlate the results and systems the tests did run.
-- 
Vallo Kallaste



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030514073205.GA1324>