Athlon runtime problems

Athlon runtime problems

Post by Alan Co » Mon, 16 Apr 2001 00:20:05



Can the folks who are seeing crashes running athlon optimised kernels all mail
me

-       CPU model/stepping
-       Chipset
-       Amount of RAM
-       /proc/mtrr output
-       compiler used

Alan

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

 
 
 

Athlon runtime problems

Post by Tim lawles » Mon, 16 Apr 2001 00:50:03



> Can the folks who are seeing crashes running athlon optimised kernels all mail
> me

> -  CPU model/stepping

Athlon Thunderbird 700mhz

/proc/cpu:

processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 6
model           : 4
model name      : AMD Athlon(tm) Processor
stepping        : 2
cpu MHz         : 700.034
cache size      : 256 KB
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 1
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 sep mtrr pge mca cmov pat pse36 mmx fxsr syscall mmxext 3dnowext 3dnow
bogomips        : 1395.91

Quote:> -  Chipset

VIA KT133

Quote:> -  Amount of RAM

256MB

Quote:> -  /proc/mtrr output

reg00: base=0x00000000 (   0MB), size= 256MB: write-back, count=1
reg01: base=0xd4000000 (3392MB), size=  32MB: write-combining, count=2
reg05: base=0xd0000000 (3328MB), size=  64MB: write-combining, count=3

Quote:> -  compiler used

kgcc under redhat:
gcc driver version 2.95.3 19991030 (prerelease) executing gcc version
egcs-2.91.66

> Alan

> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/

--
There are a thousand hacking at the branches of evil to the one
who is striking at the root.
                                --Henry D. Thoreau

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

 
 
 

Athlon runtime problems

Post by Kurt Roeck » Mon, 16 Apr 2001 03:00:06



> Can the folks who are seeing crashes running athlon optimised kernels all mail
> me

Just trying to privide you with usefull info.  I'm NOT seeing any
crashes at all.

Quote:> -  CPU model/stepping

processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 6
model           : 4
model name      : AMD Athlon(tm) Processor
stepping        : 2
cpu MHz         : 807.190
cache size      : 256 KB

Quote:> -  Chipset

VIA KT133/KM133
(An Asus A7V)

Quote:> -  Amount of RAM

128 MiB

Quote:> -  /proc/mtrr output

No support for it compiled in.

Quote:> -  compiler used

gcc version 2.95.3 20010315 (release)
(compiled myself)

Kurt

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

 
 
 

Athlon runtime problems

Post by Jeff Lightfoo » Mon, 16 Apr 2001 05:20:06


[ sent to linux-kernel due to Alan rejecting all mail from
Earthlink/Mindspring, I'm assuming he is still interested in the
report though ]


Quote:> Can the folks who are seeing crashes running athlon optimised
> kernels all mail me

I have two Athlon machines with mysterious (no oops) lockups.  I've
just started running them as 586 to see if that stops the lockups.

The first one:

Quote:> -  CPU model/stepping

model           : 4
model name      : AMD Athlon(tm) Processor
stepping                : 2
cpu MHz : 1195.214

Quote:> -  Chipset

VIA KT133/KM133
(Iwill KK266)

Quote:> -  Amount of RAM

MemTotal:       770960 kB

Quote:> -  /proc/mtrr output

reg00: base=0x00000000 (   0MB), size= 512MB: write-back, count=1
reg01: base=0x20000000 ( 512MB), size= 256MB: write-back, count=1
reg02: base=0xd4000000 (3392MB), size=  32MB: write-combining, count=2
reg05: base=0xd0000000 (3328MB), size=  64MB: write-combining, count=2

Quote:> -  compiler used

gcc 2.95.4

The second one:

Quote:> -  CPU model/stepping

model           : 4
model name      : AMD Athlon(tm) Processor
stepping                : 2
cpu MHz : 1000.050

Quote:> -  Chipset

VIA KT133/KM133
(MSI K7TPro)

Quote:> -  Amount of RAM

MemTotal:       255588 kB

Quote:> -  /proc/mtrr output

reg00: base=0x00000000 (   0MB), size= 256MB: write-back, count=1
reg05: base=0xd0000000 (3328MB), size=  64MB: write-combining, count=1

Quote:> -  compiler used

gcc 2.95.4

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

 
 
 

Athlon runtime problems

Post by Moses Mcknigh » Mon, 16 Apr 2001 12:40:04



> Can the folks who are seeing crashes running athlon optimised kernels all mail
> me

> -  CPU model/stepping

AMD Athlon Thunderbird 850Mhz
Stepping - 2

Quote:> -  Chipset

VIA KT133A chipset, Iwill KK266 MB.
According to a couple other people this problem may only occur on this
motherboard.

Quote:> -  Amount of RAM

256 MB Corsair PC150

Quote:> -  /proc/mtrr output

reg: base=0x00000000 (   0MB), size= 256MB: write-back, count=1
reg: base=0xd5000000 (3408MB), size=  16MB: write-combining, count=1

Quote:> -  compiler used

2.95.3 - Debian unstable package.

Quote:

> Alan

When these errors occur, I never get to a shell prompt.  Is there a way
to save the errors or have them saved somewhere so I don't have to write
all that stuff down?  Also, how can I set the console buffer (what is it
called, where you can view previous screens with SHIFT + PgUP/DOWN?) to
hold more so I don't lose some of the errors?

Thanks,
Moses

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

 
 
 

Athlon runtime problems

Post by Disconnec » Mon, 16 Apr 2001 13:00:08


Quote:> Can the folks who are seeing crashes running athlon optimised kernels all mail
> me
> -  CPU model/stepping

vendor_id       : AuthenticAMD
cpu family      : 6
model           : 4
model name      : AMD Athlon(tm) Processor
stepping        : 2
cpu MHz         : 1202.743

(/proc/cpuinfo attached) 1.2G Tbird

Quote:> -  Chipset

Iwill KK266, VIA KT133

Quote:> -  Amount of RAM

512M PC133 amd-approved

Quote:> -  /proc/mtrr output

reg00: base=0x00000000 (   0MB), size= 512MB: write-back, count=1
reg01: base=0xd0000000 (3328MB), size=  64MB: write-combining, count=1
reg05: base=0xd8000000 (3456MB), size=  64MB: write-combining, count=1

(This is from inside X on a K6 kernel. I can try to save it out from the
K7 kernel if needed.)

Quote:> -  compiler used

gcc version 2.95.3 20010219 (prerelease)
debian gcc 2.95.3-5

---
   _.-=<Disconnect>=-._


 PGP Key given on Request  Or at least the Purple parts!

-----BEGIN GEEK CODE BLOCK-----
Version: 3.1 [www.ebb.org/ungeek]



------END GEEK CODE BLOCK------

  cpuinfo
< 1K Download
 
 
 

Athlon runtime problems

Post by David Smit » Tue, 17 Apr 2001 17:20:05


Quote:> Can the folks who are seeing crashes running athlon optimised kernels all
> mail me
> - CPU model/stepping

vendor_id       : AuthenticAMD
cpu family      : 6
model           : 4
model name      : AMD Athlon(tm) Processor
stepping        : 2
cpu MHz         : 902.064

thunderbird 900 (200 MHz FSB)

Quote:> - Chipset

IWill KK266R, VIA KT133A north, 686B south bridges. IDE RAID is disabled.

Quote:> - Amount of RAM

256 M generic pc100.

Quote:> - /proc/mtrr output

(while in X, with geforce2 card, and AGP aperature set to 128)
reg00: base=0x00000000 (   0MB), size= 256MB: write-back, count=1
reg01: base=0xd8000000 (3456MB), size=  32MB: write-combining, count=1
reg05: base=0xd0000000 (3328MB), size= 128MB: write-combining, count=1

Quote:> - compiler used

gcc version 2.95.4 20010319 (Debian prerelease)
debian gcc package version 1:2.95.3-7

Is there any other information I can provide?

I also seem to have a problem running 2.4.3 (official and ac1-6) kernels
without K7 optimizations, it locks up under I/O using several interrupts (no
IDE involved). I'll post a message about it when I can keep it up long enough
to get debugging information.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

 
 
 

Athlon runtime problems

Post by Network Administrat » Wed, 18 Apr 2001 09:00:11



> Can the folks who are seeing crashes running athlon optimised kernels all mail
> me

> -       CPU model/stepping

vendor_id      : AuthenticAMD
cpu family      : 6
model            : 4
model name   : AMD Athlon(tm) Processor
stepping         : 2
cpu MHz       : 1009.002
cache size      : 256 KB

Quote:> -       Chipset

Asus A7V133/WOA
VIA Technologies, Inc. VT8363/8365

Quote:> -       Amount of RAM

Mem:     525275136  469438464   55836672          0  179589120  221396992
-/+ buffers/cache:          68452352  456822784
Swap:             518180864          0  518180864

Quote:

> -       /proc/mtrr output

reg00: base=0x00000000 (   0MB), size= 512MB: write-back, count=1
reg01: base=0xe2000000 (3616MB), size=  32MB: write-combining, count=2
reg07: base=0xe4000000 (3648MB), size=  64MB: write-combining, count=1

Quote:

> -       compiler used

Tried both....
gcc-2.95.3
egcs-2.91.66

> Alan

> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/

--
Gary White                 Network Administrator

Voice 601-776-3355            Fax 601-776-2314

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

 
 
 

Athlon runtime problems

Post by Ray Sha » Wed, 18 Apr 2001 15:10:05


Quote:>CPU model/stepping

AMD Duron, 800mhz

Quote:>chipset

VIA KT-133; motherboard is an ABIT KT7A-RAID

Quote:>amount of RAM

256M, single PC-133 SDRAM

Quote:>/proc/mtrr output

reg00: base=0x00000000 (   0MB), size= 256MB: write-back, count=1
reg05: base=0xd0000000 (3328MB), size=  64MB: write-combining, count=1

Quote:>compiler used

gcc version 2.95.2

It seems to blow up when I'm doing something which probably wants lots
of memory, ie running X and opening up several mozilla windows (though
it still crashes while just running X, Enlightenment, and w3m in an
Eterm...but it does take a little longer, though still < 30 min.).

I went back to 2.2.18 and the crashing stopped.  I am using UDMA66 on
one of my drives, no DMA on the other two.

I haven't tried a non-Athlon optimised kernel, nor one with as few
options as possible; hopefully I will get the chance to do this soon.

--
--Ray

-----------------------------
Sotto la panca la capra crepa
sopra la panca la capra campa
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

 
 
 

1. Athlon + Athlon optimized kernel => _mmx_mmcpy problems

Hi,

I thought, as I have an Athlon, I should recompile my 2.4.18-ac3 kernel
for Athlon optimzied ... yadda ... but this causes serious problems.

After booting, it has quite a lot of depmod problems, with depmod -e it
shows all are '_mmx_mmcpy' and vmware can't compile, cause of the same
error.

so I had to go back to PIII style ... or I wouldn't have been able to
update vmware ... sad thing

--
"Der Krieg ist ein Massaker von Leuten, die sich nicht kennen, zum
Nutzen von Leuten, die sich kennen, aber nicht massakrieren"
- Paul Valry (1871-1945)
mfg, Clemens Schwaighofer                       PIXELWINGS Medien GMBH
Kandlgasse 15/5, A-1070 Wien                      T: [+43 1] 524 58 50
JETZT NEU! MIT FEWA GEWASCHEN       -->      http://www.pixelwings.com

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

2. bugs in drivers/ide/ide-pci.c and drivers/ide/hpt366.c prevents boot up with VIA KT266A chipsets

3. Athlon doesn't like Athlon optimisation?

4. message queue size limits?

5. 2.4.4 on Athlon/Duron compiled for Athlon/Duron

6. PNP SoundBlaster 16 with Pentium II PNP Bios?

7. 2.4 config giving -march=athlon for all athlons/durons

8. Bizzare Elm stuff...

9. Athlon: Try this (was: Re: Athlon bug stomping #2)

10. To athlon or not to athlon

11. Dual Athlon problem - random flaky problems

12. C++ Exception runtime problem

13. Help: Can different versions of C runtime cause problems with fopen?