public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* APIC revisited
@ 2001-10-01 22:56 Rinaldi J. Montessi
  2001-10-01 22:59 ` Benjamin LaHaise
  2001-10-02  2:01 ` Keith Owens
  0 siblings, 2 replies; 3+ messages in thread
From: Rinaldi J. Montessi @ 2001-10-01 22:56 UTC (permalink / raw)
  To: linux-kernel

I realize that this is a FAQ item, but the information contained therein
is a bit sparse.  I have an Abitbp6 motherboard with dual celerons 533's
not overclocked.  The bus is 66mhz.

My boot params are (from dmesg)

Kernel command line: BOOT_IMAGE=linux2410 ro root=2203
BOOT_FILE=/boot/vmlinuz-2.4.10 hdc=ide-scsi noapic

The BIOS is set for MPS 1.1

These are both recommended in the FAQ (as is trashing the Abit mobo, but
that is not feasible at the present time).

I am of the impression that with the noapic parameter all calls are to
be handled via CPU0, yet I am getting several errors on CPU1 as well. 

uptime
4:28pm  up 4 days, 17:50,  4 users,  load average: 0.00, 0.00, 0.00

/proc/interrupts

           CPU0       CPU1       
  0:   40989069          0          XT-PIC  timer
  1:      64603          0          XT-PIC  keyboard
  2:          0          0          XT-PIC  cascade
  3:     663114          0          XT-PIC  eth1
  7:     230556          0          XT-PIC  soundblaster
  8:          1          0          XT-PIC  rtc
  9:       2735          0          XT-PIC  eth0
 10:     720950          0          XT-PIC  ide2, ide3
 12:    2096913          0          XT-PIC  PS/2 Mouse
 14:     705487          0          XT-PIC  ide0
 15:          5          0          XT-PIC  ide1
NMI:          0          0 
LOC:   40988011   40988007 
ERR:         97
MIS:          0

The errors are fairly divided between CPU0 and CPU1 54/43 per dmesg,
although this seems to indicate otherwise.

The last series of errors is fairly representative:

APIC error on CPU0: 02(04)
APIC error on CPU1: 04(08)
APIC error on CPU1: 08(08)
APIC error on CPU0: 04(04)
APIC error on CPU0: 04(02)
APIC error on CPU0: 02(02)

Can I assume there is no kernel solution to this problem; and is there a
way for me to quantify potential/probable file corruption?

Thanks,

Rinaldi
-- 
By all means marry. If you get a good wife you will become happy, 
and if you get a bad one you will become a philosopher. --Socrates

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: APIC revisited
  2001-10-01 22:56 APIC revisited Rinaldi J. Montessi
@ 2001-10-01 22:59 ` Benjamin LaHaise
  2001-10-02  2:01 ` Keith Owens
  1 sibling, 0 replies; 3+ messages in thread
From: Benjamin LaHaise @ 2001-10-01 22:59 UTC (permalink / raw)
  To: Rinaldi J. Montessi; +Cc: linux-kernel

On Mon, Oct 01, 2001 at 06:56:16PM -0400, Rinaldi J. Montessi wrote:
> I realize that this is a FAQ item, but the information contained therein
> is a bit sparse.  I have an Abitbp6 motherboard with dual celerons 533's
> not overclocked.  The bus is 66mhz.

This is a BP6 FAQ.  Try increasing the voltage to your CPUs by .1V, or 
by taking the BP6 and introducing it to a hammer.  Either should be an 
improvement.

		-ben (ex-BP6 user)

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: APIC revisited
  2001-10-01 22:56 APIC revisited Rinaldi J. Montessi
  2001-10-01 22:59 ` Benjamin LaHaise
@ 2001-10-02  2:01 ` Keith Owens
  1 sibling, 0 replies; 3+ messages in thread
From: Keith Owens @ 2001-10-02  2:01 UTC (permalink / raw)
  To: Rinaldi J. Montessi; +Cc: linux-kernel

On Mon, 01 Oct 2001 18:56:16 -0400, 
"Rinaldi J. Montessi" <rinaldij@adelphia.net> wrote:
>I am of the impression that with the noapic parameter all calls are to
>be handled via CPU0, yet I am getting several errors on CPU1 as well. 

noapic only affects external internal interrupts.  Inter processor
interrupts (IPIs) always use the APIC bus.  Ix86 SMP does a lot of
IPIs.


^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2001-10-02  2:01 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2001-10-01 22:56 APIC revisited Rinaldi J. Montessi
2001-10-01 22:59 ` Benjamin LaHaise
2001-10-02  2:01 ` Keith Owens

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox