All interrupts going to CPU 1 on a Pentium D system

From: Mikhail Ramendik
Date: Wed Sep 07 2011 - 19:20:33 EST


ello,

I have a Pentium D system with a SiS 661FX chipset.

I found that most IRQs are always processed by CPU 1 only. This
happens even if I explicitly set the smp_ffinity value for the IRQ to
1, so it would be processed by CPU 0. This happens n both 2.6.32 and
3.0 kernels (Debian builds).

Is this normal? And can this be changed?

(I am debugging stability issues on this system; I don't know if they
can be linked to this).

$ cat /proc/interrupts
CPU0 CPU1
0: 41 1 IO-APIC-edge timer
1: 0 4 IO-APIC-edge i8042
3: 0 2 IO-APIC-edge
4: 0 2 IO-APIC-edge
6: 0 2 IO-APIC-edge floppy
7: 0 0 IO-APIC-edge parport0
8: 0 0 IO-APIC-edge rtc0
9: 0 0 IO-APIC-fasteoi acpi
12: 0 6 IO-APIC-edge i8042
14: 0 425 IO-APIC-edge pata_sis
15: 0 0 IO-APIC-edge pata_sis
17: 0 8086 IO-APIC-fasteoi sata_sis
18: 0 824 IO-APIC-fasteoi SiS SI7012, 0000:00:09.0
19: 0 0 IO-APIC-fasteoi saa7133[0], saa7133[0]
20: 0 183 IO-APIC-fasteoi ohci_hcd:usb2
21: 0 171 IO-APIC-fasteoi ohci_hcd:usb3
22: 0 0 IO-APIC-fasteoi ohci_hcd:usb4
23: 0 3 IO-APIC-fasteoi ehci_hcd:usb1
NMI: 0 0 Non-maskable interrupts
LOC: 6337 7518 Local timer interrupts
SPU: 0 0 Spurious interrupts
PMI: 0 0 Performance monitoring interrupts
IWI: 0 0 IRQ work interrupts
RES: 981 703 Rescheduling interrupts
CAL: 3511 578 Function call interrupts
TLB: 681 492 TLB shootdowns
TRM: 0 0 Thermal event interrupts
THR: 0 0 Threshold APIC interrupts
MCE: 0 0 Machine check exceptions
MCP: 1 1 Machine check polls
ERR: 0
MIS: 0

--
Yours, Mikhail Ramendik

Unless explicitly stated, all opinions in my mail are my own and do
not reflect the views of any organization
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/