Hello Everyone,
I have been trying to track down a problem with my TDM2400p card for a few weeks now. Ive gotten very close, but im still unable to find a solution.
I have found in the /var/log/messages log that every 15 minutes and 4 seconds, something causes causes a missed interrupt in the wctdm24xxp driver.
Nov 15 11:33:52 localhost kernel: wctdm24xxp 0000:03:03.0: Missed interrupt. Increasing latency to 15 ms in order to compensate.
Nov 15 11:48:47 localhost kernel: wctdm24xxp 0000:03:03.0: Missed interrupt. Increasing latency to 21 ms in order to compensate.
Nov 15 12:03:43 localhost kernel: wctdm24xxp 0000:03:03.0: ERROR: Unable to service card within 25 ms and unable to further increase latency.
The car is on acpi interrupt #72. This was a battle to get it this low. It was originally on 209.
[root@localhost ~]# cat /proc/interrupts
CPU0 CPU1 CPU2 CPU3
0: 133 2 3 4 IO-APIC-edge timer
1: 4 2 2 1 IO-APIC-edge i8042
8: 0 0 0 1 IO-APIC-edge rtc0
9: 0 0 0 0 IO-APIC-fasteoi acpi
12: 0 1 1 2 IO-APIC-edge i8042
14: 40 45 32 38 IO-APIC-edge ata_piix
15: 0 0 0 0 IO-APIC-edge ata_piix
16: 36759 36511 36788 37111 IO-APIC-fasteoi uhci_hcd:usb2, eth0
19: 12 16 14 11 IO-APIC-fasteoi uhci_hcd:usb3
20: 178 155 174 173 IO-APIC-fasteoi radeon
23: 1 1 1 0 IO-APIC-fasteoi ehci_hcd:usb1
38: 3547 3602 3496 3620 IO-APIC-fasteoi ips
72: 975567 975774 975600 975148 IO-APIC-fasteoi wctdm24xxp0
NMI: 1 1 1 1 Non-maskable interrupts
LOC: 208050 220966 210407 268246 Local timer interrupts
SPU: 0 0 0 0 Spurious interrupts
PMI: 1 1 1 1 Performance monitoring interrupts
PND: 0 0 0 0 Performance pending work
RES: 2287 1885 2991 3349 Rescheduling interrupts
CAL: 4634 3555 172 171 Function call interrupts
TLB: 2607 4519 5950 5632 TLB shootdowns
TRM: 0 0 0 0 Thermal event interrupts
THR: 0 0 0 0 Threshold APIC interrupts
MCE: 0 0 0 0 Machine check exceptions
MCP: 14 14 14 14 Machine check polls
ERR: 0
MIS: 0
For simple testing I stopped all cron jobs temporarily with service crond stop.
Here is the output of dahdi_test:
99.997% 99.997% 96.290% 99.999% 99.998% 99.998% 99.998% 99.997%
99.998% 99.998% 99.998% 99.998% 99.999% 99.998% 99.998% 99.998%
99.998% 99.998% 99.998% 99.998% 99.998% 99.999% 99.999% 100.000%
99.998% 96.290%99.999% 99.999% ^C
— Results after 1211 passes —
Best: 100.000% – Worst: 95.705% – Average: 99.990554%
Cummulative Accuracy (not per pass): 99.995
You can see the 1 dip at the end of 96.290. This was with crond off.
I am running the 64 bit distro. Version Stable-1.1010.210.62
Does anybody have any idea what could be running everything 15 minutes that would cause this?
-Adam