Gordon, Nov 29
ssh'd into the systems, and checked the interrupt rates With the "intcount" command.
On vipers, PC104/GPIO interrupt is number 25, GPIO 01.
On titans, PC104/GPIO interrupt is number 129, GPIO 17.
On vipers and titans, ttyS1 is irq 37, ttyS2 is irq 36.
On vipers, ttyS3 is interrupt 116.
On titans, ttyS3 is interrupt 122
Interrupts/second
DSM |
ttyS5-20, IRQ 3 |
PC104/GPIO |
ttyS2, IRQ 36 |
ttyS1, 37 |
ttyS3 116/122 |
USB |
kernel |
notes |
|---|---|---|---|---|---|---|---|---|
a1 |
150-900 |
150-900 |
20 |
3.2 |
20 |
1018 |
2.6.35.9-ael1-1-viper Sep 14 10:54:19 MDT 2012 |
1,3 |
a2 |
5.4 |
5.4 |
20 |
3 |
20 |
1019 |
2.6.35.9-ael1-1-viper Sep 14 10:54:19 MDT 2012 |
3 |
a3 |
18.8 |
18.8 |
20 |
2 |
|
13.4 |
2.6.35.9-ael1-2-titan Oct 13 12:45:33 MDT 2012 |
|
a4 |
|
|
20 |
3 |
4 |
13.4 |
2.6.35.9-ael1-2-titan Sep 14 11:29:27 MDT 2012 |
|
a5 |
2300-3900 |
2300-3900 |
20 |
3 |
20 |
1020 |
2.6.35.9-ael1-1-viper Oct 4 13:21:09 MDT 2012 |
1,3 |
a6 |
5.4 |
5.4 |
20 |
3 |
20 |
1044 |
2.6.35.9-ael1-1-viper Sep 14 10:54:19 MDT 2012 |
3 |
a7 |
|
|
20 |
2 |
4 |
15 |
2.6.35.9-ael1-2-titan Sep 14 11:29:27 MDT 2012 |
|
a8 |
1500-2550 |
1500-2550 |
20 |
2 |
20 |
1020 |
2.6.35.9-ael1-1-viper Sep 14 10:54:19 MDT 2012 |
1,3 |
a9 |
|
|
20 |
2 |
20 |
1020 |
2.6.35.9-ael1-1-viper Sep 14 10:54:19 MDT 2012 |
3 |
a10 |
|
|
20 |
13 |
20 |
1020 |
2.6.35.9-ael1-1-viper Sep 14 10:54:19 MDT 2012 |
3 |
a11 |
|
|
20 |
3 |
4 |
18.6 |
2.6.35.9-ael1-2-titan Sep 14 11:29:27 MDT 2012 |
|
a12 |
|
|
20 |
2 |
3 |
15.6 |
2.6.35.9-ael1-2-titan Sep 14 11:29:27 MDT 2012 |
|
a13 |
|
|
20 |
3 |
4 |
12.8 |
2.6.35.9-ael1-2-titan Sep 14 11:29:27 MDT 2012 |
|
a14 |
|
|
20 |
3 |
20 |
1020 |
2.6.35.9-ael1-1-viper Sep 14 10:54:19 MDT 2012 |
3 |
a15 |
|
|
20 |
3 |
4 |
13.2 |
2.6.35.9-ael1-2-titan Sep 14 11:29:27 MDT 2012 |
|
a16 |
|
|
20 |
3 |
4 |
13.4 |
2.6.35.9-ael1-2-titan Sep 14 11:29:27 MDT 2012 |
|
a17 |
|
|
20 |
3 |
4 |
18.2 |
2.6.35.9-ael1-2-titan Sep 14 11:29:27 MDT 2012 |
|
a18 |
|
|
20 |
3 |
4 |
13.8 |
2.6.35.9-ael1-2-titan Sep 14 11:29:27 MDT 2012 |
|
a19 |
|
|
20 |
3 |
4 |
14.6 |
2.6.35.9-ael1-2-titan Sep 14 11:29:27 MDT 2012 |
|
c20 |
52 |
52 |
3 |
2 |
20 |
7.2 |
2.6.35.9-ael1-1-viper Sep 14 10:54:19 MDT 2012 |
4 |
m21 |
350 |
6000-17500 |
3 |
21 |
20 |
14 |
2.6.35.9-ael1-1-viper Oct 3 12:12:46 MDT 2012 |
1,2,4 |
m22 |
64 |
64 |
2 |
3 |
|
3 |
2.6.35.9-ael1-2-titan Oct 2 21:50:26 MDT 2012 |
4 |
Notes:
1: These vipers have large pc104 interrupt rates. Occurs with both Sep 14 (a1,a8) and the Oct 4 (a5) kernels.
2: Not completely sure why on m21 the IRQ3 rate is less than the pc104 load. Perhaps that version of the pc104 irq routine exits if pending bits are 0.
3: High USB interrupts are seen on vipers with bluetooth radios interfaced via USB. High USB interrupts are not seen on Titans, even though on "A" site titans, USB serves both the bluetooth radios and flash drives. On "A" site Vipers, USB has only bluetooth radios. Viper USB driver is isp116x_hcd. Titan USB driver is ohci_hcd.
4: On c20,m21, m22, USB is used only for flash drives
The big question is why the huge PC104 interrupt rates on vipers at a1, a5, a8 and m21. Previously traced this to a floating CTS/RTS line, but I don't think that is the current reason. Saw high PC104 interrupt rate on m21 even with the ribbon cables disconnected from the Emerald headers! Will have to investigate those systems back in the lab.
The only titans with PC104 serial are a3 and m22. They're both OK.
Vipers at a2, a6 and c20 are OK.
USB info
The viper kernel has a patch to use an assembler delay function for the isp116x, and not the kernel ndelay() function. Don't think this is related though.
The driver code that sets up the interrupt, uses two configuration values, int_act_high and int_edge_triggered:
if (board->int_act_high)
val |= HCHWCFG_INT_POL;
if (board->int_edge_triggered)
val |= HCHWCFG_INT_TRIGGER;
The current isp116x, driver is configured for level triggered, active high interrupts. However, the setting for the corresponding GPIO interrupt is IORESOURCE_IRQ_HIGHEDGE. Maybe that's a problem.
