We have many servers here running 2.0.3x kernels. Most of these don't have
any problems at all, it is very seldom these hangs, even those under heavy
load. Exept all the terminal servers.
The difference between these is:
They mostly run ppp, sometimes slip
They use many serial ports
They do "slow" forwarding
They handle alot of interrups
If I compare this to the other people who have problems, I can only think
of the massive amount of interrupts. Here are two examples:
upime 21:22h:
# more /proc/interrupts
0: 7694854 timer
1: 528 keyboard
2: 0 cascade
4: 9515 + serial
5: 8173548 + serial
7: 9461273 + serial
9: 10002290 + serial
10: 1554783 DS21140 Tulip
13: 1 math error
14: 212553 + ide0
average 480 interrups/second
uptime 17:33h:
# more /proc/interrupts
0: 6322647 timer
1: 1210 keyboard
2: 0 cascade
3: 464915 + serial
5: 4386863 + serial
7: 4298928 + serial
9: 11915981 + serial
11: 936885 SMC EPIC/100
13: 1 math error
14: 267463 + ide0
average 450 interrupts/second.
Is there anyone that have much less amount of interrupts, but still
experience these hangs?
Due to the nature of these hangs I guess it can be:
During interrupt before new interrupts is enabeld.
Dead loop inside cli/sti.
Destroyed interrupt table.
/D.Ryde
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu