Messages in this thread | | | From | David Laight <> | Subject | Repeated 'watchdog soft lockup' messages | Date | Thu, 12 Nov 2020 10:50:24 +0000 |
| |
Due to a coding fubar (in my own driver) I managed to sleep a process that held a spinlock. Unluckily all 8 cpus ended up trying to acquire the spinlock before the process woke. As might be expected the system froze.
I'd got a serial console connected so could see the kernel messages. It was almost continuously generating output saying that each cpu was 'stuck for 22s!' (sometimes 23s).
What I don't understand is what was resetting the watchdog so that I got multiple messages for each cpu at intervals of (typically) 28 seconds.
The watchdog code seems to only output the trace once. But that clearly wasn't working. Any idea why?
kernel is 5.9.0
David
- Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK Registration No: 1397386 (Wales)
| |