panic: kmem_map too small
Stefan Bethke
stb at lassitu.de
Thu Oct 26 13:46:56 UTC 2006
Am 26.10.2006 um 15:37 schrieb Robert Watson:
> On Thu, 26 Oct 2006, Stefan Bethke wrote:
>
>> acpica 3024 159K 20026966
> ...
>> db> show uma
>> Zone Allocs Frees Used Cache
>> 64 9990754 9986054 4700 9980755
>
> Looks like acpica has gone crazy performing allocation/freeing at a
> very high rate, and that for some reason, UMA is failing to
> properly reuse/release memory. So there are two bugs/problems
> here: whatever is causing ACPI to behave this way, and then the
> fact that UMA is failing to deal properly with its misbehavior.
We had the machines running with ACPI disabled for a week or so, and
we were still getting these panics, but I'll disable it again in the
BIOS to make sure.
> Alternatively, that we have a bug in the way statistics are
> handled. If you can generate a coredump, it would be quite useful
> to be able to run umstat (src/tools/tools/umastat in HEAD) on it.
> The tool probably needs a bit of tweaking to run on the core dump
> -- in particular, the first and second arguments of kvm_open() need
> to be the name of the kernel and dumpfile, rather than NULL. This
> would help confirm what actual state UMA is in.
So far, the machines always just hang instead of dumping core; I'll
see if I can get them to write a dump. Can umastat be run against a
live kernel? Then I could try running it as a cron job to record
data up to just before the panic.
Stefan
--
Stefan Bethke <stb at lassitu.de> Fon +49 170 346 0140
More information about the freebsd-stable
mailing list