Re: OOM kernel behaviour

[Jonathan Miles <jon@cybus.co.uk>]

On 01/12/09 16:08 Christoph Lameter said the following:

> Anonymous page use may fluctuate unpredictably based on the processes
> being started. A spike may take out your system.

I agree that swap should be there for these times. Once I'm happy that
the system behaves properly without it, I'll re-enable swap and set a
low swappiness value.

> The kernel will prefer to reclaim from clean page cache over
> swapping in general. The aggressiveness of swap can be controlled via
> /proc/sys/vm/swappiness.
> 
> The OOM killer output shows that the DMA is zone is marked as
> unreclaimable but the allocation causing it is not using DMA. Other zones
> all seem to have enough memory. Is this straight 2.6.31? No use of
> containers, memory policies etc right?

Okay, so my kernel shouldn't be behaving like this?

It's Ubuntu's (Karmic) 2.6.31 .deb and I don't know exactly what they've
done to it, but AFAIK, no containers or policies. I'll compile 2.6.31.6
and test with that. Won't be able to do this until Friday, so will check
back in then.

Thanks,

J