bug?: strange behaviour with memory hogs and 2.6.9-rc3

[Chris Friesen]

I'm running 2.6.9-rc3 with 2GB of ram.

I've got a test app that loops allocating chunks of memory 60 pages at a time, 
scribbles on each page, and mlock()s it, for a total of about a gig and a half. 
 It then sleeps for 100 seconds, and exits.

I ran one instance fine.

I ran the second instance, and userspace locked up.  The machine still responds 
to pings, but no userspace stuff works.

It's been about 10 minutes, and userspace still hasn't come back.

Obviously I'm out of memory, but I would have expected that the oom killer would 
wake up or something.

Anyone have any ideas?

Chris
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/