I don't think anybody has a good solution to that. I've never heard of
any, at least.
Right now we kill "random" stuff, although obviously statistical
probability tends to mean that if we have a high rate of page allocations
from some process then that process gets killed (during my tests the
system actually always killed the right process, but that was done by
having a process that rapidly ate lots of memory).
Linus
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/