Re: [patch 1/7 -mm] oom: filter tasks not sharing the same cpuset

[David Rientjes]

On Tue, 16 Feb 2010, Nick Piggin wrote:

> I don't really agree with your black and white view. We equally
> can't tell a lot of cases about who is pinning memory where. The
> fact is that any task can be pinning memory and the heuristic
> was specifically catering for that.
> 

That's a main source of criticism of the current heuristic: it needlessly 
kills tasks.  There is only one thing we know for certain: current is 
trying to allocate memory on its nodes.  We can either kill a task that 
is allowed that same set or current itself; there's no evidence that 
killing anything else will lead to memory freeing that will allow the 
allocation to succeed.  The heuristic will never perfectly select the task 
that it should kill 100% of the time when playing around with mempolicy 
nodes or cpuset mems, but relying on their current placement is a good 
indicator of what is more likely than not to free memory of interest.
--
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/