On Tue, 25 Sep 2007, David Rientjes wrote:

	void dump_tasks(const struct mem_cgroup *mem)
	{
		struct task_struct *g, *p;

		do_each_thread(g, p) {
			...

			if (!task_in_mem_cgroup(p, mem)
				continue;
			if (!cpuset_mems_allowed_intersects(current, p))
				continue;

			/* show the task information */

		} while_each_thread(g, p);
	}

By the way, the only reason I didn't code it like this was because tasks 
that overlap nodes in mems_allowed with the OOM-triggering task aren't 
necessarily excluded from being OOM killed, as I mentioned.  In other 
words, coding it like the above opens up the possibility of filtering the 
task that ends up getting killed.  Not a good idea.

Tasks that aren't in the same mem_cgroup, however, are filtered from the 
dump because they are explicitly excluded from being a target.  The check 
for that is actually misplaced and currently appears in badness() when it 
should appear in select_bad_process().

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>