Re: [PATCH v3] oom-kill: add lowmem usage aware oom kill handling

[David Rientjes]

On Wed, 27 Jan 2010, KAMEZAWA Hiroyuki wrote:

> Yes, I think you're right. But "breaking current behaviro of our servers!"
> arguments kills all proposal to this area and this oom-killer or vmscan is
> a feature should be tested by real users.

Nobody has said we should discount lowmem rss when dealing with a GFP_DMA 
allocation, it simply wasn't possible until the lowmem rss counters were 
introduced in -mm.  It would prevent the needless killing of innocent 
tasks which would not allow the page allocation to succeed, so it's a good 
feature to have.  It doesn't need to be configurable at all, we just need 
to find a way to introduce it into the heuristic without mangling oom_adj.
--
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/