Re: [PATCH] mm: clarify COMPACTION Kconfig text

[Michal Hocko <mhocko@kernel.org>]

On Mon 29-08-16 10:10:45, Johannes Weiner wrote:
> On Tue, Aug 23, 2016 at 10:09:17AM +0200, Michal Hocko wrote:
> > From: Michal Hocko <mhocko@suse.com>
> > 
> > The current wording of the COMPACTION Kconfig help text doesn't
> > emphasise that disabling COMPACTION might cripple the page allocator
> > which relies on the compaction quite heavily for high order requests and
> > an unexpected OOM can happen with the lack of compaction. Make sure
> > we are vocal about that.
> 
> I find it weird to even have this as a config option after we removed
> lumpy reclaim. Why offer a configuration that may easily OOM on allocs
> that we don't even consider "costly" to generate? There might be some
> specialized setups that know they can live without the higher-order
> allocations and rather have the savings in kernel size, but I'd argue
> that for the vast majority of Linux setups compaction is an essential
> part of our VM at this point. Seems like a candidate for EXPERT to me.

I was thinking about making it depend on EXPERT as well but then I just
felt like making the text more verbose should be sufficient. If somebody
runs a kernel without COMPACTION and doesn't see any issues then why
should we make life harder for him. But I was thinking about a different
thing. We should warn that the compaction is disabled when the oom
killer hits for higher order. What do you think?
--- 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 10f686969fc4..b3c47072a206 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -406,6 +406,8 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 	pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n",
 		current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order,
 		current->signal->oom_score_adj);
+	if (!IS_ENABLED(COMPACTION) && oc->order)
+		pr_warn("COMPACTION is disabled!!!\n");
 
 	cpuset_print_current_mems_allowed();
 	dump_stack();

-- 
Michal Hocko
SUSE Labs