Re: [PATCH 0/6] mm/hugetlb: gigantic hugetlb page pools shrinksupporting

[Michal Hocko]

On Fri 05-04-13 16:27:59, Wanpeng Li wrote:
> On Fri, Apr 05, 2013 at 10:12:39AM +0200, Michal Hocko wrote:
> >On Fri 05-04-13 07:41:23, Wanpeng Li wrote:
> >> On Thu, Apr 04, 2013 at 06:17:46PM +0200, Michal Hocko wrote:
> >> >On Thu 04-04-13 17:09:08, Wanpeng Li wrote:
> >> >> order >= MAX_ORDER pages are only allocated at boot stage using the 
> >> >> bootmem allocator with the "hugepages=xxx" option. These pages are never 
> >> >> free after boot by default since it would be a one-way street(>= MAX_ORDER
> >> >> pages cannot be allocated later), but if administrator confirm not to 
> >> >> use these gigantic pages any more, these pinned pages will waste memory
> >> >> since other users can't grab free pages from gigantic hugetlb pool even
> >> >> if OOM, it's not flexible.  The patchset add hugetlb gigantic page pools
> >> >> shrink supporting. Administrator can enable knob exported in sysctl to
> >> >> permit to shrink gigantic hugetlb pool.
> >> >
> >> >I am not sure I see why the new knob is needed.
> >> >/sys/kernel/mm/hugepages/hugepages-*/nr_hugepages is root interface so
> >> >an additional step to allow writing to the file doesn't make much sense
> >> >to me to be honest.
> >> >
> >> >Support for shrinking gigantic huge pages makes some sense to me but I
> >> >would be interested in the real world example. GB pages are usually used
> >> >in very specific environments where the amount is usually well known.
> >> 
> >> Gigantic huge pages in hugetlb means h->order >= MAX_ORDER instead of GB 
> >> pages. ;-)
> >
> >Yes, I am aware of that but the question remains the same (and
> >unanswered). What is the use case?
> 
> The use case I can figure out is when memory pressure is serious and gigantic 
> huge pages pools still pin large number of free pages. 

Then this is a configuration issue. I understand that reboot is lame way
to fix it but the gigantic pages usage is so specific that I would be
really surprise if this kind of problem would pop out. I would also find
surprising if those pages were unused.

So the only use case I can figure out ATM is a hotplug scenario (after
hugetlb migration patchset is ready) but even then I would find it more
useful for in kernel usage (read hotplug).
-- 
Michal Hocko
SUSE Labs
--
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/