On Wed, Oct 16, 2013 at 06:11:56PM -0700, David Rientjes wrote:
> On Wed, 16 Oct 2013, Mel Gorman wrote:
>
> > It has been reported on very large machines that show_mem is taking almost
> > 5 minutes to display information. This is a serious problem if there is
> > an OOM storm. The bulk of the cost is in show_mem doing a very expensive
> > PFN walk to give us the following information
> >
> > Total RAM: Also available as totalram_pages
> > Highmem pages: Also available as totalhigh_pages
> > Reserved pages: Can be inferred from the zone structure
> > Shared pages: PFN walk required
> > Unshared pages: PFN walk required
> > Quick pages: Per-cpu walk required
> >
> > Only the shared/unshared pages requires a full PFN walk but that information
> > is useless. It is also inaccurate as page pins of unshared pages would
> > be accounted for as shared. Even if the information was accurate, I'm
> > struggling to think how the shared/unshared information could be useful
> > for debugging OOM conditions. Maybe it was useful before rmap existed when
> > reclaiming shared pages was costly but it is less relevant today.
> >
> > The PFN walk could be optimised a bit but why bother as the information is
> > useless. This patch deletes the PFN walker and infers the total RAM, highmem
> > and reserved pages count from struct zone. It omits the shared/unshared page
> > usage on the grounds that it is useless. It also corrects the reporting
> > of HighMem as HighMem/MovableOnly as ZONE_MOVABLE has similar problems to
> > HighMem with respect to lowmem/highmem exhaustion.
> >
>
> We haven't been hit by this for the oom killer, but we did get hit with
> this for page allocation failure warnings as a result of having irqs
> disabled and passing GFP_ATOMIC to the page allocator without GFP_NOWARN.
> That was the intention of passing SHOW_MEM_FILTER_PAGE_COUNT into
> show_mem() in 4b59e6c47309 ("mm, show_mem: suppress page counts in
> non-blockable contexts").
>
> With this, I assume we can just remove SHOW_MEM_FILTER_PAGE_COUNT
> entirely?
We could once all the per-arch show_mem functions were updated similar
to lib/show_mem.c. I've added a todo item to do just that. Thanks.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>