On Tue, 23 Aug 2016, Michal Hocko wrote: > From: Michal Hocko <mho...@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. >
Since when has this been an issue? I don't believe it has been an issue in the past for any archs that don't use thp. > Signed-off-by: Michal Hocko <mho...@suse.com> > --- > mm/Kconfig | 9 ++++++++- > 1 file changed, 8 insertions(+), 1 deletion(-) > > diff --git a/mm/Kconfig b/mm/Kconfig > index 78a23c5c302d..0dff2f05b6d1 100644 > --- a/mm/Kconfig > +++ b/mm/Kconfig > @@ -262,7 +262,14 @@ config COMPACTION > select MIGRATION > depends on MMU > help > - Allows the compaction of memory for the allocation of huge pages. > + Compaction is the only memory management component to form > + high order (larger physically contiguous) memory blocks > + reliably. Page allocator relies on the compaction heavily and > + the lack of the feature can lead to unexpected OOM killer > + invocation for high order memory requests. You shouldnm't > + disable this option unless there is really a strong reason for > + it and then we are really interested to hear about that at > + linux...@kvack.org. > > # > # support for page migration This seems to strongly suggest that all kernels should be built with CONFIG_COMPACTION and its requirement, CONFIG_MIGRATION. Migration has a dependency of NUMA or memory hot-remove (not all popular). Compaction can defragment memory within single zone without reliance on NUMA. This seems like a very bizarre requirement and I'm wondering where we regressed from this thp-only behavior.
