On Fri, Aug 28, 2015 at 07:13:22PM +0200, Michal Hocko wrote:
...

quoted

* If the allocation doesn't have __GFP_WAIT, direct reclaim is
  skipped.  If a process performs only speculative allocations, it can
  blow way past the high limit.  This is actually easily reproducible
  by simply doing "find /".  VFS tries speculative !__GFP_WAIT
  allocations first, so as long as there's memory which can be
  consumed without blocking, it can keep allocating memory regardless
  of the high limit.

It is a bit confusing that you are talking about direct reclaim but in
fact mean high limit reclaim. But yeah, you are right there is no
protection against GFP_NOWAIT allocations there.

Actually, memory.high by itself *is* the protection against GFP_NOWAIT
allocations, similarly to zone watermarks. W/o it we would have no other
choice but fail a GFP_NOWAIT allocation on hitting memory.max. One
should just set it so that

  memory.max - memory.high > [max sum size of !__GFP_WAIT allocations
                              that can normally occur in a row]

That being said, currently I don't see any point in making memory.high
!__GFP_WAIT-safe.

Thanks,
Vladimir

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>