Comment 18 for bug 1497428

The newer kernel may have some change/fix that prevents this bug, as I haven't seen any reports of this (from google, at least) on any other kernel. Plus, the unusual requirement of the memory having to end at not a multiple of 2M.

> But the “Node 0 Normal” zone, judging from (start_pfn, start_pfn+spanned) spans 100000000-f18000000.
> The machine in question is a c4.8xlarge in EC2.

Awesome, I'll set up a vm with that flavor to see if I can reproduce this, or at least reproduce the problematic zone setup. Thanks!