Messages in this thread | | | Date | Mon, 22 Dec 2014 14:27:39 -0800 (PST) | From | David Rientjes <> | Subject | Re: [PATCH] proc: task_mmu: show page size in /proc/<pid>/numa_maps |
| |
On Sat, 20 Dec 2014, Dave Hansen wrote:
> I sometimes wonder what 'numa_maps' purpose is any if we should have > _some_ kind of policy about what goes in there vs. smaps. numa_maps > seems to be turning in to smaps, minus the \n. :) >
It seems like an interface, similar to the one proposed by Ulrich, that described the NUMA topology would have obsoleted numa_maps and you could only rely on smaps to determine locality. There's existing userspace dependencies on numa_maps already, though, so owell.
I had to fix numa_maps output when autonuma was merged for a much more subtle difference at http://marc.info/?l=git-commits-head&m=139113691614467 so I know some people actually parse this and care quite a bit about its accuracy, it's a shame it can't be deprecated in favor of adding the necessary information to smaps.
| |