Messages in this thread | | | Date | Sat, 20 Dec 2014 08:40:56 -0800 | From | Dave Hansen <> | Subject | Re: [PATCH] proc: task_mmu: show page size in /proc/<pid>/numa_maps |
| |
On 12/20/2014 05:54 AM, Rafael Aquini wrote: > This patch introduces 'pagesize' line element to /proc/<pid>/numa_maps > report file in order to help disambiguating the size of pages that are > backing memory areas mapped by a task. When the VMA backing page size > is observed different from kernel's default PAGE_SIZE, the new element > is printed out to complement report output. This is specially useful to > help differentiating between HUGE and GIGANTIC page VMAs.
Heh, I completely forgot about this. Thanks for picking it back up.
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. :)
But that isn't the case for this patch. The "anon=50 dirty=50 N0=50" output of numa_maps is wholly *useless* without either this patch or some other mechanism to find out of hugetbfs memory is present. I think that needs to make it in to the description.
I'm fine with the code, though. Feel free to add my acked-by.
| |