lkml.org 
[lkml]   [2014]   [Dec]   [20]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] proc: task_mmu: show page size in /proc/<pid>/numa_maps
On Sat, Dec 20, 2014 at 01:36:13PM -0500, Johannes Weiner wrote:
> On Sat, Dec 20, 2014 at 08:54:45AM -0500, 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.
> >
> > This patch is based on Dave Hansen's proposal and reviewer's follow ups
> > taken from this dicussion: https://lkml.org/lkml/2011/9/21/454
> >
> > Signed-off-by: Rafael Aquini <aquini@redhat.com>
> > ---
> > fs/proc/task_mmu.c | 5 +++++
> > 1 file changed, 5 insertions(+)
> >
> > diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> > index 246eae8..9f2e2c8 100644
> > --- a/fs/proc/task_mmu.c
> > +++ b/fs/proc/task_mmu.c
> > @@ -1479,6 +1479,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
> > struct mm_struct *mm = vma->vm_mm;
> > struct mm_walk walk = {};
> > struct mempolicy *pol;
> > + unsigned long page_size;
> > char buffer[64];
> > int nid;
> >
> > @@ -1533,6 +1534,10 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
> > if (!md->pages)
> > goto out;
> >
> > + page_size = vma_kernel_pagesize(vma);
> > + if (page_size != PAGE_SIZE)
> > + seq_printf(m, " pagesize=%lu", page_size);
>
> It would be simpler to include this unconditionally. Otherwise you
> are forcing everybody parsing the file and trying to run calculations
> of it to check for its presence, and then have them fall back and get
> the value from somewhere else if not.

I'm fine either way, it makes the change even simpler. Also, if we
decide to get rid of page_size != PAGE_SIZE condition I believe we can
also get rid of that "huge" hint being conditionally printed out too.

-- Rafael


\
 
 \ /
  Last update: 2014-12-20 21:21    [W:0.059 / U:0.932 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site