On Tue, Jun 19, 2018 at 12:27:41PM -0400, Johannes Weiner wrote:
> On Mon, Jun 18, 2018 at 10:13:27PM -0700, Shakeel Butt wrote:
> > The buffer_head can consume a significant amount of system memory and
> > is directly related to the amount of page cache. In our production
> > environment we have observed that a lot of machines are spending a
> > significant amount of memory as buffer_head and can not be left as
> > system memory overhead.
> >
> > Charging buffer_head is not as simple as adding __GFP_ACCOUNT to the
> > allocation. The buffer_heads can be allocated in a memcg different from
> > the memcg of the page for which buffer_heads are being allocated. One
> > concrete example is memory reclaim. The reclaim can trigger I/O of pages
> > of any memcg on the system. So, the right way to charge buffer_head is
> > to extract the memcg from the page for which buffer_heads are being
> > allocated and then use targeted memcg charging API.
> >
> > Signed-off-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
> > Cc: Jan Kara <jack@xxxxxxx>
> > Cc: Greg Thelen <gthelen@xxxxxxxxxx>
> > Cc: Michal Hocko <mhocko@xxxxxxxxxx>
> > Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
> > Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
> > Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
> > Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> > ---
> > fs/buffer.c | 14 +++++++++++++-
> > include/linux/memcontrol.h | 7 +++++++
> > mm/memcontrol.c | 21 +++++++++++++++++++++
> > 3 files changed, 41 insertions(+), 1 deletion(-)
> >
> > diff --git a/fs/buffer.c b/fs/buffer.c
> > index 8194e3049fc5..26389b7a3cab 100644
> > --- a/fs/buffer.c
> > +++ b/fs/buffer.c
> > @@ -815,10 +815,17 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
> > struct buffer_head *bh, *head;
> > gfp_t gfp = GFP_NOFS;
> > long offset;
> > + struct mem_cgroup *old_memcg;
> > + struct mem_cgroup *memcg = get_mem_cgroup_from_page(page);
> >
> > if (retry)
> > gfp |= __GFP_NOFAIL;
> >
> > + if (memcg) {
> > + gfp |= __GFP_ACCOUNT;
> > + old_memcg = memalloc_memcg_save(memcg);
> > + }
>
> Please move the get_mem_cgroup_from_page() call out of the
> declarations and down to right before the if (memcg) branch.
>
> > head = NULL;
> > offset = PAGE_SIZE;
> > while ((offset -= size) >= 0) {
> > @@ -835,6 +842,11 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
> > /* Link the buffer to its page */
> > set_bh_page(bh, page, offset);
> > }
> > +out:
> > + if (memcg) {
> > + memalloc_memcg_restore(old_memcg);
> > +#ifdef CONFIG_MEMCG
> > + css_put(&memcg->css);
> > +#endif
>
> Please add a put_mem_cgroup() ;)
I've added such helper by commit 8a34a8b7fd62 ("mm, oom: cgroup-aware OOM killer").
It's in the mm tree.
Thanks!
--
To unsubscribe from this list: send the line "unsubscribe cgroups" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
