linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <brouer@redhat.com>
To: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: linux-mm@kvack.org, Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Christoph Lameter <cl@linux.com>,
	brouer@redhat.com
Subject: Re: [PATCH V2 2/2] slub: add missing kmem cgroup support to kmem_cache_free_bulk
Date: Sat, 7 Nov 2015 17:53:38 +0100	[thread overview]
Message-ID: <20151107175338.12a0368b@redhat.com> (raw)
In-Reply-To: <20151105162514.GI29259@esperanza>

On Thu, 5 Nov 2015 19:25:14 +0300
Vladimir Davydov <vdavydov@virtuozzo.com> wrote:

> On Thu, Nov 05, 2015 at 04:38:06PM +0100, Jesper Dangaard Brouer wrote:
> > Initial implementation missed support for kmem cgroup support
> > in kmem_cache_free_bulk() call, add this.
> > 
> > If CONFIG_MEMCG_KMEM is not enabled, the compiler should
> > be smart enough to not add any asm code.
> > 
> > Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
> > 
> > ---
> > V2: Fixes according to input from:
> >  Vladimir Davydov <vdavydov@virtuozzo.com>
> >  and Joonsoo Kim <iamjoonsoo.kim@lge.com>
> > 
> >  mm/slub.c |    3 +++
> >  1 file changed, 3 insertions(+)
> > 
> > diff --git a/mm/slub.c b/mm/slub.c
> > index 8e9e9b2ee6f3..bc64514ad1bb 100644
> > --- a/mm/slub.c
> > +++ b/mm/slub.c
> > @@ -2890,6 +2890,9 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
> >  	do {
> >  		struct detached_freelist df;
> >  
> > +		/* Support for memcg */
> > +		s = cache_from_obj(s, p[size - 1]);
> > +
> 
> AFAIU all objects in the array should come from the same cache (should
> they?), so it should be enough to call this only once:

Can we be sure all objects in the array come from same cache?

Imagine my use case:
 1. application send packet alloc a SKB (from a slab)
 2. packet TX to NIC via DMA
 3. TX DMA completion cleans up 256 packets and kmem free SKBs

I don't know enough about mem cgroups... but I can imagine two
applications belonging to different mem-cgroups sending packet out same
NIC and later getting their SKB (pkt-metadata struct) free'ed during
the same TX completion (TX softirq) cycle, as a bulk free.

With my limited mem cgroups, it looks like memcg works on the slab-page
level?  And what I'm doing in this code is to group object together
belonging to the same slab-page.

-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  Author of http://www.iptv-analyzer.org
  LinkedIn: http://www.linkedin.com/in/brouer

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2015-11-07 16:53 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-05 15:37 [PATCH V2 0/2] SLUB bulk API interactions with kmem cgroup Jesper Dangaard Brouer
2015-11-05 15:37 ` [PATCH V2 1/2] slub: fix kmem cgroup bug in kmem_cache_alloc_bulk Jesper Dangaard Brouer
2015-11-05 16:18   ` Vladimir Davydov
2015-11-07 16:40     ` Jesper Dangaard Brouer
2015-11-05 15:38 ` [PATCH V2 2/2] slub: add missing kmem cgroup support to kmem_cache_free_bulk Jesper Dangaard Brouer
2015-11-05 16:25   ` Vladimir Davydov
2015-11-07 16:53     ` Jesper Dangaard Brouer [this message]
2015-11-07 20:25       ` Vladimir Davydov
2015-11-07 20:55         ` Christoph Lameter
2015-11-09 16:39         ` Jesper Dangaard Brouer
2015-11-09 18:38           ` Vladimir Davydov
2015-11-05 16:10 ` [PATCH V2 0/2] SLUB bulk API interactions with kmem cgroup Vladimir Davydov
2015-11-09 18:16   ` [PATCH V3 " Jesper Dangaard Brouer
2015-11-09 18:17     ` [PATCH V3 1/2] slub: fix kmem cgroup bug in kmem_cache_alloc_bulk Jesper Dangaard Brouer
2015-11-09 19:13       ` Vladimir Davydov
2015-11-09 20:25         ` Jesper Dangaard Brouer
2015-11-10  8:46           ` Vladimir Davydov
2015-11-10 15:55             ` Jesper Dangaard Brouer
2015-11-10 16:17               ` Christoph Lameter
2015-11-10 18:32               ` Vladimir Davydov
2015-11-11 15:28                 ` Jesper Dangaard Brouer
2015-11-11 18:30                   ` Jesper Dangaard Brouer
2015-11-11 18:56                     ` Vladimir Davydov
2015-11-12 14:27                       ` Jesper Dangaard Brouer
2015-11-09 22:04         ` Christoph Lameter
2015-11-10  8:30           ` Vladimir Davydov
2015-11-10 15:23             ` Christoph Lameter
2015-11-09 18:17     ` [PATCH V3 2/2] slub: add missing kmem cgroup support to kmem_cache_free_bulk Jesper Dangaard Brouer
2015-11-09 18:56       ` Vladimir Davydov
2015-11-13 10:57   ` [PATCH V4 0/2] SLUB bulk API interactions with kmem cgroup Jesper Dangaard Brouer
2015-11-13 10:57     ` [PATCH V4 1/2] slub: fix kmem cgroup bug in kmem_cache_alloc_bulk Jesper Dangaard Brouer
2015-11-14 11:04       ` Vladimir Davydov
2015-11-13 10:57     ` [PATCH V4 2/2] slub: add missing kmem cgroup support to kmem_cache_free_bulk Jesper Dangaard Brouer

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20151107175338.12a0368b@redhat.com \
    --to=brouer@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=cl@linux.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-mm@kvack.org \
    --cc=vdavydov@virtuozzo.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).