[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-Id: <20180629.215705.881234148380578564.davem@davemloft.net>
Date: Fri, 29 Jun 2018 21:57:05 +0900 (KST)
From: David Miller <davem@...emloft.net>
To: shakeelb@...gle.com
Cc: akpm@...ux-foundation.org, hannes@...xchg.org,
vdavydov.dev@...il.com, gthelen@...gle.com, guro@...com,
edumazet@...gle.com, ktkhai@...tuozzo.com,
linux-kernel@...r.kernel.org, netdev@...r.kernel.org,
linux-mm@...ck.org
Subject: Re: [PATCH v2] net, mm: account sock objects to kmemcg
From: Shakeel Butt <shakeelb@...gle.com>
Date: Wed, 27 Jun 2018 15:16:42 -0700
> Currently the kernel accounts the memory for network traffic through
> mem_cgroup_[un]charge_skmem() interface. However the memory accounted
> only includes the truesize of sk_buff which does not include the size of
> sock objects. In our production environment, with opt-out kmem
> accounting, the sock kmem caches (TCP[v6], UDP[v6], RAW[v6], UNIX) are
> among the top most charged kmem caches and consume a significant amount
> of memory which can not be left as system overhead. So, this patch
> converts the kmem caches of all sock objects to SLAB_ACCOUNT.
>
> Signed-off-by: Shakeel Butt <shakeelb@...gle.com>
> Suggested-by: Eric Dumazet <edumazet@...gle.com>
> ---
> Changelog since v1:
> - Instead of specific sock kmem_caches, convert all sock kmem_caches to
> use SLAB_ACCOUNT.
Applied, thank you.
Powered by blists - more mailing lists