| Re: [PATCH v6 3/8] foundations of per-cgroup memory pressure controlling. [message #43748 is a reply to message #43725] |
Thu, 13 October 2011 05:53   |
KAMEZAWA Hiroyuki
Messages: 463
Registered: September 2006
|
Senior Member |
|
|
On Mon, 10 Oct 2011 14:24:23 +0400
Glauber Costa <glommer@parallels.com> wrote:
> This patch converts struct sock fields memory_pressure,
> memory_allocated, sockets_allocated, and sysctl_mem (now prot_mem)
> to function pointers, receiving a struct mem_cgroup parameter.
>
> enter_memory_pressure is kept the same, since all its callers
> have socket a context, and the kmem_cgroup can be derived from
> the socket itself.
>
> To keep things working, the patch convert all users of those fields
> to use acessor functions.
>
> In my benchmarks I didn't see a significant performance difference
> with this patch applied compared to a baseline (around 1 % diff, thus
> inside error margin).
>
> Signed-off-by: Glauber Costa <glommer@parallels.com>
> CC: David S. Miller <davem@davemloft.net>
> CC: Hiroyouki Kamezawa <kamezawa.hiroyu@jp.fujitsu.com>
> CC: Eric W. Biederman <ebiederm@xmission.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
a nitpick.
> #ifdef CONFIG_INET
> +enum {
> + UNDER_LIMIT,
> + OVER_LIMIT,
> +};
> +
It may be better to move this to res_counter.h or memcontrol.h
|
|
|
|
OpenVZ Forum
Members
Search
Help
Register
Login
Home
