Re: [PATCH v6 3/8] foundations of per-cgroup memory pressure controlling.
From: Glauber Costa <hidden>
Date: 2011-10-13 08:26:27
Also in:
lkml, netdev
On 10/13/2011 09:53 AM, KAMEZAWA Hiroyuki wrote:
On Mon, 10 Oct 2011 14:24:23 +0400 Glauber Costa[off-list ref] wrote:quoted
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<redacted> CC: David S. Miller<davem@davemloft.net> CC: Hiroyouki Kamezawa<redacted> CC: Eric W. Biederman<redacted>Reviewed-by: KAMEZAWA Hiroyuki<redacted> a nitpick.quoted
#ifdef CONFIG_INET +enum { + UNDER_LIMIT, + OVER_LIMIT, +}; +It may be better to move this to res_counter.h or memcontrol.h
Sorry Kame, It is in memcontrol.h already. What exactly do you mean here ? -- 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/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>