From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757438AbZCAGbA (ORCPT ); Sun, 1 Mar 2009 01:31:00 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754390AbZCAGaV (ORCPT ); Sun, 1 Mar 2009 01:30:21 -0500 Received: from e28smtp02.in.ibm.com ([59.145.155.2]:37607 "EHLO e28smtp02.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753288AbZCAGaT (ORCPT ); Sun, 1 Mar 2009 01:30:19 -0500 From: Balbir Singh To: linux-mm@kvack.org Cc: Sudhir Kumar , YAMAMOTO Takashi , Bharata B Rao , Paul Menage , lizf@cn.fujitsu.com, linux-kernel@vger.kernel.org, KOSAKI Motohiro , David Rientjes , Pavel Emelianov , Dhaval Giani , Balbir Singh , Rik van Riel , Andrew Morton , KAMEZAWA Hiroyuki Date: Sun, 01 Mar 2009 12:00:11 +0530 Message-Id: <20090301063011.31557.42094.sendpatchset@localhost.localdomain> In-Reply-To: <20090301062959.31557.31079.sendpatchset@localhost.localdomain> References: <20090301062959.31557.31079.sendpatchset@localhost.localdomain> Subject: [PATCH 2/4] Memory controller soft limit interface (v3) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Balbir Singh Changelog v2...v1 1. Add support for res_counter_check_soft_limit_locked. This is used by the hierarchy code. Add an interface to allow get/set of soft limits. Soft limits for memory plus swap controller (memsw) is currently not supported. Resource counters have been enhanced to support soft limits and new type RES_SOFT_LIMIT has been added. Unlike hard limits, soft limits can be directly set and do not need any reclaim or checks before setting them to a newer value. Kamezawa-San raised a question as to whether soft limit should belong to res_counter. Since all resources understand the basic concepts of hard and soft limits, it is justified to add soft limits here. Soft limits are a generic resource usage feature, even file system quotas support soft limits. Signed-off-by: Balbir Singh --- include/linux/res_counter.h | 47 +++++++++++++++++++++++++++++++++++++++++++ kernel/res_counter.c | 3 +++ mm/memcontrol.c | 20 ++++++++++++++++++ 3 files changed, 70 insertions(+), 0 deletions(-) diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 4c5bcf6..b5f14fa 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -35,6 +35,10 @@ struct res_counter { */ unsigned long long limit; /* + * the limit that usage can be exceed + */ + unsigned long long soft_limit; + /* * the number of unsuccessful attempts to consume the resource */ unsigned long long failcnt; @@ -85,6 +89,7 @@ enum { RES_MAX_USAGE, RES_LIMIT, RES_FAILCNT, + RES_SOFT_LIMIT, }; /* @@ -130,6 +135,36 @@ static inline bool res_counter_limit_check_locked(struct res_counter *cnt) return false; } +static inline bool res_counter_soft_limit_check_locked(struct res_counter *cnt) +{ + if (cnt->usage < cnt->soft_limit) + return true; + + return false; +} + +/** + * Get the difference between the usage and the soft limit + * @cnt: The counter + * + * Returns 0 if usage is less than or equal to soft limit + * The difference between usage and soft limit, otherwise. + */ +static inline unsigned long long +res_counter_soft_limit_excess(struct res_counter *cnt) +{ + unsigned long long excess; + unsigned long flags; + + spin_lock_irqsave(&cnt->lock, flags); + if (cnt->usage <= cnt->soft_limit) + excess = 0; + else + excess = cnt->usage - cnt->soft_limit; + spin_unlock_irqrestore(&cnt->lock, flags); + return excess; +} + /* * Helper function to detect if the cgroup is within it's limit or * not. It's currently called from cgroup_rss_prepare() @@ -178,4 +213,16 @@ static inline int res_counter_set_limit(struct res_counter *cnt, return ret; } +static inline int +res_counter_set_soft_limit(struct res_counter *cnt, + unsigned long long soft_limit) +{ + unsigned long flags; + + spin_lock_irqsave(&cnt->lock, flags); + cnt->soft_limit = soft_limit; + spin_unlock_irqrestore(&cnt->lock, flags); + return 0; +} + #endif diff --git a/kernel/res_counter.c b/kernel/res_counter.c index bf8e753..4e6dafe 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -19,6 +19,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent) { spin_lock_init(&counter->lock); counter->limit = (unsigned long long)LLONG_MAX; + counter->soft_limit = (unsigned long long)LLONG_MAX; counter->parent = parent; } @@ -101,6 +102,8 @@ res_counter_member(struct res_counter *counter, int member) return &counter->limit; case RES_FAILCNT: return &counter->failcnt; + case RES_SOFT_LIMIT: + return &counter->soft_limit; }; BUG(); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7bb14fd..75a7b1a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1939,6 +1939,20 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, else ret = mem_cgroup_resize_memsw_limit(memcg, val); break; + case RES_SOFT_LIMIT: + ret = res_counter_memparse_write_strategy(buffer, &val); + if (ret) + break; + /* + * For memsw, soft limits are hard to implement in terms + * of semantics, for now, we support soft limits for + * control without swap + */ + if (type == _MEM) + ret = res_counter_set_soft_limit(&memcg->res, val); + else + ret = -EINVAL; + break; default: ret = -EINVAL; /* should be BUG() ? */ break; @@ -2188,6 +2202,12 @@ static struct cftype mem_cgroup_files[] = { .read_u64 = mem_cgroup_read, }, { + .name = "soft_limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), + .write_string = mem_cgroup_write, + .read_u64 = mem_cgroup_read, + }, + { .name = "failcnt", .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), .trigger = mem_cgroup_reset, -- Balbir