Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757546AbZAVJjh (ORCPT ); Thu, 22 Jan 2009 04:39:37 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754820AbZAVJj2 (ORCPT ); Thu, 22 Jan 2009 04:39:28 -0500 Received: from fgwmail6.fujitsu.co.jp ([192.51.44.36]:49831 "EHLO fgwmail6.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754793AbZAVJj1 (ORCPT ); Thu, 22 Jan 2009 04:39:27 -0500 Date: Thu, 22 Jan 2009 18:38:20 +0900 From: KAMEZAWA Hiroyuki To: KAMEZAWA Hiroyuki Cc: "linux-mm@kvack.org" , "menage@google.com" , "lizf@cn.fujitsu.com" , "balbir@linux.vnet.ibm.com" , "nishimura@mxp.nes.nec.co.jp" , "linux-kernel@vger.kernel.org" Subject: [FIX][PATCH 4/7] memcg : make set_limit return -EBUSY after reasonable retries Message-Id: <20090122183820.83aefb55.kamezawa.hiroyu@jp.fujitsu.com> In-Reply-To: <20090122183411.3cabdfd2.kamezawa.hiroyu@jp.fujitsu.com> References: <20090122183411.3cabdfd2.kamezawa.hiroyu@jp.fujitsu.com> Organization: FUJITSU Co. LTD. X-Mailer: Sylpheed 2.5.0 (GTK+ 2.10.14; i686-pc-mingw32) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6296 Lines: 189 From: KAMEZAWA Hiroyuki As pointed out, shrinking memcg's limit should return -EBUSY after reasonable retries. This patch tries to fix the current behavior of shrink_usage. Before looking into "shrink should return -EBUSY" problem, we should fix hierarchical reclaim code. It compares current usage and current limit, but it only makes sense when the kernel reclaims memory because hit limits. This is also a problem. What this patch does are. 1. add new argument "shrink" to hierarchical reclaim. If "shrink==true", hierarchical reclaim returns immediately and the caller checks the kernel should shrink more or not. (At shrinking memory, usage is always smaller than limit. So check for usage < limit is useless.) 2. For adjusting to above change, 2 changes in "shrink"'s retry path. 2-a. retry_count depends on # of children because the kernel visits the children under hierarchy one by one. 2-b. rather than checking return value of hierarchical_reclaim's progress, compares usage-before-shrink and usage-after-shrink. If usage-before-shrink <= usage-after-shrink, retry_count is decremented. Reported-by: Li Zefan Signed-off-by: KAMEZAWA Hiroyuki --- mm/memcontrol.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 59 insertions(+), 12 deletions(-) Index: mmotm-2.6.29-Jan16/mm/memcontrol.c =================================================================== --- mmotm-2.6.29-Jan16.orig/mm/memcontrol.c +++ mmotm-2.6.29-Jan16/mm/memcontrol.c @@ -702,6 +702,23 @@ static unsigned int get_swappiness(struc return swappiness; } +static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data) +{ + int *val = data; + (*val)++; + return 0; +} +/* + * This function returns the number of memcg under hierarchy tree. Returns + * 1(self count) if no children. + */ +static int mem_cgroup_count_children(struct mem_cgroup *mem) +{ + int num = 0; + mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb); + return num; +} + /* * Visit the first child (need not be the first child as per the ordering * of the cgroup list, since we track last_scanned_child) of @mem and use @@ -750,9 +767,11 @@ mem_cgroup_select_victim(struct mem_cgro * * We give up and return to the caller when we visit root_mem twice. * (other groups can be removed while we're walking....) + * + * If shrink==true, for avoiding to free too much, this returns immedieately. */ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, - gfp_t gfp_mask, bool noswap) + gfp_t gfp_mask, bool noswap, bool shrink) { struct mem_cgroup *victim; int ret, total = 0; @@ -771,6 +790,13 @@ static int mem_cgroup_hierarchical_recla ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, noswap, get_swappiness(victim)); css_put(&victim->css); + /* + * At shrinking usage, we can't check we should stop here or + * reclaim more. It's depends on callers. last_scanned_child + * will work enough for keeping fairness under tree. + */ + if (shrink) + return ret; total += ret; if (mem_cgroup_check_under_limit(root_mem)) return 1 + total; @@ -856,7 +882,7 @@ static int __mem_cgroup_try_charge(struc goto nomem; ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask, - noswap); + noswap, false); if (ret) continue; @@ -1489,7 +1515,8 @@ int mem_cgroup_shrink_usage(struct page return 0; do { - progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true); + progress = mem_cgroup_hierarchical_reclaim(mem, + gfp_mask, true, false); progress += mem_cgroup_check_under_limit(mem); } while (!progress && --retry); @@ -1504,11 +1531,21 @@ static DEFINE_MUTEX(set_limit_mutex); static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val) { - - int retry_count = MEM_CGROUP_RECLAIM_RETRIES; + int retry_count; int progress; u64 memswlimit; int ret = 0; + int children = mem_cgroup_count_children(memcg); + u64 curusage, oldusage; + + /* + * For keeping hierarchical_reclaim simple, how long we should retry + * is depends on callers. We set our retry-count to be function + * of # of children which we should visit in this loop. + */ + retry_count = MEM_CGROUP_RECLAIM_RETRIES * children; + + oldusage = res_counter_read_u64(&memcg->res, RES_USAGE); while (retry_count) { if (signal_pending(current)) { @@ -1534,8 +1571,13 @@ static int mem_cgroup_resize_limit(struc break; progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, - false); - if (!progress) retry_count--; + false, true); + curusage = res_counter_read_u64(&memcg->res, RES_USAGE); + /* Usage is reduced ? */ + if (curusage >= oldusage) + retry_count--; + else + oldusage = curusage; } return ret; @@ -1544,13 +1586,16 @@ static int mem_cgroup_resize_limit(struc int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, unsigned long long val) { - int retry_count = MEM_CGROUP_RECLAIM_RETRIES; + int retry_count; u64 memlimit, oldusage, curusage; - int ret; + int children = mem_cgroup_count_children(memcg); + int ret = -EBUSY; if (!do_swap_account) return -EINVAL; - + /* see mem_cgroup_resize_res_limit */ + retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; + oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); while (retry_count) { if (signal_pending(current)) { ret = -EINTR; @@ -1574,11 +1619,13 @@ int mem_cgroup_resize_memsw_limit(struct if (!ret) break; - oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); - mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true); + mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true, true); curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); + /* Usage is reduced ? */ if (curusage >= oldusage) retry_count--; + else + oldusage = curusage; } return ret; } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/