From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761116Ab2EQVdd (ORCPT ); Thu, 17 May 2012 17:33:33 -0400 Received: from mail-pb0-f46.google.com ([209.85.160.46]:36209 "EHLO mail-pb0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755165Ab2EQVda (ORCPT ); Thu, 17 May 2012 17:33:30 -0400 Date: Thu, 17 May 2012 14:33:27 -0700 (PDT) From: David Rientjes X-X-Sender: rientjes@chino.kir.corp.google.com To: Andrew Morton cc: KOSAKI Motohiro , KAMEZAWA Hiroyuki , Dave Jones , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: [patch] mm, oom: normalize oom scores to oom_score_adj scale only for userspace In-Reply-To: <20120503222949.GA13762@redhat.com> Message-ID: References: <20120426193551.GA24968@redhat.com> <20120503222949.GA13762@redhat.com> User-Agent: Alpine 2.00 (DEB 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The oom_score_adj scale ranges from -1000 to 1000 and represents the proportion of memory available to the process at allocation time. This means an oom_score_adj value of 300, for example, will bias a process as though it was using an extra 30.0% of available memory and a value of -350 will discount 35.0% of available memory from its usage. The oom killer badness heuristic also uses this scale to report the oom score for each eligible process in determining the "best" process to kill. Thus, it can only differentiate each process's memory usage by 0.1% of system RAM. On large systems, this can end up being a large amount of memory: 256MB on 256GB systems, for example. This can be fixed by having the badness heuristic to use the actual memory usage in scoring threads and then normalizing it to the oom_score_adj scale for userspace. This results in better comparison between eligible threads for kill and no change from the userspace perspective. Suggested-by: KOSAKI Motohiro Tested-by: Dave Jones Signed-off-by: David Rientjes --- fs/proc/base.c | 5 +++-- include/linux/oom.h | 5 +++-- mm/oom_kill.c | 39 ++++++++++++++------------------------- 3 files changed, 20 insertions(+), 29 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -410,12 +410,13 @@ static const struct file_operations proc_lstats_operations = { static int proc_oom_score(struct task_struct *task, char *buffer) { + unsigned long totalpages = totalram_pages + total_swap_pages; unsigned long points = 0; read_lock(&tasklist_lock); if (pid_alive(task)) - points = oom_badness(task, NULL, NULL, - totalram_pages + total_swap_pages); + points = oom_badness(task, NULL, NULL, totalpages) * + 1000 / totalpages; read_unlock(&tasklist_lock); return sprintf(buffer, "%lu\n", points); } diff --git a/include/linux/oom.h b/include/linux/oom.h --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -43,8 +43,9 @@ enum oom_constraint { extern void compare_swap_oom_score_adj(int old_val, int new_val); extern int test_set_oom_score_adj(int new_val); -extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg, - const nodemask_t *nodemask, unsigned long totalpages); +extern unsigned long oom_badness(struct task_struct *p, + struct mem_cgroup *memcg, const nodemask_t *nodemask, + unsigned long totalpages); extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); diff --git a/mm/oom_kill.c b/mm/oom_kill.c --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -180,10 +180,10 @@ static bool oom_unkillable_task(struct task_struct *p, * predictable as possible. The goal is to return the highest value for the * task consuming the most memory to avoid subsequent oom failures. */ -unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg, - const nodemask_t *nodemask, unsigned long totalpages) +unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, + const nodemask_t *nodemask, unsigned long totalpages) { - long points; + unsigned long points; if (oom_unkillable_task(p, memcg, nodemask)) return 0; @@ -198,45 +198,33 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg, } /* - * The memory controller may have a limit of 0 bytes, so avoid a divide - * by zero, if necessary. - */ - if (!totalpages) - totalpages = 1; - - /* * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ - points = get_mm_rss(p->mm) + p->mm->nr_ptes; - points += get_mm_counter(p->mm, MM_SWAPENTS); - - points *= 1000; - points /= totalpages; + points = get_mm_rss(p->mm) + p->mm->nr_ptes + + get_mm_counter(p->mm, MM_SWAPENTS); task_unlock(p); /* * Root processes get 3% bonus, just like the __vm_enough_memory() * implementation used by LSMs. */ - if (has_capability_noaudit(p, CAP_SYS_ADMIN)) - points -= 30; + if (has_capability_noaudit(p, CAP_SYS_ADMIN) && totalpages) + points -= 30 * totalpages / 1000; /* * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may * either completely disable oom killing or always prefer a certain * task. */ - points += p->signal->oom_score_adj; + points += p->signal->oom_score_adj * totalpages / 1000; /* * Never return 0 for an eligible task that may be killed since it's * possible that no single user task uses more than 0.1% of memory and * no single admin tasks uses more than 3.0%. */ - if (points <= 0) - return 1; - return (points < 1000) ? points : 1000; + return points <= 0 ? 1 : points; } /* @@ -314,7 +302,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, { struct task_struct *g, *p; struct task_struct *chosen = NULL; - *ppoints = 0; + unsigned long chosen_points = 0; do_each_thread(g, p) { unsigned int points; @@ -354,7 +342,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, */ if (p == current) { chosen = p; - *ppoints = 1000; + chosen_points = ULONG_MAX; } else if (!force_kill) { /* * If this task is not being ptraced on exit, @@ -367,12 +355,13 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, } points = oom_badness(p, memcg, nodemask, totalpages); - if (points > *ppoints) { + if (points > chosen_points) { chosen = p; - *ppoints = points; + chosen_points = points; } } while_each_thread(g, p); + *ppoints = chosen_points * 1000 / totalpages; return chosen; } From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from psmtp.com (na3sys010amx158.postini.com [74.125.245.158]) by kanga.kvack.org (Postfix) with SMTP id 098966B0092 for ; Thu, 17 May 2012 17:33:30 -0400 (EDT) Received: by pbbrp2 with SMTP id rp2so4563943pbb.14 for ; Thu, 17 May 2012 14:33:30 -0700 (PDT) Date: Thu, 17 May 2012 14:33:27 -0700 (PDT) From: David Rientjes Subject: [patch] mm, oom: normalize oom scores to oom_score_adj scale only for userspace In-Reply-To: <20120503222949.GA13762@redhat.com> Message-ID: References: <20120426193551.GA24968@redhat.com> <20120503222949.GA13762@redhat.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-linux-mm@kvack.org List-ID: To: Andrew Morton Cc: KOSAKI Motohiro , KAMEZAWA Hiroyuki , Dave Jones , linux-mm@kvack.org, linux-kernel@vger.kernel.org The oom_score_adj scale ranges from -1000 to 1000 and represents the proportion of memory available to the process at allocation time. This means an oom_score_adj value of 300, for example, will bias a process as though it was using an extra 30.0% of available memory and a value of -350 will discount 35.0% of available memory from its usage. The oom killer badness heuristic also uses this scale to report the oom score for each eligible process in determining the "best" process to kill. Thus, it can only differentiate each process's memory usage by 0.1% of system RAM. On large systems, this can end up being a large amount of memory: 256MB on 256GB systems, for example. This can be fixed by having the badness heuristic to use the actual memory usage in scoring threads and then normalizing it to the oom_score_adj scale for userspace. This results in better comparison between eligible threads for kill and no change from the userspace perspective. Suggested-by: KOSAKI Motohiro Tested-by: Dave Jones Signed-off-by: David Rientjes --- fs/proc/base.c | 5 +++-- include/linux/oom.h | 5 +++-- mm/oom_kill.c | 39 ++++++++++++++------------------------- 3 files changed, 20 insertions(+), 29 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -410,12 +410,13 @@ static const struct file_operations proc_lstats_operations = { static int proc_oom_score(struct task_struct *task, char *buffer) { + unsigned long totalpages = totalram_pages + total_swap_pages; unsigned long points = 0; read_lock(&tasklist_lock); if (pid_alive(task)) - points = oom_badness(task, NULL, NULL, - totalram_pages + total_swap_pages); + points = oom_badness(task, NULL, NULL, totalpages) * + 1000 / totalpages; read_unlock(&tasklist_lock); return sprintf(buffer, "%lu\n", points); } diff --git a/include/linux/oom.h b/include/linux/oom.h --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -43,8 +43,9 @@ enum oom_constraint { extern void compare_swap_oom_score_adj(int old_val, int new_val); extern int test_set_oom_score_adj(int new_val); -extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg, - const nodemask_t *nodemask, unsigned long totalpages); +extern unsigned long oom_badness(struct task_struct *p, + struct mem_cgroup *memcg, const nodemask_t *nodemask, + unsigned long totalpages); extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); diff --git a/mm/oom_kill.c b/mm/oom_kill.c --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -180,10 +180,10 @@ static bool oom_unkillable_task(struct task_struct *p, * predictable as possible. The goal is to return the highest value for the * task consuming the most memory to avoid subsequent oom failures. */ -unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg, - const nodemask_t *nodemask, unsigned long totalpages) +unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, + const nodemask_t *nodemask, unsigned long totalpages) { - long points; + unsigned long points; if (oom_unkillable_task(p, memcg, nodemask)) return 0; @@ -198,45 +198,33 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg, } /* - * The memory controller may have a limit of 0 bytes, so avoid a divide - * by zero, if necessary. - */ - if (!totalpages) - totalpages = 1; - - /* * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ - points = get_mm_rss(p->mm) + p->mm->nr_ptes; - points += get_mm_counter(p->mm, MM_SWAPENTS); - - points *= 1000; - points /= totalpages; + points = get_mm_rss(p->mm) + p->mm->nr_ptes + + get_mm_counter(p->mm, MM_SWAPENTS); task_unlock(p); /* * Root processes get 3% bonus, just like the __vm_enough_memory() * implementation used by LSMs. */ - if (has_capability_noaudit(p, CAP_SYS_ADMIN)) - points -= 30; + if (has_capability_noaudit(p, CAP_SYS_ADMIN) && totalpages) + points -= 30 * totalpages / 1000; /* * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may * either completely disable oom killing or always prefer a certain * task. */ - points += p->signal->oom_score_adj; + points += p->signal->oom_score_adj * totalpages / 1000; /* * Never return 0 for an eligible task that may be killed since it's * possible that no single user task uses more than 0.1% of memory and * no single admin tasks uses more than 3.0%. */ - if (points <= 0) - return 1; - return (points < 1000) ? points : 1000; + return points <= 0 ? 1 : points; } /* @@ -314,7 +302,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, { struct task_struct *g, *p; struct task_struct *chosen = NULL; - *ppoints = 0; + unsigned long chosen_points = 0; do_each_thread(g, p) { unsigned int points; @@ -354,7 +342,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, */ if (p == current) { chosen = p; - *ppoints = 1000; + chosen_points = ULONG_MAX; } else if (!force_kill) { /* * If this task is not being ptraced on exit, @@ -367,12 +355,13 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, } points = oom_badness(p, memcg, nodemask, totalpages); - if (points > *ppoints) { + if (points > chosen_points) { chosen = p; - *ppoints = points; + chosen_points = points; } } while_each_thread(g, p); + *ppoints = chosen_points * 1000 / totalpages; return chosen; } -- 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: email@kvack.org