The patch titled memcg: show memcg information during OOM has been added to the -mm tree. Its filename is memcg-show-memcg-information-during-oom.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find out what to do about this The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: memcg: show memcg information during OOM From: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx> Add RSS and swap to OOM output from memcg Display memcg values like failcnt, usage and limit when an OOM occurs due to memcg. Thanks to Johannes Weiner, Li Zefan, David Rientjes, Kamezawa Hiroyuki, Daisuke Nishimura and KOSAKI Motohiro for review. Sample output ------------- Task in /a/x killed as a result of limit of /a memory: usage 1048576kB, limit 1048576kB, failcnt 4183 memory+swap: usage 1400964kB, limit 9007199254740991kB, failcnt 0 Signed-off-by: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx> Cc: Li Zefan <lizf@xxxxxxxxxxxxxx> Cc: Paul Menage <menage@xxxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/memcontrol.h | 6 +++ mm/memcontrol.c | 63 +++++++++++++++++++++++++++++++++++ mm/oom_kill.c | 1 3 files changed, 70 insertions(+) diff -puN include/linux/memcontrol.h~memcg-show-memcg-information-during-oom include/linux/memcontrol.h --- a/include/linux/memcontrol.h~memcg-show-memcg-information-during-oom +++ a/include/linux/memcontrol.h @@ -104,6 +104,8 @@ struct zone_reclaim_stat *mem_cgroup_get struct zone *zone); struct zone_reclaim_stat* mem_cgroup_get_reclaim_stat_from_page(struct page *page); +extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, + struct task_struct *p); #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP extern int do_swap_account; @@ -270,6 +272,10 @@ mem_cgroup_get_reclaim_stat_from_page(st return NULL; } +void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) +{ +} + #endif /* CONFIG_CGROUP_MEM_CONT */ #endif /* _LINUX_MEMCONTROL_H */ diff -puN mm/memcontrol.c~memcg-show-memcg-information-during-oom mm/memcontrol.c --- a/mm/memcontrol.c~memcg-show-memcg-information-during-oom +++ a/mm/memcontrol.c @@ -27,6 +27,7 @@ #include <linux/backing-dev.h> #include <linux/bit_spinlock.h> #include <linux/rcupdate.h> +#include <linux/limits.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/swap.h> @@ -721,6 +722,68 @@ static int mem_cgroup_count_children_cb( (*val)++; return 0; } + +/** + * mem_cgroup_print_mem_info: Called from OOM with tasklist_lock held in + * read mode. + * @memcg: The memory cgroup that went over limit + * @p: Task that is going to be killed + * + * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is + * enabled + */ +void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) +{ + struct cgroup *task_cgrp; + struct cgroup *mem_cgrp; + /* + * Need a buffer on stack, can't rely on allocations. The code relies + * on the assumption that OOM is serialized for memory controller. + * If this assumption is broken, revisit this code. + */ + static char task_memcg_name[PATH_MAX]; + static char memcg_name[PATH_MAX]; + int ret; + + if (!memcg) + return; + + mem_cgrp = memcg->css.cgroup; + task_cgrp = mem_cgroup_from_task(p)->css.cgroup; + + rcu_read_lock(); + ret = cgroup_path(task_cgrp, task_memcg_name, PATH_MAX); + if (ret < 0) { + /* + * Unfortunately, we are unable to convert to a useful name + * But we'll still print out the usage information + */ + rcu_read_unlock(); + goto done; + } + ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX); + if (ret < 0) { + rcu_read_unlock(); + goto done; + } + + rcu_read_unlock(); + + printk(KERN_INFO "Task in %s killed as a result of limit of %s\n", + task_memcg_name, memcg_name); +done: + + printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n", + res_counter_read_u64(&memcg->res, RES_USAGE) >> 10, + res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10, + res_counter_read_u64(&memcg->res, RES_FAILCNT)); + printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, " + "failcnt %llu\n", + res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10, + res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10, + res_counter_read_u64(&memcg->memsw, RES_FAILCNT)); +} + /* * This function returns the number of memcg under hierarchy tree. Returns * 1(self count) if no children. diff -puN mm/oom_kill.c~memcg-show-memcg-information-during-oom mm/oom_kill.c --- a/mm/oom_kill.c~memcg-show-memcg-information-during-oom +++ a/mm/oom_kill.c @@ -394,6 +394,7 @@ static int oom_kill_process(struct task_ cpuset_print_task_mems_allowed(current); task_unlock(current); dump_stack(); + mem_cgroup_print_oom_info(mem, current); show_mem(); if (sysctl_oom_dump_tasks) dump_tasks(mem); _ Patches currently in -mm which might be from balbir@xxxxxxxxxxxxxxxxxx are origin.patch linux-next.patch memcg-show-memcg-information-during-oom.patch memcg-show-memcg-information-during-oom-fix.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html