On Mon 18-11-13 15:31:26, Markus Blank-Burian wrote: > > There is one more issue which is discussed in another thread > > (https://lkml.org/lkml/2013/11/15/31) and Tejun has posted a patch (and > > Hugh followed up on it https://lkml.org/lkml/2013/11/17/166) to fix > > the cgroup destruction path which may get stuck. > > > > Tried out the patches from Johannes, Tejun+Hugh and Michal all You do not have to apply my patch as Johannes' one should be sufficient. > together and my problem still persists :-( > Anything I can try besides bisectioning (which I still could not get > to work yet)? Add more debugging information I guess. Let's see if something like the following helps --- diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3d69a3fe4c55..602db53c690d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3928,6 +3928,8 @@ static int mem_cgroup_move_parent(struct page *page, put: put_page(page); out: + if (ret) + trace_printk("%s failed with %d for memcg:%p\n", __FUNCTION__, ret, child); return ret; } @@ -4946,7 +4948,7 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg, static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) { int node, zid; - u64 usage; + u64 usage, u, k; do { /* This is for making all *used* pages to be on LRU. */ @@ -4978,8 +4980,11 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) * right after the check. RES_USAGE should be safe as we always * charge before adding to the LRU. */ - usage = res_counter_read_u64(&memcg->res, RES_USAGE) - - res_counter_read_u64(&memcg->kmem, RES_USAGE); + u = res_counter_read_u64(&memcg->res, RES_USAGE); + k = res_counter_read_u64(&memcg->kmem, RES_USAGE); + usage = u - k; + if (usage > 0) + trace_printk("memcg:%p u:%lu k:%lu tasks:%d\n", memcg, u, k, cgroup_task_count(memcg->css.cgrp)); } while (usage > 0); } @@ -6358,12 +6363,14 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); + trace_printk("memcg:%p is going offline now\n", memcg); kmem_cgroup_css_offline(memcg); mem_cgroup_invalidate_reclaim_iterators(memcg); mem_cgroup_reparent_charges(memcg); mem_cgroup_destroy_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); + trace_printk("memcg:%p is offline now\n", memcg); } static void mem_cgroup_css_free(struct cgroup_subsys_state *css) @@ -6746,6 +6753,10 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, struct mem_cgroup *memcg = mem_cgroup_from_css(css); unsigned long move_charge_at_immigrate; + if (!css_tryget(css)) + trace_printk("Target memcg %p is dead!\n", memcg); + else + css_put(css); /* * We are now commited to this value whatever it is. Changes in this * tunable will only affect upcoming migrations, not the current one. -- Michal Hocko SUSE Labs -- To unsubscribe from this list: send the line "unsubscribe cgroups" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
