memcg: oom kill disable and oom status

This adds a feature to disable oom-killer for memcg, if disabled, of
course, tasks under memcg will stop.

But now, we have oom-notifier for memcg.  And the world around memcg is
not under out-of-memory.  memcg's out-of-memory just shows memcg hits
limit.  Then, administrator or management daemon can recover the situation
by

	- kill some process
	- enlarge limit, add more swap.
	- migrate some tasks
	- remove file cache on tmps (difficult ?)

Unlike oom-killer, you can take enough information before killing tasks.
(by gcore, or, ps etc.)

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index eac22d3b2f7b70f662740518122866b8ea460e97..44e7ded3344813fc9b2f2179c8501bd0417d5ddf 100644 (file)
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -493,6 +493,8 @@ It's applicable for root and non-root cgroup.
 
 10. OOM Control
 
+memory.oom_control file is for OOM notification and other controls.
+
 Memory controler implements oom notifier using cgroup notification
 API (See cgroups.txt). It allows to register multiple oom notification
 delivery and gets notification when oom happens.
@@ -505,6 +507,27 @@ To register a notifier, application need:
 Application will be notifier through eventfd when oom happens.
 OOM notification doesn't work for root cgroup.
 
+You can disable oom-killer by writing "1" to memory.oom_control file.
+As.
+       #echo 1 > memory.oom_control
+
+This operation is only allowed to the top cgroup of subhierarchy.
+If oom-killer is disabled, tasks under cgroup will hang/sleep
+in memcg's oom-waitq when they request accountable memory.
+
+For running them, you have to relax the memcg's oom sitaution by
+       * enlarge limit or reduce usage.
+To reduce usage,
+       * kill some tasks.
+       * move some tasks to other group with account migration.
+       * remove some files (on tmpfs?)
+
+Then, stopped tasks will work again.
+
+At reading, current status of OOM is shown.
+       oom_kill_disable 0 or 1 (if 1, oom-killer is disabled)
+       under_oom        0 or 1 (if 1, the memcg is under OOM,tasks may
+                                be stopped.)
 
 11. TODO
 

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index da2ed3913316c107fd175abc912023bd4616e521..53eb30ebdb49a2ae898c5acb3006c6e19bcfd18d 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -214,6 +214,8 @@ struct mem_cgroup {
        atomic_t        refcnt;
 
        unsigned int    swappiness;
+       /* OOM-Killer disable */
+       int             oom_kill_disable;
 
        /* set when res.limit == memsw.limit */
        bool            memsw_is_minimum;
@@ -235,7 +237,6 @@ struct mem_cgroup {
         * mem_cgroup ? And what type of charges should we move ?
         */
        unsigned long   move_charge_at_immigrate;
-
        /*
         * percpu counter.
         */
@@ -1342,20 +1343,26 @@ static void memcg_wakeup_oom(struct mem_cgroup *mem)
        __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, mem);
 }
 
+static void memcg_oom_recover(struct mem_cgroup *mem)
+{
+       if (mem->oom_kill_disable && atomic_read(&mem->oom_lock))
+               memcg_wakeup_oom(mem);
+}
+
 /*
  * try to call OOM killer. returns false if we should exit memory-reclaim loop.
  */
 bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask)
 {
        struct oom_wait_info owait;
-       bool locked;
+       bool locked, need_to_kill;
 
        owait.mem = mem;
        owait.wait.flags = 0;
        owait.wait.func = memcg_oom_wake_function;
        owait.wait.private = current;
        INIT_LIST_HEAD(&owait.wait.task_list);
-
+       need_to_kill = true;
        /* At first, try to OOM lock hierarchy under mem.*/
        mutex_lock(&memcg_oom_mutex);
        locked = mem_cgroup_oom_lock(mem);
@@ -1364,15 +1371,17 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask)
         * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL
         * under OOM is always welcomed, use TASK_KILLABLE here.
         */
-       if (!locked)
-               prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
-       else
+       prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
+       if (!locked || mem->oom_kill_disable)
+               need_to_kill = false;
+       if (locked)
                mem_cgroup_oom_notify(mem);
        mutex_unlock(&memcg_oom_mutex);
 
-       if (locked)
+       if (need_to_kill) {
+               finish_wait(&memcg_oom_waitq, &owait.wait);
                mem_cgroup_out_of_memory(mem, mask);
-       else {
+       } else {
                schedule();
                finish_wait(&memcg_oom_waitq, &owait.wait);
        }
@@ -2162,15 +2171,6 @@ __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype)
        /* If swapout, usage of swap doesn't decrease */
        if (!do_swap_account || ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
                uncharge_memsw = false;
-       /*
-        * do_batch > 0 when unmapping pages or inode invalidate/truncate.
-        * In those cases, all pages freed continously can be expected to be in
-        * the same cgroup and we have chance to coalesce uncharges.
-        * But we do uncharge one by one if this is killed by OOM(TIF_MEMDIE)
-        * because we want to do uncharge as soon as possible.
-        */
-       if (!current->memcg_batch.do_batch || test_thread_flag(TIF_MEMDIE))
-               goto direct_uncharge;
 
        batch = &current->memcg_batch;
        /*
@@ -2180,6 +2180,17 @@ __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype)
         */
        if (!batch->memcg)
                batch->memcg = mem;
+       /*
+        * do_batch > 0 when unmapping pages or inode invalidate/truncate.
+        * In those cases, all pages freed continously can be expected to be in
+        * the same cgroup and we have chance to coalesce uncharges.
+        * But we do uncharge one by one if this is killed by OOM(TIF_MEMDIE)
+        * because we want to do uncharge as soon as possible.
+        */
+
+       if (!batch->do_batch || test_thread_flag(TIF_MEMDIE))
+               goto direct_uncharge;
+
        /*
         * In typical case, batch->memcg == mem. This means we can
         * merge a series of uncharges to an uncharge of res_counter.
@@ -2196,6 +2207,8 @@ direct_uncharge:
        res_counter_uncharge(&mem->res, PAGE_SIZE);
        if (uncharge_memsw)
                res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+       if (unlikely(batch->memcg != mem))
+               memcg_oom_recover(mem);
        return;
 }
 
@@ -2332,6 +2345,7 @@ void mem_cgroup_uncharge_end(void)
                res_counter_uncharge(&batch->memcg->res, batch->bytes);
        if (batch->memsw_bytes)
                res_counter_uncharge(&batch->memcg->memsw, batch->memsw_bytes);
+       memcg_oom_recover(batch->memcg);
        /* forget this pointer (for sanity check) */
        batch->memcg = NULL;
 }
@@ -2568,10 +2582,11 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
                                unsigned long long val)
 {
        int retry_count;
-       u64 memswlimit;
+       u64 memswlimit, memlimit;
        int ret = 0;
        int children = mem_cgroup_count_children(memcg);
        u64 curusage, oldusage;
+       int enlarge;
 
        /*
         * For keeping hierarchical_reclaim simple, how long we should retry
@@ -2582,6 +2597,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 
        oldusage = res_counter_read_u64(&memcg->res, RES_USAGE);
 
+       enlarge = 0;
        while (retry_count) {
                if (signal_pending(current)) {
                        ret = -EINTR;
@@ -2599,6 +2615,11 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
                        mutex_unlock(&set_limit_mutex);
                        break;
                }
+
+               memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+               if (memlimit < val)
+                       enlarge = 1;
+
                ret = res_counter_set_limit(&memcg->res, val);
                if (!ret) {
                        if (memswlimit == val)
@@ -2620,6 +2641,8 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
                else
                        oldusage = curusage;
        }
+       if (!ret && enlarge)
+               memcg_oom_recover(memcg);
 
        return ret;
 }
@@ -2628,9 +2651,10 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
                                        unsigned long long val)
 {
        int retry_count;
-       u64 memlimit, oldusage, curusage;
+       u64 memlimit, memswlimit, oldusage, curusage;
        int children = mem_cgroup_count_children(memcg);
        int ret = -EBUSY;
+       int enlarge = 0;
 
        /* see mem_cgroup_resize_res_limit */
        retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
@@ -2652,6 +2676,9 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
                        mutex_unlock(&set_limit_mutex);
                        break;
                }
+               memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+               if (memswlimit < val)
+                       enlarge = 1;
                ret = res_counter_set_limit(&memcg->memsw, val);
                if (!ret) {
                        if (memlimit == val)
@@ -2674,6 +2701,8 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
                else
                        oldusage = curusage;
        }
+       if (!ret && enlarge)
+               memcg_oom_recover(memcg);
        return ret;
 }
 
@@ -2865,6 +2894,7 @@ move_account:
                        if (ret)
                                break;
                }
+               memcg_oom_recover(mem);
                /* it seems parent cgroup doesn't have enough mem */
                if (ret == -ENOMEM)
                        goto try_to_free;
@@ -3645,6 +3675,46 @@ static int mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
        return 0;
 }
 
+static int mem_cgroup_oom_control_read(struct cgroup *cgrp,
+       struct cftype *cft,  struct cgroup_map_cb *cb)
+{
+       struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+
+       cb->fill(cb, "oom_kill_disable", mem->oom_kill_disable);
+
+       if (atomic_read(&mem->oom_lock))
+               cb->fill(cb, "under_oom", 1);
+       else
+               cb->fill(cb, "under_oom", 0);
+       return 0;
+}
+
+/*
+ */
+static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
+       struct cftype *cft, u64 val)
+{
+       struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+       struct mem_cgroup *parent;
+
+       /* cannot set to root cgroup and only 0 and 1 are allowed */
+       if (!cgrp->parent || !((val == 0) || (val == 1)))
+               return -EINVAL;
+
+       parent = mem_cgroup_from_cont(cgrp->parent);
+
+       cgroup_lock();
+       /* oom-kill-disable is a flag for subhierarchy. */
+       if ((parent->use_hierarchy) ||
+           (mem->use_hierarchy && !list_empty(&cgrp->children))) {
+               cgroup_unlock();
+               return -EINVAL;
+       }
+       mem->oom_kill_disable = val;
+       cgroup_unlock();
+       return 0;
+}
+
 static struct cftype mem_cgroup_files[] = {
        {
                .name = "usage_in_bytes",
@@ -3702,6 +3772,8 @@ static struct cftype mem_cgroup_files[] = {
        },
        {
                .name = "oom_control",
+               .read_map = mem_cgroup_oom_control_read,
+               .write_u64 = mem_cgroup_oom_control_write,
                .register_event = mem_cgroup_oom_register_event,
                .unregister_event = mem_cgroup_oom_unregister_event,
                .private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL),
@@ -3943,6 +4015,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
        } else {
                parent = mem_cgroup_from_cont(cont->parent);
                mem->use_hierarchy = parent->use_hierarchy;
+               mem->oom_kill_disable = parent->oom_kill_disable;
        }
 
        if (parent && parent->use_hierarchy) {
@@ -4215,6 +4288,7 @@ static void mem_cgroup_clear_mc(void)
        if (mc.precharge) {
                __mem_cgroup_cancel_charge(mc.to, mc.precharge);
                mc.precharge = 0;
+               memcg_oom_recover(mc.to);
        }
        /*
         * we didn't uncharge from mc.from at mem_cgroup_move_account(), so
@@ -4223,6 +4297,7 @@ static void mem_cgroup_clear_mc(void)
        if (mc.moved_charge) {
                __mem_cgroup_cancel_charge(mc.from, mc.moved_charge);
                mc.moved_charge = 0;
+               memcg_oom_recover(mc.from);
        }
        /* we must fixup refcnts and charges */
        if (mc.moved_swap) {