The patch titled
memcg: oom kill disable and oom status
has been added to the -mm tree. Its filename is
memcg-oom-kill-disable-and-oom-status.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: oom kill disable and oom status
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
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-Kill by the kernel, the users can take snapshot or coredump of
guilty process, cgroups.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxx>
Cc: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/cgroups/memory.txt | 19 ++++
mm/memcontrol.c | 113 ++++++++++++++++++++++++-----
2 files changed, 113 insertions(+), 19 deletions(-)
diff -puN Documentation/cgroups/memory.txt~memcg-oom-kill-disable-and-oom-status Documentation/cgroups/memory.txt
--- a/Documentation/cgroups/memory.txt~memcg-oom-kill-disable-and-oom-status
+++ a/Documentation/cgroups/memory.txt
@@ -493,6 +493,8 @@ It's applicable for root and non-root cg
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 +507,23 @@ 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
+ * kill some tasks.
+ * move some tasks to other group with account migration.
+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 -puN mm/memcontrol.c~memcg-oom-kill-disable-and-oom-status mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-oom-kill-disable-and-oom-status
+++ a/mm/memcontrol.c
@@ -235,7 +235,8 @@ struct mem_cgroup {
* mem_cgroup ? And what type of charges should we move ?
*/
unsigned long move_charge_at_immigrate;
-
+ /* Disable OOM killer */
+ unsigned long oom_kill_disable;
/*
* percpu counter.
*/
@@ -1340,20 +1341,26 @@ static void memcg_wakeup_oom(struct 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);
@@ -1362,15 +1369,17 @@ bool mem_cgroup_handle_oom(struct mem_cg
* 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, co
/* 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 = ¤t->memcg_batch;
/*
@@ -2181,6 +2181,17 @@ __do_uncharge(struct mem_cgroup *mem, co
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.
* If not, we uncharge res_counter ony by one.
@@ -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(struc
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(struc
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(struc
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(struc
else
oldusage = curusage;
}
+ if (!ret && enlarge)
+ memcg_oom_recover(memcg);
return ret;
}
@@ -2628,9 +2651,10 @@ static int mem_cgroup_resize_memsw_limit
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
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
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_eve
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 *
} 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) {
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
origin.patch
memcg-avoid-use-cmpxchg-in-swap-cgroup-maintainance.patch
memory-hotplug-allow-setting-of-phys_device.patch
memory-hotplug-s390-set-phys_device.patch
memcg-disable-move-charge-in-no-mmu-case.patch
memcontrol-fix-potential-null-deref.patch
linux-next.patch
cgroups-net_cls-as-module.patch
vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos.patch
memcg-oom-wakeup-filter.patch
memcg-oom-notifier.patch
memcg-oom-notifier-fix.patch
memcg-oom-kill-disable-and-oom-status.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
