The patch titled
memcg: fix oom kill behavior
has been added to the -mm tree. Its filename is
memcg-fix-oom-kill-behavior-v3.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: fix oom kill behavior
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
In current page-fault code,
handle_mm_fault()
-> ...
-> mem_cgroup_charge()
-> map page or handle error.
-> check return code.
If page fault's return code is VM_FAULT_OOM, page_fault_out_of_memory() is
called. But if it's caused by memcg, OOM should have been already
invoked.
Then, I added a patch: a636b327f731143ccc544b966cfd8de6cb6d72c6. That
patch records last_oom_jiffies for memcg's sub-hierarchy and prevents
page_fault_out_of_memory from being invoked in near future.
But Nishimura-san reported that check by jiffies is not enough when the
system is terribly heavy.
This patch changes memcg's oom logic as.
* If memcg causes OOM-kill, continue to retry.
* remove jiffies check which is used now.
* add memcg-oom-lock which works like perzone oom lock.
* If current is killed(as a process), bypass charge.
Something more sophisticated can be added but this pactch does
fundamental things.
TODO:
- add oom notifier
- add permemcg disable-oom-kill flag and freezer at oom.
- more chances for wake up oom waiter (when changing memory limit etc..)
Reviewed-by: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Tested-by: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/memcontrol.h | 6 -
mm/memcontrol.c | 119 +++++++++++++++++++++++++++--------
mm/oom_kill.c | 8 --
3 files changed, 92 insertions(+), 41 deletions(-)
diff -puN include/linux/memcontrol.h~memcg-fix-oom-kill-behavior-v3 include/linux/memcontrol.h
--- a/include/linux/memcontrol.h~memcg-fix-oom-kill-behavior-v3
+++ a/include/linux/memcontrol.h
@@ -124,7 +124,6 @@ static inline bool mem_cgroup_disabled(v
return false;
}
-extern bool mem_cgroup_oom_called(struct task_struct *task);
void mem_cgroup_update_file_mapped(struct page *page, int val);
unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
gfp_t gfp_mask, int nid,
@@ -258,11 +257,6 @@ static inline bool mem_cgroup_disabled(v
return true;
}
-static inline bool mem_cgroup_oom_called(struct task_struct *task)
-{
- return false;
-}
-
static inline int
mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
{
diff -puN mm/memcontrol.c~memcg-fix-oom-kill-behavior-v3 mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-fix-oom-kill-behavior-v3
+++ a/mm/memcontrol.c
@@ -203,7 +203,7 @@ struct mem_cgroup {
* Should the accounting and control be hierarchical, per subtree?
*/
bool use_hierarchy;
- unsigned long last_oom_jiffies;
+ atomic_t oom_lock;
atomic_t refcnt;
unsigned int swappiness;
@@ -1246,32 +1246,87 @@ static int mem_cgroup_hierarchical_recla
return total;
}
-bool mem_cgroup_oom_called(struct task_struct *task)
+static int mem_cgroup_oom_lock_cb(struct mem_cgroup *mem, void *data)
{
- bool ret = false;
- struct mem_cgroup *mem;
- struct mm_struct *mm;
+ int *val = (int *)data;
+ int x;
- rcu_read_lock();
- mm = task->mm;
- if (!mm)
- mm = &init_mm;
- mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
- if (mem && time_before(jiffies, mem->last_oom_jiffies + HZ/10))
- ret = true;
- rcu_read_unlock();
- return ret;
+ x = atomic_inc_return(&mem->oom_lock);
+ *val = max(x, *val);
+ return 0;
}
+/*
+ * Check OOM-Killer is already running under our hierarchy.
+ * If someone is running, return false.
+ */
+static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
+{
+ int lock_count = 0;
+
+ mem_cgroup_walk_tree(mem, &lock_count, mem_cgroup_oom_lock_cb);
-static int record_last_oom_cb(struct mem_cgroup *mem, void *data)
+ if (lock_count == 1)
+ return true;
+ return false;
+}
+
+static int mem_cgroup_oom_unlock_cb(struct mem_cgroup *mem, void *data)
{
- mem->last_oom_jiffies = jiffies;
+ atomic_dec(&mem->oom_lock);
return 0;
}
-static void record_last_oom(struct mem_cgroup *mem)
+static void mem_cgroup_oom_unlock(struct mem_cgroup *mem)
{
- mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb);
+ mem_cgroup_walk_tree(mem, NULL, mem_cgroup_oom_unlock_cb);
+}
+
+static DEFINE_MUTEX(memcg_oom_mutex);
+static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
+
+/*
+ * 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)
+{
+ DEFINE_WAIT(wait);
+ bool locked;
+
+ /* At first, try to OOM lock hierarchy under mem.*/
+ mutex_lock(&memcg_oom_mutex);
+ locked = mem_cgroup_oom_lock(mem);
+ if (!locked)
+ prepare_to_wait(&memcg_oom_waitq, &wait, TASK_INTERRUPTIBLE);
+ mutex_unlock(&memcg_oom_mutex);
+
+ if (locked)
+ mem_cgroup_out_of_memory(mem, mask);
+ else {
+ schedule();
+ finish_wait(&memcg_oom_waitq, &wait);
+ }
+ mutex_lock(&memcg_oom_mutex);
+ mem_cgroup_oom_unlock(mem);
+ /*
+ * Here, we use global waitq .....more fine grained waitq ?
+ * Assume following hierarchy.
+ * A/
+ * 01
+ * 02
+ * assume OOM happens both in A and 01 at the same time. Tthey are
+ * mutually exclusive by lock. (kill in 01 helps A.)
+ * When we use per memcg waitq, we have to wake up waiters on A and 02
+ * in addtion to waiters on 01. We use global waitq for avoiding mess.
+ * It will not be a big problem.
+ */
+ wake_up_all(&memcg_oom_waitq);
+ mutex_unlock(&memcg_oom_mutex);
+
+ if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
+ return false;
+ /* Give chance to dying process */
+ schedule_timeout(1);
+ return true;
}
/*
@@ -1443,11 +1498,14 @@ static int __mem_cgroup_try_charge(struc
struct res_counter *fail_res;
int csize = CHARGE_SIZE;
- if (unlikely(test_thread_flag(TIF_MEMDIE))) {
- /* Don't account this! */
- *memcg = NULL;
- return 0;
- }
+ /*
+ * Unlike gloval-vm's OOM-kill, we're not in memory shortage
+ * in system level. So, allow to go ahead dying process in addition to
+ * MEMDIE process.
+ */
+ if (unlikely(test_thread_flag(TIF_MEMDIE)
+ || fatal_signal_pending(current)))
+ goto bypass;
/*
* We always charge the cgroup the mm_struct belongs to.
@@ -1560,11 +1618,15 @@ static int __mem_cgroup_try_charge(struc
}
if (!nr_retries--) {
- if (oom) {
- mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
- record_last_oom(mem_over_limit);
+ if (!oom)
+ goto nomem;
+ if (mem_cgroup_handle_oom(mem_over_limit, gfp_mask)) {
+ nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+ continue;
}
- goto nomem;
+ /* When we reach here, current task is dying .*/
+ css_put(&mem->css);
+ goto bypass;
}
}
if (csize > PAGE_SIZE)
@@ -1574,6 +1636,9 @@ done:
nomem:
css_put(&mem->css);
return -ENOMEM;
+bypass:
+ *memcg = NULL;
+ return 0;
}
/*
diff -puN mm/oom_kill.c~memcg-fix-oom-kill-behavior-v3 mm/oom_kill.c
--- a/mm/oom_kill.c~memcg-fix-oom-kill-behavior-v3
+++ a/mm/oom_kill.c
@@ -603,13 +603,6 @@ void pagefault_out_of_memory(void)
/* Got some memory back in the last second. */
return;
- /*
- * If this is from memcg, oom-killer is already invoked.
- * and not worth to go system-wide-oom.
- */
- if (mem_cgroup_oom_called(current))
- goto rest_and_return;
-
if (sysctl_panic_on_oom)
panic("out of memory from page fault. panic_on_oom is selected.\n");
@@ -621,7 +614,6 @@ void pagefault_out_of_memory(void)
* Give "p" a good chance of killing itself before we
* retry to allocate memory.
*/
-rest_and_return:
if (!test_thread_flag(TIF_MEMDIE))
schedule_timeout_uninterruptible(1);
}
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
origin.patch
linux-next.patch
vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos.patch
mm-clean-up-mm_counter.patch
mm-avoid-false-sharing-of-mm_counter.patch
mm-avoid-false-sharing-of-mm_counter-checkpatch-fixes.patch
mm-count-swap-usage.patch
mm-count-swap-usage-checkpatch-fixes.patch
vmscan-get_scan_ratio-cleanup.patch
mm-restore-zone-all_unreclaimable-to-independence-word.patch
mm-restore-zone-all_unreclaimable-to-independence-word-fix.patch
mm-restore-zone-all_unreclaimable-to-independence-word-fix-2.patch
mm-migratec-kill-anon-local-variable-from-migrate_page_copy.patch
mm-add-comment-about-deprecation-of-__gfp_nofail.patch
nodemaskh-remove-macro-any_online_node.patch
devmem-dont-allow-seek-to-last-page.patch
drivers-char-memc-cleanups.patch
drivers-char-memc-cleanups-fix.patch
drivers-char-memc-cleanups-fix-fix.patch
cgroup-introduce-cancel_attach.patch
cgroup-introduce-coalesce-css_get-and-css_put.patch
cgroups-revamp-subsys-array.patch
cgroups-subsystem-module-loading-interface.patch
cgroups-subsystem-module-loading-interface-fix.patch
cgroups-subsystem-module-unloading.patch
cgroups-net_cls-as-module.patch
cgroups-blkio-subsystem-as-module.patch
cgroups-clean-up-cgroup_pidlist_find-a-bit.patch
memcg-add-interface-to-move-charge-at-task-migration.patch
memcg-move-charges-of-anonymous-page.patch
memcg-move-charges-of-anonymous-page-cleanup.patch
memcg-improve-performance-in-moving-charge.patch
memcg-avoid-oom-during-moving-charge.patch
memcg-move-charges-of-anonymous-swap.patch
memcg-move-charges-of-anonymous-swap-fix.patch
memcg-improve-performance-in-moving-swap-charge.patch
memcg-improve-performance-in-moving-swap-charge-fix.patch
cgroup-implement-eventfd-based-generic-api-for-notifications.patch
cgroup-implement-eventfd-based-generic-api-for-notifications-kconfig-fix.patch
cgroup-implement-eventfd-based-generic-api-for-notifications-fixes.patch
cgroup-implement-eventfd-based-generic-api-for-notifications-fixes-fix.patch
memcg-extract-mem_group_usage-from-mem_cgroup_read.patch
memcg-rework-usage-of-stats-by-soft-limit.patch
memcg-implement-memory-thresholds.patch
memcg-implement-memory-thresholds-checkpatch-fixes.patch
memcg-implement-memory-thresholds-checkpatch-fixes-fix.patch
memcg-implement-memory-thresholds-check-if-first-threshold-crossed.patch
memcg-typo-in-comment-to-mem_cgroup_print_oom_info.patch
memcg-use-generic-percpu-instead-of-private-implementation.patch
memcg-update-threshold-and-softlimit-at-commit-v2.patch
memcg-share-event-counter-rather-than-duplicate-v2.patch
memcg-update-memcg_testtxt.patch
memcg-handle-panic_on_oom=always-case-v2.patch
cgroups-fix-race-between-userspace-and-kernelspace.patch
cgroups-add-simple-listener-of-cgroup-events-to-documentation.patch
cgroups-add-simple-listener-of-cgroup-events-to-documentation-fix.patch
memcg-update-memcg_testtxt-to-describe-memory-thresholds.patch
memcg-fix-oom-kill-behavior-v3.patch
sysctl-clean-up-vm-related-variable-declarations.patch
sysctl-clean-up-vm-related-variable-declarations-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
