[to-be-updated] refactor-part-of-the-oom-report-in-dump_header.patch removed from -mm tree

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



The patch titled
     Subject: mm: oom-kill, memcg: refactor part of the oom report in dump_header
has been removed from the -mm tree.  Its filename was
     refactor-part-of-the-oom-report-in-dump_header.patch

This patch was dropped because an updated version will be merged

------------------------------------------------------
From: yuzhoujian <yuzhoujian@xxxxxxxxxxxxxxx>
Subject: mm: oom-kill, memcg: refactor part of the oom report in dump_header

dump_header() does not print the memcg's name when system oom happened, so
users cannot locate the container which contains the task that has been
killed by the oom killer.

Following the advices of David Rientjes and Michal Hocko, refactor part of
the oom report in a backwards compatible way.  After this patch, users can
get the memcg's path from the oom report and check the container name more
quickly.

Below is the part of the oom report in the dmesg
...
[  142.158316] panic cpuset=/ mems_allowed=0-1
[  142.158983] CPU: 15 PID: 8682 Comm: panic Not tainted 4.17.0-rc6+ #13
[  142.159659] Hardware name: Inspur SA5212M4/YZMB-00370-107, BIOS 4.1.10 11/14/2016
[  142.160342] Call Trace:
[  142.161037]  dump_stack+0x78/0xb3
[  142.161734]  dump_header+0x7d/0x334
[  142.162433]  oom_kill_process+0x228/0x490
[  142.163126]  ? oom_badness+0x2a/0x130
[  142.163821]  out_of_memory+0xf0/0x280
[  142.164532]  __alloc_pages_slowpath+0x711/0xa07
[  142.165241]  __alloc_pages_nodemask+0x23f/0x260
[  142.165947]  alloc_pages_vma+0x73/0x180
[  142.166665]  do_anonymous_page+0xed/0x4e0
[  142.167388]  __handle_mm_fault+0xbd2/0xe00
[  142.168114]  handle_mm_fault+0x116/0x250
[  142.168841]  __do_page_fault+0x233/0x4d0
[  142.169567]  do_page_fault+0x32/0x130
[  142.170303]  ? page_fault+0x8/0x30
[  142.171036]  page_fault+0x1e/0x30
[  142.171764] RIP: 0033:0x7f403000a860
[  142.172517] RSP: 002b:00007ffc9f745c28 EFLAGS: 00010206
[  142.173268] RAX: 00007f3f6fd7d000 RBX: 0000000000000000 RCX: 00007f3f7f5cd000
[  142.174040] RDX: 00007f3fafd7d000 RSI: 0000000000000000 RDI: 00007f3f6fd7d000
[  142.174806] RBP: 00007ffc9f745c50 R08: ffffffffffffffff R09: 0000000000000000
[  142.175623] R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000400490
[  142.176542] R13: 00007ffc9f745d30 R14: 0000000000000000 R15: 0000000000000000
[  142.177709] oom-kill: constrain=CONSTRAINT_NONE nodemask=(null) origin_memcg= kill_memcg=/test/test1/test2 task=panic pid= 8622 uid=    0
...

[akpm@xxxxxxxxxxxxxxxxxxxx: s/constrain/constraint/ in printk]
Link: http://lkml.kernel.org/r/1527213613-7922-1-git-send-email-ufo19890607@xxxxxxxxx
Signed-off-by: yuzhoujian <yuzhoujian@xxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Cc: Yang Shi <yang.s@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---

 include/linux/memcontrol.h |   12 ++++++++--
 mm/memcontrol.c            |   42 ++++++++++++++++++++---------------
 mm/oom_kill.c              |   22 +++++++++++++++++-
 3 files changed, 55 insertions(+), 21 deletions(-)

diff -puN include/linux/memcontrol.h~refactor-part-of-the-oom-report-in-dump_header include/linux/memcontrol.h
--- a/include/linux/memcontrol.h~refactor-part-of-the-oom-report-in-dump_header
+++ a/include/linux/memcontrol.h
@@ -477,9 +477,11 @@ void mem_cgroup_handle_over_high(void);
 
 unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
 
-void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
+void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
 				struct task_struct *p);
 
+void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg);
+
 static inline void mem_cgroup_oom_enable(void)
 {
 	WARN_ON(current->memcg_may_oom);
@@ -877,7 +879,13 @@ static inline unsigned long mem_cgroup_g
 }
 
 static inline void
-mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
+					struct task_struct *p)
+{
+}
+
+static inline void
+mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
 {
 }
 
diff -puN mm/memcontrol.c~refactor-part-of-the-oom-report-in-dump_header mm/memcontrol.c
--- a/mm/memcontrol.c~refactor-part-of-the-oom-report-in-dump_header
+++ a/mm/memcontrol.c
@@ -1132,33 +1132,39 @@ static const char *const memcg1_stat_nam
 };
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
+
 /**
- * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller.
- * @memcg: The memory cgroup that went over limit
- * @p: Task that is going to be killed
+ * mem_cgroup_print_oom_context: Print OOM context information including allocation
+ * constraint, nodemask, orgin memcg that has reached its limit, kill memcg that
+ * contains the killed process, killed process's command, pid and pid.
  *
- * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
- * enabled
+ * @oc: pointer to struct oom_control
+ * @p: Task that is going to be killed
  */
-void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
 {
-	struct mem_cgroup *iter;
-	unsigned int i;
-
 	rcu_read_lock();
-
+	pr_cont("origin_memcg=");
+	if (memcg)
+		pr_cont_cgroup_path(memcg->css.cgroup);
 	if (p) {
-		pr_info("Task in ");
+		pr_cont(" kill_memcg=");
 		pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
-		pr_cont(" killed as a result of limit of ");
-	} else {
-		pr_info("Memory limit reached of cgroup ");
+		pr_cont(" task=%s pid=%5d uid=%5d\n", p->comm, p->pid,
+			from_kuid(&init_user_ns, task_uid(p)));
 	}
-
-	pr_cont_cgroup_path(memcg->css.cgroup);
-	pr_cont("\n");
-
 	rcu_read_unlock();
+}
+
+/**
+ * mem_cgroup_print_oom_meminfo: Print OOM memory information relevant to
+ * memory controller.
+ * @memcg: The memory cgroup that went over limit
+ */
+void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *iter;
+	unsigned int i;
 
 	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
 		K((u64)page_counter_read(&memcg->memory)),
diff -puN mm/oom_kill.c~refactor-part-of-the-oom-report-in-dump_header mm/oom_kill.c
--- a/mm/oom_kill.c~refactor-part-of-the-oom-report-in-dump_header
+++ a/mm/oom_kill.c
@@ -421,6 +421,8 @@ static void dump_tasks(struct mem_cgroup
 
 static void dump_header(struct oom_control *oc, struct task_struct *p)
 {
+	enum oom_constraint constraint = constrained_alloc(oc);
+
 	pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=%*pbl, order=%d, oom_score_adj=%hd\n",
 		current->comm, oc->gfp_mask, &oc->gfp_mask,
 		nodemask_pr_args(oc->nodemask), oc->order,
@@ -430,8 +432,26 @@ static void dump_header(struct oom_contr
 
 	cpuset_print_current_mems_allowed();
 	dump_stack();
+	pr_info("oom-kill: constraint=CONSTRAINT_");
+	switch (constraint) {
+	case CONSTRAINT_NONE:
+		pr_cont("NONE ");
+		break;
+	case CONSTRAINT_CPUSET:
+		pr_cont("CPUSET ");
+		break;
+	case CONSTRAINT_MEMORY_POLICY:
+		pr_cont("MEMORY_POLICY ");
+		break;
+	default:
+		pr_cont("MEMCG ");
+		break;
+	}
+	pr_cont("nodemask=%*pbl ", nodemask_pr_args(oc->nodemask));
+	mem_cgroup_print_oom_context(oc->memcg, p);
+	pr_cont("\n");
 	if (is_memcg_oom(oc))
-		mem_cgroup_print_oom_info(oc->memcg, p);
+		mem_cgroup_print_oom_meminfo(oc->memcg);
 	else {
 		show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask);
 		if (is_dump_unreclaim_slabs())
_

Patches currently in -mm which might be from yuzhoujian@xxxxxxxxxxxxxxx are


--
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



[Index of Archives]     [Kernel Archive]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]

  Powered by Linux