专题：Linux内存管理专题
关键词：OOM、oom_adj、oom_score、badness。
Linux内核为了提高内存的使用效率采用过度分配内存(over-commit memory)的办法，造成物理内存过度紧张进而触发OOM机制来杀死一些进程回收内存。
该机制会监控那些占用内存过大，尤其是瞬间很快消耗大量内存的进程，为了防止内存耗尽会把该进程杀掉。
1. 关于OOM
内核检测到系统内存不足，在内存分配路径上触发out_of_memory，然后调用select_bad_process()选择一个'bad'进程杀掉，判断和选择一个‘bad'进程的过程由oom_badness()决定。
Linux下每个进程都有自己的OOM权重，在/proc/<pid>/oom_adj里面，范围是-17到+15，取值越高，越容易被杀掉。
下面从几个方便来分析OOM：
- 触发OOM的条件是什么？
- 影响OOM行为有哪些参数？
- OOM流程分析。
- 一个OOM实例的解析。
2. OOM触发路径
在内存分配路径上，当内存不足的时候会触发kswapd、或者内存规整，极端情况会触发OOM，来获取更多内存。
在内存回收失败之后，__alloc_pages_may_oom是OOM的入口，但是主要工作在out_of_memory中进行处理。
由于Linux内存都是以页为单位，所以__alloc_pages_nodemask是必经之处。
alloc_pages
->_alloc_pages
->__alloc_pages_nodemask
->__alloc_pages_slowpath-------------------------此时已经说明内存不够，会触发一些内存回收、内存规整机制，极端情况触发OOM。
->__alloc_pages_may_oom -----------------------进入OOM的开始，包括一些检查动作。 ->out_of_memory------------------------------OOM的核心 ->select_bad_process-----------------------选择最'bad'进程 ->oom_scan_process_thread
->oom_badness----------------------------计算当前进程有多'badness' ->oom_kill_process-------------------------杀死选中的进程
还有一种情况是do_page_fault()，如果产生VM_FAULT_OOM错误，就进入pagefault_out_of_memory()。
asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
unsigned long mmu_meh)
{
...
good_area:
...
fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)-------------------------------------------handle_mm_fault()时产生VM_FAULT_OOM错误，进入out_of_memory处理。
goto out_of_memory;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
BUG();
}
if (fault & VM_FAULT_MAJOR)
tsk->maj_flt++;
else
tsk->min_flt++;
up_read(&mm->mmap_sem);
return;
...
out_of_memory:
pagefault_out_of_memory();
return;
...
}
void pagefault_out_of_memory(void)
{
struct oom_control oc = {
.zonelist = NULL,
.nodemask = NULL,
.memcg = NULL,
.gfp_mask = 0,
.order = 0,------------------------------------------------------------------单个页面情况。
};
...
out_of_memory(&oc);
}
3. 影响OOM的内核参数
参照Linux内存管理 (23)内存sysfs节点和工具的OOM章节。
4. OOM代码分析
OOM的核心数据结构是struct oom_control，在include/linux/oom.h中。
struct oom_control {
/* Used to determine cpuset */
struct zonelist *zonelist;
/* Used to determine mempolicy */
nodemask_t *nodemask;
/* Memory cgroup in which oom is invoked, or NULL for global oom */
struct mem_cgroup *memcg;
/* Used to determine cpuset and node locality requirement */
const gfp_t gfp_mask;----------------------------------发生异常时页面分配掩码。
/*
* order == -1 means the oom kill is required by sysrq, otherwise only
* for display purposes.
*/
const int order;---------------------------------------发生异常时申请页面order大小。
/* Used by oom implementation, do not set */
unsigned long totalpages;
struct task_struct *chosen;----------------------------OOM选中的当前进程结构。
unsigned long chosen_points;---------------------------OOM对进程评分的最高分。
};
__alloc_pages_may_oom是内存分配路径上的OOM入口，在进入OOM之前还会检查一些特殊情况。
static inline struct page *
__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
const struct alloc_context *ac, unsigned long *did_some_progress)
{
struct oom_control oc = {---------------------------------------------------------OOM控制参数。
.zonelist = ac->zonelist,
.nodemask = ac->nodemask,
.memcg = NULL,
.gfp_mask = gfp_mask,
.order = order,
};
struct page *page;
*did_some_progress = 0;
/*
* Acquire the oom lock. If that fails, somebody else is
* making progress for us.
*/
if (!mutex_trylock(&oom_lock)) {
*did_some_progress = 1;
schedule_timeout_uninterruptible(1);
return NULL;
}
page = get_page_from_freelist(gfp_mask | __GFP_HARDWALL, order,
ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac);-----------------------------再次使用高水位检查一次，是否需要启动OOM流程。
if (page)
goto out;
if (!(gfp_mask & __GFP_NOFAIL)) {----------------------------------------------__GFP_NOFAIL是不允许内存申请失败的情况，下面都是允许失败的处理。
/* Coredumps can quickly deplete all memory reserves */
if (current->flags & PF_DUMPCORE)
goto out;
/* The OOM killer will not help higher order allocs */
if (order > PAGE_ALLOC_COSTLY_ORDER)---------------------------------------order超过3的申请失败，不会启动OOM回收。
goto out;
/* The OOM killer does not needlessly kill tasks for lowmem */
if (ac->high_zoneidx < ZONE_NORMAL)
goto out;
if (pm_suspended_storage())
goto out;
/* The OOM killer may not free memory on a specific node */
if (gfp_mask & __GFP_THISNODE)
goto out;
}
/* Exhausted what can be done so it's blamo time */
if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {-------------经过上面各种情况，任然需要进行OOM处理。调用out_of_memory()。
*did_some_progress = 1;
if (gfp_mask & __GFP_NOFAIL) {
page = get_page_from_freelist(gfp_mask, order,
ALLOC_NO_WATERMARKS|ALLOC_CPUSET, ac);-------------------------对于__GFP_NOFAIL的分配情况，降低分配条件从ALLOC_WMARK_HIGH|ALLOC_CPUSET降低到ALLOC_NO_WATERMARKS|ALLOC_CPUSET。
/*
* fallback to ignore cpuset restriction if our nodes
* are depleted
*/
if (!page)
page = get_page_from_freelist(gfp_mask, order,
ALLOC_NO_WATERMARKS, ac);--------------------------------------如果还是分配失败，再次降低分配标准，从ALLOC_NO_WATERMARKS|ALLOC_CPUSET降低到ALLOC_NO_WATERMARKS。真的是为了成功，节操越来越低啊。
}
}
out:
mutex_unlock(&oom_lock);
return page;
}
out_of_memory函数是OOM机制的核心，他可以分为两部分。一是调挑选最’bad‘的进程，二是杀死它。
bool out_of_memory(struct oom_control *oc)
{
unsigned long freed = 0;
enum oom_constraint constraint = CONSTRAINT_NONE;
if (oom_killer_disabled)----------------------------------------------------在freeze_processes会将其置位，即禁止OOM；在thaw_processes会将其清零，即打开OOM。所以，如果在冻结过程，不允许OOM。
return false;
if (!is_memcg_oom(oc)) {
blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
if (freed > 0)
/* Got some memory back in the last second. */
return true;
}
/*
* If current has a pending SIGKILL or is exiting, then automatically
* select it. The goal is to allow it to allocate so that it may
* quickly exit and free its memory.
*/
if (task_will_free_mem(current)) {----------------------------------------如果当前进程正因为各种原因将要退出，或者释放内存，将当前进程作为OOM候选者，然后唤醒OOM reaper去收割进而释放内存。
mark_oom_victim(current);
wake_oom_reaper(current);
return true;
}
/*
* The OOM killer does not compensate for IO-less reclaim.
* pagefault_out_of_memory lost its gfp context so we have to
* make sure exclude 0 mask - all other users should have at least
* ___GFP_DIRECT_RECLAIM to get here.
*/
if (oc->gfp_mask && !(oc->gfp_mask & (__GFP_FS|__GFP_NOFAIL)))-----------如果内存申请掩码包括__GFP_DS或__GFP_NOFAIL，则不进行OOM收割。
return true;
constraint = constrained_alloc(oc);--------------------------------------未定义CONFIG_NUMA返回CONSTRAINT_NONE。
if (constraint != CONSTRAINT_MEMORY_POLICY)
oc->nodemask = NULL;
check_panic_on_oom(oc, constraint);--------------------------------------检查sysctl_panic_on_oom设置，以及是否由sysrq触发，来决定是否触发panic。
if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task &&--------------如果设置了sysctl_oom_kill_allocating_task，那么当内存耗尽时，会把当前申请内存分配的进程杀掉。
current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) &&
current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
get_task_struct(current);
oc->chosen = current;
oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)");
return true;
}
select_bad_process(oc);-------------------------------------------------遍历所有进程，进程下的线程，查找合适的候选进程。
/* Found nothing?!?! Either we hang forever, or we panic. */
if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {------------如果没有合适候选进程，并且OOM不是由sysrq触发的，进入panic。
dump_header(oc, NULL);
panic("Out of memory and no killable processes...\n");
}
if (oc->chosen && oc->chosen != (void *)-1UL) {
oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" :
"Memory cgroup out of memory");----------------------------杀死选中的进程。
schedule_timeout_killable(1);
}
return !!oc->chosen;
}
select_bad_process()通过oom_evaluate_task()来评估每个进程的得分，对于进程1、内核线程、得分低的进程直接跳过。
static void select_bad_process(struct oom_control *oc)
{
if (is_memcg_oom(oc))
mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc);
else {
struct task_struct *p;
rcu_read_lock();
for_each_process(p)----------------------------------------------遍历系统范围内所有进程线程。
if (oom_evaluate_task(p, oc))
break;
rcu_read_unlock();
}
oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages;
}
static int oom_evaluate_task(struct task_struct *task, void *arg)
{
struct oom_control *oc = arg;
unsigned long points;
if (oom_unkillable_task(task, NULL, oc->nodemask))-------------------进程1以及内核线程等等不能被kill的线程跳过。
goto next;
if (!is_sysrq_oom(oc) && tsk_is_oom_victim(task)) {
if (test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags))
goto next;
goto abort;
}
if (oom_task_origin(task)) {
points = ULONG_MAX;
goto select;
}
points = oom_badness(task, NULL, oc->nodemask, oc->totalpages);------对进程task进行打分。
if (!points || points < oc->chosen_points)---------------------------这里保证只取最高分的进程，所以分数最高者被选中。其他情况则直接跳过。
goto next;
/* Prefer thread group leaders for display purposes */
if (points == oc->chosen_points && thread_group_leader(oc->chosen))
goto next;
select:
if (oc->chosen)
put_task_struct(oc->chosen);
get_task_struct(task);
oc->chosen = task;--------------------------------------------------更新OOM选中的进程和当前最高分。
oc->chosen_points = points;
next:
return 0;
abort:
if (oc->chosen)
put_task_struct(oc->chosen);
oc->chosen = (void *)-1UL;
return 1;
}
在oom_badness中计算当前进程的得分，返回选中进程的结构体，以及进程得分ppoints。
oom_badness()是给进程打分的函数，可以说是核心中的核心。最终结果受oom_score_adj和当前进程内存使用量综合影响。
unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
const nodemask_t *nodemask, unsigned long totalpages)
{
long points;
long adj;
if (oom_unkillable_task(p, memcg, nodemask))-------------------------------如果进程不可被杀，直接跳过。
return 0;
p = find_lock_task_mm(p);
if (!p)
return 0;
/*
* Do not even consider tasks which are explicitly marked oom
* unkillable or have been already oom reaped or the are in
* the middle of vfork
*/
adj = (long)p->signal->oom_score_adj;--------------------------------------获取当前进程的oom_score_adj参数。
if (adj == OOM_SCORE_ADJ_MIN ||
test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
in_vfork(p)) {
task_unlock(p);
return 0;--------------------------------------------------------------如果当前进程oom_score_adj为OOM_SCORE_ADJ_MIN的话，就返回0.等于告诉OOM，此进程不参数'bad'评比。
}
/*
* The baseline for the badness score is the proportion of RAM that each
* task's rss, pagetable and swap space use.
*/
points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) +
atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm);-----------------可以看出points综合了内存占用情况，包括RSS部分、swap file或者swap device占用内存、以及页表占用内存。
task_unlock(p);
/*
* Root processes get 3% bonus, just like the __vm_enough_memory()
* implementation used by LSMs.
*/
if (has_capability_noaudit(p, CAP_SYS_ADMIN))------------------------------如果是root用户，增加3%的使用特权。
points -= (points * 3) / 100;
/* Normalize to oom_score_adj units */
adj *= totalpages / 1000;--------------------------------------------------这里可以看出oom_score_adj对最终分数的影响，如果oom_score_adj小于0，则最终points就会变小，进程更加不会被选中。
points += adj;-------------------------------------------------------------将归一化后的adj和points求和，作为当前进程的分数。
/*
* Never return 0 for an eligible task regardless of the root bonus and
* oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
*/
return points > 0 ? points : 1;
}
oom_kill_process()用于杀死最高分的进程，包括进程下的线程。
static void oom_kill_process(struct oom_control *oc, const char *message)
{
struct task_struct *p = oc->chosen;
unsigned int points = oc->chosen_points;
struct task_struct *victim = p;
struct task_struct *child;
struct task_struct *t;
struct mm_struct *mm;
unsigned int victim_points = 0;
static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
bool can_oom_reap = true;
task_lock(p);
if (task_will_free_mem(p)) {------------------------------------------对于非coredump正处于退出状态的线程，标注TIF_MEMDIE并唤醒reaper线程进行收割，然后退出。
mark_oom_victim(p);
wake_oom_reaper(p);
task_unlock(p);
put_task_struct(p);
return;
}
task_unlock(p);
if (__ratelimit(&oom_rs))
dump_header(oc, p);----------------------------------------------在kill进程之前，将系统栈信息、内存信息、所有进程的内存消耗情况打印。
pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
message, task_pid_nr(p), p->comm, points);-----------------------输出将要kill掉的进程名、pid、score。
/*
* If any of p's children has a different mm and is eligible for kill,
* the one with the highest oom_badness() score is sacrificed for its
* parent. This attempts to lose the minimal amount of work done while
* still freeing memory.
*/
read_lock(&tasklist_lock);
for_each_thread(p, t) {-----------------------------------------------遍历进程下的线程
list_for_each_entry(child, &t->children, sibling) {
unsigned int child_points;
if (process_shares_mm(child, p->mm))
continue;
/*
* oom_badness() returns 0 if the thread is unkillable
*/
child_points = oom_badness(child,
oc->memcg, oc->nodemask, oc->totalpages);-----------------计算子线程的得分情况
if (child_points > victim_points) {---------------------------将得分最高者计为victim，得分为victim_points。
put_task_struct(victim);
victim = child;
victim_points = child_points;
get_task_struct(victim);
}
}
}
read_unlock(&tasklist_lock);
p = find_lock_task_mm(victim);
if (!p) {
put_task_struct(victim);
return;
} else if (victim != p) {
get_task_struct(p);
put_task_struct(victim);
victim = p;
}
/* Get a reference to safely compare mm after task_unlock(victim) */
mm = victim->mm;
atomic_inc(&mm->mm_count);
/*
* We should send SIGKILL before setting TIF_MEMDIE in order to prevent
* the OOM victim from depleting the memory reserves from the user
* space under its control.
*/
do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);--------------发送SIGKILL信号给victim进程。
mark_oom_victim(victim);-----------------------------------------------标注TIF_MEMDIE是因为OOM被杀死。
pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
K(get_mm_counter(victim->mm, MM_ANONPAGES)),
K(get_mm_counter(victim->mm, MM_FILEPAGES)),
K(get_mm_counter(victim->mm, MM_SHMEMPAGES)));---------------------被kill进程的内存信息。
task_unlock(victim);
/*
* Kill all user processes sharing victim->mm in other thread groups, if
* any. They don't get access to memory reserves, though, to avoid
* depletion of all memory. This prevents mm->mmap_sem livelock when an
* oom killed thread cannot exit because it requires the semaphore and
* its contended by another thread trying to allocate memory itself.
* That thread will now get access to memory reserves since it has a
* pending fatal signal.
*/
rcu_read_lock();
for_each_process(p) {--------------------------------------------------继续处理共享内存的相关线程
if (!process_shares_mm(p, mm))
continue;
if (same_thread_group(p, victim))
continue;
if (is_global_init(p)) {
can_oom_reap = false;
set_bit(MMF_OOM_SKIP, &mm->flags);
pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n",
task_pid_nr(victim), victim->comm,
task_pid_nr(p), p->comm);
continue;
}
/*
* No use_mm() user needs to read from the userspace so we are
* ok to reap it.
*/
if (unlikely(p->flags & PF_KTHREAD))-----------------------------内核线程跳过。
continue;
do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
}
rcu_read_unlock();
if (can_oom_reap)
wake_oom_reaper(victim);
mmdrop(mm);---------------------------------------------------------释放mm空间的内存。包括申请的页面、mm结构体等。
put_task_struct(victim);--------------------------------------------释放task_struct占用的内存空间，包括cgroup等等。
}
dump_head()有助于发现OOM现场，找出OOM原因。
static void dump_header(struct oom_control *oc, struct task_struct *p)
{
nodemask_t *nm = (oc->nodemask) ? oc->nodemask : &cpuset_current_mems_allowed;
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(nm), oc->order,
current->signal->oom_score_adj);
if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order)
pr_warn("COMPACTION is disabled!!!\n");
cpuset_print_current_mems_allowed();
dump_stack();-------------------------------------------------------输出当前现场的栈信息。
if (oc->memcg)
mem_cgroup_print_oom_info(oc->memcg, p);
else
show_mem(SHOW_MEM_FILTER_NODES);--------------------------------输出整个系统的内存使用情况。
if (sysctl_oom_dump_tasks)
dump_tasks(oc->memcg, oc->nodemask);----------------------------dump系统所有进程的内存使用情况。
}
static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
struct task_struct *p;
struct task_struct *task;
pr_info("[ pid ] uid tgid total_vm rss nr_ptes nr_pmds swapents oom_score_adj name\n");
rcu_read_lock();
for_each_process(p) {
if (oom_unkillable_task(p, memcg, nodemask))-------------------不可被kill的进程不显示。
continue;
task = find_lock_task_mm(p);-----------------------------------内核线程等没有自己的mm，也无法被kill，所以不显示。
if (!task) {
/*
* This is a kthread or all of p's threads have already
* detached their mm's. There's no need to report
* them; they can't be oom killed anyway.
*/
continue;
}
pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %8lu %5hd %s\n",
task->pid, from_kuid(&init_user_ns, task_uid(task)),
task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
atomic_long_read(&task->mm->nr_ptes),
mm_nr_pmds(task->mm),
get_mm_counter(task->mm, MM_SWAPENTS),
task->signal->oom_score_adj, task->comm);-----------------total_vm和rss单位都是页。
task_unlock(task);
}
rcu_read_unlock();
}
5. OOM实例解析
对照一个OOM实例并解析如下：
[19174.926798] copy invoked oom-killer: gfp_mask=0x24200c8(GFP_USER|__GFP_MOVABLE), nodemask=0, order=0, oom_score_adj=0--------参考dump_header()，输出OOM产生现场线程信息，包括分配掩码、OOM信息。 [19174.937586] CPU: 0 PID: 163 Comm: copy Not tainted 4.9.56 #1-----------------------------------------------------------------参考show_stack()，显示栈信息。可以看出OOM现场的调用信息，这里可以看出是CMA分配出发了OOM。 [19174.943274] Call Trace: [<802f63c2>] dump_stack+0x1e/0x3c [<80132224>] dump_header.isra.6+0x84/0x1a0 [<800f2d68>] oom_kill_process+0x23c/0x49c [<800f32fc>] out_of_memory+0xb0/0x3a0 [<800f7834>] __alloc_pages_nodemask+0xa84/0xb5c [<801306b8>] alloc_migrate_target+0x34/0x6c [<8012f30c>] migrate_pages+0x108/0xbe4 [<800f8a0c>] alloc_contig_range+0x188/0x378 [<80130c54>] cma_alloc+0x100/0x220 [<80388fe2>] dma_alloc_from_contiguous+0x2e/0x48 [<8037bb30>] xxxxx_dma_alloc_coherent+0x48/0xdc [<8037be8c>] mem_zone_ioctl+0xf0/0x198 [<80148cec>] do_vfs_ioctl+0x84/0x70c [<80149408>] SyS_ioctl+0x94/0xb8 [<8004a246>] csky_systemcall+0x96/0xe0 [19175.001223] Mem-Info:--------------------------------------------------------------------------------------------------------参考show_mem()，输出系统内存详细使用情况。这里可以看出free=592很少，active_anon和shmem非常大。 [19175.003535] active_anon:99682 inactive_anon:12 isolated_anon:1---------------------------------------------------------------显示当前系统所有node不同类型页面的统计信息，单位是页面。 [19175.003535] active_file:55 inactive_file:75 isolated_file:0 [19175.003535] unevictable:0 dirty:0 writeback:0 unstable:0 [19175.003535] slab_reclaimable:886 slab_unreclaimable:652 [19175.003535] mapped:2 shmem:91862 pagetables:118 bounce:0 [19175.003535] free:592 free_pcp:61 free_cma:0 [19175.035394] Node 0 active_anon:398728kB inactive_anon:48kB active_file:220kB inactive_file:300kB unevictable:0kB isolated(anon):4kB isolated(file):0kB mapped:8kB dirty:0kB writeback:0kB shmem:367448kB writeback_tmp:0kB unstable:0kB pages_scanned:2515 all_unreclaimable? yes--------------------------------------------------------------------------------------------------------------------------------显示单个节点的内存统计信息，单位是kB。 [19175.059602] Normal free:2368kB min:2444kB low:3052kB high:3660kB active_anon:398728kB inactive_anon:48kB active_file:220kB inactive_file:300kB unevictable:0kB writepending:0kB present:1048572kB managed:734584kB mlocked:0kB slab_reclaimable:3544kB slab_unreclaimable:2608kB kernel_stack:624kB pagetables:472kB bounce:0kB free_pcp:244kB local_pcp:244kB free_cma:0kB--------------------------------------------------------------------------------------------------------------------------------显示某一zone下内存统计信息，单位是kB。 [19175.091602] lowmem_reserve[]: 0 0 0 [19175.095144] Normal: 21*4kB (MHI) 14*8kB (MHI) 13*16kB (HI) 2*32kB (HI) 4*64kB (MI) 2*128kB (MH) 0*256kB 2*512kB (HI) 1*1024kB (H) 1*2048kB (I) 0*4096kB = 5076kB--------------------------------------------------------------------------------------------------------------------------------显示某一zone的按页面可迁移类型划分页面大小，单位是KB。M表示Movable，U表示Unmovable，E表示rEclaimable，H表示Highatomic，C表示CMA，I表示Isolate。 91996 total pagecache pages [19175.112370] 262143 pages RAM [19175.115254] 0 pages HighMem/MovableOnly [19175.119106] 78497 pages reserved [19175.122350] 90112 pages cma reserved [19175.125942] [ pid ] uid tgid total_vm rss nr_ptes nr_pmds swapents oom_score_adj name-------------------------------参考dump_tasks(),输出系统可被kill的进程内存使用情况。 [19175.134514] [ 135] 0 135 1042 75 4 0 0 -1000 sshd [19175.143070] [ 146] 0 146 597 141 3 0 0 0 autologin [19175.152057] [ 147] 0 147 608 152 4 0 0 0 sh [19175.160434] [ 161] 0 161 109778 7328 104 0 0 0 xxxxx [19175.169068] Out of memory: Kill process 161 (xxxxx) score 39 or sacrifice child [19175.176439] Killed process 161 (xxxxx) total-vm:439112kB, anon-rss:29304kB, file-rss:8kB, shmem-rss:0kB
通过上面的信息可以知道是哪个进程、OOM现场、哪些内存消耗太多。
这里需要重点查看系统的active_anon和shmem为什么如此大，造成了OOM。
相关阅读：《Linux OOM机制介绍》、《Linux内核OOM机制的详细分析》、《Linux内核OOM机制分析》
来源：https://www.cnblogs.com/arnoldlu/p/8567559.html