- LowMemoryKiller概述
LowMemoryKiller是Android基于Linux的OOM killer定制的进程管理功能，通过对进程的管理来保证Android系统可以流畅运行。避免出现一些由于内存不足造成系统异常。
所有应用进程都是从zygote孵化出来的，记录在AMS中mLruProcesses列表中，由AMS进行统一管理，AMS中会根据进程的状态更新进程对应的oom_adj值，这个值会通过文件传递到kernel中去，kernel有个低内存回收机制，在内存达到一定阀值时会触发清理oom_adj值高的进程腾出更多的内存空间。
- LowMemoryKill的查杀流程
- Framework层
位于ProcessList.java中定义了3种命令类型，这些文件的定义必须跟lmkd.c定义完全一致，格式分别如下：
LMK_TARGET <minfree> <minkillprio> ... (up to 6 pairs)
LMK_PROCPRIO <pid> <prio>
LMK_PROCREMOVE <pid>
上述3个命令的使用都通过ProcessList.java中的如下方法:
功能 | 命令 | 对应方法 |
LMK_PROCPRIO | 设置进程adj | PL.setOomAdj() |
LMK_TARGET | 更新oom_adj | PL.updateOomLevels() |
LMK_PROCREMOVE | 移除进程 | PL.remove() |
当AMS.applyOomAdjLocked()过程,则会设置某个进程的adj;
当AMS.updateConfiguration()过程中便会更新整个各个级别的oom_adj信息.
当AMS.cleanUpApplicationRecordLocked()或者handleAppDiedLocked()过程,则会将某个进程从lmkd策略中移除.
- lmkd
lmkd是由init进程，通过解析init.rc文件来启动的lmkd守护进程，lmkd会创建名为lmkd的socket，节点位于/dev/socket/lmkd，该socket用于跟上层framework交互。
- Kernel层
lowmemorykiller driver位于 drivers/staging/Android/lowmemorykiller.c
1. lowmemorykiller初始化
static struct shrinker lowmem_shrinker = {
.scan_objects = lowmem_scan,
.count_objects = lowmem_count,
.seeks = DEFAULT_SEEKS * 16
};
static int __init lowmem_init(void)
{
register_shrinker(&lowmem_shrinker);
return 0;
}
static void __exit lowmem_exit(void)
{
unregister_shrinker(&lowmem_shrinker);
}
module_init(lowmem_init);
module_exit(lowmem_exit);通过register_shrinker和unregister_shrinker分别用于初始化和退出。
- shrinker
LMK驱动通过注册shrinker来实现的，shrinker是linux kernel标准的回收内存page的机制，由内核线程kswapd负责监控。
当内存不足时kswapd线程会遍历一张shrinker链表，并回调已注册的shrinker函数来回收内存page，kswapd还会周期性唤醒来执行内存操作。每个zone维护active_list和inactive_list链表，内核根据页面活动状态将page在这两个链表之间移动，最终通过shrink_slab和shrink_zone来回收内存页，有兴趣想进一步了解linux内存回收机制，可自行研究，这里再回到LowMemoryKiller的过程分析。
- lowmem_count
static unsigned long lowmem_count(struct shrinker *s,
struct shrink_control *sc)
{
return global_page_state(NR_ACTIVE_ANON) +
global_page_state(NR_ACTIVE_FILE) +
global_page_state(NR_INACTIVE_ANON) +
global_page_state(NR_INACTIVE_FILE);
}ANON代表匿名映射，没有后备存储器；FILE代表文件映射； 内存计算公式= 活动匿名内存 + 活动文件内存 + 不活动匿名内存 + 不活动文件内存
- lowmem_scan
static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
{
struct task_struct *tsk;
struct task_struct *selected = NULL;
unsigned long rem = 0;
int tasksize;
int i;
int ret = 0;
short min_score_adj = OOM_SCORE_ADJ_MAX + 1;
int minfree = 0;
int selected_tasksize = 0;
short selected_oom_score_adj;
int array_size = ARRAY_SIZE(lowmem_adj);
int other_free;
int other_file;
//get mutex lock
if (mutex_lock_interruptible(&scan_mutex) < 0)
return 0;
//get the free
other_free = global_page_state(NR_FREE_PAGES);
if (global_page_state(NR_SHMEM) + total_swapcache_pages() <
global_page_state(NR_FILE_PAGES) + zcache_pages())
other_file = global_page_state(NR_FILE_PAGES) + zcache_pages() -
global_page_state(NR_SHMEM) -
total_swapcache_pages();
else
other_file = 0;
tune_lmk_param(&other_free, &other_file, sc);
//reset the score from the define lowmem_adj
if (lowmem_adj_size < array_size)
array_size = lowmem_adj_size;
if (lowmem_minfree_size < array_size)
array_size = lowmem_minfree_size;
for (i = 0; i < array_size; i++) {
minfree = lowmem_minfree[i];
if (other_free < minfree && other_file < minfree) {
min_score_adj = lowmem_adj[i];
break;
}
}
ret = adjust_minadj(&min_score_adj);
lowmem_print(3, "lowmem_scan %lu, %x, ofree %d %d, ma %hd\n",
sc->nr_to_scan, sc->gfp_mask, other_free,
other_file, min_score_adj);
if (min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
trace_almk_shrink(0, ret, other_free, other_file, 0);
lowmem_print(5, "lowmem_scan %lu, %x, return 0\n",
sc->nr_to_scan, sc->gfp_mask);
mutex_unlock(&scan_mutex);
return 0;
}
selected_oom_score_adj = min_score_adj;
rcu_read_lock();
for_each_process(tsk) {
struct task_struct *p;
short oom_score_adj;
if (tsk->flags & PF_KTHREAD)
continue;
/* if task no longer has any memory ignore it */
if (test_task_flag(tsk, TIF_MM_RELEASED))
continue;
if (time_before_eq(jiffies, lowmem_deathpending_timeout)) {
if (test_task_flag(tsk, TIF_MEMDIE)) {
rcu_read_unlock();
/* give the system time to free up the memory */
msleep_interruptible(20);
mutex_unlock(&scan_mutex);
return 0;
}
}
p = find_lock_task_mm(tsk);
if (!p)
continue;
oom_score_adj = p->signal->oom_score_adj;
if (oom_score_adj < min_score_adj) {
task_unlock(p);
continue;
}
tasksize = get_mm_rss(p->mm);
task_unlock(p);
if (tasksize <= 0)
continue;
if (selected) {
if (oom_score_adj < selected_oom_score_adj)
continue;
if (oom_score_adj == selected_oom_score_adj &&
tasksize <= selected_tasksize)
continue;
}
selected = p;
selected_tasksize = tasksize;
selected_oom_score_adj = oom_score_adj;
lowmem_print(3, "select '%s' (%d), adj %hd, size %d, to kill\n",
p->comm, p->pid, oom_score_adj, tasksize);
}
if (selected) {
long cache_size = other_file * (long)(PAGE_SIZE / 1024);
long cache_limit = minfree * (long)(PAGE_SIZE / 1024);
long free = other_free * (long)(PAGE_SIZE / 1024);
trace_lowmemory_kill(selected, cache_size, cache_limit, free);
lowmem_print(1, "Killing '%s' (%d), adj %hd,\n" \
" to free %ldkB on behalf of '%s' (%d) because\n" \
" cache %ldkB is below limit %ldkB for oom_score_adj %hd\n" \
" Free memory is %ldkB above reserved.\n" \
" Free CMA is %ldkB\n" \
" Total reserve is %ldkB\n" \
" Total free pages is %ldkB\n" \
" Total file cache is %ldkB\n" \
" Total zcache is %ldkB\n" \
" GFP mask is 0x%x\n",
selected->comm, selected->pid,
selected_oom_score_adj,
selected_tasksize * (long)(PAGE_SIZE / 1024),
current->comm, current->pid,
cache_size, cache_limit,
min_score_adj,
other_free * (long)(PAGE_SIZE / 1024),
global_page_state(NR_FREE_CMA_PAGES) *
(long)(PAGE_SIZE / 1024),
totalreserve_pages * (long)(PAGE_SIZE / 1024),
global_page_state(NR_FREE_PAGES) *
(long)(PAGE_SIZE / 1024),
global_page_state(NR_FILE_PAGES) *
(long)(PAGE_SIZE / 1024),
(long)zcache_pages() * (long)(PAGE_SIZE / 1024),
sc->gfp_mask);
if (lowmem_debug_level >= 2 && selected_oom_score_adj == 0) {
show_mem(SHOW_MEM_FILTER_NODES);
dump_tasks(NULL, NULL);
}
lowmem_deathpending_timeout = jiffies + HZ;
set_tsk_thread_flag(selected, TIF_MEMDIE);
send_sig(SIGKILL, selected, 0);
rem += selected_tasksize;
rcu_read_unlock();
/* give the system time to free up the memory */
msleep_interruptible(20);
trace_almk_shrink(selected_tasksize, ret,
other_free, other_file, selected_oom_score_adj);
} else {
trace_almk_shrink(1, ret, other_free, other_file, 0);
rcu_read_unlock();
}
lowmem_print(4, "lowmem_scan %lu, %x, return %lu\n",
sc->nr_to_scan, sc->gfp_mask, rem);
mutex_unlock(&scan_mutex);
return rem;
}
- 总结
本文主要从frameworks的ProcessList.java调整adj，通过socket通信将事件发送给native的守护进程lmkd；lmkd再根据具体的命令来执行相应操作，其主要功能 更新进程的oom_score_adj值以及lowmemorykiller驱动的parameters(包括minfree和adj)；
最后讲到了lowmemorykiller驱动，通过注册shrinker，借助linux标准的内存回收机制，根据当前系统可用内存以及parameters配置参数(adj,minfree)来选取合适的selected_oom_score_adj，再从所有进程中选择adj大于该目标值的并且占用rss内存最大的进程，将其杀掉，从而释放出内存。
- Lowmemorykiller的参数设置
- lmkd参数
oom_adj:代表进程的优先级, 数值越大,优先级越低,越容易被杀. 取值范围[-16, 15]
oom_score_adj: 取值范围[-1000, 1000]
oom_score：lmk策略中貌似并没有看到使用的地方，这个应该是oom才会使用。
想查看某个进程的上述3值，只需要知道pid，查看以下几个节点:
/proc/<pid>/oom_adj
/proc/<pid>/oom_score_adj
/proc/<pid>/oom_score
对于oom_adj与oom_score_adj通过方法lowmem_oom_adj_to_oom_score_adj()建立有一定的映射关系：
当oom_adj = 15, 则oom_score_adj=1000;
当oom_adj < 15, 则oom_score_adj= oom_adj * 1000/17;
例如
oom_score_adj取值: 0, 58, 117, 176, 529, 700, 1000
oom_adj对应值: 0, 1, 2, 3, 9, 12, 15
- driver参数
/sys/module/lowmemorykiller/parameters/minfree (代表page个数)
/sys/module/lowmemorykiller/parameters/adj (代表oom_score_adj)
举例说明：
参数设置：
1,6写入节点/sys/module/lowmemorykiller/parameters/adj
1024,8192写入节点/sys/module/lowmemorykiller/parameters/minfree
策略解读：
当系统可用内存低于8192个pages时，则会杀掉oom_score_adj>=6的进程
当系统可用内存低于1024个pages时，则会杀掉oom_score_adj>=1的进程
