安卓内核内存回收

背景

  一般上层由于业务需要，需要内核提供一些定制的内存回收接口。或者内核层本来就想做内存机制的优化。便需要在原有内存回收机制上做一些hook操作。所以了解Linux内核内存回收流程很重要
  本章节主要讲kswapd线程，当内存低watermark时，kswapd会被唤醒并开始工作。

内存回收步骤

1. kswapd初始化
   1、设置每次swap的page数
   2、创建所有numa节点对应的kswapd线程
2. 项目2
3. 项目3

内存回收详细步骤

1. kswapd初始化

static int __init kswapd_init(void)
{
	int nid;
	swap_setup();//设置page_cluster，作用是确定每次swap in/out多少page(2^page_cluster)
	for_each_node_state(nid, N_MEMORY)//遍历所有numa节点
 		kswapd_run(nid);//为每个numa节点创建kswapd线程
	return 0;
}
void kswapd_run(int nid)
{
	//创建节点id对应的kswapd线程
	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
}

2. 执行kswapd逻辑

static int kswapd(void *p)
{
	for ( ; ; ) {
kswapd_try_sleep:
		//判断kswapd是否进入睡眠
		kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, highest_zoneidx);

		/* Read the new order and highest_zoneidx */
		alloc_order = READ_ONCE(pgdat->kswapd_order);
		highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx);
		WRITE_ONCE(pgdat->kswapd_order, 0);
		WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);

		reclaim_order = balance_pgdat(pgdat, alloc_order, highest_zoneidx);
		if (reclaim_order < alloc_order)
			goto kswapd_try_sleep;
	}

	tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD);

	return 0;
}

static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
				unsigned int highest_zoneidx)
{
	//将kswapd线程加入此内存节点的wait队列
	prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);

	/*
	 * Try to sleep for a short interval. Note that kcompactd will only be
	 * woken if it is possible to sleep for a short interval. This is
	 * deliberate on the assumption that if reclaim cannot keep an
	 * eligible zone balanced that it's also unlikely that compaction will
	 * succeed.
	 */
	if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
		/*
		 * Compaction records what page blocks it recently failed to
		 * isolate pages from and skips them in the future scanning.
		 * When kswapd is going to sleep, it is reasonable to assume
		 * that pages and compaction may succeed so reset the cache.
		 */
		reset_isolation_suitable(pgdat);

		/*
		 * We have freed the memory, now we should compact it to make
		 * allocation of the requested order possible.
		 */
		wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx);

		remaining = schedule_timeout(HZ/10);

		/*
		 * If woken prematurely then reset kswapd_highest_zoneidx and
		 * order. The values will either be from a wakeup request or
		 * the previous request that slept prematurely.
		 */
		if (remaining) {
			WRITE_ONCE(pgdat->kswapd_highest_zoneidx,
					kswapd_highest_zoneidx(pgdat,
							highest_zoneidx));

			if (READ_ONCE(pgdat->kswapd_order) < reclaim_order)
				WRITE_ONCE(pgdat->kswapd_order, reclaim_order);
		}

		finish_wait(&pgdat->kswapd_wait, &wait);
		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
	}

	/*
	 * After a short sleep, check if it was a premature sleep. If not, then
	 * go fully to sleep until explicitly woken up.
	 */
	if (!remaining &&
	    prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
		trace_mm_vmscan_kswapd_sleep(pgdat->node_id);

		/*
		 * vmstat counters are not perfectly accurate and the estimated
		 * value for counters such as NR_FREE_PAGES can deviate from the
		 * true value by nr_online_cpus * threshold. To avoid the zone
		 * watermarks being breached while under pressure, we reduce the
		 * per-cpu vmstat threshold while kswapd is awake and restore
		 * them before going back to sleep.
		 */
		set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);

		if (!kthread_should_stop())
			schedule();

		set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
	} else {
		if (remaining)
			count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
		else
			count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
	}
	finish_wait(&pgdat->kswapd_wait, &wait);
}

4. 尽情期待

源码

  参考kernel 6.1