balance_dirty_pages_ratelimited分析

balance_dirty_pages_ratelimited分析

• nr_dirtied_pause：当前task的脏页门限；
• dirty_exceeded：全局的脏页数超过门限或者该bdi的脏页数超过门限；（dirty_exceeded = (bdi_dirty > bdi_thresh) &&((nr_dirty > dirty_thresh) || strictlimit); ）
• bdp_ratelimits：percpu变量，当前CPU的脏页数
• ratelimit_pages：CPU的脏页门限

调用balance_dirty_pages的条件有：

1：当前task的脏页数量大于ratelimit ，（如果dirty_exceeded为0，则为current->nr_dirtied_pause；如果dirty_exceeded为1，则最大为32KB）

2：当前CPU的脏页数超过了门限值ratelimit_pages；

3：当前脏页数+退出线程遗留的脏页超过了门限；

void balance_dirty_pages_ratelimited(struct address_space *mapping)
{
	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
	int ratelimit;
	int *p;

	if (!bdi_cap_account_dirty(bdi))
		return;

	ratelimit = current->nr_dirtied_pause;  /* 门限：初始值为32表示128KB */
	if (bdi->dirty_exceeded)                /* 如果该值设置了，则需要通过降低平衡触发的门限来加速脏页回收 */
		ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10));  /* 重新修改门限，最大为32KB，初始值128KB，加快回收 */

	preempt_disable();
	/*
	 * This prevents one CPU to accumulate too many dirtied pages without
	 * calling into balance_dirty_pages(), which can happen when there are
	 * 1000+ tasks, all of them start dirtying pages at exactly the same
	 * time, hence all honoured too large initial task->nr_dirtied_pause.
	 */
	/* 即保证当前线程脏页数超过门限，或者当前CPU超过门限，都要回收 */
	p =  this_cpu_ptr(&bdp_ratelimits);  /* 当前CPU的脏页计数 */
	if (unlikely(current->nr_dirtied >= ratelimit))  /* 如果当前线程脏页数超过门限值，则肯定会触发下面的回收流程。同时重新计算当前CPU的脏页数 */
		*p = 0;
	else if (unlikely(*p >= ratelimit_pages)) {     /* 默认值为32页 */ /* 当前线程的脏页数未超过门限值，但是当前CPU的脏页数超过CPU脏页门限值，则设置门限为0，肯定会触发回收。同时重新计算当前CPU的脏页数 */
		*p = 0;
		ratelimit = 0;
	}
	/*
	 * Pick up the dirtied pages by the exited tasks. This avoids lots of
	 * short-lived tasks (eg. gcc invocations in a kernel build) escaping
	 * the dirty throttling and livelock other long-run dirtiers.
	 */
	p = this_cpu_ptr(&dirty_throttle_leaks);   /* 退出的线程，也放在这里处理 */
	if (*p > 0 && current->nr_dirtied < ratelimit) {
		unsigned long nr_pages_dirtied;
		nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied);
		*p -= nr_pages_dirtied;
		current->nr_dirtied += nr_pages_dirtied;
	}
	preempt_enable();

	if (unlikely(current->nr_dirtied >= ratelimit))    /* 当前线程脏页超过门限值 */
		balance_dirty_pages(mapping, current->nr_dirtied);
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited);

正常情况下应该是周期回收和背景回收，不会占用当前task的时间。但是当dirty > dirty_freerun_ceiling(thresh, bg_thresh) 即脏页数大于直接回收门限和背景回收门限的1/2时，需要将当前CPU休眠一会，让回收线程工作。

但是dirty <= dirty_freerun_ceiling(thresh, bg_thresh)，也会动态的调整nr_dirtied_pause ，号让其更好的回收，调整的策略为：

static unsigned long dirty_poll_interval(unsigned long dirty,
					 unsigned long thresh)
{
	/*  */
	if (thresh > dirty)  /*  */
		return 1UL << (ilog2(thresh - dirty) >> 1);

	return 1;  /* 脏页数超过门限值，则返回1页就需要回收 */
}

至于为什么这么做，可以参考如下解析：

/*

Ideally if we know there are N dirtiers, it’s safe to let each task

poll at (thresh-dirty)/N without exceeding the dirty limit.

However we neither know the current N, nor is sure whether it will

rush high at next second. So sqrt is used to tolerate larger N on

increased (thresh-dirty) gap:

irb> 0.upto(10) { |i| mb=2**i; pages=mb<<(20-12); printf “%4d\t%4d\n”, mb, Math.sqrt(pages)}

1 16

2 22

4 32

8 45

16 64

32 90

64 128

128 181

256 256

512 362

1024 512

The above table means, given 1MB (or 1GB) gap and the dd tasks polling

balance_dirty_pages() on every 16 (or 512) pages, the dirty limit

won’t be exceeded as long as there are less than 16 (or 512) concurrent

dd’s.

Note that dirty_poll_interval() will mainly be used when (dirty < freerun).

When the dirty pages are floating in range [freerun, limit],

“[PATCH 14/18] writeback: control dirty pause time” will independently

adjust tsk->nr_dirtied_pause to get suitable pause time.

So the sqrt naturally leads to less overheads and more N tolerance for

large memory servers, which have large (thresh-freerun) gaps.

*/

void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
{
	/* 可用内存并不是系统所有内存，而是free pages + reclaimable pages(文件页) */
	const unsigned long available_memory = global_dirtyable_memory();
	unsigned long background;
	unsigned long dirty;
	struct task_struct *tsk;

	if (vm_dirty_bytes)
		dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
	else
		dirty = (vm_dirty_ratio * available_memory) / 100;

	if (dirty_background_bytes)
		background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
	else
		background = (dirty_background_ratio * available_memory) / 100;

	if (background >= dirty)
		background = dirty / 2;
	tsk = current;
	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {   /* 如果设置了该属性PF_LESS_THROTTLE或者是实时线程，门限稍微提高1/4 */
		background += background / 4;
		dirty += dirty / 4;
	}
	*pbackground = background;
	*pdirty = dirty;
	trace_global_dirty_state(background, dirty);
}

static unsigned long global_dirtyable_memory(void)
{
	unsigned long x;

	/* 可用内存并不是系统所有内存，而是free pages + file pages(文件页) */
	x = global_page_state(NR_FREE_PAGES);
	x -= min(x, dirty_balance_reserve);

	x += global_page_state(NR_INACTIVE_FILE);
	x += global_page_state(NR_ACTIVE_FILE);

	if (!vm_highmem_is_dirtyable)
		x -= highmem_dirtyable_memory(x);

	return x + 1;	/* Ensure that we never return 0 */
}

1：如果可回收+正在回写脏页数量 < background和显式回写阈值的均值此次先不启动回写，否则启动background回写

2：如果可回收的脏页数大于背景回收门限值，则触发背景回收执行；

static void balance_dirty_pages(struct address_space *mapping,
				unsigned long pages_dirtied)
{
	unsigned long nr_reclaimable;	/* = file_dirty + unstable_nfs */
	unsigned long nr_dirty;  /* = file_dirty + writeback + unstable_nfs */
	unsigned long background_thresh;
	unsigned long dirty_thresh;
	long period;
	long pause;
	long max_pause;
	long min_pause;
	int nr_dirtied_pause;
	bool dirty_exceeded = false;
	unsigned long task_ratelimit;
	unsigned long dirty_ratelimit;
	unsigned long pos_ratio;
	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
	bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; //单独门限值回收
	unsigned long start_time = jiffies;

	for (;;) {
		unsigned long now = jiffies;
		unsigned long uninitialized_var(bdi_thresh);
		unsigned long thresh;
		unsigned long uninitialized_var(bdi_dirty);
		unsigned long dirty;
		unsigned long bg_thresh;

		/*
		 * Unstable writes are a feature of certain networked
		 * filesystems (i.e. NFS) in which data may have been
		 * written to the server's write cache, but has not yet
		 * been flushed to permanent storage.
		 */
		nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
					global_page_state(NR_UNSTABLE_NFS);  /* 全局 文件脏页  + 网络文件系统 */  /* = file_dirty + unstable_nfs */
		nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK); /*全局 文件总的脏页+包括正在回写 */  /* = file_dirty + writeback + unstable_nfs */

		global_dirty_limits(&background_thresh, &dirty_thresh);//获取两个门限值

		if (unlikely(strictlimit)) {  /* 单独bdi回收 */
			bdi_dirty_limits(bdi, dirty_thresh, background_thresh,
					 &bdi_dirty, &bdi_thresh, &bg_thresh);

			dirty = bdi_dirty;
			thresh = bdi_thresh;
		} else {                       /* 全局回收 */
			dirty = nr_dirty;          /* 全局 文件总的脏页+包括正在回写 */
			thresh = dirty_thresh;
			bg_thresh = background_thresh;
		}

		/*
		 * Throttle it only when the background writeback cannot
		 * catch-up. This avoids (excessively) small writeouts
		 * when the bdi limits are ramping up in case of !strictlimit.
		 *
		 * In strictlimit case make decision based on the bdi counters
		 * and limits. Small writeouts when the bdi limits are ramping
		 * up are the price we consciously pay for strictlimit-ing.
		 */
		/* 小于直接回收文件和背景回收的/2, 不占用本线程时间；否则说明背景回收没有运行，需要占用本线程时间,  */
		if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh)) {  //(thresh + bg_thresh) / 2; 不回收
			current->dirty_paused_when = now;
			current->nr_dirtied = 0;                 /* 脏页数量重新置0 */
			current->nr_dirtied_pause =
				dirty_poll_interval(dirty, thresh);   /* 重新设置线程脏页门限 */
			break;
		}

		if (unlikely(!writeback_in_progress(bdi)))  /* 唤醒真正的回写线程 */
			bdi_start_background_writeback(bdi);

		if (!strictlimit)
			bdi_dirty_limits(bdi, dirty_thresh, background_thresh,
					 &bdi_dirty, &bdi_thresh, NULL);

		//nr_dirty > dirty_thresh
		/*
		 * 如果是单个bdi独自回收，当前bdi的 脏页超过门限即回收；
		 * 如果是整个系统回收，当前bdi超过门限且系统的脏页也要超超过门限;
		 */
		dirty_exceeded = (bdi_dirty > bdi_thresh) &&
				 ((nr_dirty > dirty_thresh) || strictlimit); //超过门限

		if (dirty_exceeded && !bdi->dirty_exceeded)
			bdi->dirty_exceeded = 1;                        //超过门限，后面需要加速回收

		bdi_update_bandwidth(bdi, dirty_thresh, background_thresh,
				     nr_dirty, bdi_thresh, bdi_dirty,
				     start_time);

		dirty_ratelimit = bdi->dirty_ratelimit;
		pos_ratio = bdi_position_ratio(bdi, dirty_thresh,
					       background_thresh, nr_dirty,
					       bdi_thresh, bdi_dirty);
		task_ratelimit = ((u64)dirty_ratelimit * pos_ratio) >>
							RATELIMIT_CALC_SHIFT;
		max_pause = bdi_max_pause(bdi, bdi_dirty);
		min_pause = bdi_min_pause(bdi, max_pause,
					  task_ratelimit, dirty_ratelimit,
					  &nr_dirtied_pause);

		if (unlikely(task_ratelimit == 0)) {
			period = max_pause;
			pause = max_pause;
			goto pause;
		}
		period = HZ * pages_dirtied / task_ratelimit;
		pause = period;
		if (current->dirty_paused_when)
			pause -= now - current->dirty_paused_when;
		/*
		 * For less than 1s think time (ext3/4 may block the dirtier
		 * for up to 800ms from time to time on 1-HDD; so does xfs,
		 * however at much less frequency), try to compensate it in
		 * future periods by updating the virtual time; otherwise just
		 * do a reset, as it may be a light dirtier.
		 */
		if (pause < min_pause) {
			trace_balance_dirty_pages(bdi,
						  dirty_thresh,
						  background_thresh,
						  nr_dirty,
						  bdi_thresh,
						  bdi_dirty,
						  dirty_ratelimit,
						  task_ratelimit,
						  pages_dirtied,
						  period,
						  min(pause, 0L),
						  start_time);
			if (pause < -HZ) {
				current->dirty_paused_when = now;
				current->nr_dirtied = 0;
			} else if (period) {
				current->dirty_paused_when += period;
				current->nr_dirtied = 0;
			} else if (current->nr_dirtied_pause <= pages_dirtied)
				current->nr_dirtied_pause += pages_dirtied;
			break;
		}
		if (unlikely(pause > max_pause)) {
			/* for occasional dropped task_ratelimit */
			now += min(pause - max_pause, max_pause);
			pause = max_pause;
		}

pause:
		trace_balance_dirty_pages(bdi,
					  dirty_thresh,
					  background_thresh,
					  nr_dirty,
					  bdi_thresh,
					  bdi_dirty,
					  dirty_ratelimit,
					  task_ratelimit,
					  pages_dirtied,
					  period,
					  pause,
					  start_time);
		__set_current_state(TASK_KILLABLE);
		io_schedule_timeout(pause);//有可能会切出去，但最大超过200ms

		current->dirty_paused_when = now + pause;
		current->nr_dirtied = 0;
		current->nr_dirtied_pause = nr_dirtied_pause;

		/*
		 * This is typically equal to (nr_dirty < dirty_thresh) and can
		 * also keep "1000+ dd on a slow USB stick" under control.
		 */
		if (task_ratelimit)
			break;

		/*
		 * In the case of an unresponding NFS server and the NFS dirty
		 * pages exceeds dirty_thresh, give the other good bdi's a pipe
		 * to go through, so that tasks on them still remain responsive.
		 *
		 * In theory 1 page is enough to keep the comsumer-producer
		 * pipe going: the flusher cleans 1 page => the task dirties 1
		 * more page. However bdi_dirty has accounting errors.  So use
		 * the larger and more IO friendly bdi_stat_error.
		 */
		if (bdi_dirty <= bdi_stat_error(bdi))
			break;

		if (fatal_signal_pending(current))
			break;
	}

	if (!dirty_exceeded && bdi->dirty_exceeded)  //如果不超过门限，则置0
		bdi->dirty_exceeded = 0;

	if (writeback_in_progress(bdi))  //正在回收，则退出
		return;

	/*
	 * In laptop mode, we wait until hitting the higher threshold before
	 * starting background writeout, and then write out all the way down
	 * to the lower threshold.  So slow writers cause minimal disk activity.
	 *
	 * In normal mode, we start background writeout at the lower
	 * background_thresh, to keep the amount of dirty memory low.
	 */
	/*
	* 节能模式，起到什么作用呢？？
	*/
	if (laptop_mode)
		return;

	if (nr_reclaimable > background_thresh) //可回收的页面大于background_thresh，则触发线程异步回收
		bdi_start_background_writeback(bdi);
}