page-writeback.c

最新最稳定的Linux内存管理模块源代码

 * balance_dirty_pages() must be called by processes which are generating dirty
 * data.  It looks at the number of dirty pages in the machine and will force
 * the caller to perform writeback if the system is over `vm_dirty_ratio'.
 * If we're over `background_thresh' then pdflush is woken to perform some
 * writeout.
 */
static void balance_dirty_pages(struct address_space *mapping)
{
	long nr_reclaimable, bdi_nr_reclaimable;
	long nr_writeback, bdi_nr_writeback;
	unsigned long background_thresh;
	unsigned long dirty_thresh;
	unsigned long bdi_thresh;
	unsigned long pages_written = 0;
	unsigned long write_chunk = sync_writeback_pages();

	struct backing_dev_info *bdi = mapping->backing_dev_info;

	for (;;) {
		struct writeback_control wbc = {
			.bdi		= bdi,
			.sync_mode	= WB_SYNC_NONE,
			.older_than_this = NULL,
			.nr_to_write	= write_chunk,
			.range_cyclic	= 1,
		};

		get_dirty_limits(&background_thresh, &dirty_thresh,
				&bdi_thresh, bdi);

		nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
					global_page_state(NR_UNSTABLE_NFS);
		nr_writeback = global_page_state(NR_WRITEBACK);

		bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
		bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);

		if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
			break;

		/*
		 * Throttle it only when the background writeback cannot
		 * catch-up. This avoids (excessively) small writeouts
		 * when the bdi limits are ramping up.
		 */
		if (nr_reclaimable + nr_writeback <
				(background_thresh + dirty_thresh) / 2)
			break;

		if (!bdi->dirty_exceeded)
			bdi->dirty_exceeded = 1;

		/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
		 * 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.
		 */
		if (bdi_nr_reclaimable) {
			writeback_inodes(&wbc);
			pages_written += write_chunk - wbc.nr_to_write;
			get_dirty_limits(&background_thresh, &dirty_thresh,
				       &bdi_thresh, bdi);
		}

		/*
		 * In order to avoid the stacked BDI deadlock we need
		 * to ensure we accurately count the 'dirty' pages when
		 * the threshold is low.
		 *
		 * Otherwise it would be possible to get thresh+n pages
		 * reported dirty, even though there are thresh-m pages
		 * actually dirty; with m+n sitting in the percpu
		 * deltas.
		 */
		if (bdi_thresh < 2*bdi_stat_error(bdi)) {
			bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
			bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK);
		} else if (bdi_nr_reclaimable) {
			bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
			bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
		}

		if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
			break;
		if (pages_written >= write_chunk)
			break;		/* We've done our duty */

		congestion_wait(WRITE, HZ/10);
	}

	if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
			bdi->dirty_exceeded)
		bdi->dirty_exceeded = 0;

	if (writeback_in_progress(bdi))
		return;		/* pdflush is already working this queue */

	/*
	 * 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.
	 */
	if ((laptop_mode && pages_written) ||
			(!laptop_mode && (global_page_state(NR_FILE_DIRTY)
					  + global_page_state(NR_UNSTABLE_NFS)
					  > background_thresh)))
		pdflush_operation(background_writeout, 0);
}

void set_page_dirty_balance(struct page *page, int page_mkwrite)
{
	if (set_page_dirty(page) || page_mkwrite) {
		struct address_space *mapping = page_mapping(page);

		if (mapping)
			balance_dirty_pages_ratelimited(mapping);
	}
}

/**
 * balance_dirty_pages_ratelimited_nr - balance dirty memory state
 * @mapping: address_space which was dirtied
 * @nr_pages_dirtied: number of pages which the caller has just dirtied
 *
 * Processes which are dirtying memory should call in here once for each page
 * which was newly dirtied.  The function will periodically check the system's
 * dirty state and will initiate writeback if needed.
 *
 * On really big machines, get_writeback_state is expensive, so try to avoid
 * calling it too often (ratelimiting).  But once we're over the dirty memory
 * limit we decrease the ratelimiting by a lot, to prevent individual processes
 * from overshooting the limit by (ratelimit_pages) each.
 */
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
					unsigned long nr_pages_dirtied)
{
	static DEFINE_PER_CPU(unsigned long, ratelimits) = 0;
	unsigned long ratelimit;
	unsigned long *p;

	ratelimit = ratelimit_pages;
	if (mapping->backing_dev_info->dirty_exceeded)
		ratelimit = 8;

	/*
	 * Check the rate limiting. Also, we do not want to throttle real-time
	 * tasks in balance_dirty_pages(). Period.
	 */
	preempt_disable();
	p =  &__get_cpu_var(ratelimits);
	*p += nr_pages_dirtied;
	if (unlikely(*p >= ratelimit)) {
		*p = 0;
		preempt_enable();
		balance_dirty_pages(mapping);
		return;
	}
	preempt_enable();
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);

void throttle_vm_writeout(gfp_t gfp_mask)
{
	unsigned long background_thresh;
	unsigned long dirty_thresh;

        for ( ; ; ) {
		get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);

                /*
                 * Boost the allowable dirty threshold a bit for page
                 * allocators so they don't get DoS'ed by heavy writers
                 */
                dirty_thresh += dirty_thresh / 10;      /* wheeee... */

                if (global_page_state(NR_UNSTABLE_NFS) +
			global_page_state(NR_WRITEBACK) <= dirty_thresh)
                        	break;
                congestion_wait(WRITE, HZ/10);

		/*
		 * The caller might hold locks which can prevent IO completion
		 * or progress in the filesystem.  So we cannot just sit here
		 * waiting for IO to complete.
		 */
		if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO))
			break;
        }
}

/*
 * writeback at least _min_pages, and keep writing until the amount of dirty
 * memory is less than the background threshold, or until we're all clean.
 */
static void background_writeout(unsigned long _min_pages)
{
	long min_pages = _min_pages;
	struct writeback_control wbc = {
		.bdi		= NULL,
		.sync_mode	= WB_SYNC_NONE,
		.older_than_this = NULL,
		.nr_to_write	= 0,
		.nonblocking	= 1,
		.range_cyclic	= 1,
	};

	for ( ; ; ) {
		unsigned long background_thresh;
		unsigned long dirty_thresh;

		get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
		if (global_page_state(NR_FILE_DIRTY) +
			global_page_state(NR_UNSTABLE_NFS) < background_thresh
				&& min_pages <= 0)
			break;
		wbc.more_io = 0;
		wbc.encountered_congestion = 0;
		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
		wbc.pages_skipped = 0;
		writeback_inodes(&wbc);
		min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
			/* Wrote less than expected */
			if (wbc.encountered_congestion || wbc.more_io)
				congestion_wait(WRITE, HZ/10);
			else
				break;
		}
	}
}

/*
 * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
 * the whole world.  Returns 0 if a pdflush thread was dispatched.  Returns
 * -1 if all pdflush threads were busy.
 */
int wakeup_pdflush(long nr_pages)
{
	if (nr_pages == 0)
		nr_pages = global_page_state(NR_FILE_DIRTY) +
				global_page_state(NR_UNSTABLE_NFS);
	return pdflush_operation(background_writeout, nr_pages);
}

static void wb_timer_fn(unsigned long unused);
static void laptop_timer_fn(unsigned long unused);

static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);

/*
 * Periodic writeback of "old" data.
 *
 * Define "old": the first time one of an inode's pages is dirtied, we mark the
 * dirtying-time in the inode's address_space.  So this periodic writeback code
 * just walks the superblock inode list, writing back any inodes which are
 * older than a specific point in time.
 *
 * Try to run once per dirty_writeback_interval.  But if a writeback event
 * takes longer than a dirty_writeback_interval interval, then leave a
 * one-second gap.
 *
 * older_than_this takes precedence over nr_to_write.  So we'll only write back
 * all dirty pages if they are all attached to "old" mappings.
 */
static void wb_kupdate(unsigned long arg)
{
	unsigned long oldest_jif;
	unsigned long start_jif;
	unsigned long next_jif;
	long nr_to_write;
	struct writeback_control wbc = {
		.bdi		= NULL,
		.sync_mode	= WB_SYNC_NONE,
		.older_than_this = &oldest_jif,
		.nr_to_write	= 0,
		.nonblocking	= 1,
		.for_kupdate	= 1,
		.range_cyclic	= 1,
	};

	sync_supers();

	oldest_jif = jiffies - dirty_expire_interval;
	start_jif = jiffies;
	next_jif = start_jif + dirty_writeback_interval;
	nr_to_write = global_page_state(NR_FILE_DIRTY) +
			global_page_state(NR_UNSTABLE_NFS) +
			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
	while (nr_to_write > 0) {
		wbc.more_io = 0;
		wbc.encountered_congestion = 0;
		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
		writeback_inodes(&wbc);
		if (wbc.nr_to_write > 0) {
			if (wbc.encountered_congestion || wbc.more_io)
				congestion_wait(WRITE, HZ/10);
			else
				break;	/* All the old data is written */
		}
		nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
	}
	if (time_before(next_jif, jiffies + HZ))
		next_jif = jiffies + HZ;
	if (dirty_writeback_interval)
		mod_timer(&wb_timer, next_jif);
}

/*
 * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
 */
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec_userhz_jiffies(table, write, file, buffer, length, ppos);
	if (dirty_writeback_interval)
		mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
	else
		del_timer(&wb_timer);
	return 0;
}

static void wb_timer_fn(unsigned long unused)
{
	if (pdflush_operation(wb_kupdate, 0) < 0)
		mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */
}

static void laptop_flush(unsigned long unused)
{
	sys_sync();
}

static void laptop_timer_fn(unsigned long unused)
{
	pdflush_operation(laptop_flush, 0);
}

/*
 * We've spun up the disk and we're in laptop mode: schedule writeback
 * of all dirty data a few seconds from now.  If the flush is already scheduled
 * then push it back - the user is still using the disk.
 */
void laptop_io_completion(void)
{
	mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode);
}

/*
 * We're in laptop mode and we've just synced. The sync's writes will have
 * caused another writeback to be scheduled by laptop_io_completion.
 * Nothing needs to be written back anymore, so we unschedule the writeback.
 */
void laptop_sync_completion(void)
{
	del_timer(&laptop_mode_wb_timer);
}

/*
 * If ratelimit_pages is too high then we can get into dirty-data overload
 * if a large number of processes all perform writes at the same time.
 * If it is too low then SMP machines will call the (expensive)
 * get_writeback_state too often.
 *
 * Here we set ratelimit_pages to a level which ensures that when all CPUs are
 * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory
 * thresholds before writeback cuts in.
 *
 * But the limit should not be set too high.  Because it also controls the
 * amount of memory which the balance_dirty_pages() caller has to write back.
 * If this is too large then the caller will block on the IO queue all the
 * time.  So limit it to four megabytes - the balance_dirty_pages() caller
 * will write six megabyte chunks, max.
 */

void writeback_set_ratelimit(void)
{
	ratelimit_pages = vm_total_pages / (num_online_cpus() * 32);
	if (ratelimit_pages < 16)
		ratelimit_pages = 16;
	if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024)
		ratelimit_pages = (4096 * 1024) / PAGE_CACHE_SIZE;
}

static int __cpuinit
ratelimit_handler(struct notifier_block *self, unsigned long u, void *v)
{
	writeback_set_ratelimit();
	return NOTIFY_DONE;
}

static struct notifier_block __cpuinitdata ratelimit_nb = {
	.notifier_call	= ratelimit_handler,
	.next		= NULL,
};

/*
 * Called early on to tune the page writeback dirty limits.
 *
 * We used to scale dirty pages according to how total memory
 * related to pages that could be allocated for buffers (by
 * comparing nr_free_buffer_pages() to vm_total_pages.
 *
 * However, that was when we used "dirty_ratio" to scale with
 * all memory, and we don't do that any more. "dirty_ratio"
 * is now applied to total non-HIGHPAGE memory (by subtracting
 * totalhigh_pages from vm_total_pages), and as such we can't
 * get into the old insane situation any more where we had
 * large amounts of dirty pages compared to a small amount of
 * non-HIGHMEM memory.
 *
 * But we might still want to scale the dirty_ratio by how
 * much memory the box has..
 */
void __init page_writeback_init(void)
{
	int shift;

	mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
	writeback_set_ratelimit();
	register_cpu_notifier(&ratelimit_nb);

	shift = calc_period_shift();
	prop_descriptor_init(&vm_completions, shift);
	prop_descriptor_init(&vm_dirties, shift);
}

/**
 * write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
 * @mapping: address space structure to write
 * @wbc: subtract the number of written pages from *@wbc->nr_to_write
 * @writepage: function called for each page
 * @data: data passed to writepage function
 *
 * If a page is already under I/O, write_cache_pages() skips it, even
 * if it's dirty.  This is desirable behaviour for memory-cleaning writeback,
 * but it is INCORRECT for data-integrity system calls such as fsync().  fsync()
 * and msync() need to guarantee that all the data which was dirty at the time
 * the call was made get new I/O started against them.  If wbc->sync_mode is
 * WB_SYNC_ALL then we were called for data integrity and we must wait for
 * existing IO to complete.
 */
int write_cache_pages(struct address_space *mapping,
		      struct writeback_control *wbc, writepage_t writepage,
		      void *data)
{
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	int ret = 0;
	int done = 0;
	struct pagevec pvec;
	int nr_pages;
	pgoff_t uninitialized_var(writeback_index);
	pgoff_t index;
	pgoff_t end;		/* Inclusive */
	pgoff_t done_index;
	int cycled;
	int range_whole = 0;
	long nr_to_write = wbc->nr_to_write;

	if (wbc->nonblocking && bdi_write_congested(bdi)) {
		wbc->encountered_congestion = 1;
		return 0;
	}

	pagevec_init(&pvec, 0);
	if (wbc->range_cyclic) {
		writeback_index = mapping->writeback_index; /* prev offset */
		index = writeback_index;
		if (index == 0)
			cycled = 1;
		else
			cycled = 0;
		end = -1;
	} else {
		index = wbc->range_start >> PAGE_CACHE_SHIFT;
		end = wbc->range_end >> PAGE_CACHE_SHIFT;
		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
			range_whole = 1;
		cycled = 1; /* ignore range_cyclic tests */
	}
retry: