writeback fixes and trace events

@@ -437,10 +437,17 @@ void global_dirty_limits(unsigned long *
 	*pdirty = dirty;
 }
 
-/*
+/**
  * bdi_dirty_limit - @bdi's share of dirty throttling threshold
+ * @bdi: the backing_dev_info to query
+ * @dirty: global dirty limit in pages
+ *
+ * Returns @bdi's dirty limit in pages. The term "dirty" in the context of
+ * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages.
+ * And the "limit" in the name is not seriously taken as hard limit in
+ * balance_dirty_pages().
  *
- * Allocate high/low dirty limits to fast/slow devices, in order to prevent
+ * It allocates high/low dirty limits to fast/slow devices, in order to prevent
  * - starving fast devices
  * - piling up dirty pages (that will take long time to sync) on slow devices
  *

@@ -244,13 +244,8 @@ void task_dirty_inc(struct task_struct *
 static void bdi_writeout_fraction(struct backing_dev_info *bdi,
 		long *numerator, long *denominator)
 {
-	if (bdi_cap_writeback_dirty(bdi)) {
-		prop_fraction_percpu(&vm_completions, &bdi->completions,
+	prop_fraction_percpu(&vm_completions, &bdi->completions,
 				numerator, denominator);
-	} else {
-		*numerator = 0;
-		*denominator = 1;
-	}
 }
 
 static inline void task_dirties_fraction(struct task_struct *tsk,

@@ -495,6 +490,9 @@ static void balance_dirty_pages(struct a
 	bool dirty_exceeded = false;
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 
+	if (!bdi_cap_account_dirty(bdi))
+		return;
+
 	for (;;) {
 		struct writeback_control wbc = {
 			.sync_mode	= WB_SYNC_NONE,

@@ -346,6 +346,8 @@ writeback_single_inode(struct inode *ino
 		       struct writeback_control *wbc)
 {
 	struct address_space *mapping = inode->i_mapping;
+	long per_file_limit = wbc->per_file_limit;
+	long uninitialized_var(nr_to_write);
 	unsigned dirty;
 	int ret;
 

@@ -385,8 +387,16 @@ writeback_single_inode(struct inode *ino
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&wb->list_lock);
 
+	if (per_file_limit) {
+		nr_to_write = wbc->nr_to_write;
+		wbc->nr_to_write = per_file_limit;
+	}
+
 	ret = do_writepages(mapping, wbc);
 
+	if (per_file_limit)
+		wbc->nr_to_write += nr_to_write - per_file_limit;
+
 	/*
 	 * Make sure to wait on the data before writing out the metadata.
 	 * This is important for filesystems that modify metadata on data

@@ -710,6 +720,7 @@ static long wb_writeback(struct bdi_writ
 
 		wbc.more_io = 0;
 		wbc.nr_to_write = write_chunk;
+		wbc.per_file_limit = write_chunk;
 		wbc.pages_skipped = 0;
 		wbc.inodes_cleaned = 0;
 

@@ -28,6 +28,7 @@ struct writeback_control {
 					   older than this */
 	long nr_to_write;		/* Write this many pages, and decrement
 					   this for each page written */
+	long per_file_limit;		/* Write this many pages for one file */
 	long pages_skipped;		/* Pages which were not written */
 	long inodes_cleaned;		/* # of inodes cleaned */
 

@@ -30,22 +30,6 @@
 #include "internal.h"
 
 /*
- * Passed into wb_writeback(), essentially a subset of writeback_control
- */
-struct wb_writeback_work {
-	long nr_pages;
-	struct super_block *sb;
-	enum writeback_sync_modes sync_mode;
-	unsigned int tagged_sync:1;
-	unsigned int for_kupdate:1;
-	unsigned int range_cyclic:1;
-	unsigned int for_background:1;
-
-	struct list_head list;		/* pending work list */
-	struct completion *done;	/* set if the caller waits */
-};
-
-/*
  * Include the creation of the trace points after defining the
  * wb_writeback_work structure so that the definition remains local to this
  * file.

@@ -463,7 +447,6 @@ writeback_single_inode(struct inode *ino
 			 * No need to add it back to the LRU.
 			 */
 			list_del_init(&inode->i_wb_list);
-			wbc->inodes_cleaned++;
 		}
 	}
 	inode_sync_complete(inode);

@@ -502,19 +485,53 @@ static bool pin_sb_for_writeback(struct 
  * If @only_this_sb is true, then find and write all such
  * inodes. Otherwise write only ones which go sequentially
  * in reverse order.
- *
- * Return 1, if the caller writeback routine should be
- * interrupted. Otherwise return 0.
  */
-static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
-		struct writeback_control *wbc, bool only_this_sb)
+enum writeback_progress {
+	WROTE_FULL_CHUNK,
+	WROTE_SOME_PAGES,
+	WROTE_SOME_INODES,
+	WROTE_NOTHING,
+};
+
+static int writeback_sb_inodes(struct super_block *sb,
+			       struct bdi_writeback *wb,
+			       struct wb_writeback_work *work)
 {
+	struct writeback_control wbc = {
+		.sync_mode		= work->sync_mode,
+		.tagged_sync		= work->tagged_sync,
+		.older_than_this	= work->older_than_this,
+		.for_kupdate		= work->for_kupdate,
+		.for_background		= work->for_background,
+		.range_cyclic		= work->range_cyclic,
+		.range_start		= 0;
+		.range_end		= LLONG_MAX;
+	};
+	long write_chunk = MAX_WRITEBACK_PAGES;
+	long wrote = 0;
+	bool inode_cleaned = false;
+
+	/*
+	 * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
+	 * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
+	 * here avoids calling into writeback_inodes_wb() more than once.
+	 *
+	 * The intended call sequence for WB_SYNC_ALL writeback is:
+	 *
+	 *      wb_writeback()
+	 *          writeback_sb_inodes()       <== called only once
+	 *              write_cache_pages()     <== called once for each inode
+	 *                   (quickly) tag currently dirty pages
+	 *                   (maybe slowly) sync all tagged pages
+	 */
+	if (work->sync_mode == WB_SYNC_ALL || work->tagged_sync)
+		write_chunk = LONG_MAX;
+
 	while (!list_empty(&wb->b_io)) {
-		long pages_skipped;
 		struct inode *inode = wb_inode(wb->b_io.prev);
 
 		if (inode->i_sb != sb) {
-			if (only_this_sb) {
+			if (work->sb) {
 				/*
 				 * We only want to write back data for this
 				 * superblock, move all inodes not belonging

@@ -529,7 +546,7 @@ static int writeback_sb_inodes(struct su
 			 * Bounce back to the caller to unpin this and
 			 * pin the next superblock.
 			 */
-			return 0;
+			break;
 		}
 
 		/*

@@ -543,34 +560,44 @@ static int writeback_sb_inodes(struct su
 			requeue_io(inode, wb);
 			continue;
 		}
-
 		__iget(inode);
+		write_chunk = min(write_chunk, work->nr_pages);
+		wbc.nr_to_write = write_chunk;
+		wbc.pages_skipped = 0;
+
+		writeback_single_inode(inode, wb, &wbc);
 
-		pages_skipped = wbc->pages_skipped;
-		writeback_single_inode(inode, wb, wbc);
-		if (wbc->pages_skipped != pages_skipped) {
+		work->nr_pages -= write_chunk - wbc.nr_to_write;
+		wrote += write_chunk - wbc.nr_to_write;
+		if (wbc.pages_skipped) {
 			/*
 			 * writeback is not making progress due to locked
 			 * buffers.  Skip this inode for now.
 			 */
 			redirty_tail(inode, wb);
-		}
+		} else if (!(inode->i_state & I_DIRTY))
+			inode_cleaned = true;
 		spin_unlock(&inode->i_lock);
 		spin_unlock(&wb->list_lock);
 		iput(inode);
 		cond_resched();
 		spin_lock(&wb->list_lock);
-		if (wbc->nr_to_write <= 0)
-			return 1;
+		if (wrote >= MAX_WRITEBACK_PAGES)
+			return WROTE_FULL_CHUNK;
+		if (work->nr_pages <= 0)
+			return WROTE_FULL_CHUNK;
 	}
-	/* b_io is empty */
-	return 1;
+	if (wrote)
+		return WROTE_SOME_PAGES;
+	if (inode_cleaned)
+		return WROTE_SOME_INODES;
+	return WROTE_NOTHING;
 }
 
-static void __writeback_inodes_wb(struct bdi_writeback *wb,
-				  struct writeback_control *wbc)
+static int __writeback_inodes_wb(struct bdi_writeback *wb,
+				 struct wb_writeback_work *work)
 {
-	int ret = 0;
+	int ret = WROTE_NOTHING;
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);

@@ -580,34 +607,26 @@ static void __writeback_inodes_wb(struct
 			requeue_io(inode, wb);
 			continue;
 		}
-		ret = writeback_sb_inodes(sb, wb, wbc, false);
+		ret = writeback_sb_inodes(sb, wb, work);
 		drop_super(sb);
 
-		if (ret)
+		if (ret == WROTE_FULL_CHUNK)
 			break;
 	}
 	/* Leave any unwritten inodes on b_io */
+	return ret;
 }
 
 void writeback_inodes_wb(struct bdi_writeback *wb,
-		struct writeback_control *wbc)
+			 struct wb_writeback_work *work)
 {
 	spin_lock(&wb->list_lock);
 	if (list_empty(&wb->b_io))
-		queue_io(wb, wbc->older_than_this);
-	__writeback_inodes_wb(wb, wbc);
+		queue_io(wb, work->older_than_this);
+	__writeback_inodes_wb(wb, work);
 	spin_unlock(&wb->list_lock);
 }
 
-/*
- * The maximum number of pages to writeout in a single bdi flush/kupdate
- * operation.  We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode.  Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES     1024
-
 static inline bool over_bground_thresh(void)
 {
 	unsigned long background_thresh, dirty_thresh;

@@ -636,42 +655,12 @@ static inline bool over_bground_thresh(v
 static long wb_writeback(struct bdi_writeback *wb,
 			 struct wb_writeback_work *work)
 {
-	struct writeback_control wbc = {
-		.sync_mode		= work->sync_mode,
-		.tagged_sync		= work->tagged_sync,
-		.older_than_this	= NULL,
-		.for_kupdate		= work->for_kupdate,
-		.for_background		= work->for_background,
-		.range_cyclic		= work->range_cyclic,
-	};
-	unsigned long oldest_jif;
-	long wrote = 0;
-	long write_chunk = MAX_WRITEBACK_PAGES;
+	long nr_pages = work->nr_pages;
+	unsigned long oldest_jif = jiffies;
 	struct inode *inode;
+	int progress;
 
-	if (!wbc.range_cyclic) {
-		wbc.range_start = 0;
-		wbc.range_end = LLONG_MAX;
-	}
-
-	/*
-	 * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
-	 * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
-	 * here avoids calling into writeback_inodes_wb() more than once.
-	 *
-	 * The intended call sequence for WB_SYNC_ALL writeback is:
-	 *
-	 *      wb_writeback()
-	 *          writeback_sb_inodes()       <== called only once
-	 *              write_cache_pages()     <== called once for each inode
-	 *                   (quickly) tag currently dirty pages
-	 *                   (maybe slowly) sync all tagged pages
-	 */
-	if (wbc.sync_mode == WB_SYNC_ALL || wbc.tagged_sync) {
-		write_chunk = LONG_MAX;
-		oldest_jif = jiffies;
-		wbc.older_than_this = &oldest_jif;
-	}
+	work->older_than_this = &oldest_jif;
 
 	for (;;) {
 		/*

@@ -700,27 +689,18 @@ static long wb_writeback(struct bdi_writ
 		if (work->for_kupdate || work->for_background) {
 			oldest_jif = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
-			wbc.older_than_this = &oldest_jif;
+			work->older_than_this = &oldest_jif;
 		}
 
-		wbc.nr_to_write = write_chunk;
-		wbc.pages_skipped = 0;
-		wbc.inodes_cleaned = 0;
-
 retry:
-		trace_wbc_writeback_start(&wbc, wb->bdi);
 		spin_lock(&wb->list_lock);
 		if (list_empty(&wb->b_io))
-			queue_io(wb, wbc->older_than_this);
+			queue_io(wb, work->older_than_this);
 		if (work->sb)
-			writeback_sb_inodes(work->sb, wb, &wbc, true);
+			progress = writeback_sb_inodes(work->sb, wb, work);
 		else
-			__writeback_inodes_wb(wb, &wbc);
+			progress = __writeback_inodes_wb(wb, work);
 		spin_unlock(&wb->list_lock);
-		trace_wbc_writeback_written(&wbc, wb->bdi);
-
-		work->nr_pages -= write_chunk - wbc.nr_to_write;
-		wrote += write_chunk - wbc.nr_to_write;
 
 		/*
 		 * Did we write something? Try for more

@@ -730,9 +710,7 @@ retry:
 		 * mean the overall work is done. So we keep looping as long
 		 * as made some progress on cleaning pages or inodes.
 		 */
-		if (wbc.nr_to_write < write_chunk)
-			continue;
-		if (wbc.inodes_cleaned)
+		if (progress != WROTE_NOTHING)
 			continue;
 		/*
 		 * background writeback will start with expired inodes, and

@@ -741,10 +719,10 @@ retry:
 		 * lists and cause trouble to the page reclaim.
 		 */
 		if (work->for_background &&
-		    wbc.older_than_this &&
+		    work->older_than_this &&
 		    list_empty(&wb->b_io) &&
 		    list_empty(&wb->b_more_io)) {
-			wbc.older_than_this = NULL;
+			work->older_than_this = NULL;
 			goto retry;
 		}
 		/*

@@ -760,7 +738,6 @@ retry:
 		spin_lock(&wb->list_lock);
 		if (!list_empty(&wb->b_more_io))  {
 			inode = wb_inode(wb->b_more_io.prev);
-			trace_wbc_writeback_wait(&wbc, wb->bdi);
 			spin_lock(&inode->i_lock);
 			inode_wait_for_writeback(inode, wb);
 			spin_unlock(&inode->i_lock);

@@ -768,7 +745,7 @@ retry:
 		spin_unlock(&wb->list_lock);
 	}
 
-	return wrote;
+	return nr_pages - work->nr_pages;
 }
 
 /*

@@ -262,14 +262,14 @@ int bdi_has_dirty_io(struct backing_dev_
 
 static void bdi_flush_io(struct backing_dev_info *bdi)
 {
-	struct writeback_control wbc = {
+	struct wb_writeback_work work = {
 		.sync_mode		= WB_SYNC_NONE,
 		.older_than_this	= NULL,
 		.range_cyclic		= 1,
-		.nr_to_write		= 1024,
+		.nr_pages		= 1024,
 	};
 
-	writeback_inodes_wb(&bdi->wb, &wbc);
+	writeback_inodes_wb(&bdi->wb, &work);
 }
 
 /*

@@ -494,10 +494,10 @@ static void balance_dirty_pages(struct a
 		return;
 
 	for (;;) {
-		struct writeback_control wbc = {
+		struct wb_writeback_work work = {
 			.sync_mode	= WB_SYNC_NONE,
 			.older_than_this = NULL,
-			.nr_to_write	= write_chunk,
+			.nr_pages	= write_chunk,
 			.range_cyclic	= 1,
 		};
 

@@ -562,15 +562,12 @@ static void balance_dirty_pages(struct a
 		 * threshold otherwise wait until the disk writes catch
 		 * up.
 		 */
-		trace_wbc_balance_dirty_start(&wbc, bdi);
 		if (bdi_nr_reclaimable > bdi_thresh) {
-			writeback_inodes_wb(&bdi->wb, &wbc);
-			pages_written += write_chunk - wbc.nr_to_write;
-			trace_wbc_balance_dirty_written(&wbc, bdi);
+			writeback_inodes_wb(&bdi->wb, &work);
+			pages_written += write_chunk - work.nr_pages;
 			if (pages_written >= write_chunk)
 				break;		/* We've done our duty */
 		}
-		trace_wbc_balance_dirty_wait(&wbc, bdi);
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		io_schedule_timeout(pause);
 

@@ -7,6 +7,15 @@
 #include <linux/sched.h>
 #include <linux/fs.h>
 
+/*
+ * The maximum number of pages to writeout in a single bdi flush/kupdate
+ * operation.  We do this so we don't hold I_SYNC against an inode for
+ * enormous amounts of time, which would block a userspace task which has
+ * been forced to throttle against that inode.  Also, the code reevaluates
+ * the dirty each time it has written this many pages.
+ */
+#define MAX_WRITEBACK_PAGES     1024
+
 struct backing_dev_info;
 
 /*

@@ -29,7 +38,6 @@ struct writeback_control {
 	long nr_to_write;		/* Write this many pages, and decrement
 					   this for each page written */
 	long pages_skipped;		/* Pages which were not written */
-	long inodes_cleaned;		/* # of inodes cleaned */
 
 	/*
 	 * For a_ops->writepages(): is start or end are non-zero then this is

@@ -49,6 +57,23 @@ struct writeback_control {
 };
 
 /*
+ * Passed into wb_writeback(), essentially a subset of writeback_control
+ */
+struct wb_writeback_work {
+	long nr_pages;
+	struct super_block *sb;
+	enum writeback_sync_modes sync_mode;
+	unsigned long *older_than_this;
+	unsigned int tagged_sync:1;
+	unsigned int for_kupdate:1;
+	unsigned int range_cyclic:1;
+	unsigned int for_background:1;
+
+	struct list_head list;		/* pending work list */
+	struct completion *done;	/* set if the caller waits */
+};
+
+/*
  * fs/fs-writeback.c
  */	
 struct bdi_writeback;

@@ -59,7 +84,7 @@ int writeback_inodes_sb_if_idle(struct s
 int writeback_inodes_sb_nr_if_idle(struct super_block *, unsigned long nr);
 void sync_inodes_sb(struct super_block *);
 void writeback_inodes_wb(struct bdi_writeback *wb,
-		struct writeback_control *wbc);
+		struct wb_writeback_work *work);
 long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
 void wakeup_flusher_threads(long nr_pages);
 

@@ -30,11 +30,21 @@
 #include "internal.h"
 
 /*
+ * The maximum number of pages to writeout in a single bdi flush/kupdate
+ * operation.  We do this so we don't hold I_SYNC against an inode for
+ * enormous amounts of time, which would block a userspace task which has
+ * been forced to throttle against that inode.  Also, the code reevaluates
+ * the dirty each time it has written this many pages.
+ */
+#define MAX_WRITEBACK_PAGES     1024L
+
+/*
  * Passed into wb_writeback(), essentially a subset of writeback_control
  */
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
+	unsigned long *older_than_this;
 	enum writeback_sync_modes sync_mode;
 	unsigned int tagged_sync:1;
 	unsigned int for_kupdate:1;

@@ -463,7 +473,6 @@ writeback_single_inode(struct inode *ino
 			 * No need to add it back to the LRU.
 			 */
 			list_del_init(&inode->i_wb_list);
-			wbc->inodes_cleaned++;
 		}
 	}
 	inode_sync_complete(inode);

@@ -496,6 +505,31 @@ static bool pin_sb_for_writeback(struct 
 	return false;
 }
 
+static long writeback_chunk_size(struct wb_writeback_work *work)
+{
+	long pages;
+
+	/*
+	 * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
+	 * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
+	 * here avoids calling into writeback_inodes_wb() more than once.
+	 *
+	 * The intended call sequence for WB_SYNC_ALL writeback is:
+	 *
+	 *      wb_writeback()
+	 *          writeback_sb_inodes()       <== called only once
+	 *              write_cache_pages()     <== called once for each inode
+	 *                   (quickly) tag currently dirty pages
+	 *                   (maybe slowly) sync all tagged pages
+	 */
+	if (work->sync_mode == WB_SYNC_ALL || work->tagged_sync)
+		pages = LONG_MAX;
+	else
+		pages = min(MAX_WRITEBACK_PAGES, work->nr_pages);
+
+	return pages;
+}
+
 /*
  * Write a portion of b_io inodes which belong to @sb.
  *

@@ -503,18 +537,29 @@ static bool pin_sb_for_writeback(struct 
  * inodes. Otherwise write only ones which go sequentially
  * in reverse order.
  *
- * Return 1, if the caller writeback routine should be
- * interrupted. Otherwise return 0.
+ * Return the number of pages and/or inodes cleaned.
  */
-static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
-		struct writeback_control *wbc, bool only_this_sb)
+static long writeback_sb_inodes(struct super_block *sb,
+				struct bdi_writeback *wb,
+				struct wb_writeback_work *work)
 {
+	struct writeback_control wbc = {
+		.sync_mode		= work->sync_mode,
+		.tagged_sync		= work->tagged_sync,
+		.for_kupdate		= work->for_kupdate,
+		.for_background		= work->for_background,
+		.range_cyclic		= work->range_cyclic,
+		.range_start		= 0,
+		.range_end		= LLONG_MAX,
+	};
+	long write_chunk;
+	long wrote = 0;  /* count both pages and inodes */
+
 	while (!list_empty(&wb->b_io)) {
-		long pages_skipped;
 		struct inode *inode = wb_inode(wb->b_io.prev);
 
 		if (inode->i_sb != sb) {
-			if (only_this_sb) {
+			if (work->sb) {
 				/*
 				 * We only want to write back data for this
 				 * superblock, move all inodes not belonging

@@ -529,7 +574,7 @@ static int writeback_sb_inodes(struct su
 			 * Bounce back to the caller to unpin this and
 			 * pin the next superblock.
 			 */
-			return 0;
+			break;
 		}
 
 		/*

@@ -543,34 +588,40 @@ static int writeback_sb_inodes(struct su
 			requeue_io(inode, wb);
 			continue;
 		}
-
 		__iget(inode);
+		write_chunk = writeback_chunk_size(work);
+		wbc.nr_to_write = write_chunk;
+		wbc.pages_skipped = 0;
+
+		writeback_single_inode(inode, wb, &wbc);
 
-		pages_skipped = wbc->pages_skipped;
-		writeback_single_inode(inode, wb, wbc);
-		if (wbc->pages_skipped != pages_skipped) {
+		work->nr_pages -= write_chunk - wbc.nr_to_write;
+		wrote += write_chunk - wbc.nr_to_write;
+		if (wbc.pages_skipped) {
 			/*
 			 * writeback is not making progress due to locked
 			 * buffers.  Skip this inode for now.
 			 */
 			redirty_tail(inode, wb);
-		}
+		} else if (!(inode->i_state & I_DIRTY))
+			wrote++;
 		spin_unlock(&inode->i_lock);
 		spin_unlock(&wb->list_lock);
 		iput(inode);
 		cond_resched();
 		spin_lock(&wb->list_lock);
-		if (wbc->nr_to_write <= 0)
-			return 1;
+		if (wrote >= MAX_WRITEBACK_PAGES)
+			break;
+		if (work->nr_pages <= 0)
+			break;
 	}
-	/* b_io is empty */
-	return 1;
+	return wrote;
 }
 
-static void __writeback_inodes_wb(struct bdi_writeback *wb,
-				  struct writeback_control *wbc)
+static long __writeback_inodes_wb(struct bdi_writeback *wb,
+				  struct wb_writeback_work *work)
 {
-	int ret = 0;
+	long wrote = 0;
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);

@@ -580,33 +631,35 @@ static void __writeback_inodes_wb(struct
 			requeue_io(inode, wb);
 			continue;
 		}
-		ret = writeback_sb_inodes(sb, wb, wbc, false);
+		wrote += writeback_sb_inodes(sb, wb, work);
 		drop_super(sb);
 
-		if (ret)
+		if (wrote >= MAX_WRITEBACK_PAGES)
+			break;
+		if (work->nr_pages <= 0)
 			break;
 	}
 	/* Leave any unwritten inodes on b_io */
+	return wrote;
 }
 
 void writeback_inodes_wb(struct bdi_writeback *wb,
-		struct writeback_control *wbc)
+			 struct writeback_control *wbc)
 {
+	struct wb_writeback_work work = {
+		.nr_pages	= wbc->nr_to_write,
+		.sync_mode	= wbc->sync_mode,
+		.range_cyclic	= wbc->range_cyclic,
+	};
+
 	spin_lock(&wb->list_lock);
 	if (list_empty(&wb->b_io))
-		queue_io(wb, wbc->older_than_this);
-	__writeback_inodes_wb(wb, wbc);
+		queue_io(wb, NULL);
+	__writeback_inodes_wb(wb, &work);
 	spin_unlock(&wb->list_lock);
-}
 
-/*
- * The maximum number of pages to writeout in a single bdi flush/kupdate
- * operation.  We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode.  Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES     1024
+	wbc->nr_to_write = work.nr_pages;
+}
 
 static inline bool over_bground_thresh(void)
 {

@@ -636,42 +689,13 @@ static inline bool over_bground_thresh(v
 static long wb_writeback(struct bdi_writeback *wb,
 			 struct wb_writeback_work *work)
 {
-	struct writeback_control wbc = {
-		.sync_mode		= work->sync_mode,
-		.tagged_sync		= work->tagged_sync,
-		.older_than_this	= NULL,
-		.for_kupdate		= work->for_kupdate,
-		.for_background		= work->for_background,
-		.range_cyclic		= work->range_cyclic,
-	};
+	long nr_pages = work->nr_pages;
 	unsigned long oldest_jif;
-	long wrote = 0;
-	long write_chunk = MAX_WRITEBACK_PAGES;
 	struct inode *inode;
-
-	if (!wbc.range_cyclic) {
-		wbc.range_start = 0;
-		wbc.range_end = LLONG_MAX;
-	}
-
-	/*
-	 * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
-	 * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
-	 * here avoids calling into writeback_inodes_wb() more than once.
-	 *
-	 * The intended call sequence for WB_SYNC_ALL writeback is:
-	 *
-	 *      wb_writeback()
-	 *          writeback_sb_inodes()       <== called only once
-	 *              write_cache_pages()     <== called once for each inode
-	 *                   (quickly) tag currently dirty pages
-	 *                   (maybe slowly) sync all tagged pages
-	 */
-	if (wbc.sync_mode == WB_SYNC_ALL || wbc.tagged_sync)
-		write_chunk = LONG_MAX;
+	long progress;
 
 	oldest_jif = jiffies;
-	wbc.older_than_this = &oldest_jif;
+	work->older_than_this = &oldest_jif;
 
 	for (;;) {
 		/*

@@ -700,27 +724,18 @@ static long wb_writeback(struct bdi_writ
 		if (work->for_kupdate || work->for_background) {
 			oldest_jif = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
-			wbc.older_than_this = &oldest_jif;
+			work->older_than_this = &oldest_jif;
 		}
 
-		wbc.nr_to_write = write_chunk;
-		wbc.pages_skipped = 0;
-		wbc.inodes_cleaned = 0;
-
 retry:
-		trace_wbc_writeback_start(&wbc, wb->bdi);
 		spin_lock(&wb->list_lock);
 		if (list_empty(&wb->b_io))
-			queue_io(wb, wbc->older_than_this);
+			queue_io(wb, work->older_than_this);
 		if (work->sb)
-			writeback_sb_inodes(work->sb, wb, &wbc, true);
+			progress = writeback_sb_inodes(work->sb, wb, work);
 		else
-			__writeback_inodes_wb(wb, &wbc);
+			progress = __writeback_inodes_wb(wb, work);
 		spin_unlock(&wb->list_lock);
-		trace_wbc_writeback_written(&wbc, wb->bdi);
-
-		work->nr_pages -= write_chunk - wbc.nr_to_write;
-		wrote += write_chunk - wbc.nr_to_write;
 
 		/*
 		 * Did we write something? Try for more

@@ -730,9 +745,7 @@ retry:
 		 * mean the overall work is done. So we keep looping as long
 		 * as made some progress on cleaning pages or inodes.
 		 */
-		if (wbc.nr_to_write < write_chunk)
-			continue;
-		if (wbc.inodes_cleaned)
+		if (progress)
 			continue;
 		/*
 		 * background writeback will start with expired inodes, and

@@ -741,10 +754,10 @@ retry:
 		 * lists and cause trouble to the page reclaim.
 		 */
 		if (work->for_background &&
-		    wbc.older_than_this &&
+		    work->older_than_this &&
 		    list_empty(&wb->b_io) &&
 		    list_empty(&wb->b_more_io)) {
-			wbc.older_than_this = NULL;
+			work->older_than_this = NULL;
 			goto retry;
 		}
 		/*

@@ -760,7 +773,6 @@ retry:
 		spin_lock(&wb->list_lock);
 		if (!list_empty(&wb->b_more_io))  {
 			inode = wb_inode(wb->b_more_io.prev);
-			trace_wbc_writeback_wait(&wbc, wb->bdi);
 			spin_lock(&inode->i_lock);
 			inode_wait_for_writeback(inode, wb);
 			spin_unlock(&inode->i_lock);

@@ -768,7 +780,7 @@ retry:
 		spin_unlock(&wb->list_lock);
 	}
 
-	return wrote;
+	return nr_pages - work->nr_pages;
 }
 
 /*

@@ -24,12 +24,9 @@ enum writeback_sync_modes {
  */
 struct writeback_control {
 	enum writeback_sync_modes sync_mode;
-	unsigned long *older_than_this;	/* If !NULL, only write back inodes
-					   older than this */
 	long nr_to_write;		/* Write this many pages, and decrement
 					   this for each page written */
 	long pages_skipped;		/* Pages which were not written */
-	long inodes_cleaned;		/* # of inodes cleaned */
 
 	/*
 	 * For a_ops->writepages(): is start or end are non-zero then this is

@@ -264,7 +264,6 @@ static void bdi_flush_io(struct backing_
 {
 	struct writeback_control wbc = {
 		.sync_mode		= WB_SYNC_NONE,
-		.older_than_this	= NULL,
 		.range_cyclic		= 1,
 		.nr_to_write		= 1024,
 	};

@@ -496,7 +496,6 @@ static void balance_dirty_pages(struct a
 	for (;;) {
 		struct writeback_control wbc = {
 			.sync_mode	= WB_SYNC_NONE,
-			.older_than_this = NULL,
 			.nr_to_write	= write_chunk,
 			.range_cyclic	= 1,
 		};

@@ -101,7 +101,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__field(int, for_background)
 		__field(int, for_reclaim)
 		__field(int, range_cyclic)
-		__field(unsigned long, older_than_this)
 		__field(long, range_start)
 		__field(long, range_end)
 	),

@@ -115,14 +114,12 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->for_background	= wbc->for_background;
 		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
-		__entry->older_than_this = wbc->older_than_this ?
-						*wbc->older_than_this : 0;
 		__entry->range_start	= (long)wbc->range_start;
 		__entry->range_end	= (long)wbc->range_end;
 	),
 
 	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
-		"bgrd=%d reclm=%d cyclic=%d older=0x%lx "
+		"bgrd=%d reclm=%d cyclic=%d "
 		"start=0x%lx end=0x%lx",
 		__entry->name,
 		__entry->nr_to_write,

@@ -132,7 +129,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->for_background,
 		__entry->for_reclaim,
 		__entry->range_cyclic,
-		__entry->older_than_this,
 		__entry->range_start,
 		__entry->range_end)
 )

@@ -2587,7 +2587,6 @@ int extent_write_full_page(struct extent
 	};
 	struct writeback_control wbc_writepages = {
 		.sync_mode	= wbc->sync_mode,
-		.older_than_this = NULL,
 		.nr_to_write	= 64,
 		.range_start	= page_offset(page) + PAGE_CACHE_SIZE,
 		.range_end	= (loff_t)-1,

@@ -2620,7 +2619,6 @@ int extent_write_locked_range(struct ext
 	};
 	struct writeback_control wbc_writepages = {
 		.sync_mode	= mode,
-		.older_than_this = NULL,
 		.nr_to_write	= nr_pages * 2,
 		.range_start	= start,
 		.range_end	= end + 1,

@@ -347,7 +347,7 @@ writeback_single_inode(struct inode *ino
 {
 	struct address_space *mapping = inode->i_mapping;
 	long per_file_limit = wbc->per_file_limit;
-	long uninitialized_var(nr_to_write);
+	long nr_to_write = wbc->nr_to_write;
 	unsigned dirty;
 	int ret;
 

@@ -370,7 +370,8 @@ writeback_single_inode(struct inode *ino
 		 */
 		if (wbc->sync_mode != WB_SYNC_ALL) {
 			requeue_io(inode, wb);
-			return 0;
+			ret = 0;
+			goto out;
 		}
 
 		/*

@@ -387,10 +388,8 @@ writeback_single_inode(struct inode *ino
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&wb->list_lock);
 
-	if (per_file_limit) {
-		nr_to_write = wbc->nr_to_write;
+	if (per_file_limit)
 		wbc->nr_to_write = per_file_limit;
-	}
 
 	ret = do_writepages(mapping, wbc);
 

@@ -477,6 +476,9 @@ writeback_single_inode(struct inode *ino
 		}
 	}
 	inode_sync_complete(inode);
+out:
+	trace_writeback_single_inode(inode, wbc,
+				     nr_to_write - wbc->nr_to_write);
 	return ret;
 }
 

68 lines not on this page · raw message

@@ -248,15 +248,16 @@ static bool inode_dirtied_after(struct i
 /*
  * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
  */
-static void move_expired_inodes(struct list_head *delaying_queue,
-				struct list_head *dispatch_queue,
-				struct writeback_control *wbc)
+static int move_expired_inodes(struct list_head *delaying_queue,
+			       struct list_head *dispatch_queue,
+			       struct writeback_control *wbc)
 {
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
 	struct super_block *sb = NULL;
 	struct inode *inode;
 	int do_sb_sort = 0;
+	int moved = 0;
 
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);

@@ -267,12 +268,13 @@ static void move_expired_inodes(struct l
 			do_sb_sort = 1;
 		sb = inode->i_sb;
 		list_move(&inode->i_wb_list, &tmp);
+		moved++;
 	}
 
 	/* just one sb in list, splice to dispatch_queue and we're done */
 	if (!do_sb_sort) {
 		list_splice(&tmp, dispatch_queue);
-		return;
+		goto out;
 	}
 
 	/* Move inodes from one superblock together */

@@ -284,6 +286,8 @@ static void move_expired_inodes(struct l
 				list_move(&inode->i_wb_list, dispatch_queue);
 		}
 	}
+out:
+	return moved;
 }
 
 /*

@@ -299,9 +303,11 @@ static void move_expired_inodes(struct l
  */
 static void queue_io(struct bdi_writeback *wb, struct writeback_control *wbc)
 {
+	int moved;
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	move_expired_inodes(&wb->b_dirty, &wb->b_io, wbc);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, wbc);
+	trace_writeback_queue_io(wb, wbc, moved);
 }
 
 static int write_inode(struct inode *inode, struct writeback_control *wbc)

@@ -165,6 +165,29 @@ DEFINE_WBC_EVENT(wbc_balance_dirty_writt
 DEFINE_WBC_EVENT(wbc_balance_dirty_wait);
 DEFINE_WBC_EVENT(wbc_writepage);
 
+TRACE_EVENT(writeback_queue_io,
+	TP_PROTO(struct bdi_writeback *wb,
+		 struct writeback_control *wbc,
+		 int moved),
+	TP_ARGS(wb, wbc, moved),
+	TP_STRUCT__entry(
+		__array(char,	name, 32)
+		__field(int,	older)
+		__field(int,	moved)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
+		__entry->older	= wbc->older_than_this ?
+				  (jiffies - *wbc->older_than_this) * 1000 / HZ
+				  : -1;
+		__entry->moved	= moved;
+	),
+	TP_printk("bdi %s: older=%d enqueue=%d",
+		__entry->name,
+		__entry->older,
+		__entry->moved)
+);
+
 DECLARE_EVENT_CLASS(writeback_congest_waited_template,
 
 	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),

@@ -258,15 +258,16 @@ static bool inode_dirtied_after(struct i
 /*
  * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
  */
-static void move_expired_inodes(struct list_head *delaying_queue,
+static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
-				unsigned long *older_than_this)
+			       unsigned long *older_than_this)
 {
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
 	struct super_block *sb = NULL;
 	struct inode *inode;
 	int do_sb_sort = 0;
+	int moved = 0;
 
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);

@@ -277,12 +278,13 @@ static void move_expired_inodes(struct l
 			do_sb_sort = 1;
 		sb = inode->i_sb;
 		list_move(&inode->i_wb_list, &tmp);
+		moved++;
 	}
 
 	/* just one sb in list, splice to dispatch_queue and we're done */
 	if (!do_sb_sort) {
 		list_splice(&tmp, dispatch_queue);
-		return;
+		goto out;
 	}
 
 	/* Move inodes from one superblock together */

@@ -294,6 +296,8 @@ static void move_expired_inodes(struct l
 				list_move(&inode->i_wb_list, dispatch_queue);
 		}
 	}
+out:
+	return moved;
 }
 
 /*

@@ -309,9 +313,11 @@ static void move_expired_inodes(struct l
  */
 static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
 {
+	int moved;
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
+	trace_writeback_queue_io(wb, older_than_this, moved);
 }
 
 static int write_inode(struct inode *inode, struct writeback_control *wbc)

@@ -158,6 +158,31 @@ DEFINE_WBC_EVENT(wbc_balance_dirty_writt
 DEFINE_WBC_EVENT(wbc_balance_dirty_wait);
 DEFINE_WBC_EVENT(wbc_writepage);
 
+TRACE_EVENT(writeback_queue_io,
+	TP_PROTO(struct bdi_writeback *wb,
+		 unsigned long *older_than_this,
+		 int moved),
+	TP_ARGS(wb, older_than_this, moved),
+	TP_STRUCT__entry(
+		__array(char,		name, 32)
+		__field(unsigned long,	older)
+		__field(long,		age)
+		__field(int,		moved)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
+		__entry->older	= older_than_this ?  *older_than_this : 0;
+		__entry->age	= older_than_this ?
+				  (jiffies - *older_than_this) * 1000 / HZ : -1;
+		__entry->moved	= moved;
+	),
+	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d",
+		__entry->name,
+		__entry->older,	/* older_than_this in jiffies */
+		__entry->age,	/* older_than_this in relative milliseconds */
+		__entry->moved)
+);
+
 DECLARE_EVENT_CLASS(writeback_congest_waited_template,
 
 	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),

@@ -115,7 +115,7 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__field(int, for_reclaim)
 		__field(int, range_cyclic)
 		__field(int, more_io)
-		__field(unsigned long, older_than_this)
+		__field(int, older)
 		__field(long, range_start)
 		__field(long, range_end)
 	),

@@ -130,14 +130,15 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
 		__entry->more_io	= wbc->more_io;
-		__entry->older_than_this = wbc->older_than_this ?
-						*wbc->older_than_this : 0;
+		__entry->older		= wbc->older_than_this ?
+				(jiffies - *wbc->older_than_this) * 1000 / HZ
+				: -1;
 		__entry->range_start	= (long)wbc->range_start;
 		__entry->range_end	= (long)wbc->range_end;
 	),
 
 	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
-		"bgrd=%d reclm=%d cyclic=%d more=%d older=0x%lx "
+		"bgrd=%d reclm=%d cyclic=%d more=%d older=%d "
 		"start=0x%lx end=0x%lx",
 		__entry->name,
 		__entry->nr_to_write,

@@ -148,7 +149,7 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->for_reclaim,
 		__entry->range_cyclic,
 		__entry->more_io,
-		__entry->older_than_this,
+		__entry->older,
 		__entry->range_start,
 		__entry->range_end)
 )