Signed-off-by: Jan Kara <jack@xxxxxxx>
---
fs/fs-writeback.c | 52 ++++++++++++++++++++++++++++++++++++----------------
1 file changed, 36 insertions(+), 16 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 6caf55858dcb..f9d8aa7f1ff7 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -695,8 +695,7 @@ static bool over_bground_thresh(struct backing_dev_info *bdi)
}
/*
- * Called under wb->list_lock. If there are multiple wb per bdi,
- * only the flusher working on the first wb should do it.
+ * Update writeback bandwidth estimate
*/
static void update_bandwidth(struct backing_dev_info *bdi,
unsigned long start_time)
@@ -707,19 +706,22 @@ static void update_bandwidth(struct backing_dev_info *bdi,
}
/*
- * Explicit flushing or periodic writeback of "old" data.
+ * Handle flushing according to passed work item
*
- * 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.
+ * There are two 'background' type of writeback work - flushing of old data
+ * (have work->for_kupdate set) and flushing to get below dirty limit (have
+ * work->for_background set). These types of work get interrupted when someone
+ * asks for more specific writeback by queueing work item. They get restarted
+ * when the more specific writeback terminates (if still necessary).
*
- * 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.
+ * For writeback which can be easily livelocked (!WB_SYNC_ALL &&
+ * !work->tagged_writepages) we limit how many pages should be written for
+ * one inode (see writeback_chunk_size()). When these pages are written we
+ * continue with next inode in the dirty list to avoid spending too much time
+ * on one inode while starving other inodes from writeback.
*
- * 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.
+ * Note that 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" enough inodes.
*/
static long bdi_writeback(struct backing_dev_info *bdi,
struct wb_writeback_work *work)
@@ -823,6 +825,14 @@ static unsigned long get_nr_dirty_pages(void)
get_nr_dirty_inodes();
}
+/*
+ * Handle dirty data flushing when we are over background dirty limits
+ *
+ * In this type of writeback we writeback all dirty inodes (starting with
+ * the first dirtied inode) until we get below background dirty limits
+ * or until someone requests specific type of writeback from the flusher]
+ * (by queueing work item).
+ */
static long wb_check_background_flush(struct backing_dev_info *bdi)
{
if (over_bground_thresh(bdi)) {
@@ -841,6 +851,17 @@ static long wb_check_background_flush(struct backing_dev_info *bdi)
return 0;
}
+/*
+ * Handle periodic writeback of "old" data.
+ *
+ * Define "old": the first time one of an inode's pages is dirtied, we mark the
+ * dirtying-time in inode->i_dirtied_when. So this periodic writeback just
+ * walks the dirty inode list, writing back any inodes which are older than a
+ * specific point in time.
+ *
+ * Note that this type of writeback can be interrupted if anyone requests
+ * specific writeback by queueing work item.
+ */
static long wb_check_old_data_flush(struct backing_dev_info *bdi)
{
unsigned long expired;
@@ -901,9 +922,7 @@ restart:
kfree(work);
}
- /*
- * Check for periodic writeback, kupdated() style
- */
+ /* Check for background and kupdate-style writeback */
wrote += wb_check_old_data_flush(bdi);
wrote += wb_check_background_flush(bdi);
@@ -917,7 +936,8 @@ restart:
/*
* Handle writeback of dirty data for the device backed by this bdi. Also
- * reschedules periodically and does kupdated style flushing.
+ * reschedules periodically (once per dirty_writeback_interval) and does
+ * kupdated style flushing.
*/
void bdi_writeback_workfn(struct work_struct *work)
{
--
1.8.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
