A background flush work may run for ever. So it's reasonable for it to mimic the kupdate behavior of syncing old/expired inodes first. The policy is - enqueue all newly expired inodes at each queue_io() time - enqueue all dirty inodes if there are no more expired inodes to sync This will help reduce the number of dirty pages encountered by page reclaim, eg. the pageout() calls. Normally older inodes contain older dirty pages, which are more close to the end of the LRU lists. So syncing older inodes first helps reducing the dirty pages reached by the page reclaim code. Side effects: it will reduce the batch size and hence reduce inode_wb_list_lock hold time, but also make the cluster-by-partition logic in the same function less effective on reducing disk seeks. CC: Jan Kara Acked-by: Mel Gorman Signed-off-by: Wu Fengguang --- fs/fs-writeback.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) --- linux-next.orig/fs/fs-writeback.c 2011-04-19 10:18:29.000000000 +0800 +++ linux-next/fs/fs-writeback.c 2011-04-19 10:18:30.000000000 +0800 @@ -255,14 +255,14 @@ static void move_expired_inodes(struct l struct writeback_control *wbc) { unsigned long expire_interval = 0; - unsigned long older_than_this; + unsigned long uninitialized_var(older_than_this); LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; - if (wbc->for_kupdate) { + if (wbc->for_kupdate || wbc->for_background) { expire_interval = msecs_to_jiffies(dirty_expire_interval * 10); older_than_this = jiffies - expire_interval; } @@ -270,8 +270,20 @@ static void move_expired_inodes(struct l while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (expire_interval && - inode_dirtied_after(inode, older_than_this)) + inode_dirtied_after(inode, older_than_this)) { + /* + * background writeback will start with expired inodes, + * and then fresh inodes. This order helps reduce the + * number of dirty pages reaching the end of LRU lists + * and cause trouble to the page reclaim. + */ + if (wbc->for_background && + list_empty(dispatch_queue) && list_empty(&tmp)) { + expire_interval = 0; + continue; + } break; + } if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; @@ -585,7 +597,8 @@ void writeback_inodes_wb(struct bdi_writ if (!wbc->wb_start) wbc->wb_start = jiffies; /* livelock avoidance */ spin_lock(&inode_wb_list_lock); - if (!wbc->for_kupdate || list_empty(&wb->b_io)) + + if (list_empty(&wb->b_io)) queue_io(wb, wbc); while (!list_empty(&wb->b_io)) { @@ -612,7 +625,7 @@ static void __writeback_inodes_sb(struct WARN_ON(!rwsem_is_locked(&sb->s_umount)); spin_lock(&inode_wb_list_lock); - if (!wbc->for_kupdate || list_empty(&wb->b_io)) + if (list_empty(&wb->b_io)) queue_io(wb, wbc); writeback_sb_inodes(sb, wb, wbc, true); spin_unlock(&inode_wb_list_lock); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/