From b3af9468aebf5fcb573d0a116b31d2be1d43c0e9 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Fri, 25 Sep 2009 06:04:10 +0200 Subject: [PATCH] writeback: don't delay inodes redirtied by a fast dirtier Debug traces show that in per-bdi writeback, the inode under writeback almost always get redirtied by a busy dirtier. We used to call redirty_tail() in this case, which could delay inode for up to 30s. This is unacceptable because it now happens so frequently for plain cp/dd, that the accumulated delays could make writeback of big files very slow. So let's distinguish between data redirty and metadata only redirty. The first one is caused by a busy dirtier, while the latter one could happen in XFS, NFS, etc. when they are doing delalloc or updating isize. The inode being busy dirtied will now be requeued for next io, while the inode being redirtied by fs will continue to be delayed to avoid repeated IO. CC: Jan Kara CC: Theodore Ts'o CC: Dave Chinner CC: Chris Mason CC: Christoph Hellwig Signed-off-by: Wu Fengguang Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index c6bf775..52aa545 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -474,10 +474,15 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_lock(&inode_lock); inode->i_state &= ~I_SYNC; if (!(inode->i_state & (I_FREEING | I_CLEAR))) { - if (inode->i_state & I_DIRTY) { + if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) { /* - * Someone redirtied the inode while were writing back - * the pages. + * More pages get dirtied by a fast dirtier. + */ + goto select_queue; + } else if (inode->i_state & I_DIRTY) { + /* + * At least XFS will redirty the inode during the + * writeback (delalloc) and on io completion (isize). */ redirty_tail(inode); } else if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { @@ -502,6 +507,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * soon as the queue becomes uncongested. */ inode->i_state |= I_DIRTY_PAGES; +select_queue: if (wbc->nr_to_write <= 0) { /* * slice used up: queue for next turn -- 1.8.2.3