From 7d455e0030eeab820773e7786605be4d9e56a04b Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Fri, 15 Aug 2008 00:40:43 -0700 Subject: fs/inode.c: properly init address_space->writeback_index write_cache_pages() uses i_mapping->writeback_index to pick up where it left off the last time a given inode was found by pdflush or balance_dirty_pages (or anyone else who sets wbc->range_cyclic) alloc_inode() should set it to a sane value so that writeback doesn't start in the middle of a file. It is somewhat difficult to notice the bug since write_cache_pages will loop around to the start of the file and the elevator helps hide the resulting seeks. For whatever reason, Btrfs hits this often. Unpatched, untarring 30 copies of the linux kernel in series runs at 47MB/s on a single sata drive. With this fix, it jumps to 62MB/s. Signed-off-by: Chris Mason Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/inode.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/inode.c') diff --git a/fs/inode.c b/fs/inode.c index b6726f64453..0487ddba139 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -166,6 +166,7 @@ static struct inode *alloc_inode(struct super_block *sb) mapping_set_gfp_mask(mapping, GFP_HIGHUSER_PAGECACHE); mapping->assoc_mapping = NULL; mapping->backing_dev_info = &default_backing_dev_info; + mapping->writeback_index = 0; /* * If the block_device provides a backing_dev_info for client -- cgit v1.2.3