From dcd79a1423f64ee0184629874805c3ac40f3a2c5 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 28 Sep 2010 12:27:25 +1000 Subject: xfs: don't use vfs writeback for pure metadata modifications Under heavy multi-way parallel create workloads, the VFS struggles to write back all the inodes that have been changed in age order. The bdi flusher thread becomes CPU bound, spending 85% of it's time in the VFS code, mostly traversing the superblock dirty inode list to separate dirty inodes old enough to flush. We already keep an index of all metadata changes in age order - in the AIL - and continued log pressure will do age ordered writeback without any extra overhead at all. If there is no pressure on the log, the xfssyncd will periodically write back metadata in ascending disk address offset order so will be very efficient. Hence we can stop marking VFS inodes dirty during transaction commit or when changing timestamps during transactions. This will keep the inodes in the superblock dirty list to those containing data or unlogged metadata changes. However, the timstamp changes are slightly more complex than this - there are a couple of places that do unlogged updates of the timestamps, and the VFS need to be informed of these. Hence add a new function xfs_trans_ichgtime() for transactional changes, and leave xfs_ichgtime() for the non-transactional changes. Signed-off-by: Dave Chinner Reviewed-by: Alex Elder Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_rename.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'fs/xfs/xfs_rename.c') diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c index 8fca957200df..9028733f7ed8 100644 --- a/fs/xfs/xfs_rename.c +++ b/fs/xfs/xfs_rename.c @@ -211,7 +211,9 @@ xfs_rename( goto error_return; if (error) goto abort_return; - xfs_ichgtime(target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + + xfs_trans_ichgtime(tp, target_dp, + XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); if (new_parent && src_is_directory) { error = xfs_bumplink(tp, target_dp); @@ -249,7 +251,9 @@ xfs_rename( &first_block, &free_list, spaceres); if (error) goto abort_return; - xfs_ichgtime(target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + + xfs_trans_ichgtime(tp, target_dp, + XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); /* * Decrement the link count on the target since the target @@ -292,7 +296,7 @@ xfs_rename( * inode isn't really being changed, but old unix file systems did * it and some incremental backup programs won't work without it. */ - xfs_ichgtime(src_ip, XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG); /* * Adjust the link count on src_dp. This is necessary when @@ -315,7 +319,7 @@ xfs_rename( if (error) goto abort_return; - xfs_ichgtime(src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE); if (new_parent) xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE); -- cgit v1.2.3