From 513e2dae9422223072ed3887e91efebec2fc0a01 Mon Sep 17 00:00:00 2001 From: Xue jiufei Date: Fri, 4 Sep 2015 15:44:11 -0700 Subject: ocfs2: flush inode data to disk and free inode when i_count becomes zero Disk inode deletion may be heavily delayed when one node unlink a file after the same dentry is freed on another node(say N1) because of memory shrink but inode is left in memory. This inode can only be freed while N1 doing the orphan scan work. However, N1 may skip orphan scan for several times because other nodes may do the work earlier. In our tests, it may take 1 hour on 4 nodes cluster and it hurts the user experience. So we think the inode should be freed after the data flushed to disk when i_count becomes zero to avoid such circumstances. Signed-off-by: Joyce.xue Cc: Joel Becker Reviewed-by: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/inode.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index b254416dc8d9..4e69f3cbc5f1 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -1191,17 +1191,19 @@ void ocfs2_evict_inode(struct inode *inode) int ocfs2_drop_inode(struct inode *inode) { struct ocfs2_inode_info *oi = OCFS2_I(inode); - int res; trace_ocfs2_drop_inode((unsigned long long)oi->ip_blkno, inode->i_nlink, oi->ip_flags); - if (oi->ip_flags & OCFS2_INODE_MAYBE_ORPHANED) - res = 1; - else - res = generic_drop_inode(inode); + assert_spin_locked(&inode->i_lock); + inode->i_state |= I_WILL_FREE; + spin_unlock(&inode->i_lock); + write_inode_now(inode, 1); + spin_lock(&inode->i_lock); + WARN_ON(inode->i_state & I_NEW); + inode->i_state &= ~I_WILL_FREE; - return res; + return 1; } /* -- cgit v1.2.3