summaryrefslogtreecommitdiffstats
path: root/fs/nfs
diff options
context:
space:
mode:
authorTrond Myklebust <trond.myklebust@primarydata.com>2016-06-25 23:45:40 +0200
committerTrond Myklebust <trond.myklebust@primarydata.com>2016-07-06 01:11:06 +0200
commit79566ef018f53a181f067afdf7bef9cc53f9d34b (patch)
treef1c850d39be6b1670e50eaf8baf92d4cc95831e6 /fs/nfs
parentNFS: Do not aggressively cache file attributes in the case of O_DIRECT (diff)
downloadlinux-79566ef018f53a181f067afdf7bef9cc53f9d34b.tar.xz
linux-79566ef018f53a181f067afdf7bef9cc53f9d34b.zip
NFS: Getattr doesn't require data sync semantics
When retrieving stat() information, NFS unfortunately does require us to sync writes to disk in order to ensure that mtime and ctime are up to date. However we shouldn't have to ensure that those writes are persisted. Relaxing that requirement does mean that we may see an mtime/ctime change if the server reboots and forces us to replay all writes. The exception to this rule are pNFS clients that are required to send layoutcommit, however that is dealt with by the call to pnfs_sync_inode() in _nfs_revalidate_inode(). Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Diffstat (limited to 'fs/nfs')
-rw-r--r--fs/nfs/inode.c4
1 files changed, 1 insertions, 3 deletions
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 7688436b19ba..35fda08dc4f6 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -661,9 +661,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
trace_nfs_getattr_enter(inode);
/* Flush out writes to the server in order to update c/mtime. */
if (S_ISREG(inode->i_mode)) {
- inode_lock(inode);
- err = nfs_sync_inode(inode);
- inode_unlock(inode);
+ err = filemap_write_and_wait(inode->i_mapping);
if (err)
goto out;
}