ceph: handle frag mismatch between readdir request and reply
If client has outdated directory fragments information, it may request
readdir an non-existent directory fragment. In this case, the MDS finds
an approximate directory fragment and sends its contents back to the
client. When receiving a reply with fragment that is different than the
requested one, the client need to reset the 'readdir offset'.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 1c9fea0..9a8e396 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1275,8 +1275,20 @@
int err = 0, i;
struct inode *snapdir = NULL;
struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
- u64 frag = le32_to_cpu(rhead->args.readdir.frag);
struct ceph_dentry_info *di;
+ u64 r_readdir_offset = req->r_readdir_offset;
+ u32 frag = le32_to_cpu(rhead->args.readdir.frag);
+
+ if (rinfo->dir_dir &&
+ le32_to_cpu(rinfo->dir_dir->frag) != frag) {
+ dout("readdir_prepopulate got new frag %x -> %x\n",
+ frag, le32_to_cpu(rinfo->dir_dir->frag));
+ frag = le32_to_cpu(rinfo->dir_dir->frag);
+ if (ceph_frag_is_leftmost(frag))
+ r_readdir_offset = 2;
+ else
+ r_readdir_offset = 0;
+ }
if (req->r_aborted)
return readdir_prepopulate_inodes_only(req, session);
@@ -1340,7 +1352,7 @@
}
di = dn->d_fsdata;
- di->offset = ceph_make_fpos(frag, i + req->r_readdir_offset);
+ di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
/* inode */
if (dn->d_inode) {