summaryrefslogtreecommitdiffstats
path: root/fs/ceph/inode.c
diff options
context:
space:
mode:
authorYan, Zheng <zyan@redhat.com>2017-04-05 12:54:05 -0400
committerIlya Dryomov <idryomov@gmail.com>2017-05-04 09:19:20 +0200
commit79162547b76e4979b21ef80c9629ada94a51a59b (patch)
tree2af22d86df9675d23fd500fc089f512ab958cabb /fs/ceph/inode.c
parent2827528da003ad207930f0d1af5faf3e482d6393 (diff)
downloadlinux-79162547b76e4979b21ef80c9629ada94a51a59b.tar.bz2
ceph: make seeky readdir more efficient
Current cephfs client uses string to indicate start position of readdir. The string is last entry of previous readdir reply. This approach does not work for seeky readdir because we can not easily convert the new postion to a string. For seeky readdir, mds needs to return dentries from the beginning. Client keeps retrying if the reply does not contain the dentry it wants. In current version of ceph, mds sorts CDentry in its cache in hash order. Client also uses dentry hash to compose dir postion. For seeky readdir, if client passes the hash part of dir postion to mds. mds can avoid replying useless dentries. Signed-off-by: "Yan, Zheng" <zyan@redhat.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Diffstat (limited to 'fs/ceph/inode.c')
-rw-r--r--fs/ceph/inode.c17
1 files changed, 12 insertions, 5 deletions
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index d3119fe3ab45..dcce79b84406 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1482,10 +1482,17 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags))
return readdir_prepopulate_inodes_only(req, session);
- if (rinfo->hash_order && req->r_path2) {
- last_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
- req->r_path2, strlen(req->r_path2));
- last_hash = ceph_frag_value(last_hash);
+ if (rinfo->hash_order) {
+ if (req->r_path2) {
+ last_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
+ req->r_path2,
+ strlen(req->r_path2));
+ last_hash = ceph_frag_value(last_hash);
+ } else if (rinfo->offset_hash) {
+ /* mds understands offset_hash */
+ WARN_ON_ONCE(req->r_readdir_offset != 2);
+ last_hash = le32_to_cpu(rhead->args.readdir.offset_hash);
+ }
}
if (rinfo->dir_dir &&
@@ -1510,7 +1517,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
}
if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2 &&
- !(rinfo->hash_order && req->r_path2)) {
+ !(rinfo->hash_order && last_hash)) {
/* note dir version at start of readdir so we can tell
* if any dentries get dropped */
req->r_dir_release_cnt = atomic64_read(&ci->i_release_count);