ceph: do not include cap/dentry releases in replayed messages

Strip the cap and dentry releases from replayed messages.  They can
cause the shared state to get out of sync because they were generated
(with the request message) earlier, and no longer reflect the current
client state.

Signed-off-by: Sage Weil <sage@newdream.net>
This commit is contained in:
Sage Weil 2010-07-15 14:58:39 -07:00
parent 01a92f174f
commit e979cf5039
2 changed files with 9 additions and 0 deletions

View File

@ -1514,6 +1514,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
ceph_encode_filepath(&p, end, ino1, path1);
ceph_encode_filepath(&p, end, ino2, path2);
/* make note of release offset, in case we need to replay */
req->r_request_release_offset = p - msg->front.iov_base;
/* cap releases */
releases = 0;
if (req->r_inode_drop)
@ -1598,6 +1601,11 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc,
rhead->ino = cpu_to_le64(ceph_ino(req->r_target_inode));
rhead->num_retry = req->r_attempts - 1;
/* remove cap/dentry releases from message */
rhead->num_releases = 0;
msg->hdr.front_len = cpu_to_le32(req->r_request_release_offset);
msg->front.iov_len = req->r_request_release_offset;
return 0;
}

View File

@ -188,6 +188,7 @@ struct ceph_mds_request {
int r_old_inode_drop, r_old_inode_unless;
struct ceph_msg *r_request; /* original request */
int r_request_release_offset;
struct ceph_msg *r_reply;
struct ceph_mds_reply_info_parsed r_reply_info;
int r_err;