Commit 61c5d6bf authored by Yan, Zheng's avatar Yan, Zheng Committed by Sage Weil

libceph: call r_unsafe_callback when unsafe reply is received

We can't use !req->r_sent to check if OSD request is sent for the
first time, this is because __cancel_request() zeros req->r_sent
when OSD map changes. Rather than adding a new variable to struct
ceph_osd_request to indicate if it's sent for the first time, We
can call the unsafe callback only when unsafe OSD reply is received.
If OSD's first reply is safe, just skip calling the unsafe callback.

The purpose of unsafe callback is adding unsafe request to a list,
so that fsync(2) can wait for the safe reply. fsync(2) doesn't need
to wait for a write(2) that hasn't returned yet. So it's OK to add
request to the unsafe list when the first OSD reply is received.
(ceph_sync_write() returns after receiving the first OSD reply)
Signed-off-by: default avatarYan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: default avatarSage Weil <sage@inktank.com>
parent 6ee6b953
...@@ -1337,10 +1337,6 @@ static void __send_request(struct ceph_osd_client *osdc, ...@@ -1337,10 +1337,6 @@ static void __send_request(struct ceph_osd_client *osdc,
ceph_msg_get(req->r_request); /* send consumes a ref */ ceph_msg_get(req->r_request); /* send consumes a ref */
/* Mark the request unsafe if this is the first timet's being sent. */
if (!req->r_sent && req->r_unsafe_callback)
req->r_unsafe_callback(req, true);
req->r_sent = req->r_osd->o_incarnation; req->r_sent = req->r_osd->o_incarnation;
ceph_con_send(&req->r_osd->o_con, req->r_request); ceph_con_send(&req->r_osd->o_con, req->r_request);
...@@ -1431,8 +1427,6 @@ static void handle_osds_timeout(struct work_struct *work) ...@@ -1431,8 +1427,6 @@ static void handle_osds_timeout(struct work_struct *work)
static void complete_request(struct ceph_osd_request *req) static void complete_request(struct ceph_osd_request *req)
{ {
if (req->r_unsafe_callback)
req->r_unsafe_callback(req, false);
complete_all(&req->r_safe_completion); /* fsync waiter */ complete_all(&req->r_safe_completion); /* fsync waiter */
} }
...@@ -1559,14 +1553,20 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, ...@@ -1559,14 +1553,20 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
mutex_unlock(&osdc->request_mutex); mutex_unlock(&osdc->request_mutex);
if (!already_completed) { if (!already_completed) {
if (req->r_unsafe_callback &&
result >= 0 && !(flags & CEPH_OSD_FLAG_ONDISK))
req->r_unsafe_callback(req, true);
if (req->r_callback) if (req->r_callback)
req->r_callback(req, msg); req->r_callback(req, msg);
else else
complete_all(&req->r_completion); complete_all(&req->r_completion);
} }
if (flags & CEPH_OSD_FLAG_ONDISK) if (flags & CEPH_OSD_FLAG_ONDISK) {
if (req->r_unsafe_callback && already_completed)
req->r_unsafe_callback(req, false);
complete_request(req); complete_request(req);
}
done: done:
dout("req=%p req->r_linger=%d\n", req, req->r_linger); dout("req=%p req->r_linger=%d\n", req, req->r_linger);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment