libceph: init sent and completed when starting
PATCH 1/1 libceph: init sent and completed when starting
The rbd code has a need to be able to restart an osd request that has already been started and completed once before. This currently wouldn't work right because the osd client code assumes an osd request will be started exactly once Certain fields in a request are never cleared and this leads to trouble if you try to reuse it.
Specifically, the r_sent, r_got_reply, and r_completed fields are never cleared. The r_sent field records the osd incarnation at the time the request was sent to that osd. If that's non-zero, the message won't get re-mapped to a target osd properly, and won't be put on the unsafe requests list the first time it's sent as it should. The r_got_reply field is used in handle_reply() to ensure the reply to a request is processed only once. And the r_completed field is used for lingering requests to avoid calling the callback function every time the osd client re-sends the request on behalf of its initiator.
Each osd request passes through ceph_osdc_start_request() when responsibility for the request is handed over to the osd client for completion. We can safely zero these three fields there each time a request gets started.
One last related change--clear the r_linger flag when a request is no longer registered as a linger request.
This resolves:
http://tracker.ceph.com/issues/5026
--- net/ceph/osd_client.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
net/ceph/osd_client.c +0 -0
@@ -1204,6 +1204,7 @@ void ceph_osdc_unregister_linger_request(struct
ceph_osd_client *osdc,
mutex_lock(&osdc->request_mutex);
if (req->r_linger) {
__unregister_linger_request(osdc, req);
+ req->r_linger = 0;
ceph_osdc_put_request(req);
}
mutex_unlock(&osdc->request_mutex);
@@ -2120,7 +2121,9 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
down_read(&osdc->map_sem); mutex_lock(&osdc->request_mutex); __register_request(osdc, req);
- WARN_ON(req->r_sent);
+ req->r_sent = 0;
+ req->r_got_reply = 0;
+ req->r_completed = 0;
rc = __map_request(osdc, req, 0);
if (rc < 0) {
if (nofail) {
Signature · 1 line
1.7.9.5
Quoted 5 lines · Alex Elder
The rbd code has a need to be able to restart an osd request that has already been started and completed once before. This currently wouldn't work right because the osd client code assumes an osd request will be started exactly once Certain fields in a request are never cleared and this leads to trouble if you try to reuse it.
This patch and the next two, and the two series of patches that follow them, are available in the "review/wip-flatten" branch of the ceph-glient git repository.
-Alex
Quoted 53 lines
Specifically, the
r_sent,r_got_reply, andr_completedfields are never cleared. Ther_sentfield records the osd incarnation at the time the request was sent to that osd. If that's non-zero, the message won't get re-mapped to a target osd properly, and won't be put on the unsafe requests list the first time it's sent as it should. Ther_got_replyfield is used inhandle_reply()to ensure the reply to a request is processed only once. And ther_completedfield is used for lingering requests to avoid calling the callback function every time the osd client re-sends the request on behalf of its initiator.Each osd request passes through
ceph_osdc_start_request()when responsibility for the request is handed over to the osd client for completion. We can safely zero these three fields there each time a request gets started.One last related change--clear the
r_lingerflag when a request is no longer registered as a linger request.This resolves:
http://tracker.ceph.com/issues/5026Signed-off-by Alex Elder <[email protected]>--- net/ceph/osd_client.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)net/ceph/osd_client.c +1
-0@@ -1204,6 +1204,7 @@ void ceph_osdc_unregister_linger_request(struct ceph_osd_client *osdc,mutex_lock (&osdc->request_mutex);if (req->r_linger) {__unregister_linger_request (osdc, req); + req->r_linger =0 ;ceph_osdc_put_request (req); }net/ceph/osd_client.c +3
-1mutex_unlock (&osdc->request_mutex);@@ -2120,7 +2121,9 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,down_read (&osdc->map_sem);mutex_lock (&osdc->request_mutex);__register_request (osdc, req); -WARN_ON (req->r_sent); + req->r_sent =0 ; + req->r_got_reply =0 ; + req->r_completed =0 ; rc =__map_request (osdc, req,0 );if (rc <0 ) {if (nofail) {
Quoted 59 lines · Alex Elder
The rbd code has a need to be able to restart an osd request that has already been started and completed once before. This currently wouldn't work right because the osd client code assumes an osd request will be started exactly once Certain fields in a request are never cleared and this leads to trouble if you try to reuse it.
Specifically, the
r_sent,r_got_reply, andr_completedfields are never cleared. Ther_sentfield records the osd incarnation at the time the request was sent to that osd. If that's non-zero, the message won't get re-mapped to a target osd properly, and won't be put on the unsafe requests list the first time it's sent as it should. Ther_got_replyfield is used inhandle_reply()to ensure the reply to a request is processed only once. And ther_completedfield is used for lingering requests to avoid calling the callback function every time the osd client re-sends the request on behalf of its initiator.Each osd request passes through
ceph_osdc_start_request()when responsibility for the request is handed over to the osd client for completion. We can safely zero these three fields there each time a request gets started.One last related change--clear the
r_lingerflag when a request is no longer registered as a linger request.This resolves:
http://tracker.ceph.com/issues/5026Signed-off-by Alex Elder <[email protected]>--- net/ceph/osd_client.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)net/ceph/osd_client.c +1
-0@@ -1204,6 +1204,7 @@ void ceph_osdc_unregister_linger_request(struct ceph_osd_client *osdc,mutex_lock (&osdc->request_mutex);if (req->r_linger) {__unregister_linger_request (osdc, req); + req->r_linger =0 ;ceph_osdc_put_request (req); }mutex_unlock(&osdc->request_mutex);net/ceph/osd_client.c +3
-1@@ -2120,7 +2121,9 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,down_read (&osdc->map_sem);mutex_lock (&osdc->request_mutex);__register_request (osdc, req); -WARN_ON (req->r_sent); + req->r_sent =0 ; + req->r_got_reply =0 ; + req->r_completed =0 ; rc =__map_request (osdc, req,0 );if (rc <0 ) {if (nofail) {