libceph: don't time out osd requests that haven't been received

Keep track of when an outgoing message is ACKed (i.e., the server fully
received it and, presumably, queued it for processing).  Time out OSD
requests only if it's been too long since they've been received.

This prevents timeouts and connection thrashing when the OSDs are simply
busy and are throttling the requests they read off the network.

Reviewed-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>

1 files changed, 5 insertions, 7 deletions

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 78b55f49de7c..c340e2e0765b 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -486,13 +486,10 @@ static void prepare_write_message(struct ceph_connection *con)
         m = list_first_entry(&con->out_queue,
                        struct ceph_msg, list_head);
         con->out_msg = m;
-        if (test_bit(LOSSYTX, &con->state)) {
-                list_del_init(&m->list_head);
-        } else {
-                /* put message on sent list */
-                ceph_msg_get(m);
-                list_move_tail(&m->list_head, &con->out_sent);
-        }
+
+        /* put message on sent list */
+        ceph_msg_get(m);
+        list_move_tail(&m->list_head, &con->out_sent);
 
         /*
          * only assign outgoing seq # if we haven't sent this message
@@ -1399,6 +1396,7 @@ static void process_ack(struct ceph_connection *con)
                         break;
                 dout("got ack for seq %llu type %d at %p\n", seq,
                      le16_to_cpu(m->hdr.type), m);
+                m->ack_stamp = jiffies;
                 ceph_msg_remove(m);
         }
         prepare_read_tag(con);