Sage Weil 5bdca4e076 libceph: fix messenger retry
In ancient times, the messenger could both initiate and accept connections.
An artifact if that was data structures to store/process an incoming
ceph_msg_connect request and send an outgoing ceph_msg_connect_reply.
Sadly, the negotiation code was referencing those structures and ignoring
important information (like the peer's connect_seq) from the correct ones.

Among other things, this fixes tight reconnect loops where the server sends
RETRY_SESSION and we (the client) retries with the same connect_seq as last
time.  This bug pretty easily triggered by injecting socket failures on the
MDS and running some fs workload like workunits/direct_io/test_sync_io.

Signed-off-by: Sage Weil <sage@inktank.com>
2012-07-17 19:35:59 -07:00
..
2012-07-16 23:22:36 -07:00
2012-06-15 15:30:15 -07:00
2012-07-17 19:35:59 -07:00
2012-04-25 19:47:17 -04:00
2012-05-17 04:50:21 -04:00
2012-06-15 15:30:15 -07:00
2012-04-15 12:44:40 -04:00
2012-05-17 18:45:20 -04:00
2012-05-17 04:50:21 -04:00
2012-06-25 16:35:30 -07:00
2012-07-12 08:33:18 -07:00
2012-06-15 17:37:23 -07:00
2012-05-27 01:11:22 -04:00
2010-10-15 15:53:27 +02:00