From 5bdca4e0768d3e0f4efa43d9a2cc8210aeb91ab9 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 10 Jul 2012 11:53:34 -0700 Subject: 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 --- net/ceph/messenger.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'net/ceph/messenger.c') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index b332c3d76059..10255e81be79 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1423,7 +1423,7 @@ static int process_connect(struct ceph_connection *con) * dropped messages. */ dout("process_connect got RESET peer seq %u\n", - le32_to_cpu(con->in_connect.connect_seq)); + le32_to_cpu(con->in_reply.connect_seq)); pr_err("%s%lld %s connection reset\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr)); @@ -1450,10 +1450,10 @@ static int process_connect(struct ceph_connection *con) * If we sent a smaller connect_seq than the peer has, try * again with a larger value. */ - dout("process_connect got RETRY my seq = %u, peer_seq = %u\n", + dout("process_connect got RETRY_SESSION my seq %u, peer %u\n", le32_to_cpu(con->out_connect.connect_seq), - le32_to_cpu(con->in_connect.connect_seq)); - con->connect_seq = le32_to_cpu(con->in_connect.connect_seq); + le32_to_cpu(con->in_reply.connect_seq)); + con->connect_seq = le32_to_cpu(con->in_reply.connect_seq); ceph_con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) @@ -1468,9 +1468,9 @@ static int process_connect(struct ceph_connection *con) */ dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n", con->peer_global_seq, - le32_to_cpu(con->in_connect.global_seq)); + le32_to_cpu(con->in_reply.global_seq)); get_global_seq(con->msgr, - le32_to_cpu(con->in_connect.global_seq)); + le32_to_cpu(con->in_reply.global_seq)); ceph_con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) -- cgit v1.2.3