lkml.org 
[lkml]   [2012]   [Nov]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[ 087/171] libceph: fix messenger retry
Date
3.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Sage Weil <sage@inktank.com>

(cherry picked from commit 5bdca4e0768d3e0f4efa43d9a2cc8210aeb91ab9)

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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
include/linux/ceph/messenger.h | 12 ++----------
net/ceph/messenger.c | 12 ++++++------
2 files changed, 8 insertions(+), 16 deletions(-)

--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -163,16 +163,8 @@ struct ceph_connection {

/* connection negotiation temps */
char in_banner[CEPH_BANNER_MAX_LEN];
- union {
- struct { /* outgoing connection */
- struct ceph_msg_connect out_connect;
- struct ceph_msg_connect_reply in_reply;
- };
- struct { /* incoming */
- struct ceph_msg_connect in_connect;
- struct ceph_msg_connect_reply out_reply;
- };
- };
+ struct ceph_msg_connect out_connect;
+ struct ceph_msg_connect_reply in_reply;
struct ceph_entity_addr actual_peer_addr;

/* message out temps */
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1423,7 +1423,7 @@ static int process_connect(struct ceph_c
* 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_c
* 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_c
*/
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)



\
 
 \ /
  Last update: 2012-11-26 08:01    [W:0.607 / U:0.560 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site