ceph: reset osd after relevant messages timed out

This simplifies the process of timing out messages. We
keep lru of current messages that are in flight. If a
timeout has passed, we reset the osd connection, so that
messages will be retransmitted.  This is a failsafe in case
we hit some sort of problem sending out message to the OSD.
Normally, we'll get notification via an updated osdmap if
there are problems.

If a request is older than the keepalive timeout, send a
keepalive to ensure we detect any breaks in the TCP connection.

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

1 files changed, 3 insertions, 0 deletions

diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 6a778f2c3f6e..02c0ddcf3eaf 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -62,6 +62,7 @@ struct ceph_mount_args {
         int max_readdir;      /* max readdir size */
         int congestion_kb;      /* max readdir size */
         int osd_timeout;
+        int osd_keepalive_timeout;
         char *snapdir_name;   /* default ".snap" */
         char *name;
         char *secret;
@@ -72,6 +73,8 @@ struct ceph_mount_args {
  * defaults
  */
 #define CEPH_MOUNT_TIMEOUT_DEFAULT  60
+#define CEPH_OSD_TIMEOUT_DEFAULT    60  /* seconds */
+#define CEPH_OSD_KEEPALIVE_DEFAULT  5
 #define CEPH_OSD_IDLE_TTL_DEFAULT    60
 #define CEPH_MOUNT_RSIZE_DEFAULT    (512*1024) /* readahead */