protocol/client,server: fcntl lock self healing.

Currently(with out this patch), on a disconnect the server cleans up
the transport which inturn closes the fd's and releases the locks acquired on
those fd's by that client. On a reconnect, client just reopens the fd's but
doesn't reacquire the locks. The application that had previously acquired
the locks still is under the assumption that it is the owner of those locks
which might have been granted to other clients(if they request) by the server
leading to data corruption.

This patch allows the client to reacquire the fcntl locks (held on the fd's)
during client-server handshake.

* The server identifies the client via process-uuid-xl (which is a combination
  of uuid and client-protocol name, it is assumed to be unique) and lk-version
  number.

* The client maintains a list of process-uuid-xl, lk-version pair for each
  accepted connection. On a connect, the server traverses the list for a
  matching pair, if a matching pair is not found the the server returns
  lk-version with value 0, else it returns the lk-version it has in store.

* On a disconnect, the server and client enter grace period, and on the
  completion of the grace period, the client bumps up its lk-version number
  (which means, it will reacquire the locks the next time) and the server will
  distroy the connection. If reconnection happens within the grace period, the
  server will find the matching (process-uuid-xl, lk-version) pair in its list
  which guarantees that the fd's and there corresponding locks are still valid
  for this client.

Configurable options:
  To set grace-timeout, the following options are
    option server.grace-timeout value
    option client.grace-timeout value

  To enable or disable the lk-heal,
    option lk-heal [on|off]

gluster volume set command can be used to configurable options
Change-Id: Id677ef1087b300d649f278b8b2aa0d94eae85ed2
BUG: 795386
Signed-off-by: Mohammed Junaid <junaid@redhat.com>
Reviewed-on: http://review.gluster.com/2766
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vijay@gluster.com>

5 files changed, 56 insertions, 1 deletions

diff --git a/rpc/rpc-lib/src/protocol-common.h b/rpc/rpc-lib/src/protocol-common.h
index 874f46e0b70..827201e2dad 100644
--- a/rpc/rpc-lib/src/protocol-common.h
+++ b/rpc/rpc-lib/src/protocol-common.h
@@ -73,6 +73,7 @@ enum gf_handshake_procnum {
         GF_HNDSK_SETVOLUME,
         GF_HNDSK_GETSPEC,
         GF_HNDSK_PING,
+        GF_HNDSK_SET_LK_VER,
         GF_HNDSK_MAXVALUE,
 };
 
diff --git a/rpc/rpc-lib/src/rpc-clnt.c b/rpc/rpc-lib/src/rpc-clnt.c
index 540c72c82d6..adf6fd87620 100644
--- a/rpc/rpc-lib/src/rpc-clnt.c
+++ b/rpc/rpc-lib/src/rpc-clnt.c
@@ -838,7 +838,6 @@ out:
         return;
 }
 
-
 int
 rpc_clnt_notify (rpc_transport_t *trans, void *mydata,
                  rpc_transport_event_t event, void *data, ...)
diff --git a/rpc/xdr/src/glusterfs3-xdr.c b/rpc/xdr/src/glusterfs3-xdr.c
index 8008a747026..47d7328db28 100644
--- a/rpc/xdr/src/glusterfs3-xdr.c
+++ b/rpc/xdr/src/glusterfs3-xdr.c
@@ -1821,3 +1821,31 @@ xdr_gfs3_readdirp_rsp (XDR *xdrs, gfs3_readdirp_rsp *objp)
 		 return FALSE;
 	return TRUE;
 }
+
+bool_t
+xdr_gf_set_lk_ver_rsp (XDR *xdrs, gf_set_lk_ver_rsp *objp)
+{
+	register int32_t *buf;
+        buf = NULL;
+
+	 if (!xdr_int (xdrs, &objp->op_ret))
+		 return FALSE;
+	 if (!xdr_int (xdrs, &objp->op_errno))
+		 return FALSE;
+	 if (!xdr_int (xdrs, &objp->lk_ver))
+		 return FALSE;
+	return TRUE;
+}
+
+bool_t
+xdr_gf_set_lk_ver_req (XDR *xdrs, gf_set_lk_ver_req *objp)
+{
+	register int32_t *buf;
+        buf = NULL;
+
+	 if (!xdr_string (xdrs, &objp->uid, ~0))
+		 return FALSE;
+	 if (!xdr_int (xdrs, &objp->lk_ver))
+		 return FALSE;
+	return TRUE;
+}
diff --git a/rpc/xdr/src/glusterfs3-xdr.h b/rpc/xdr/src/glusterfs3-xdr.h
index 2b8129a3354..49e9d6cc0b4 100644
--- a/rpc/xdr/src/glusterfs3-xdr.h
+++ b/rpc/xdr/src/glusterfs3-xdr.h
@@ -1088,6 +1088,19 @@ struct gfs3_readdirp_rsp {
 };
 typedef struct gfs3_readdirp_rsp gfs3_readdirp_rsp;
 
+struct gf_set_lk_ver_rsp {
+	int op_ret;
+	int op_errno;
+	int lk_ver;
+};
+typedef struct gf_set_lk_ver_rsp gf_set_lk_ver_rsp;
+
+struct gf_set_lk_ver_req {
+	char *uid;
+	int lk_ver;
+};
+typedef struct gf_set_lk_ver_req gf_set_lk_ver_req;
+
 /* the xdr functions */
 
 #if defined(__STDC__) || defined(__cplusplus)
@@ -1177,6 +1190,8 @@ extern  bool_t xdr_gfs3_dirlist (XDR *, gfs3_dirlist*);
 extern  bool_t xdr_gfs3_readdir_rsp (XDR *, gfs3_readdir_rsp*);
 extern  bool_t xdr_gfs3_dirplist (XDR *, gfs3_dirplist*);
 extern  bool_t xdr_gfs3_readdirp_rsp (XDR *, gfs3_readdirp_rsp*);
+extern  bool_t xdr_gf_set_lk_ver_rsp (XDR *, gf_set_lk_ver_rsp*);
+extern  bool_t xdr_gf_set_lk_ver_req (XDR *, gf_set_lk_ver_req*);
 
 #else /* K&R C */
 extern bool_t xdr_gf_statfs ();
@@ -1265,6 +1280,8 @@ extern bool_t xdr_gfs3_dirlist ();
 extern bool_t xdr_gfs3_readdir_rsp ();
 extern bool_t xdr_gfs3_dirplist ();
 extern bool_t xdr_gfs3_readdirp_rsp ();
+extern bool_t xdr_gf_set_lk_ver_rsp ();
+extern bool_t xdr_gf_set_lk_ver_req ();
 
 #endif /* K&R C */
 
diff --git a/rpc/xdr/src/glusterfs3-xdr.x b/rpc/xdr/src/glusterfs3-xdr.x
index 710a9037807..f35820b57cb 100644
--- a/rpc/xdr/src/glusterfs3-xdr.x
+++ b/rpc/xdr/src/glusterfs3-xdr.x
@@ -675,3 +675,13 @@ struct gfs3_readdirp_rsp {
         opaque   xdata<>; /* Extra data */
 };
 
+struct gf_set_lk_ver_rsp {
+       int op_ret;
+       int op_errno;
+       int lk_ver;
+};
+
+struct gf_set_lk_ver_req {
+       string uid<>;
+       int lk_ver;
+};