static void o2net_sc_postpone_idle(struct o2net_sock_container *sc);
static void o2net_sc_reset_idle_timer(struct o2net_sock_container *sc);
-/*
- * FIXME: These should use to_o2nm_cluster_from_node(), but we end up
- * losing our parent link to the cluster during shutdown. This can be
- * solved by adding a pre-removal callback to configfs, or passing
- * around the cluster with the node. -jeffm
- */
-static inline int o2net_reconnect_delay(struct o2nm_node *node)
+#ifdef CONFIG_DEBUG_FS
+void o2net_init_nst(struct o2net_send_tracking *nst, u32 msgtype,
+ u32 msgkey, struct task_struct *task, u8 node)
+{
+ INIT_LIST_HEAD(&nst->st_net_debug_item);
+ nst->st_task = task;
+ nst->st_msg_type = msgtype;
+ nst->st_msg_key = msgkey;
+ nst->st_node = node;
+}
+
+void o2net_set_nst_sock_time(struct o2net_send_tracking *nst)
+{
+ do_gettimeofday(&nst->st_sock_time);
+}
+
+void o2net_set_nst_send_time(struct o2net_send_tracking *nst)
+{
+ do_gettimeofday(&nst->st_send_time);
+}
+
+void o2net_set_nst_status_time(struct o2net_send_tracking *nst)
+{
+ do_gettimeofday(&nst->st_status_time);
+}
+
+void o2net_set_nst_sock_container(struct o2net_send_tracking *nst,
+ struct o2net_sock_container *sc)
+{
+ nst->st_sc = sc;
+}
+
+void o2net_set_nst_msg_id(struct o2net_send_tracking *nst, u32 msg_id)
+{
+ nst->st_id = msg_id;
+}
+#endif /* CONFIG_DEBUG_FS */
+
+static inline int o2net_reconnect_delay(void)
{
return o2nm_single_cluster->cl_reconnect_delay_ms;
}
-static inline int o2net_keepalive_delay(struct o2nm_node *node)
+static inline int o2net_keepalive_delay(void)
{
return o2nm_single_cluster->cl_keepalive_delay_ms;
}
-static inline int o2net_idle_timeout(struct o2nm_node *node)
+static inline int o2net_idle_timeout(void)
{
return o2nm_single_cluster->cl_idle_timeout_ms;
}
o2nm_node_put(sc->sc_node);
sc->sc_node = NULL;
+ o2net_debug_del_sc(sc);
kfree(sc);
}
ret = sc;
sc->sc_page = page;
+ o2net_debug_add_sc(sc);
sc = NULL;
page = NULL;
/* delay if we're withing a RECONNECT_DELAY of the
* last attempt */
delay = (nn->nn_last_connect_attempt +
- msecs_to_jiffies(o2net_reconnect_delay(NULL)))
+ msecs_to_jiffies(o2net_reconnect_delay()))
- jiffies;
- if (delay > msecs_to_jiffies(o2net_reconnect_delay(NULL)))
+ if (delay > msecs_to_jiffies(o2net_reconnect_delay()))
delay = 0;
mlog(ML_CONN, "queueing conn attempt in %lu jiffies\n", delay);
queue_delayed_work(o2net_wq, &nn->nn_connect_work, delay);
* the connect_expired work will do anything. The rest will see
* that it's already queued and do nothing.
*/
- delay += msecs_to_jiffies(o2net_idle_timeout(NULL));
+ delay += msecs_to_jiffies(o2net_idle_timeout());
queue_delayed_work(o2net_wq, &nn->nn_connect_expired, delay);
}
struct o2net_status_wait nsw = {
.ns_node_item = LIST_HEAD_INIT(nsw.ns_node_item),
};
+ struct o2net_send_tracking nst;
+
+ o2net_init_nst(&nst, msg_type, key, current, target_node);
if (o2net_wq == NULL) {
mlog(0, "attempt to tx without o2netd running\n");
goto out;
}
+ o2net_debug_add_nst(&nst);
+
+ o2net_set_nst_sock_time(&nst);
+
ret = wait_event_interruptible(nn->nn_sc_wq,
o2net_tx_can_proceed(nn, &sc, &error));
if (!ret && error)
if (ret)
goto out;
+ o2net_set_nst_sock_container(&nst, sc);
+
veclen = caller_veclen + 1;
vec = kmalloc(sizeof(struct kvec) * veclen, GFP_ATOMIC);
if (vec == NULL) {
goto out;
msg->msg_num = cpu_to_be32(nsw.ns_id);
+ o2net_set_nst_msg_id(&nst, nsw.ns_id);
+
+ o2net_set_nst_send_time(&nst);
/* finally, convert the message header to network byte-order
* and send */
}
/* wait on other node's handler */
+ o2net_set_nst_status_time(&nst);
wait_event(nsw.ns_wq, o2net_nsw_completed(nn, &nsw));
/* Note that we avoid overwriting the callers status return
mlog(0, "woken, returning system status %d, user status %d\n",
ret, nsw.ns_status);
out:
+ o2net_debug_del_nst(&nst); /* must be before dropping sc and node */
if (sc)
sc_put(sc);
if (vec)
* but isn't. This can ultimately cause corruption.
*/
if (be32_to_cpu(hand->o2net_idle_timeout_ms) !=
- o2net_idle_timeout(sc->sc_node)) {
+ o2net_idle_timeout()) {
mlog(ML_NOTICE, SC_NODEF_FMT " uses a network idle timeout of "
"%u ms, but we use %u ms locally. disconnecting\n",
SC_NODEF_ARGS(sc),
be32_to_cpu(hand->o2net_idle_timeout_ms),
- o2net_idle_timeout(sc->sc_node));
+ o2net_idle_timeout());
o2net_ensure_shutdown(nn, sc, -ENOTCONN);
return -1;
}
if (be32_to_cpu(hand->o2net_keepalive_delay_ms) !=
- o2net_keepalive_delay(sc->sc_node)) {
+ o2net_keepalive_delay()) {
mlog(ML_NOTICE, SC_NODEF_FMT " uses a keepalive delay of "
"%u ms, but we use %u ms locally. disconnecting\n",
SC_NODEF_ARGS(sc),
be32_to_cpu(hand->o2net_keepalive_delay_ms),
- o2net_keepalive_delay(sc->sc_node));
+ o2net_keepalive_delay());
o2net_ensure_shutdown(nn, sc, -ENOTCONN);
return -1;
}
{
o2net_hand->o2hb_heartbeat_timeout_ms = cpu_to_be32(
O2HB_MAX_WRITE_TIMEOUT_MS);
- o2net_hand->o2net_idle_timeout_ms = cpu_to_be32(
- o2net_idle_timeout(NULL));
+ o2net_hand->o2net_idle_timeout_ms = cpu_to_be32(o2net_idle_timeout());
o2net_hand->o2net_keepalive_delay_ms = cpu_to_be32(
- o2net_keepalive_delay(NULL));
+ o2net_keepalive_delay());
o2net_hand->o2net_reconnect_delay_ms = cpu_to_be32(
- o2net_reconnect_delay(NULL));
+ o2net_reconnect_delay());
}
/* ------------------------------------------------------------ */
printk(KERN_INFO "o2net: connection to " SC_NODEF_FMT " has been idle for %u.%u "
"seconds, shutting it down.\n", SC_NODEF_ARGS(sc),
- o2net_idle_timeout(sc->sc_node) / 1000,
- o2net_idle_timeout(sc->sc_node) % 1000);
+ o2net_idle_timeout() / 1000,
+ o2net_idle_timeout() % 1000);
mlog(ML_NOTICE, "here are some times that might help debug the "
"situation: (tmr %ld.%ld now %ld.%ld dr %ld.%ld adv "
"%ld.%ld:%ld.%ld func (%08x:%u) %ld.%ld:%ld.%ld)\n",
{
o2net_sc_cancel_delayed_work(sc, &sc->sc_keepalive_work);
o2net_sc_queue_delayed_work(sc, &sc->sc_keepalive_work,
- msecs_to_jiffies(o2net_keepalive_delay(sc->sc_node)));
+ msecs_to_jiffies(o2net_keepalive_delay()));
do_gettimeofday(&sc->sc_tv_timer);
mod_timer(&sc->sc_idle_timeout,
- jiffies + msecs_to_jiffies(o2net_idle_timeout(sc->sc_node)));
+ jiffies + msecs_to_jiffies(o2net_idle_timeout()));
}
static void o2net_sc_postpone_idle(struct o2net_sock_container *sc)
mlog(ML_ERROR, "no connection established with node %u after "
"%u.%u seconds, giving up and returning errors.\n",
o2net_num_from_nn(nn),
- o2net_idle_timeout(NULL) / 1000,
- o2net_idle_timeout(NULL) % 1000);
+ o2net_idle_timeout() / 1000,
+ o2net_idle_timeout() % 1000);
o2net_set_nn_state(nn, NULL, 0, -ENOTCONN);
}
/* ensure an immediate connect attempt */
nn->nn_last_connect_attempt = jiffies -
- (msecs_to_jiffies(o2net_reconnect_delay(node)) + 1);
+ (msecs_to_jiffies(o2net_reconnect_delay()) + 1);
if (node_num != o2nm_this_node()) {
/* believe it or not, accept and node hearbeating testing
o2quo_init();
+ if (o2net_debugfs_init())
+ return -ENOMEM;
+
o2net_hand = kzalloc(sizeof(struct o2net_handshake), GFP_KERNEL);
o2net_keep_req = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
o2net_keep_resp = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
kfree(o2net_hand);
kfree(o2net_keep_req);
kfree(o2net_keep_resp);
+ o2net_debugfs_exit();
}
projects / linux-2.6 / blobdiff