staging: lustre: improvement to router checker

This patch starts router checker thread all the time.

The router checker only checks routes by ping if
live_router_check_interval or dead_router_check_interval are set
to something other than 0, and there are routes configured.

If these conditions are not met the router checker sleeps until woken
up when a route is added.  It is also woken up whenever the RC is
being stopped to ensure the thread doesn't hang.

In the future when DLC starts configuring the live and dead
router_check_interval parameters, then by manipulating them
the router checker can be turned on and off by the user.

Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6003
Reviewed-on: http://review.whamcloud.com/13035
Reviewed-by: Liang Zhen <liang.zhen@intel.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/staging/lustre/include/linux/lnet/lib-types.h b/drivers/staging/lustre/include/linux/lnet/lib-types.h
index e4a8f6e4e4b1513ad7021433fd0958bcc468db0e..06d46568b7b5d06f73aa81947f0907e218c57211 100644 (file)
--- a/drivers/staging/lustre/include/linux/lnet/lib-types.h
+++ b/drivers/staging/lustre/include/linux/lnet/lib-types.h
@@ -635,6 +635,13 @@ typedef struct {
         */
        bool                              ln_nis_from_mod_params;
 
+       /*
+        * waitq for router checker.  As long as there are no routes in
+        * the list, the router checker will sleep on this queue.  when
+        * routes are added the thread will wake up
+        */
+       wait_queue_head_t                 ln_rc_waitq;
+
 } lnet_t;
 
 #endif

diff --git a/drivers/staging/lustre/lnet/lnet/api-ni.c b/drivers/staging/lustre/lnet/lnet/api-ni.c
index ed121a8692054ce49a3a705d686145cceee445f2..0ec656ac0fd4bb9babc99598f976552a91bfdaec 100644 (file)
--- a/drivers/staging/lustre/lnet/lnet/api-ni.c
+++ b/drivers/staging/lustre/lnet/lnet/api-ni.c
@@ -98,6 +98,7 @@ lnet_init_locks(void)
 {
        spin_lock_init(&the_lnet.ln_eq_wait_lock);
        init_waitqueue_head(&the_lnet.ln_eq_waitq);
+       init_waitqueue_head(&the_lnet.ln_rc_waitq);
        mutex_init(&the_lnet.ln_lnd_mutex);
        mutex_init(&the_lnet.ln_api_mutex);
 }

diff --git a/drivers/staging/lustre/lnet/lnet/router.c b/drivers/staging/lustre/lnet/lnet/router.c
index 511e446026949e772e746a1d1e4fa05b37ccb6c0..ad9cd448971689ebcab4523b79487d3baeb84c9d 100644 (file)
--- a/drivers/staging/lustre/lnet/lnet/router.c
+++ b/drivers/staging/lustre/lnet/lnet/router.c
@@ -405,6 +405,9 @@ lnet_add_route(__u32 net, unsigned int hops, lnet_nid_t gateway,
        if (rnet != rnet2)
                LIBCFS_FREE(rnet, sizeof(*rnet));
 
+       /* indicate to startup the router checker if configured */
+       wake_up(&the_lnet.ln_rc_waitq);
+
        return rc;
 }
 
@@ -1056,11 +1059,6 @@ lnet_router_checker_start(void)
                return -EINVAL;
        }
 
-       if (!the_lnet.ln_routing &&
-           live_router_check_interval <= 0 &&
-           dead_router_check_interval <= 0)
-               return 0;
-
        sema_init(&the_lnet.ln_rc_signal, 0);
        /*
         * EQ size doesn't matter; the callback is guaranteed to get every
@@ -1109,6 +1107,8 @@ lnet_router_checker_stop(void)
 
        LASSERT(the_lnet.ln_rc_state == LNET_RC_STATE_RUNNING);
        the_lnet.ln_rc_state = LNET_RC_STATE_STOPPING;
+       /* wakeup the RC thread if it's sleeping */
+       wake_up(&the_lnet.ln_rc_waitq);
 
        /* block until event callback signals exit */
        down(&the_lnet.ln_rc_signal);
@@ -1199,6 +1199,33 @@ lnet_prune_rc_data(int wait_unlink)
        lnet_net_unlock(LNET_LOCK_EX);
 }
 
+/*
+ * This function is called to check if the RC should block indefinitely.
+ * It's called from lnet_router_checker() as well as being passed to
+ * wait_event_interruptible() to avoid the lost wake_up problem.
+ *
+ * When it's called from wait_event_interruptible() it is necessary to
+ * also not sleep if the rc state is not running to avoid a deadlock
+ * when the system is shutting down
+ */
+static inline bool
+lnet_router_checker_active(void)
+{
+       if (the_lnet.ln_rc_state != LNET_RC_STATE_RUNNING)
+               return true;
+
+       /*
+        * Router Checker thread needs to run when routing is enabled in
+        * order to call lnet_update_ni_status_locked()
+        */
+       if (the_lnet.ln_routing)
+               return true;
+
+       return !list_empty(&the_lnet.ln_routers) &&
+               (live_router_check_interval > 0 ||
+                dead_router_check_interval > 0);
+}
+
 static int
 lnet_router_checker(void *arg)
 {
@@ -1252,8 +1279,18 @@ rescan:
                 * because kernel counts # active tasks as nr_running
                 * + nr_uninterruptible.
                 */
-               set_current_state(TASK_INTERRUPTIBLE);
-               schedule_timeout(cfs_time_seconds(1));
+               /*
+                * if there are any routes then wakeup every second.  If
+                * there are no routes then sleep indefinitely until woken
+                * up by a user adding a route
+                */
+               if (!lnet_router_checker_active())
+                       wait_event_interruptible(the_lnet.ln_rc_waitq,
+                                                lnet_router_checker_active());
+               else
+                       wait_event_interruptible_timeout(the_lnet.ln_rc_waitq,
+                                                        false,
+                                                        cfs_time_seconds(1));
        }
 
        LASSERT(the_lnet.ln_rc_state == LNET_RC_STATE_STOPPING);