LU-13569 lnet: Recover peer NI w/exponential backoff interval

[fs/lustre-release.git] / lnet / lnet / peer.c

diff --git a/lnet/lnet/peer.c b/lnet/lnet/peer.c
index 903bf78..04765cf 100644 (file)
--- a/lnet/lnet/peer.c
+++ b/lnet/lnet/peer.c
@@ -4029,14 +4029,22 @@ lnet_peer_ni_add_to_recoveryq_locked(struct lnet_peer_ni *lpni,
                CDEBUG(D_NET, "lpni %s aged out last alive %lld\n",
                       libcfs_nid2str(lpni->lpni_nid),
                       lpni->lpni_last_alive);
+               /* Reset the ping count so that if this peer NI is added back to
+                * the recovery queue we will send the first ping right away.
+                */
+               lpni->lpni_ping_count = 0;
                return;
        }
 
        /* This peer NI is going on the recovery queue, so take a ref on it */
        lnet_peer_ni_addref_locked(lpni);
 
-       CDEBUG(D_NET, "%s added to recovery queue. last alive: %lld health: %d\n",
+       lnet_peer_ni_set_next_ping(lpni, now);
+
+       CDEBUG(D_NET, "%s added to recovery queue. ping count: %u next ping: %lld last alive: %lld health: %d\n",
               libcfs_nid2str(lpni->lpni_nid),
+              lpni->lpni_ping_count,
+              lpni->lpni_next_ping,
               lpni->lpni_last_alive,
               atomic_read(&lpni->lpni_healthv));