LU-14660 lnet: Fix destination NID for discovery PUSH

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

diff --git a/lnet/lnet/peer.c b/lnet/lnet/peer.c
index 20ae558..155419d 100644 (file)
--- a/lnet/lnet/peer.c
+++ b/lnet/lnet/peer.c
@@ -263,6 +263,7 @@ lnet_peer_alloc(lnet_nid_t nid)
        spin_lock_init(&lp->lp_lock);
        lp->lp_primary_nid = nid;
        lp->lp_disc_src_nid = LNET_NID_ANY;
+       lp->lp_disc_dst_nid = LNET_NID_ANY;
        if (lnet_peers_start_down())
                lp->lp_alive = false;
        else
@@ -1347,7 +1348,13 @@ LNetPrimaryNID(lnet_nid_t nid)
        }
        lp = lpni->lpni_peer_net->lpn_peer;
 
-       while (!lnet_peer_is_uptodate(lp)) {
+       /* If discovery is disabled locally then we needn't bother running
+        * discovery here because discovery will not modify whatever
+        * primary NID is currently set for this peer. If the specified peer is
+        * down then this discovery can introduce long delays into the mount
+        * process, so skip it if it isn't necessary.
+        */
+       while (!lnet_peer_discovery_disabled && !lnet_peer_is_uptodate(lp)) {
                spin_lock(&lp->lp_lock);
                /* force a full discovery cycle */
                lp->lp_state |= LNET_PEER_FORCE_PING | LNET_PEER_FORCE_PUSH;
@@ -1368,7 +1375,11 @@ LNetPrimaryNID(lnet_nid_t nid)
                }
                lp = lpni->lpni_peer_net->lpn_peer;
 
-               /* Only try once if discovery is disabled */
+               /* If we find that the peer has discovery disabled then we will
+                * not modify whatever primary NID is currently set for this
+                * peer. Thus, we can break out of this loop even if the peer
+                * is not fully up to date.
+                */
                if (lnet_is_discovery_disabled(lp))
                        break;
        }
@@ -2521,6 +2532,7 @@ lnet_discovery_event_reply(struct lnet_peer *lp, struct lnet_event *ev)
        spin_lock(&lp->lp_lock);
 
        lp->lp_disc_src_nid = ev->target.nid;
+       lp->lp_disc_dst_nid = ev->source.nid;
 
        /*
         * If some kind of error happened the contents of message
@@ -3227,8 +3239,10 @@ __must_hold(&lp->lp_lock)
                         * received by lp, we need to set the discovery source
                         * NID for new_lp to the NID stored in lp.
                         */
-                       if (lp->lp_disc_src_nid != LNET_NID_ANY)
+                       if (lp->lp_disc_src_nid != LNET_NID_ANY) {
                                new_lp->lp_disc_src_nid = lp->lp_disc_src_nid;
+                               new_lp->lp_disc_dst_nid = lp->lp_disc_dst_nid;
+                       }
                        spin_unlock(&new_lp->lp_lock);
                        spin_unlock(&lp->lp_lock);
 
@@ -3278,41 +3292,10 @@ __must_hold(&lp->lp_lock)
        return rc ? rc : LNET_REDISCOVER_PEER;
 }
 
-/*
- * Select NID to send a Ping or Push to.
- */
-static lnet_nid_t lnet_peer_select_nid(struct lnet_peer *lp)
-{
-       struct lnet_peer_ni *lpni;
-
-       /* Look for a direct-connected NID for this peer. */
-       lpni = NULL;
-       while ((lpni = lnet_get_next_peer_ni_locked(lp, NULL, lpni)) != NULL) {
-               if (!lnet_get_net_locked(lpni->lpni_peer_net->lpn_net_id))
-                       continue;
-               break;
-       }
-       if (lpni)
-               return lpni->lpni_nid;
-
-       /* Look for a routed-connected NID for this peer. */
-       lpni = NULL;
-       while ((lpni = lnet_get_next_peer_ni_locked(lp, NULL, lpni)) != NULL) {
-               if (!lnet_find_rnet_locked(lpni->lpni_peer_net->lpn_net_id))
-                       continue;
-               break;
-       }
-       if (lpni)
-               return lpni->lpni_nid;
-
-       return LNET_NID_ANY;
-}
-
 /* Active side of ping. */
 static int lnet_peer_send_ping(struct lnet_peer *lp)
 __must_hold(&lp->lp_lock)
 {
-       lnet_nid_t pnid;
        int nnis;
        int rc;
        int cpt;
@@ -3324,12 +3307,11 @@ __must_hold(&lp->lp_lock)
        cpt = lnet_net_lock_current();
        /* Refcount for MD. */
        lnet_peer_addref_locked(lp);
-       pnid = lnet_peer_select_nid(lp);
        lnet_net_unlock(cpt);
 
        nnis = max(lp->lp_data_nnis, LNET_INTERFACES_MIN);
 
-       rc = lnet_send_ping(pnid, &lp->lp_ping_mdh, nnis, lp,
+       rc = lnet_send_ping(lp->lp_primary_nid, &lp->lp_ping_mdh, nnis, lp,
                            the_lnet.ln_dc_handler, false);
 
        /*
@@ -3454,18 +3436,17 @@ __must_hold(&lp->lp_lock)
                CERROR("Can't bind push source MD: %d\n", rc);
                goto fail_error;
        }
+
        cpt = lnet_net_lock_current();
        /* Refcount for MD. */
        lnet_peer_addref_locked(lp);
        id.pid = LNET_PID_LUSTRE;
-       id.nid = lnet_peer_select_nid(lp);
+       if (lp->lp_disc_dst_nid != LNET_NID_ANY)
+               id.nid = lp->lp_disc_dst_nid;
+       else
+               id.nid = lp->lp_primary_nid;
        lnet_net_unlock(cpt);
 
-       if (id.nid == LNET_NID_ANY) {
-               rc = -EHOSTUNREACH;
-               goto fail_unlink;
-       }
-
        rc = LNetPut(lp->lp_disc_src_nid, lp->lp_push_mdh,
                     LNET_ACK_REQ, id, LNET_RESERVED_PORTAL,
                     LNET_PROTO_PING_MATCHBITS, 0, 0);
@@ -3477,6 +3458,7 @@ __must_hold(&lp->lp_lock)
         * scratch
         */
        lp->lp_disc_src_nid = LNET_NID_ANY;
+       lp->lp_disc_dst_nid = LNET_NID_ANY;
 
        if (rc)
                goto fail_unlink;