X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lnet%2Flnet%2Fpeer.c;h=20f78fb30ec2953192733a6df1f6d2a9f80c7862;hp=3719a74aada345311f0025a9f80d10b0f987beff;hb=9ed12d2e8f3f2189d7794e55e7c0e8c0178ffde7;hpb=71ca66bcd9c3a08edfbb67c9711c17428f599bcf

diff --git a/lnet/lnet/peer.c b/lnet/lnet/peer.c
index 3719a74..20f78fb 100644
--- a/lnet/lnet/peer.c
+++ b/lnet/lnet/peer.c
@@ -1193,6 +1193,11 @@ LNetPrimaryNID(lnet_nid_t nid)
 	lp = lpni->lpni_peer_net->lpn_peer;
 
 	while (!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;
+		spin_unlock(&lp->lp_lock);
+
 		rc = lnet_discover_peer_locked(lpni, cpt, true);
 		if (rc)
 			goto out_decref;
@@ -2032,13 +2037,17 @@ void lnet_peer_push_event(struct lnet_event *ev)
 		CDEBUG(D_NET, "Peer %s has discovery disabled\n",
 		       libcfs_nid2str(lp->lp_primary_nid));
 		/*
-		 * If the peer is going from discovery enabled to
-		 * discovery disabled, we need to reflect that in our
-		 * representation of the peer.
+		 * Mark the peer for deletion if we already know about it
+		 * and it's going from discovery set to no discovery set
 		 */
 		if (!(lp->lp_state & (LNET_PEER_NO_DISCOVERY |
-				      LNET_PEER_DISCOVERING)))
+				      LNET_PEER_DISCOVERING)) &&
+		     lp->lp_state & LNET_PEER_DISCOVERED) {
+			CDEBUG(D_NET, "Marking %s:0x%x for deletion\n",
+			       libcfs_nid2str(lp->lp_primary_nid),
+			       lp->lp_state);
 			lp->lp_state |= LNET_PEER_MARK_DELETION;
+		}
 		lp->lp_state |= LNET_PEER_NO_DISCOVERY;
 	} else if (lp->lp_state & LNET_PEER_NO_DISCOVERY) {
 		CDEBUG(D_NET, "Peer %s has discovery enabled\n",
@@ -3060,6 +3069,21 @@ __must_hold(&lp->lp_lock)
 	return rc ? rc : LNET_REDISCOVER_PEER;
 }
 
+/*
+ * Mark the peer as discovered.
+ */
+static int lnet_peer_discovered(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
+{
+	lp->lp_state |= LNET_PEER_DISCOVERED;
+	lp->lp_state &= ~(LNET_PEER_DISCOVERING |
+			  LNET_PEER_REDISCOVER);
+
+	CDEBUG(D_NET, "peer %s\n", libcfs_nid2str(lp->lp_primary_nid));
+
+	return 0;
+}
+
 /* Active side of push. */
 static int lnet_peer_send_push(struct lnet_peer *lp)
 __must_hold(&lp->lp_lock)
@@ -3073,6 +3097,12 @@ __must_hold(&lp->lp_lock)
 	/* Don't push to a non-multi-rail peer. */
 	if (!(lp->lp_state & LNET_PEER_MULTI_RAIL)) {
 		lp->lp_state &= ~LNET_PEER_FORCE_PUSH;
+		/* if peer's NIDs are uptodate then peer is discovered */
+		if (lp->lp_state & LNET_PEER_NIDS_UPTODATE) {
+			rc = lnet_peer_discovered(lp);
+			return rc;
+		}
+
 		return 0;
 	}
 
@@ -3090,11 +3120,11 @@ __must_hold(&lp->lp_lock)
 	md.length    = LNET_PING_INFO_SIZE(pbuf->pb_nnis);
 	md.threshold = 2; /* Put/Ack */
 	md.max_size  = 0;
-	md.options   = 0;
+	md.options   = LNET_MD_TRACK_RESPONSE;
 	md.handler   = the_lnet.ln_dc_handler;
 	md.user_ptr  = lp;
 
-	rc = LNetMDBind(md, LNET_UNLINK, &lp->lp_push_mdh);
+	rc = LNetMDBind(&md, LNET_UNLINK, &lp->lp_push_mdh);
 	if (rc) {
 		lnet_ping_buffer_decref(pbuf);
 		CERROR("Can't bind push source MD: %d\n", rc);
@@ -3166,22 +3196,6 @@ static void lnet_peer_discovery_error(struct lnet_peer *lp, int error)
 }
 
 /*
- * Mark the peer as discovered.
- */
-static int lnet_peer_discovered(struct lnet_peer *lp)
-__must_hold(&lp->lp_lock)
-{
-	lp->lp_state |= LNET_PEER_DISCOVERED;
-	lp->lp_state &= ~(LNET_PEER_DISCOVERING |
-			  LNET_PEER_REDISCOVER);
-
-	CDEBUG(D_NET, "peer %s\n", libcfs_nid2str(lp->lp_primary_nid));
-
-	return 0;
-}
-
-
-/*
  * Discovering this peer is taking too long. Cancel any Ping or Push
  * that discovery is waiting on by unlinking the relevant MDs. The
  * lnet_discovery_event_handler() will proceed from here and complete