zebra: Fix for route node having no tracking NHT

Topology:
IXIA-----(ens192)FRR(ens224)------iXIA

Configuration:
1. Create 8 sub-interfaces on ens192 under Default VRF and configure 8
EBGP session between FRR and IXIA.
2. Create 1000 sub-interfaces on ens224 under Default VRF and configure
1000 EBGP session between FRR and IXIA.
3. 2M prefixes distributed from Left side Ixia each with 8 ECMP path.
4. So in total, there are 2M prefixes * 8 ECMP = 16M prefixes entries
in RIB and FIB.

Issue:
Shut ens192 and ens224, this is taking 1hr 15 mins to clean up the routes.

Root Cause:
In the case of route deletion, if the particular route node is having
nht count = 0, we are going to the parent and doing nht evaluation,
which is not needed.

Fix:
If the deleted the route node is having nht count > 0, then do a nht
evaluation on the parent node.
Shut ens192 and ens224, it is taking 1 min to clean up the routes
with the fix.

Signed-off-by: Sarita Patra <saritap@vmware.com>

2 files changed, 17 insertions, 6 deletions

diff --git a/zebra/rib.h b/zebra/rib.h
index fa8193bedf..b7416322f9 100644
--- a/zebra/rib.h
+++ b/zebra/rib.h
@@ -490,7 +490,8 @@ extern struct route_table *rib_tables_iter_next(rib_tables_iter_t *iter);
 
 extern uint8_t route_distance(int type);
 
-extern void zebra_rib_evaluate_rn_nexthops(struct route_node *rn, uint32_t seq);
+extern void zebra_rib_evaluate_rn_nexthops(struct route_node *rn, uint32_t seq,
+					   bool rt_delete);
 
 /*
  * Inline functions.
diff --git a/zebra/zebra_rib.c b/zebra/zebra_rib.c
index 625c966301..1279c7c9a9 100644
--- a/zebra/zebra_rib.c
+++ b/zebra/zebra_rib.c
@@ -698,7 +698,8 @@ static int rib_can_delete_dest(rib_dest_t *dest)
 	return 1;
 }
 
-void zebra_rib_evaluate_rn_nexthops(struct route_node *rn, uint32_t seq)
+void zebra_rib_evaluate_rn_nexthops(struct route_node *rn, uint32_t seq,
+				    bool rt_delete)
 {
 	rib_dest_t *dest = rib_dest_from_rnode(rn);
 	struct rnh *rnh;
@@ -719,6 +720,12 @@ void zebra_rib_evaluate_rn_nexthops(struct route_node *rn, uint32_t seq)
 				__func__, rn,
 				dest ? rnh_list_count(&dest->nht) : 0);
 
+		if (rt_delete && (!dest || !rnh_list_count(&dest->nht))) {
+			if (IS_ZEBRA_DEBUG_NHT_DETAILED)
+				zlog_debug("%pRN has no tracking NHTs. Bailing",
+					   rn);
+			break;
+		}
 		if (!dest) {
 			rn = rn->parent;
 			if (rn)
@@ -798,7 +805,8 @@ int rib_gc_dest(struct route_node *rn)
 		rnode_debug(rn, zvrf_id(zvrf), "removing dest from table");
 	}
 
-	zebra_rib_evaluate_rn_nexthops(rn, zebra_router_get_next_sequence());
+	zebra_rib_evaluate_rn_nexthops(rn, zebra_router_get_next_sequence(),
+				       true);
 
 	dest->rnode = NULL;
 	rnh_list_fini(&dest->nht);
@@ -1803,6 +1811,7 @@ static void rib_process_result(struct zebra_dplane_ctx *ctx)
 	rib_dest_t *dest;
 	bool fib_changed = false;
 	struct rib_table_info *info;
+	bool rt_delete = false;
 
 	zvrf = vrf_info_lookup(dplane_ctx_get_vrf(ctx));
 	vrf = vrf_lookup_by_id(dplane_ctx_get_vrf(ctx));
@@ -1990,6 +1999,7 @@ static void rib_process_result(struct zebra_dplane_ctx *ctx)
 		}
 		break;
 	case DPLANE_OP_ROUTE_DELETE:
+		rt_delete = true;
 		if (re)
 			SET_FLAG(re->status, ROUTE_ENTRY_FAILED);
 		/*
@@ -2032,7 +2042,7 @@ static void rib_process_result(struct zebra_dplane_ctx *ctx)
 		break;
 	}
 
-	zebra_rib_evaluate_rn_nexthops(rn, seq);
+	zebra_rib_evaluate_rn_nexthops(rn, seq, rt_delete);
 	zebra_rib_evaluate_mpls(rn);
 done:
 
@@ -2268,8 +2278,8 @@ static void rib_process_dplane_notify(struct zebra_dplane_ctx *ctx)
 	}
 
 	/* Make any changes visible for lsp and nexthop-tracking processing */
-	zebra_rib_evaluate_rn_nexthops(
-		rn, zebra_router_get_next_sequence());
+	zebra_rib_evaluate_rn_nexthops(rn, zebra_router_get_next_sequence(),
+				       false);
 
 	zebra_rib_evaluate_mpls(rn);