diff mbox

[1/2] opensm: connect roots in fat-tree - implementation

Message ID 4AE02BB5.5060600@dev.mellanox.co.il (mailing list archive)
State Not Applicable, archived
Headers show

Commit Message

Yevgeny Kliteynik Oct. 22, 2009, 9:53 a.m. UTC
None
diff mbox

Patch

diff --git a/opensm/opensm/osm_ucast_ftree.c b/opensm/opensm/osm_ucast_ftree.c
index 5b403f7..366a225 100644
--- a/opensm/opensm/osm_ucast_ftree.c
+++ b/opensm/opensm/osm_ucast_ftree.c
@@ -2949,6 +2949,82 @@  static void fabric_route_to_switches(IN ftree_fabric_t * p_ftree)
 /***************************************************
  ***************************************************/

+static void fabric_route_roots(IN ftree_fabric_t * p_ftree)
+{
+	uint16_t lid;
+	uint8_t port_num;
+	ftree_sw_t *p_sw;
+	ftree_sw_t *p_leaf_sw;
+
+	OSM_LOG_ENTER(&p_ftree->p_osm->log);
+
+	/*
+	 * We need a switch that will accomodate all the down/up turns in
+	 * the fabric. Having these turn in a single place in the fabric
+	 * will not create credit loops.
+	 * So we need to select this switch.
+	 * The idea here is to chose leaf with the highest index. I don't
+	 * have any theory to back me up on this. It's just a general thought
+	 * that this way the switch that might be a bottleneck for many mcast
+	 * groups will be far away from the OpenSM, so it will draw the
+	 * multicast traffic away from the SM.
+	 */
+
+	p_leaf_sw = p_ftree->leaf_switches[p_ftree->leaf_switches_num-1];
+
+	/*
+	 * Now go over all the switches in the fabric that
+	 * have lower rank, and route the missing LIDs to
+	 * the selected leaf switch.
+	 * In short, this leaf switch now poses a target
+	 * for all those missing LIDs.
+	 */
+
+	for (p_sw = (ftree_sw_t *) cl_qmap_head(&p_ftree->sw_tbl);
+	     p_sw != (ftree_sw_t *) cl_qmap_end(&p_ftree->sw_tbl);
+	     p_sw = (ftree_sw_t *) cl_qmap_next(&p_sw->map_item)) {
+
+		if (p_sw->rank >= p_ftree->leaf_switch_rank)
+			continue;
+
+		for (lid = 1; lid <= p_leaf_sw->p_osm_sw->max_lid_ho; lid ++) {
+
+			if (p_sw->p_osm_sw->new_lft[lid] != OSM_NO_PATH ||
+			    p_leaf_sw->hops[lid] == OSM_NO_PATH)
+				continue;
+
+			/*
+			 * the missing LID will be routed through the same
+			 * port that routes to the selected leaf switch
+			 */
+			port_num = p_sw->p_osm_sw->new_lft[p_leaf_sw->base_lid];
+
+			OSM_LOG(&p_ftree->p_osm->log, OSM_LOG_DEBUG,
+				"Switch %s: setting path to LID %u "
+				"through port %u\n",
+				tuple_to_str(p_sw->tuple), lid, port_num);
+
+			/* set local lft */
+			p_sw->p_osm_sw->new_lft[lid] = port_num;
+
+			/*
+			 * Set local min hop table.
+			 * The distance to the target LID is a distance
+			 * to the selected leaf switch plus the distance
+			 * from the leaf to the target LID.
+			 */
+			sw_set_hops(p_sw, lid, port_num,
+				p_sw->hops[p_leaf_sw->base_lid] +
+				p_leaf_sw->hops[lid], TRUE);
+		}
+	}
+
+	OSM_LOG_EXIT(&p_ftree->p_osm->log);
+}				/* fabric_route_roots() */
+
+/***************************************************
+ ***************************************************/
+
 static int fabric_populate_nodes(IN ftree_fabric_t * p_ftree)
 {
 	osm_node_t *p_osm_node;
@@ -3978,6 +4054,12 @@  static int do_routing(IN void *context)
 		"Filling switch forwarding tables for switch-to-switch paths\n");
 	fabric_route_to_switches(p_ftree);

+	if (p_ftree->p_osm->subn.opt.connect_roots) {
+		OSM_LOG(&p_ftree->p_osm->log, OSM_LOG_VERBOSE,
+			"Connecting nodes that are unreachable within Up/Down rules\n");
+		fabric_route_roots(p_ftree);
+	}
+
 	/* for each switch, set its fwd table */
 	cl_qmap_apply_func(&p_ftree->sw_tbl, set_sw_fwd_table, (void *)p_ftree);