Page History

lnet_ni lnet_get_best_ni(local_net, cur_ni, md_cpt)
{
	local_net = get_local_net(peer_net)
	for each ni in local_net {
		health_value = lnet_local_ni_health(ni)
		/* select the best health value */
		if (health_value < best_health_value)
			continue
		distance = get_distance(md_cpt, dev_cpt)
		/* select the shortest distance to the MD */
		if (distance < lnet_numa_range)
			distance = lnet_numa_range
		if (distance > shortest_distance)
			continue
		else if distance < shortest_distance
			distance = shortest_distance
		/* select based on the most available credits */
		else if ni_credits < best_credits
			continue
		/* if all is equal select based on round robin */
		else if ni_credits == best_credits
			if best_ni->ni_seq <= ni->ni_seq
				continue
	}
}
 
/*
 * lnet_select_pathway() will be modified to add a peer_nid parameter.
 * This parameter indicates that the peer_ni is predetermined,
 * and is
 * identified by the NID provided. The peer_nid parameter is the
 * next-hop NID, which can be the final destination or
 * the next-hop
 * router. If that peer_NID is not healthy then another peer_NID is
 * selected as per the current algorithm. This will
 * force the
 * algorithm to prefer the peer_ni which was selected in the initial
 * message sending. The peer_ni NID is stored in
 * the message. This
 * new parameter extends the concept of the src_nid, which is provided
 * to lnet_select_pathway() to inform it
 * that the local NI is
 * predetermined.
 */
 
/* on resend */
enum lnet_error_type {
	LNET_LOCAL_NI_DOWN, /* don't use this NI until you get an UP */
	LNET_LOCAL_NI_UP, /* start using this NI */
	LNET_LOCAL_NI_SEND_TIMOUT, /* demerit this NI so it's not selected immediately, provided there are other healthy interfaces */
	LNET_PEER_NI_NO_LISTENER, /* there is no remote listener. demerit the peer_ni and try another NI */
	LNET_PEER_NI_ADDR_ERROR, /* The address for the peer_ni is wrong. Don't use this peer_NI */
	LNET_PEER_NI_UNREACHABLE, /* temporarily don't use the peer NI */
	LNET_PEER_NI_CONNECT_ERROR, /* temporarily don't use the peer NI */
	LNET_PEER_NI_CONNECTION_REJECTED /* temporarily don't use the peer NI */
};
 
static int lnet_handle_send_failure_locked(msg, local_nid, status)
{
	switch (status)
	/*
     * LNET_LOCAL_NI_DOWN can be received without a message being sent.
     * In this case msg == NULL and it is sufficient to update the health
     * of the local NI
     */
	case LNET_LOCAL_NI_DOWN:
	 	LASSERT(!msg);
		local_ni = lnet_get_local_ni(msg->local_nid)
		if (!local_ni)
				return
		/* flag local NI down */
		lnet_set_local_ni_health(DOWN)
		break;
	case LNET_LOCAL_NI_UP:
		LASSERT(!msg);
		local_ni = lnet_get_local_ni(msg->local_nid)
		if (!local_ni)
				return
		/* flag local NI down */
		lnet_set_local_ni_health(UP)
		/* This NI will be a candidate for selection in the next message send */
	break;
...
}
 
static int lnet_complete_msg_locked(msg, cpt)
{
	status = msg->msg_ev.status
	if (status != 0)
		rc = lnet_handle_send_failure_locked(msg, status)
		if rc == 0
				return
	/* continue as currently done */
}