ConsulRegistry: use health checks to select nodes.

Consul sees a healthcheck that is in the warning state as a "failed"
node. This means that when we ask Consul for services that are passing,
it would not return nodes that have warning healthchecks.

In the cache, we only check on critical to skip for nodes. This makes
the cache out of sync with the non-cache implementation.

This patch reworks the non-cache implementation to ask for all nodes
(even unhealthy ones) and does the same check as within the cache, skip
nodes that have critical healthchecks.

We've noticed this issue when we deployed custom healthchecks where the
cache was acting properly, but after 1 minute we saw "None Available"
errors. This is due to the TTL expiry on the cache, which is then
followed by doing a non cached request.

registry/consul_registry.go

@@ -179,7 +179,7 @@ func (c *consulRegistry) Register(s *Service, opts ...RegisterOption) error {
 }
 
 func (c *consulRegistry) GetService(name string) ([]*Service, error) {
-	rsp, _, err := c.Client.Health().Service(name, "", true, nil)
+	rsp, _, err := c.Client.Health().Service(name, "", false, nil)
 	if err != nil {
 		return nil, err
 	}
@@ -216,6 +216,20 @@ func (c *consulRegistry) GetService(name string) ([]*Service, error) {
 			serviceMap[key] = svc
 		}
 
+		var del bool
+		for _, check := range s.Checks {
+			// delete the node if the status is critical
+			if check.Status == "critical" {
+				del = true
+				break
+			}
+		}
+
+		// if delete then skip the node
+		if del {
+			continue
+		}
+
 		svc.Nodes = append(svc.Nodes, &Node{
 			Id:       id,
 			Address:  address,