Possible areas to check: - too few nodes (node overload) - you did not indicate either replication factor, number of nodes. Assume nodes are *rather* full. - network overload (check your TORS's errors, also the tcp stats on the relevant nodes) - look for stop the world garbage collection on multiple nodes.
*.......* *Daemeon C.M. ReiydelleUSA (+1) 415.501.0198London (+44) (0) 20 8144 9872* On Tue, Mar 21, 2017 at 11:17 AM, Cogumelos Maravilha < cogumelosmaravi...@sapo.pt> wrote: > Hi list, > > I'm using C* 3.10; > > authenticator: PasswordAuthenticator and authorizer: CassandraAuthorizer > > When adding a node and before nodetool repair system_auth finished all my > clients die with: > > cassandra.cluster.NoHostAvailable: ('Unable to connect to any servers', > {'10.100.100.19': AuthenticationFailed('Failed to authenticate to ... > > Thanks in advance. >