[jira] [Created] (CASSANDRA-6728) Local requests get unnecessarily redirected to other cluster nodes with CL=ONE

["Aris Prassinos (JIRA)" <ji...@apache.org>]

Aris Prassinos created CASSANDRA-6728:
-----------------------------------------

             Summary: Local requests get unnecessarily redirected to other cluster nodes with CL=ONE
                 Key: CASSANDRA-6728
                 URL: https://issues.apache.org/jira/browse/CASSANDRA-6728
             Project: Cassandra
          Issue Type: Bug
          Components: Core
         Environment: Linux
            Reporter: Aris Prassinos
             Fix For: 2.0.5


Three-node cluster with RF=3. All nodes currently in sync.
Network topology strategy. Each of the three nodes defined to be on a separate rack. 
endpoint_snitch: PropertyFileSnitch
dynamic_snitch_update_interval_in_ms: 100
dynamic_snitch_reset_interval_in_ms: 600000
dynamic_snitch_badness_threshold: 0

When I query from cqlsh with tracing on and Consistency=ONE
I see that very frequently requests get redirected to other nodes even though the local node has the data.
All tables are defined with read_repair_chance=0.
There is no other activity on the cluster besides my test queries.
    



--
This message was sent by Atlassian JIRA
(v6.1.5#6160)