On Fri, Jun 27, 2014 at 7:19 AM, John Cooper <[EMAIL PROTECTED]>
wrote:
Why have each node in a different availability zone?

You monitoring latencies in and out of your nodes?

How many regions?  Is upload spread evenly across your cluster?  How big
are the entries?  Are the 5k you are uploading now the same size as the
ones that took only 50s?  What are the servers doing cpu and i/o -wise?
 Background compactions?

St.Ack

 
NEW: Monitor These Apps!
elasticsearch, apache solr, apache hbase, hadoop, redis, casssandra, amazon cloudwatch, mysql, memcached, apache kafka, apache zookeeper, apache storm, ubuntu, centOS, red hat, debian, puppet labs, java, senseiDB