Does changing only the count distinct measure from HLL to precisely make
the query slower?

With HLL some of our queries were sub-second, but after moving to precisely
- the same queries are slow.  Is this expected?  How to fix?
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