Hi,

Current HBase cluster has close to 800 regions per RS with data uniformly
distributed across the nodes. could someone share their thoughts on
following options for efficiently decreasing # of regions/server?

* Increase region file size from 10GB to 50 GB: What is the impact on
queries by increasing region size from 10GB to 50GB? Would query latency
increase 5 times?
* Add additional servers to the cluster: Why is [20-200] an ideal range for
number of regions per RS? Can a RS handle over 1000 regions?

Best...

Reply via email to