HBaseCon 2013 | How to Get the MTTR Below 1 Minute and More

Devaraj Das and Nicolas Liochon talk about why MTTR is important and why recovery time is so crucial. Liochon touches on the premise of HBase: to understand why MTTR is both difficult and important.

Date: Thursday, Jun 13 2013

Description

In this talk Hortonworks' Devaraj Das and Scaled Risk's Nicolas Liochon explain how to get to an MTTR for regions under one minute. It covers the possible failures (.meta.; master; region server, datanode, software, hardware) and then explores how HBase detects the failures, recovers the data, and makes it available again.

Next Steps