HBase has HA across the entire stack. Have you read the original Google Bigtable paper to understand the architecture of the system? That is a great place to start.
On Tuesday, July 10, 2012 at 9:40 PM, Gen Liu wrote:
> Hi, I'm new here. I'm doing evaluation on Hbase before applying it to production with big traffic and data.
> I was search for detailed documents that specifying the auto failover behavior of Hbase, e.g. What happen if Master/RegionServer/Zookeeper die(maybe at the same time), how does administrators recover the cluster, is there any data lost if master is dead for a while, etc.
> Any link, suggestion, help will be appreciated. Thanks.
> Gen Liu