Re:Bedrock – Rock-solid distributed data
by ngrilly on Wednesday October 19, 2016 @08:36AM
(#12743179)
Just found the answer to my question:
> In practice, we deploy two servers in each datacenter (across three geographically-distributed datacenters, so six nodes total in the cluster -- with one configured as a "permaslave" that doesn't participate in quorum). Given this, the node that's in the same datacenter generally gets most if not all of the master's transactions in a real world crash scenario.
> In practice, we deploy two servers in each datacenter (across three geographically-distributed datacenters, so six nodes total in the cluster -- with one configured as a "permaslave" that doesn't participate in quorum). Given this, the node that's in the same datacenter generally gets most if not all of the master's transactions in a real world crash scenario.
Source: http://p2p-hackers.709552.n3.nabble.com/p2p-hackers-Advice-o...