+1 . When Stratos grows larger it will be important to have rack/ data center awareness to make sure a sudden rack failure will not end up in lost data. AFAIK Hadoop also provides rack/ data center awareness that would be another place we can look into to get an idea on how it is achieved. Using something like an RR algorithm to change between racks would be nice.
Regards, Pulasthi On Fri, Jun 7, 2013 at 9:32 PM, Srinath Perera <[email protected]> wrote: > Hi All, > > I think this is a very useful feature. Idea is that let user specify > different reliability and local network zones so that when we create new > nodes, we spread them right. > > However, I am not sure we have enough control when we talk to EC2 and > openstack, we have this kind of control (may via availability zones) . It > worth thinking about it. > > One good place to look for what this means is how cassandra support data > replication based on rack/ data center aware manner. > > --Srinath > > -- > ============================ > Srinath Perera, Ph.D. > http://www.cs.indiana.edu/~hperera/ > http://srinathsview.blogspot.com/ > > _______________________________________________ > Architecture mailing list > [email protected] > https://mail.wso2.org/cgi-bin/mailman/listinfo/architecture > > -- -- Pulasthi Supun Software Engineer; WSO2 Inc.; http://wso2.com, Email: [email protected] Mobile: +94 (71) 9258281 Blog : http://pulasthisupun.blogspot.com/ Git hub profile: https://github.com/pulasthi
_______________________________________________ Architecture mailing list [email protected] https://mail.wso2.org/cgi-bin/mailman/listinfo/architecture
