It may not what you want, but please read about Network Topology Strategy and DC_QUORUM.
http://www.datastax.com/dev/blog/deploying-cassandra-across-multiple-data-centers You can configure your Cassandra "Data Center aware" . Your read and write will be resolved in DC local, but will be replicated across DCs. maki On 2011/06/06, at 4:28, Khanh Nguyen <nguyen.h.kh...@gmail.com> wrote: > On Sun, Jun 5, 2011 at 2:17 PM, mcasandra <mohitanch...@gmail.com> wrote: >> Please give more detailed info about what exactly you are worried about or >> trying to solve. > > In general, we are trying to devise a partitioning and replication > scheme that takes into account social relations between data. > >> Please take a step back and look at cassandra's architecture again and what >> it's trying to solve. It's a distributed database so if you do what you are >> describing there is a potential of getting hotspots. Which will probably >> lead in other problems. You might solve one problem but then intriduce >> another like slow reads or one node getting overloaded. > > Exactly, we understand that this is an issue. In fact, one reason > we're working on this project is to see how well our proposed > partitioning and replication scheme distribute the load while > preserving social locality. > >> I also suggest run some stress test and worry about the load, performance >> only if it is a real problem for your kind of data. > > Is there a way to tell where a piece of data is stored in a cluster? > For example, can I tell if LastNameColumn['A'] is stored at node 1 in > the ring? > > Thanks. > > -k
