Cassandra – A structured storage system on a P2P Network

What this post added

This post introduces Cassandra, a new structured storage system designed for massive scale and high availability. It addresses the Inbox Search problem at Facebook by providing a distributed, fault-tolerant solution that scales incrementally across commodity servers. Key technical details include its data model (rows identified by keys, column families with columns or supercolumns, and columns with name, value, and timestamp), data distribution using consistent hashing with an order-preserving hash function for range scans, gossip-style cluster membership, and accrual-style failure detection. High availability is achieved through replication across data centers, with eventual consistency enabling reads from the closest replica and background repair. The post highlights its initial deployment for Inbox Search, managing TBs of data across 600+ cores and 120+ TB of disk space, and its open-sourcing as a beta version.