Nitro: A Fast, Scalable In-Memory Storage Engine for NoSQL Global Secondary Index

We present Nitro, a high-performance in-memory key-value storage engine used in Couchbase 4.5 Global Secondary Indexes. The Nitro storage engine is well suited for the recent hardware trends like large amounts of memory and many CPU cores. The storage engine leverages latch-free data structures and tries to achieve linear scalability for the index read-write operations. The Nitro storage engine offers concurrent readers and writers, lightweight database snapshots, stable scan, backup and recovery operations. We integrated Nitro into the Couchbase Global Secondary Indexes (GSI) and observed significant improvement in performance compared to our disk oriented storage engine configured with the same amount of memory for buffer cache. On a 32 core machine, we observed an end-to-end GSI server insertion throughput of 1,650,000 entries/sec and index update throughput of 822,000 entries/sec. A single instance of Nitro data structure running on a 40 core machine achieved a peak insertion throughput of 4 million index entries/sec and entry lookup throughput of 10 million lookups/sec.