From MySQL Performance Blog:
VoltDB is very scalable; it should scale to 120 partitions, 39 servers, and 1.6 million complex transactions per second at over 300 CPU cores, on the benchmarked configuration, with the recommended level of redundancy for HA…
scaling a synchronously replicated, active-active master, fully ACID, always-consistent database to a 40-server cluster is impressive. Yes, it comes with some limitations (there’s a decent write-up on highscalability.com that explains more), but that is still nothing to sneeze at.
In the summer of 2010, SGI benchmarked VoltDB’s Voter application on a cluster of 30 SGI servers connected by a high-speed network. VoltDB tipped the scales at 3.4 million ACID transactions per second (read more here). In February 2011, Percona’s Performance Measurement team modeled VoltDB to scale to 1.6 million complex transactions per second, running with HA enabled, on 39 commodity servers and standard gigabit ethernet.
What gives VoltDB the ability to run so fast and jump so high, and deliver ACID-level consistency in the process? The answer lies in a collection of carefully chosen design principles.
From High Scalability blog:
The Six SQL Urban Myths
Here are the six myths that Mr. Stonebraker says NoSQL advocates incorrectly perpetuate: