Scylla isn't your father's Cassandra. ScyllaDB scales up linearly with the number of cores using innovative techniques. Stop paying that much for hardware. Stop maintaining huge clusters and save human labor maintaining them. Decrease your mean time to failure (MTTF) due to smaller cluster size.
Script that handles x10 traffic spikes for the holiday:
service cassandra stop; service scylla-server start
That's right, ScyllaDB is fully compatible with Cassandra. Now go buy the big screen TV you wanted.
Consistent < 1msec latency in 99% cases will position your application in the best possible position versus your competitors. Leave nothing on the floor and forget about tuning. There is no GC here!
The bigger the data, the bigger the problems. Bulk upload/download of TBs is a problem many face. If you use analytics and wish to process offline data and then load it back to the database you may experience bottlenecks which do not exist with Scylla’s 1 million ops per server. Welcome to the future.
Run repairs and compaction in minutes or hours, not days. Forget about repairs that don’t finish by 5pm. Remember time is money.
Throughput of Scylla and Cassandra in a 3-node cluster with RF=3 and CL=QUORUMLearn more
Raw speed isn’t just a nice benchmark or a low cloud bill. Scylla’s order of magnitude improvement in performance opens a wide range of possibilities. Instead of designing a complex data model to achieve adequate performance, use a straightforward data model, eliminate complexity, and finish your NoSQL project in less time with fewer bugs.
Performance improvements enable not just reduction in hardware resources, but also a reduction in architecture, debugging, and devops labor. Scylla combines the simple and familiar Cassandra architecture with new power to build a data model that fits the application, not tweak the model to fit the server.