DescriptionThe Cassandra distributed database achieves high throughput and large capacity at an unparalleled resiliency by scaling linearly to a large number of nodes, while keeping multiple copies of the data. This comes at the price of increased latency and inefficient use of CPU and storage. Viking Enterprise Solutions has developed an approach whereby storage is decoupled from the nodes that run the database by deploying a Cassandra Cluster over dockers that is connected to NVMeoF and served by the Viking Enterprise Solutions NSS-2248 NVME target appliance. We achieve significantly lower latency by using NVMe and reducing the replication factors. The decoupling of the volumes from the database nodes enables much more efficient use of CPU resources by allowing multiple instances to share CPU and memory resources on the same servers, while improving the overall flexibility and resiliency of the system.