A Bunch of Money on AWS and Some Benchmark Results

After experimenting with smaller datasets, we drove just over 800,000 transactions per minute (tpmC) against 10,000 warehouses, using a cluster with 18 leaves and 18 aggregators, all r3.8xlarge instances. This table only includes leaf vCPUs for MemSQL, as we also had to use aggregator CPU to run the benchmark driver instances. Figure 2 illustrates the ability to maintain throughput per core for a transaction processing workload as data and cluster size increase.

Source: www.memsql.com