The paper entitled “A system design for elastically scaling transaction processing engines in virtualized servers” was presented at VLDB 2020 on September 2nd.

The paper focuses on workload variations that can be addressed by modern multi-socket, multi-core servers and presents a system design for providing fine-grained elasticity to multi-tenant, scale-up OLTP deployments. It introduces novel components to the virtualization software stack that enable on-demand addition and removal of computing and memory resources. It also provides a bi-directional, low-overhead communication stack between the virtual machine and the hypervisor, which allows the former to adapt to variations coming both from the workload and the resource availability.