Efficient provisioning of bursty scientific workloads on the cloud using adaptive elasticity control

Elasticity is the ability of a cloud infrastructure to dynami-cally change the amount of resources allocated to a running service as load changes. We build an autonomous elasticity controller that changes the number of virtual machines al-located to a service based on both monitored load changes and predictions of future load. The cloud infrastructure is modeled as a G/G/N queue. This model is used to con-struct a hybrid reactive-adaptive controller that quickly re-acts to sudden load changes, prevents premature release of resources, takes into account the heterogeneity of the work-load, and avoids oscillations. Using simulations with Web and cluster workload traces, we show that our proposed con-troller lowers the number of delayed requests by a factor of 70 for the Web traces and 3 for the cluster traces when com-pared to a reactive controller. Our controller also decreases the average number of queued requests by a factor of 3 for both traces, and reduces oscillations by a factor of 7 for the Web traces and 3 for the cluster traces. This comes at the expense of between 20 % and 30 % over-provisioning, as compared to a few percent for the reactive controller