Continuous Datacenter Consolidation

Abstract

Abstract-Efficient mapping of Virtual Machines (VMs) onto physical servers is a key problem for cloud infrastructure providers as hardware utilization directly impacts revenue. Today, this mapping is commonly only performed when new VMs are created, but as VM workloads fluctuate and server availability varies, any initial mapping is bound to become suboptimal over time. We introduce a set of heuristic methods for continuous optimization of the VM-to-server mapping based on combinations of fundamental management actions, namely suspending and resuming physical machines, migrating VMs, and suspending and resuming VMs. Using these methods cloud infrastructure providers can continuously optimize their server resources regardless of the predictability of the workload. To verify that our approach is applicable in real-world scenarios, we build a proof-of-concept datacenter management system that implements the proposed algorithms. The feasibility of our approach is evaluated through a combination of simulations and real experiments where our system provisions a workload of benchmark applications. Our results indicate that the proposed algorithms are feasible, that the combined management approach achieves the best results, and that the VM suspend and resume mechanism has the largest impact.

Which is the best algorithm for virtual machine placement optimization?

“…Therefore, DC operators regularly re‐optimize the mapping of VMs to PMs, and perform the necessary migrations to get to the newly determined placement. This way, the provider can adapt resource usage to the workload's resource needs: In times of low demand, the workload will be consolidated to a low number of PMs, thereby saving a considerable amount of energy; in times of high demand, the VMs will be spread across many more PMs so that their resource requirements—and ultimately, service level objectives (SLOs)—are satisfied …”

Allocation of Virtual Machines in Cloud Data Centers—A Survey of Problem Models and Optimization Algorithms

“…There are simulators specifically for cloud research, for example CloudSim [21], but many researchers used their own simulation environments. Relatively few researchers tested their algorithms in a real environment [31,51,57,66,70,74,101,103,105] or using a combination of real hardware and simulation [85,93,95,104,109]. It has to be added though that in most of these cases, the "real" environment used for evaluation was rather small (e.g., just a handful of PMs and VMs).…”

“…However, a linear approximation of power consumption as a function of CPU load works quite well across a wide range of applications and platforms [83]. Hence, several authors assumed linear dependence on CPU load [6,51,38,60,40,93].…”

“…When the resource demand of the VMs increases, they can be migrated to other PMs with a lower load, thus avoiding SLA violations. For these reasons, VM migration is a key ingredient of dynamic VM placement schemes [93].…”

“…Beside the above reactive actions, a CP will also have to regularly review and potentially re-optimize the whole VM placement, in order to find a better fit to the changed demand of the existing VMs, modified eCP rental fees, modified electricity prices, or other changes that did not require immediate action but made the placement sub-optimal [87,93]. Such a review may be carried out at regular times (e.g., every 10 minutes), or it may be triggered by specific events.…”