Dynamic performance–Energy tradeoff consolidation with contention-aware resource provisioning in containerized clouds

Abstract

Containers have emerged as a more portable and efficient solution than virtual machines for cloud infrastructure providing both a flexible way to build and deploy applications. The quality of service, security, performance, energy consumption, among others, are essential aspects of their deployment, management, and orchestration. Inappropriate resource allocation can lead to resource contention, entailing reduced performance, poor energy efficiency, and other potentially damaging effects. In this paper, we present a set of online job allocation strategies to optimize quality of service, energy savings, and completion time, considering contention for shared on-chip resources. We consider the job allocation as the multilevel dynamic bin-packing problem that provides a lightweight runtime solution that minimizes contention and energy consumption while maximizing utilization. The proposed strategies are based on two and three levels of scheduling policies with container selection, capacity distribution, and contention-aware allocation. The energy model considers joint execution of applications of different types on shared resources generalized by the job concentration paradigm. We provide an experimental analysis of eighty-six scheduling heuristics with scientific workloads of memory and CPU-intensive jobs. The proposed techniques outperform classical solutions in terms of quality of service, energy savings, and completion time by 21.73–43.44%, 44.06–92.11%, and 16.38–24.17%, respectively, leading to a cost-efficient resource allocation for cloud infrastructures.

Energy Consumption in Microservices Architectures: A Systematic Literature Review

“…The simulation evaluation method was widely executed in cloud computing architectures, but when we observe its execution in edge computing, fog and cloud computing, we notice a huge difference in the drop in utilization compared to cloud computing. The study by Canosa-Reyes et al [25] uses simulation because it allows evaluation of the proposed technique in a controlled environment, exploring different scenarios and collecting data for performance analysis. The same happens when the measurement is the evaluation method; in cloud computing, an abundant amount of work are approaching while the others suffer a drastic fall.…”

“…Improving elasticity is crucial in distributed environments, where elasticity is essential to ensure proper system availability and performance, especially during peak traffic and demand. The work by Canosa-Reyes et al [25] presents online task allocation strategies to improve service quality based on two or three levels of scheduling policies, including container selection, capacity distribution and contention-sensitive allocation.…”

“…High energy consumption also generates other problems, such as the high cost of refrigeration equipment, overloads and energy costs. There are several techniques to mitigate energy consumption, such as load balancing and efficient task scheduling, although these techniques can degrade the quality of service and reduce the performance of cloud applications [22,25]. Therefore, new energy consumption reduction techniques are needed to optimize microservice architectures.…”

“…Task Scheduling: Efficient task flow scheduling is one of the most challenging challenges in a microservices architecture due to the variation in traffic flows generated by various cloud applications. Efficiently scheduling tasks in massive, dynamic, elastic computing environments such as microservices architectures remains a challenging task [25,50]. Task scheduling presents extra challenges, as tasks with higher priorities must be executed before tasks with lower priorities.…”

“…High energy costs have a negative impact on the environment and on companies' operating costs. The high energy consumption in microservice architectures goes beyond the energy cost itself and can affect the quality of service of the entire system, impairing the performance and availability of the [22,25] system. Therefore, it is important to study and develop solutions to improve the energy efficiency of microservice architectures.…”