Interactive Cloud Microservices

Datacenters support a large and ever-increasing fraction of the world's digital computation power, including search engines, social networks, and machine learning analytics. As modern cloud services grow in popularity, their design shifts from supporting complex monolithic applications to supporting collections of specialized, loosely-coupled microservices. These microservices impact resource requirements and complicate computer cluster management, hurting availability and service reliability. Guaranteeing the responsiveness expected from cloud services while using datacenters efficiently requires a joint hardware-software approach.

Christina Delimitrou, Electrical and Computer Engineering, is taking a holistic view toward designing a system stack for interactive cloud microservices—running on large-scale datacenters that are resource-efficient. More datacenter services are switching to this new application model. Acknowledging this trend, Delimitrou is pursuing automated, learning-based techniques, as she highlights the value of leveraging practical machine learning techniques to better navigate the increasing complexity of the cloud.

At the hardware level, this project first quantifies the implications that microservices have on server design, and second, explores their potential for hardware acceleration. At the software level, the work is developing a new cluster manager that accounts for the dependencies among microservices in an automated and transparent-to-the-user way. This guarantees end-to-end performance. By innovating in both hardware and software, Delimitrou’s research aims to achieve performance and efficiency gains that neither hardware-only or software-only approaches can provide.

Cornell Researchers

Funding Received

$500 Thousand spanning 5 years