• Home
• People
• Jobs
• Thesis Topics
• Publications
• Conference Rankings
• Research
• Bcast
• Teaching
• Contact

SPONSORS

COLLABORATIONS

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Publications of SPCL

M. Copik, A. Calotoiu, R. Bruno, R. Böhringer, T. Hoefler:
	Process-as-a-Service: FaaSt Stateful Computing with Optimized Data Planes (Jan. 2022) Abstract Fine-grained and ephemeral functions power many new applications that benefit from elastic scaling and lower computing costs of serverless platforms. However, they are hampered by expensive and limited communication and high invocation latency. Functions cannot keep track of state across invocations and must rely on remote storage, making workflows and applications with dependencies between tasks or relying on communication between workers difficult to implement using Function-as-a-Service (FaaS) computing. To continue the serverless revolution, we introduce the concept of Process as a Service (PraaS) and show how established operating system abstractions can be adapted to model and implement dynamically provisioned cloud computing workers. We present the new serverless data plane that improves invocation performance while preserving the ephemeral and elastic nature of serverless workers. Finally, we build a unified and portable communication interface for serverless, enabling optimized peer–to–peer communication allowing workers to solve problems in parallel. PraaS — serverless processes, are the next step in the ongoing move towards granular computing on elastic and efficient resources, and our work allows more complex and stateful applications to save costs. Documents download article:
	BibTeX
@techreport{,   author={Marcin Copik and Alexandru Calotoiu and Rodrigo Bruno and Roman Böhringer and Torsten Hoefler},   title={{Process-as-a-Service: FaaSt Stateful Computing with Optimized Data Planes}},   year={2022},   month={01}, }