Serverless Computing for Stateful Applications

Serverless computing, also known as Function-as-a-Service (FaaS), has seen a significant rise in popularity, becoming a staple in commercial cloud services such as AWS Lambda, Google Cloud Functions, and Azure Functions, as well as in open-source projects like OpenWhisk and OpenFaaS. Initially designed for event-driven, stateless applications such as image processing, serverless platforms are now being leveraged for more complex, stateful, parallel, data-intensive, and compute-intensive applications. These include machine learning, large language model (LLM) services, scientific computing workflows, and data analytics, which demand high parallelism and scalable computing capabilities. The pay-per-use model of FaaS platforms eliminates potential monetary waste, making them an attractive option. However, supporting large stateful applications on FaaS introduces new challenges, such as non-trivial overhead from function invocations and inherent constraints like limited network connectivity, data availability, and computing resources. Current solutions are often ad-hoc and inefficient, highlighting the need for more robust and efficient approaches.

This Research Topic aims to explore and address the challenges and opportunities associated with using serverless computing for stateful applications. The primary objectives include investigating new serverless computing applications, enhancing FaaS capabilities to support stateful computing efficiently, and developing new systems techniques to improve FaaS services. Specific questions to be answered include how to mitigate the overhead of function invocations, how to overcome the limitations of network connectivity and data availability, and how to optimize computing and memory resources for stateful applications on FaaS platforms.

To gather further insights into the boundaries and limitations of serverless computing for stateful applications, we welcome articles addressing, but not limited to, the following themes:

- New serverless computing applications
- New FaaS and serverless capabilities that enable efficient stateful computing
- New systems techniques (e.g., storage, network, etc.) to enable better FaaS service
- Big data management and processing on serverless and FaaS
- Serverless backend as a service (e.g., serverless databases, serverless storage)
- Energy and carbon efficiency of serverless
- Security, privacy, and trust management of serverless and FaaS
- Applications of machine learning and edge computing in serverless computing

Keywords: Serverless, FaaS, stateful computing, parallel computing, distributed systems

Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.