App2Net: Moving Application Functions to Network & a Case Study on Low-latency Feedback
- Resource Type
- Conference
- Authors
- Sankaran, Ganesh C.; Chung, Joaquin; Kettimuthu, Rajkumar
- Source
- 2022 IEEE/ACM International Workshop on Innovating the Network for Data-Intensive Science (INDIS) INDIS Innovating the Network for Data-Intensive Science (INDIS), 2022 IEEE/ACM International Workshop on. :1-8 Nov, 2022
- Subject
- Computing and Processing
Bridges
Technological innovation
Structured Query Language
Filtering
Conferences
Prototypes
Computer architecture
scientific computing
in-network computing
low latency
feedback
- Language
- ISSN
- 2831-3879
Recent advances in programmable networks enable custom processing of data at hundreds of gigabits per second. These advances can boost the performance of many distributed applications. Yet the high-level languages used by application developers are different from the data plane programming languages (such as P4 and NPL) used by network equipment. This language barrier slows innovation. Our hourglass-shaped architectural solution aims to lower this language barrier. This enables the application developer community to leverage programmable networks for achieving better performance. In this paper we propose a JSON-based intermediate representation to bridge the gap between applications and in-network computing. We demonstrate an instance of the solution in the context of a low-latency feedback application that enables SQL-based data filtering in a P4-based programmable environment. We also present a prototype compiler to convert an intermediate representation in JSON to P4 source.