Abstract | ||
---|---|---|
Sketches have successfully provided accurate and fine-grained measurements (e.g., flow size and heavy hitters) which are imperative for network management. In particular, Count-Min (CM) sketch is widely utilized in many applications due to its simple design and ease of implementation. There have been many efforts to build monitoring frameworks based on Count-Min sketch. However, these frameworks either support very specific measurement tasks or they cannot be implemented on high-speed programmable hardware (PISA).
In this work, we propose FCM, a framework that is designed to support generic network measurement with high accuracy. Our key contribution is FCM-Sketch, a data structure that has a lightweight implementation on the emerging PISA programmable switches. FCM-Sketch can also be used as a substitute for CM-Sketch in applications that use CM-Sketch. We have implemented FCM-Sketch on a commodity programmable switch (Barefoot Tofino) using the P4 language. Our evaluation shows that FCM-Sketch can reduce the errors in many measurement tasks by 50% to 80% compared to CM-Sketch and other state-of-the-art approaches.
|
Year | DOI | Venue |
---|---|---|
2020 | 10.1145/3386367.3432729 | CoNEXT '20: The 16th International Conference on emerging Networking EXperiments and Technologies
Barcelona
Spain
December, 2020 |
DocType | ISBN | Citations |
Conference | 978-1-4503-7948-9 | 2 |
PageRank | References | Authors |
0.36 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cha Hwan Song | 1 | 2 | 1.04 |
Pravein G. Kannan | 2 | 93 | 6.57 |
Bryan Kian Hsiang Low | 3 | 50 | 13.31 |
Mun Choon Chan | 4 | 1130 | 97.54 |