Toward Consistent State Management of Adaptive Programmable Networks Based on P4
Toward Consistent State Management of Adaptive Programmable Networks Based on P4
复制标题
DOI：
10.1145/3341558.3342202
复制
发表时间：
2019-08
期刊：
影响因子：
--
通讯作者：
Mu He;Andreas Blenk;W. Kellerer;S. Schmid
中科院分区：
文献类型：
--
作者：
Mu He;Andreas Blenk;W. Kellerer;S. Schmid
新兴网络应用（增强现实、工业互联网等）对通信网络的性能、可靠性和适应性提出了严格的新要求。可编程数据平面（例如，基于P4）通过启用自适应网络重新配置来提供满足这些要求的新机会。然而，在这种重新配置期间确保一致性仍然具有挑战性。这篇文章是朝着自适应数据平面的更自动化的状态管理迈出的第一步。特别是，我们提出了一个有效的P4状态管理框架P4State，它允许快速识别源代码中对数据平面重新配置至关重要的网络状态（例如，由于缩放、故障恢复）。我们报告的第一个有前途的评估结果，我们的原型实现的正确性和效率方面，还考虑两个案例研究使用HALGORY（数据中心的负载平衡）和HashPipe（线速率测量数据平面）。
Emerging network applications (augmented reality, industrial Internet, etc.) introduce stringent new requirements on the performance, dependability, and adaptability of communication networks. Programmable data planes (e.g., based on P4) provide new opportunities to meet these requirements, by enabling adaptive network reconfigurations. However, ensuring consistency during such reconfigurations remains challenging. This paper makes a first step toward a more automated state management of adaptive data planes. In particular, we present an efficient P4 state management framework, P4State, which allows to quickly identify the network states from the source code that are critical for data plane reconfigurations (e.g., due to scaling, failure recovery). We report on first promising evaluation results of our prototype implementation in terms of correctness and efficiency, also considering two case studies using HULA (load balancing in data center) and HashPipe (line-rate measurement in data plane).