Joint Two-Tier Network Function Parallelization on Multicore Platform
Joint Two-Tier Network Function Parallelization on Multicore Platform
复制标题
DOI：
10.1109/tnsm.2019.2920012
复制
发表时间：
2019-05
影响因子：
5.3
通讯作者：
Mengjie Liu;G. Feng;Jianhong Zhou;Shuang Qin
中科院分区：
文献类型：
--
作者：
Mengjie Liu;G. Feng;Jianhong Zhou;Shuang Qin
由于网络功能虚拟化（NFV）是基于通用处理器实现的，以避免专有硬件，因此其灵活性和敏捷性的好处可能会受到增加的分组延迟和降低的吞吐量的影响。在通用处理器上开发新的网络函数（NF）处理框架是提高延迟和吞吐量性能的有效途径。本文提出了一种新的联合两层NF并行化（TNP）框架，该框架能够灵活、敏捷地组织并行NF处理，极大地改善由一组NF构成的服务功能链（SFC）的延迟和吞吐量性能。在TNP中，我们在服务层联合组织多个NF的并行化，并在底层网络层执行单个NF的多核映射。我们制定的最佳TNP设计问题，最大限度地减少链路带宽消耗的端到端的延迟和计算资源的限制。我们通过将问题分解为两个更简单的子问题来解决该问题：1）子问题1（SP1）是结合链接映射问题来解决最优SFC并行化图设计，2）子问题2（SP2）是结合节点映射问题来共同解决计算资源分配。通过在一组可行域中按顺序搜索，实现全局最优解。数值结果表明，我们提出的TNP可以显着减少服务延迟，提高网络吞吐量相比，已知的单层NF并行化计划。此外，还可以大大提高底层网络中的链路带宽利用率和SFC请求接受率。
As network function virtualization (NFV) is realized based on general-purpose processors for avoiding proprietary hardware, its benefits of flexibility and agility could be compromised by the increased packet latency and reduced throughput. An effective approach for improving the latency and throughput performance is to exploit new network function (NF) processing framework on general purpose processors. In this paper, we propose a new joint two-tier NF parallelization (TNP) framework, which can agilely and flexibly organize parallel NF processing to greatly improve the latency and throughput performance of service function chain (SFC) which is constituted by a set of NFs. In TNP, we jointly organize the parallelization of multiple NFs at the service tier and perform multicore mapping of individual NFs at the substrate network tier. We formulate the optimal TNP design problem as minimizing link bandwidth consumption subject to end-to-end latency and computing resource constraints. We solve the problem by decomposing it into two easier subproblems: 1) subproblem 1 (SP1) is to solve the optimal SFC parallelization graph design in conjunction with link mapping problem and 2) subproblem 2 (SP2) is to jointly solve computing resource allocation in conjunction with node mapping problem. The global optimal solution is accomplished by searching in a set of feasible regions in sequence. Numerical results demonstrate that our proposed TNP can significantly decrease service latency and improve network throughput compared with known single layer NF parallelization schemes. Moreover, the link bandwidth utilization and SFC request acceptance rate in the substrate network can also be greatly improved.