Mobius: Packet Re-processing Hardware Architecture for Rich Policy Handling on a Network Processor
- PDF / 1,271,766 Bytes
- 26 Pages / 439.37 x 666.142 pts Page_size
- 15 Downloads / 155 Views
(2021) 29:3
Mobius: Packet Re‑processing Hardware Architecture for Rich Policy Handling on a Network Processor Taejune Park1 · Seungwon Shin2 Received: 19 May 2020 / Revised: 19 September 2020 / Accepted: 25 September 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Network devices generally handle traffic with predefined policies that describe the operation of packets. Since these policies explain network operation, the number of policies in network devices naturally increases as the scale of a network. Unfortunately, processing a large number of policies may lead to performance loss; Although many policies can be stored in memory, a network processor in a network device can only handle a limited number of policies at once so that the policies should be divided and processed into several groups. Thus, the processing time for one packet will be delayed, and it can fill up an input buffer of the device and drop packets. However, improving a processor that supports large capacity is not an efficient way because it also increases the cost of the processor. To address these challenges, we propose a hardware architecture for network processors called Mobius. It allows a processor to re-process packets n more times with different policies by utilizing the idle resources of the processor caused by the propagation time of packets on a wire. Consequently, Mobius extends the capacity of the processor at a low-cost so that more policies can be processed for packets without performance loss. We implement the prototype of Mobius using NetFPGA-SUME and our evaluation demonstrates that Mobius achieves a line-rate throughput with a tiny latency overhead. A comparison with other network processor models shows that Mobius exhibits a similar performance but is more economical. Keywords Network hardware · Policy management · Network processor · FPGA · Architecture
This work was supported by Institute of Civil Military Technology Cooperation Center (ICMTC) funded by the Korea government (MOTIE & DAPA) [18-CM-SW-09], and Korea Electric Power Corporation (Grant number:R18XA05). * Seungwon Shin [email protected] Extended author information available on the last page of the article
13
Vol.:(0123456789)
3
Page 2 of 26
Journal of Network and Systems Management
(2021) 29:3
1 Introduction In these days, it is commonly required for network devices, such as switches, routers and even security appliance, to process large amounts of network packets in near real-time. With the advent of diverse new network required services (e.g., IoT and 5G), each network device is enforced to handle more than gigabits-persecond with minimal loss. Moreover, it is also necessary for network devices to employ various sorts of network policies that represent a set of rules governing the behaviors of packets. For example, in an IoT network environment, we may need to enforce diverse different network policies to a network device to forward/ drop required packets to each IoT device. If the number of IoT devices is getting
Data Loading...
