A High-Performance Implementation of an IoT System Using DPDK

Abstract

An IoT (Internet of Things) system typically encompasses a number of devices and sensors and is required to process a large number of messages at a high speed. To address this requirement, we propose a dual plane architecture, which consists of a control plane and a data plane. The control plane processes signaling messages and the data plane takes charge of processing user data messages. This allows the system to process messages separately and simultaneously in the different planes according to the type of incoming message. In this paper, we present the each plane's role and how messages are processed in the different planes. We also present the interworking method between both planes. To verify the proposed architecture, we implement and apply the architecture to our previous single plane IoT system. We also compare the performance of the proposed system with that of the single plane IoT system in terms of throughput and packet loss ratio. The results reveal that the performance of the proposed architecture is much higher than that of the previous single plane IoT systems. The results prove that the proposed architecture is highly appropriate for IoT environments.

A Dynamic Plane Prediction Method Using the Extended Frame in Smart Dust IoT Environments

“…The DPDK increases packet throughput in the whole system [11][12][13][14][15]. It is a set of libraries and drivers for high-speed packet processing developed by Intel [11,12].…”

“…The DPDK system does not support the plane partitioning method [13]. Since there are few similar studies at present, to validate the proposed method we built a system to support the dual partitioning environment, a fixed plane partitioning environment using DPDK.…”

“…Previous research has examined the question of how to process control planes and data planes in physically independent processing nodes as a way to improve the system performance [13][14][15]. In particular, [14] shows that the processing performance increases when control planes and data planes exist in independent processing nodes.…”

“…Since the environment in which DPDK is typically implemented [13] has both control planes and data planes to each of the processing nodes (servers in Figure 9), one processing node can process both kinds of packets [13]. We named this environment a dual environment (see Figure 9).…”

“…In addition, the occurrence of an increased density of nodes can cause bottlenecks, which can lead to very fatal problems that can degrade the whole system throughput as well as black out the entire system [3].One way to solve the above problem is to apply Intel's (Santa Clara, CA, USA) Dual Plane Development Kit (DPDK) [11,12] to your system to speed up data processing. This type of approach has been very effective in terms of achieving increased throughput, but resulted in a new issue that reduces the throughput when signal packets and user data packets are mixed in similar proportions, because DPDK does not support dynamic partitioning [13][14][15]. This problem is called the mixed packet problem [3,14].…”