SmartNIC-based Load Management and Network Health Monitoring for Time Sensitive Applications

Abstract

Time sensitive network applications, for example in Intra-Vehicular Networks, aim to give predictable end-to-end latency guarantees. As a consequence, processing resources of involved host systems remain partially unused, because they are reserved for rare worst cases. This circumstance provides the opportunity to reduce dimensioning overheads by managing the load on the nodes flexibly within the network. In our proposed approach, a SmartNIC involving an FPGA-based load balancer achieves dynamic routing of flows whilst preserving end-to-end latency guarantees. A flow-oriented online network measurement component continuously supervises network traffic with regards to compliance to flow specifications and constraints such as bounded one-way delay, absence of packet loss, and jitter. We use the supervisor to enhance forwarding decisions on the data plane. Initial evaluation yields a saving potential of around 30 %. We showcase quick dynamic reconfiguration of the FPGA when triggered by real-time measurement of the one-way delay using realistic automotive network traffic.

Emerging Technologies for 6G Communication Networks: Machine Learning Approaches

“…That approach guarantees that if one component malfunctions, another component can seamlessly assume control and sustain the intended functionality [ 45 ]. Moreover, load balancing and monitoring help prevent any component from becoming overloaded or causing a failure by distributing traffic across multiple components and monitoring the network health tracking process [ 46 ].…”

Elastic Gateway Functional Safety Architecture and Deployment: A Case Study

“…Load balancing is one of the reliability strategies of distributed architectures such as cloud services [44] or automotive IVN E/E architectures [45]. Existing load balancing algorithms are mainly classified into two categories: static and dynamic.…”

“…Internally, the NS hosts a Finite State Machine (FSM) that takes as input the information from the SDNC and from an internal error detection unit and, based on this, decides the operation mode of the node and determines thus the internal configuration of the node. o Network Health Monitoring [74] o Load Management Layer [45] The output of this block is an error signal which will be transmitted to the Configurator Functional State Machine This error signal is transmitted using an error signaling protocol that distinguishes between three classes of errors: High, medium and low criticality.  Node Configurator: Static configuration of 8 signal groups in 6 different functional modes.…”

Contributions to the design, development and evaluation of network processors for automotive zonal gateway controllers

“…Freedom from Memory Interference [123] Safety island in safety critical hardware [124] Asil-decomposition based routing and scheduling in safety-critical time-sensitive networking [125] Network information flow [126] Coupling source routing with time-sensitive networking [127] Failure handling for time-sensitive networks using sdn and source routing [128] On the evaluation of the active queue management mechanisms [129] Achieving flexible, low-latency and 100gbps line-rate load balancing over ethernet on fpga [130] Smartnic-based load management and network health monitoring for time sensitive applications [131] Precise real-time monitoring of time-critical flows [132] Shortcutting Fast Failover Routes in the Data Plane [133] Fast failover in ethernet-based automotive networks […”