28 March 2024 in Proceedings of the ACM on Networking
Machine Learning (ML) shows promising potential for enhancing networking tasks by providing early traffic predictions. However, implementing an ML-enabled system is a challenging task due to network devices limited resources. While previous works have shown the feasibility of running simple ML models in the data plane, integrating them into a practical end-to-end system is not an easy task. It requires addressing issues related to resource management and model maintenance to ensure that the performance improvement justifies the system overhead. In this work, we propose DUMBO, a versatile end-to-end system to generate and exploit early flow size predictions at line rate. Our system seamlessly integrates and maintains a simple ML model that offers early coarse-grain flow size prediction in the data plane. We evaluate the proposed system on flow scheduling, per-flow packet inter-arrival time distribution, and flow size estimation using real traffic traces, and perform experiments using an FPGA prototype running on an AMD(R)-Xilinx(R) Alveo U280 SmartNIC. Our results show that DUMBO outperforms traditional state-of-the-art approaches by equipping network devices data planes with a lightweight ML model. Code is available at https://github.com/cpt-harlock/DUMBO.
18 March 2024 in IEEE Open Journal of the Communications Society
has also resulted in increased complexity for Cloud orchestration tools. Traditional tools were designed for centralized data centers and are ineffective for locating microservices in geographically-distributed edge-like infrastructures. This paper presents Phare, a decentralized scheduling algorithm designed to optimize the placement of microservices by satisfying their computing and communication demands while minimizing deployment costs. Phare employs a heuristic-based approach to solve the NP-Hard scheduling problem, prioritizing the microservices with the more stringent requirements and placing them on the most convenient computing facilities, based on the concept of affinity, contributing to the field by providing a more holistic approach to resource scheduling in edge computing. We validate our approach against Firmament, the state-of-the-art workload scheduling algorithm for component-based applications, on simulated edge infrastructures with hundreds of clusters. Phare achieves up to a 10× reduction in terms of deployment costs compared to Firmament while providing a much lower scheduling latency.
27 November 2023 in Proceedings of the ACM on Networking
Accurate per-flow monitoring is critical for precise network diagnosis, performance analysis, and network operation and management in general. However, the limited amount of memory available on modern programmable devices and the large number of active flows force practitioners to monitor only the most relevant flows with approximate data structures, limiting their view of network traffic. We argue that, due to the skewed nature of network traffic, such data structures are, in practice, heavily underutilized, i.e. sparse, thus wasting a significant amount of memory. This paper proposes a Sparse Approximate Data Structure (SPADA) representation that leverages sparsity to reduce the memory footprint of per-flow monitoring systems in the data plane while preserving their original accuracy. SPADA representation can be integrated into a generic per-flow monitoring system and is suitable for several measurement use cases. We prototype SPADA in P4 for a commercial FPGA target and test our approach with a custom simulator that we make publicly available, on four real network traces over three different monitoring tasks. Our results show that SPADA achieves 2× to 11× memory footprint reduction with respect to the state-of-the-art while maintaining the same accuracy, or even improving it.
1 June 2026 in Proceedings of the ACM on Networking
Distributed tracing is essential for monitoring and debugging services deployed on top of microservice architectures. However, existing solutions face a fundamental trade-off between non-intrusiveness, language/protocol independence, overhead, and accuracy. We present ChainScope, a distributed tracing system that leverages eBPF to establish a universal tracing framework within the kernel. By implementing kernel-level context propagation, ChainScope enables trace-level sampling in a non-intrusive manner, effectively controlling overhead while maintaining high accuracy across diverse service processing models. Evaluation results show that ChainScope achieves better accuracy-overhead trade-offs than existing non-intrusive tracing approaches with up to 2.2× better accuracy, and 1.6× higher end-to-end service throughput in complex scenarios such as asynchronous processing and RPC (Remote Procedure Call) protocols. Furthermore, we demonstrate that ChainScope accurately identifies the root cause of long-tail latency in a realistic use case.