Low-Rate Overuse Flow Tracer (LOFT): An Efficient and Scalable Algorithm for Detecting Overuse Flows

TL;DR

LOFT is a new scalable algorithm that efficiently detects overuse flows with 1.5x overuse in one second, significantly outperforming previous methods in high-speed network environments.

Contribution

The paper introduces LOFT, a novel algorithm for detecting overuse flows that is more accurate and faster than existing probabilistic flow monitoring techniques.

Findings

LOFT detects 1.5x overuse flows within one second.

Prior methods fail to detect 2x overuse within 300 seconds.

LOFT is implemented in DPDK and FPGA for high-speed processing.

Abstract

Current probabilistic flow-size monitoring can only detect heavy hitters (e.g., flows utilizing 10 times their permitted bandwidth), but cannot detect smaller overuse (e.g., flows utilizing 50-100% more than their permitted bandwidth). Thus, these systems lack accuracy in the challenging environment of high-throughput packet processing, where fast-memory resources are scarce. Nevertheless, many applications rely on accurate flow-size estimation, e.g. for network monitoring, anomaly detection and Quality of Service. We design, analyze, implement, and evaluate LOFT, a new approach for efficiently detecting overuse flows that achieves dramatically better properties than prior work. LOFT can detect 1.5x overuse flows in one second, whereas prior approaches fail to detect 2x overuse flows within a timeout of 300 seconds. We demonstrate LOFT's suitability for high-speed packet processing with implementations in the DPDK framework and on an FPGA.