Occamy: A Preemptive Buffer Management for On-chip Shared-memory Switches

2025-01-23

AI Summary

To address the tension between limited on-chip shared buffer capacity and surging bursty traffic in high-bandwidth datacenter switch chips, this paper proposes a preemptive buffer management mechanism. Unlike conventional non-preemptive approaches, our method enables dynamic, real-time redistribution of buffer resources across queues on modern programmable switch ASICs—achieved via memory-bandwidth-aware scheduling, fine-grained buffer migration, and a lightweight runtime preemption protocol that actively reclaims and reallocates over-provisioned buffers. Experimental evaluation demonstrates up to 55% improvement in end-to-end throughput, substantial reduction in tail latency, and significantly enhanced throughput and inter-flow fairness under shallow-buffer configurations when evaluated on realistic datacenter traffic traces.

Technology Category

• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Data Stream Mining
• Planning, Routing, and Scheduling: Scheduling under Uncertainty

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Security and Privacy: Large-scale security measurements

Abstract

Today's high-speed switches employ an on-chip shared packet buffer. The buffer is becoming increasingly insufficient as it cannot scale with the growing switching capacity. Nonetheless, the buffer needs to face highly intense bursts and meet stringent performance requirements for datacenter applications. This imposes rigorous demand on the Buffer Management (BM) scheme, which dynamically allocates the buffer across queues. However, the de facto BM scheme, designed over two decades ago, is ill-suited to meet the requirements of today's network. In this paper, we argue that shallow-buffer switches, intense bursts, along with dynamic traffic call for a highly agile BM that can quickly adjust the buffer allocation as traffic changes. However, the agility of the current BM is fundamentally limited by its non-preemptive nature. Nonetheless, we find that preemptive BM, considered unrealizable in history, is now feasible on modern switch chips. We propose Occamy, a preemptive BM that can quickly adjust buffer allocation. Occamy utilizes the redundant memory bandwidth to actively reclaim and reallocate the over-allocated buffer. Testbed experiments and large-scale simulations show that Occamy can improve the end-to-end performance by up to ~55%.

Problem

• Buffer Management
• High-Traffic
• Data Center

Innovation

• Occamy
• Buffer Management
• Dynamic Reallocation