Occamy: A Preemptive Buffer Management for On-chip Shared-memory Switches
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.
Authors
- Nan Li (ORCID: https://orcid.org/0000-0002-4095-2810)
- Wanchun Jiang (ORCID: https://orcid.org/0000-0001-5067-321X)
- Hao Li (ORCID: https://orcid.org/0000-0001-8776-6911)
- Zhenxing Zhang
- Danfeng Shan (ORCID: https://orcid.org/0000-0003-0852-5955)
- Zhihu Liang
- Fengyuan Ren (ORCID: https://orcid.org/0000-0001-6526-3889)
- Jinchao Ma (ORCID: https://orcid.org/0009-0005-3754-2967)
- Xinyu Wen
- Yunguang Li
Institutions
- Central South University (CN)
- Xi'an Jiaotong University (CN)
- Tsinghua University (CN)
Publication Details
- Published
- 2025-03-26
- DOI
- https://doi.org/10.1145/3689031.3717495
- Citations
- 2
- Primary Topic
- Interconnection Networks and Systems
- Type
- article
- Field-Weighted Citation Impact
- 2.97