$R^{3}$: A Building Block for Disordering-Tolerant Load Balancing in Data Center Networks
Packet-level load balancing has shown its massive potential for long in utilizing super high bisection bandwidth of data center network (DCN). This kind of potential, however, has still not been completely transformed into huge performance enhancement of data transmission. The fundamental reason is that packet-level load balancing can fully utilize the parallel paths of underlying physical network, but suffer from the problem of packet disordering transmission, which greatly impairs the flow-level transmission performance of DCN. This paper explores the root cause of performance impairment generated by packet disordering transmission, and proposes <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$R^{3}$</tex-math></inline-formula>, a solution focusing on “recognizably releasing redundant acknowledgements” as a building block for data center packet-level load balancer. In <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$R^{3}$</tex-math></inline-formula>'s heart, the source leaf switch perceives the global packet loss information and selectively intercepts the redundant acknowledgement packets, thus avoiding the TCP-driven end-host from experiencing frequent window reductions and unnecessary packet retransmissions. Experimental results of numerous simulation tests and real implementations show that, after integrating <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$R^{3}$</tex-math></inline-formula> into the representative data center packet-level load balancing schemes, the transmission performances of both delay-sensitive and throughput-oriented data center flows are significantly improved. Furthermore, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$R^{3}$</tex-math></inline-formula> is merely implemented by switch, leaving the end hosts and the deployed load balancing scheme totally unchanged.
Authors
- Jinbin Hu (ORCID: https://orcid.org/0000-0001-8216-9683)
- Xidao Luan (ORCID: https://orcid.org/0000-0002-5476-1767)
- Yuanzhen Hu (ORCID: https://orcid.org/0009-0001-2712-6629)
- Yuchen Wang (ORCID: https://orcid.org/0000-0001-6415-6539)
- Tao Zhang (ORCID: https://orcid.org/0000-0003-1559-406X)
- Yangfan Li (ORCID: https://orcid.org/0000-0003-3640-5088)
- Huirong Jing (ORCID: https://orcid.org/0000-0002-0784-8974)
Institutions
- Central South University (CN)
- Changsha University (CN)
- Changsha University of Science and Technology (CN)
Publication Details
- Journal
- IEEE Transactions on Services Computing
- Published
- 2025-08-29
- DOI
- https://doi.org/10.1109/tsc.2025.3603578
- Primary Topic
- Cloud Computing and Resource Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00