Skip to content

Priority flow control-sensitive: Reducing tail latency with Priority flow control-sensitive in lossless data center networks

Aug 2026 · Journal of High Speed Networks · 0 citations · 16 references

TL;DR

Initial evaluations demonstrate that PFC-S can reduce the average flow completion time and effectively prevent congestion spreading, and experimental results show that PFC-S provides better protection for victim flows compared to standard PFC, BFC, and HPCC methods.

Abstract

Lossless fabrics are widely used in many production data centers, but they can give rise to issues such as head-of-line blocking and congestion spreading during network congestion, which can significantly degrade the performance of data center applications. Additionally, the latency of end-to-end solutions can lead to the buildup of switch queues. To address these challenges, this paper proposes a method called Priority Flow Control-Sensitive (PFC-S). PFC-S monitors buffer occupancy and traffic intensity, performs proactive rerouting, and prevents the impact of PFC congestion diffusion on victim flows. This approach helps maintain low buffer usage levels, thereby enabling control over tail latency. Initial evaluations demonstrate that PFC-S can reduce the average flow completion time and effectively prevent congestion spreading. Moreover, experimental results show that PFC-S provides better protection for victim flows compared to standard PFC, BFC, and HPCC methods.

View source

Similar papers

2026

FAFC: Fast and Accurate Flow Control in Data Center Networks

In data centers, large-scale many-to-one traffic can rapidly exhaust switch buffers and trigger priority-based flow control (PFC) pause, resulting in increased flow completion time (FCT) for uncongested flows. To address this issue, we propose an innovative switch-side fast and accurate flow control (FAFC) scheme. By d...

Cheng-Di Lu, Yuang Chen, Fangyu Zhang et al. · 0 citations
Book Open access Aug 2026

ProLet: Proactive Multi-path Load Balancing for Lossless RDMA

ProLet is a load balancing scheme that enables proactive probing and reroutes elephant flows at flowlet granularity in lossless RDMA networks and reduces average and tail flow completion time slowdowns by 69% and 79%, respectively, compared to state-of-the-art load balancing schemes.

Hong Wang, Jin-Hao Luo, J. Tan et al. · 0 citations
Open access Jul 2026

Starvation ratio: letting applications drive datacenter congestion control

This work argues that applications should participate in congestion control decisions and introduces the starvation ratio (SR), a metric that detects when applications are truly limited by the network.

Anderson Henrique da Silva Marcondes, Enzo B. Boscatto, Guilherme Piêgas Koslovski · 0 citations
Open access Aug 2026

cdcPIM: a proactive congestion control scheme for cross-datacenter RDMA networks

Driven by the requirements of machine learning, cloud storage, and other network-intensive applications, remote direct memory access (RDMA) has been widely adopted in high-speed networks and is gradually being applied to geographically distributed datacenters. However, in cross-datacenter scenarios, long control loop l...

Wenqiang Deng, Jun-Yan Chen, Xue-Feng Huang et al. · 0 citations
Book Open access Aug 2026

Congestion Quarantine in Lossless Ethernet

Results show that congestion quarantine can eliminate head-of-line blocking in scenarios with multiple congestion trees, and reduces the average and 99th percentile FCT slowdown of normal flows by 25–86% and 33–90%, respectively, with negligible impact on bursty traffic.

Dongkang Hu, Ran Shu, Wenxue Cheng et al. · 0 citations
Book Open access Aug 2026

InfiniFlow: Decoupling Virtual Channel Scalability from Buffer Requirements in Lossless Datacenter Networks

InfiniFlow is presented, a credit-based hop-by-hop flow control method that supports massive VCs with a limited buffer budget via per-port buffer sharing, and introduces a paradigm shift in buffer management: Upstream Allocates Buffer for Downstream (UABD).

Ze-Rui Tian, Sen Liu, Minkun Xue et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.