SΓΆze: One Network Telemetry Is All You Need for Per-flow Weighted Bandwidth Allocation at Scale
June 01, 2025 Β· Declared Dead Β· π USENIX Symposium on Operating Systems Design and Implementation
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Weitao Wang, T. S. Eugene Ng
arXiv ID
2506.00834
Category
cs.NI: Networking & Internet
Cross-listed
cs.OS
Citations
1
Venue
USENIX Symposium on Operating Systems Design and Implementation
Last Checked
3 months ago
Abstract
Weighted bandwidth allocation is a powerful abstraction that has a wide range of use cases in modern data center networks. However, realizing highly agile and precise weighted bandwidth allocation for large-scale cloud environments is fundamentally challenging. In this paper, we propose SΓΆze, a lightweight decentralized weighted bandwidth allocation system that leverages simple network telemetry features of commodity Ethernet switches. Given the flow weights, SΓΆze can effectively use the telemetry information to compute and enforce the weighted bandwidth allocations without per-flow, topology, or routing knowledge. We demonstrate the effectiveness of SΓΆze through simulations and testbed experiments, improving TPC-H jobs completion time by up to $0.59\times$ and $0.79\times$ on average.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Networking & Internet
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Federated Learning in Mobile Edge Networks: A Comprehensive Survey
R.I.P.
π»
Ghosted
A Survey of Indoor Localization Systems and Technologies
R.I.P.
π»
Ghosted
Survey of Important Issues in UAV Communication Networks
R.I.P.
π»
Ghosted
Network Function Virtualization: State-of-the-art and Research Challenges
R.I.P.
π»
Ghosted
Applications of Deep Reinforcement Learning in Communications and Networking: A Survey
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Language Models are Few-Shot Learners
R.I.P.
π»
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
π»
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
π»
Ghosted