Metraipolis › archive › dc_9fb63a85d73a
Ordered Chaos: Towards Adaptive Multipath Load Balancing with Precise Fast Loss Detection — arXiv:2610.41707
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41707
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T07:55:05.261Z
- SHA-256 of the archived text
800ef43e003745f3c0e76e4b02c60c55d82778a74e7c9fc028935a59666e06de- Stable URL of this page
https://metraipolis.com/documento/dc_9fb63a85d73a
How to cite
Ordered Chaos: Towards Adaptive Multipath Load Balancing with Precise Fast Loss Detection — arXiv:2610.41707 — arXiv (en), https://arxiv.org/abs/2610.41707 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9fb63a85d73a (Metraipolis archive dc_9fb63a85d73a, sha256 800ef43e003745f3c0e76e4b02c60c55d82778a74e7c9fc028935a59666e06de)
BibTeX
@misc{dc9fb63a85d73a,
title = {Ordered Chaos: Towards Adaptive Multipath Load Balancing with Precise Fast Loss Detection — arXiv:2610.41707},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41707},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9fb63a85d73a; sha256 800ef43e003745f3c0e76e4b02c60c55d82778a74e7c9fc028935a59666e06de},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41707. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Load balancing in best-effort datacenter fabrics faces a tradeoff. Order-preserving schemes such as Equal-Cost Multipath (ECMP) retain loss semantics but use path diversity coarsely, while packet spraying balances load well but removes the ordering signals needed for fast, precise loss detection. We present Ordered Chaos, an end-host design that preserves enough structure for reliable loss detection without giving up fine-grained multipath routing. Reactive Subflow Spraying (RSS) divides each flow into ordered, dynamically routed subflows. Precise Fast Loss Detection (PFLD) combines this ordering with probes to distinguish reordering from congestion, corruption, tail, and retransmission losses within one RTT. Across simulations, AI and HPC workloads, and a DPU prototype, RSS+PFLD improves tail flow completion time by up to $3\times$, eliminates up to 99% of timeout-based recoveries, and accelerates collective and training communication by up to 35%. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.NI, nuovi lavori del giorno). Categorie arXiv: Networking and Internet Architecture (cs.NI). Pagina del lavoro: https://arxiv.org/abs/2610.41707 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-02T07:40:30.037Z dalla pagina https://arxiv.org/list/cs.NI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).