2026-07-25T00:39:33Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:17645 2024-03-06T11:00:12Z ddc:004 open_access

Chopin: Combining Distributed and Centralized Schedulers for Self-Adjusting Datacenter Networks Rozen-Schiff, Neta Foerster, Klaus-Tycho Schmid, Stefan Hay, David reconfigurable optical networks centralized scheduler distributed scheduler The performance of distributed and data-centric applications often critically depends on the interconnecting network. Emerging reconfigurable datacenter networks (RDCNs) are a particularly innovative approach to improve datacenter throughput. Relying on a dynamic optical topology which can be adjusted towards the workload in a demand-aware manner, RDCNs allow to exploit temporal and spatial locality in the communication pattern, and to provide topological shortcuts for frequently communicating racks. The key challenge, however, concerns how to realize demand-awareness in RDCNs in a scalable fashion. This paper presents and evaluates Chopin, a hybrid scheduler for self-adjusting networks that provides demand-awareness at low overhead, by combining centralized and distributed approaches. Chopin allocates optical circuits to elephant flows, through its slower centralized scheduler, utilizing global information. Chopin’s distributed scheduler is orders of magnitude faster and can swiftly react to changes in the traffic and adjust the optical circuits accordingly, by using only local information and running at each rack separately. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Neta Rozen-Schiff and Klaus-Tycho Foerster and Stefan Schmid and David Hay 2023 Is Part Of LIPIcs, Volume 253, 26th International Conference on Principles of Distributed Systems (OPODIS 2022) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.OPODIS.2022.25 urn:nbn:de:0030-drops-176457 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.OPODIS.2022.25 eng https://creativecommons.org/licenses/by/4.0/legalcode