EUVIMEDEUVIMED entdecken
Crossref

Component-distinguishable Co-location and Resource Reclamation for High-throughput Computing

Laiping Zhao, Yushuai Cui, Yanan Yang, Xiaobo Zhou, Tie Qiu, Keqiu Li, Yungang Bao

ACM Transactions on Computer Systems · 31.05.2024 · 42 (1-2) · 1-37

DOI: 10.1145/3630006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Computer Systems, online erschienen am 13.02.2024. Verfasst von Laiping Zhao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 108 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Shandong Provincial Natural Science Foundation, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cloud service providers improve resource utilization by co-locating latency-critical (LC) workloads with best-effort batch (BE) jobs in datacenters. However, they usually treat multi-component LCs as monolithic applications and treat BEs as “second-class citizens” when allocating resources to them. Neglecting the inconsistent interference tolerance abilities of LC components and the inconsistent preemption loss of BE workloads can result in missed co-location opportunities for higher throughput. We present Rhythm , a co-location controller that deploys workloads and reclaims resources rhythmically for maximizing the system throughput while guaranteeing LC service’s tail latency requirement. The key idea is to differentiate the BE throughput launched with each LC component, that is, components with higher interference tolerance can be deployed together with more BE jobs. It also assigns different reclamation priority values to BEs by evaluating their preemption losses into a multi-level reclamation queue. We implement and evaluate Rhythm using workloads in the form of containerized processes and microservices. Experimental results show that it can improve the system throughput by 47.3%, CPU utilization by 38.6%, and memory bandwidth utilization by 45.4% while guaranteeing the tail latency requirement.

Förderung

  • National Key Research and Development Program of China
  • Shandong Provincial Natural Science Foundation
  • National Natural Science Foundation of China
  • Zhejiang Lab

Zitieren

APA

Zhao, L., Cui, Y., Yang, Y., Zhou, X., Qiu, T., Li, K., & Bao, Y. (2024). Component-distinguishable Co-location and Resource Reclamation for High-throughput Computing. ACM Transactions on Computer Systems, 42(1-2), 1-37. https://doi.org/10.1145/3630006

Vancouver

Zhao L, Cui Y, Yang Y, Zhou X, Qiu T, Li K, et al. Component-distinguishable Co-location and Resource Reclamation for High-throughput Computing. ACM Transactions on Computer Systems. 2024;42(1-2):1-37. doi:10.1145/3630006

BibTeX
@article{Zhao2024,
  author = {Zhao, Laiping and Cui, Yushuai and Yang, Yanan and Zhou, Xiaobo and Qiu, Tie and Li, Keqiu and Bao, Yungang},
  title = {Component-distinguishable Co-location and Resource Reclamation for High-throughput Computing},
  journal = {ACM Transactions on Computer Systems},
  year = {2024},
  volume = {42},
  number = {1-2},
  pages = {1--37},
  doi = {10.1145/3630006}
}
Kostenlos starten →