Unified Cross-Layer Cluster-Node Scheduling for Heterogeneous Datacenters

Wenkai Guan; Cristinel Ababei

doi:10.1109/IGSC55832.2022.9969366

Unified Cross-Layer Cluster-Node Scheduling for Heterogeneous Datacenters

Wenkai Guan, Cristinel Ababei

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Scopus citations

Abstract

In this paper, we present a two-level hierarchical scheduler for datacenters called Qin. The goal of the proposed scheduler is to exploit increased server heterogeneity. It combines in a unified approach cluster and node level scheduling algorithms, and it can consider specific optimization objectives including job completion time, energy usage, and energy delay product (EDP). Its novelty lies in the unified approach and in modeling interference and heterogeneity. Experiments on a real cluster demonstrate the proposed approach outperforms state-of-The-Art schedulers by 10.2 % in completion time, 38.65 % in energy usage, and 41.98% in EDP.

Original language	English (US)
Title of host publication	2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665465502
DOIs	https://doi.org/10.1109/IGSC55832.2022.9969366
State	Published - 2022
Externally published	Yes
Event	13th IEEE International Green and Sustainable Computing Conference, IGSC 2022 - Virtual, Online, United States Duration: Oct 24 2022 → Oct 25 2022

Publication series

Name	2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022

Conference

Conference	13th IEEE International Green and Sustainable Computing Conference, IGSC 2022
Country/Territory	United States
City	Virtual, Online
Period	10/24/22 → 10/25/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

collaborative filtering
datacenters
heterogeneity
scheduling

Publisher link

10.1109/IGSC55832.2022.9969366

Find It

Find It at U of M Libraries

Cite this

Guan, W., & Ababei, C. (2022). Unified Cross-Layer Cluster-Node Scheduling for Heterogeneous Datacenters. In 2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022 (2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGSC55832.2022.9969366

Unified Cross-Layer Cluster-Node Scheduling for Heterogeneous Datacenters. / Guan, Wenkai; Ababei, Cristinel.
2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Guan, W & Ababei, C 2022, Unified Cross-Layer Cluster-Node Scheduling for Heterogeneous Datacenters. in 2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022. 2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022, Institute of Electrical and Electronics Engineers Inc., 13th IEEE International Green and Sustainable Computing Conference, IGSC 2022, Virtual, Online, United States, 10/24/22. https://doi.org/10.1109/IGSC55832.2022.9969366

@inproceedings{243a76714c6f40e894fc07f2718aaefa,

title = "Unified Cross-Layer Cluster-Node Scheduling for Heterogeneous Datacenters",

abstract = "In this paper, we present a two-level hierarchical scheduler for datacenters called Qin. The goal of the proposed scheduler is to exploit increased server heterogeneity. It combines in a unified approach cluster and node level scheduling algorithms, and it can consider specific optimization objectives including job completion time, energy usage, and energy delay product (EDP). Its novelty lies in the unified approach and in modeling interference and heterogeneity. Experiments on a real cluster demonstrate the proposed approach outperforms state-of-The-Art schedulers by 10.2 % in completion time, 38.65 % in energy usage, and 41.98% in EDP.",

keywords = "collaborative filtering, datacenters, heterogeneity, scheduling",

author = "Wenkai Guan and Cristinel Ababei",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 13th IEEE International Green and Sustainable Computing Conference, IGSC 2022 ; Conference date: 24-10-2022 Through 25-10-2022",

year = "2022",

doi = "10.1109/IGSC55832.2022.9969366",

language = "English (US)",

series = "2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022",

}

TY - GEN

T1 - Unified Cross-Layer Cluster-Node Scheduling for Heterogeneous Datacenters

AU - Guan, Wenkai

AU - Ababei, Cristinel

PY - 2022

Y1 - 2022

N2 - In this paper, we present a two-level hierarchical scheduler for datacenters called Qin. The goal of the proposed scheduler is to exploit increased server heterogeneity. It combines in a unified approach cluster and node level scheduling algorithms, and it can consider specific optimization objectives including job completion time, energy usage, and energy delay product (EDP). Its novelty lies in the unified approach and in modeling interference and heterogeneity. Experiments on a real cluster demonstrate the proposed approach outperforms state-of-The-Art schedulers by 10.2 % in completion time, 38.65 % in energy usage, and 41.98% in EDP.

AB - In this paper, we present a two-level hierarchical scheduler for datacenters called Qin. The goal of the proposed scheduler is to exploit increased server heterogeneity. It combines in a unified approach cluster and node level scheduling algorithms, and it can consider specific optimization objectives including job completion time, energy usage, and energy delay product (EDP). Its novelty lies in the unified approach and in modeling interference and heterogeneity. Experiments on a real cluster demonstrate the proposed approach outperforms state-of-The-Art schedulers by 10.2 % in completion time, 38.65 % in energy usage, and 41.98% in EDP.

KW - collaborative filtering

KW - datacenters

KW - heterogeneity

KW - scheduling

UR - http://www.scopus.com/inward/record.url?scp=85145434962&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85145434962&partnerID=8YFLogxK

U2 - 10.1109/IGSC55832.2022.9969366

DO - 10.1109/IGSC55832.2022.9969366

M3 - Conference contribution

AN - SCOPUS:85145434962

T3 - 2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022

BT - 2022 IEEE 13th International Green and Sustainable Computing Conference, IGSC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th IEEE International Green and Sustainable Computing Conference, IGSC 2022

Y2 - 24 October 2022 through 25 October 2022

ER -

Unified Cross-Layer Cluster-Node Scheduling for Heterogeneous Datacenters

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this