Using Kubernetes in Academic Environment : Problems and
Approaches

D 2023

Using Kubernetes in Academic Environment : Problems and Approaches

SPIŠAKOVÁ, Viktória, Dalibor KLUSÁČEK and Lukáš HEJTMÁNEK

Basic information

Original name

Using Kubernetes in Academic Environment : Problems and Approaches

Authors

SPIŠAKOVÁ, Viktória (703 Slovakia, belonging to the institution), Dalibor KLUSÁČEK (203 Czech Republic) and Lukáš HEJTMÁNEK (203 Czech Republic, belonging to the institution)

Edition

1. vyd. Cham (Switzerland), Job Scheduling Strategies for Parallel Processing, p. 235-253, 19 pp. 2023

Publisher

Springer

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10200 1.2 Computer and information sciences

Country of publisher

Switzerland

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

References:

Finální článek Preprint

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14610/23:00130019

Organization unit

Institute of Computer Science

ISBN

978-3-031-22697-7

ISSN

DOI

http://dx.doi.org/10.1007/978-3-031-22698-4_12

UT WoS

000972597400013

Keywords in English

cloud;HPC;scheduling;Kubernetes;resource management

Abstract

V originále

In this work, we discuss our experience when utilizing the Kubernetes orchestrator (K8s) to efficiently allocate resources in a heterogeneous and dynamic academic environment. In the commercial world, the "pay per use" model is a strong regulating factor for efficient resource usage. In the academic environment, resources are usually provided "for free" to the end-users, thus they often lack a clear motivation to plan their use efficiently. In this paper, we show three major sources of inefficiencies. One is the users' requirement to have interactive computing environments, where the users need resources for their application as soon as possible. Users do not appreciate waiting for interactive environments, but constantly keeping some resources available for interactive tasks is inefficient. The second phenomenon is observable in both interactive and batch workloads; users tend to overestimate necessary limits for their computations, thus wasting resources. Finally, Kubernetes does not support fair-sharing functionality (dynamic user priorities) which hampers the efforts when developing a fair scheme for Pod/job scheduling and/or eviction. We discuss various approaches to deal with these problems such as scavenger jobs, placeholder jobs, Kubernetes-specific resource allocation policies, separate clusters, priority classes, and novel hybrid cloud approach. We also show that all these proposals open interesting scheduling-related questions that are hard to answer with existing Kubernetes tools and policies. Last but not least, we provide a real workload trace from our installation to the scheduling community which captures these phenomena.

Links

LM2018140, research and development project

Name: e-Infrastruktura CZ (Acronym: e-INFRA CZ)

Investor: Ministry of Education, Youth and Sports of the CR

Citovat

SPIŠAKOVÁ, Viktória, Dalibor KLUSÁČEK and Lukáš HEJTMÁNEK. Using Kubernetes in Academic Environment : Problems and Approaches. In Dalibor Klusáček, Julita Corbalán, Gonzalo P. Rodrigo. Job Scheduling Strategies for Parallel Processing. 1st ed. Cham (Switzerland): Springer, 2023, p. 235-253. ISBN 978-3-031-22697-7. Available from: https://dx.doi.org/10.1007/978-3-031-22698-4_12.

@inproceedings{2218837,
   author = {Spišaková, Viktória and Klusáček, Dalibor and Hejtmánek, Lukáš},
   address = {Cham (Switzerland)},
   booktitle = {Job Scheduling Strategies for Parallel Processing},
   doi = {http://dx.doi.org/10.1007/978-3-031-22698-4_12},
   edition = {1},
   editor = {Dalibor Klusáček, Julita Corbalán, Gonzalo P. Rodrigo},
   keywords = {cloud;HPC;scheduling;Kubernetes;resource management},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Cham (Switzerland)},
   isbn = {978-3-031-22697-7},
   pages = {235-253},
   publisher = {Springer},
   title = {Using Kubernetes in Academic Environment : Problems and Approaches},
   url = {https://link.springer.com/chapter/10.1007/978-3-031-22698-4_12},
   year = {2023}
}

TY  - JOUR
ID  - 2218837
AU  - Spišaková, Viktória - Klusáček, Dalibor - Hejtmánek, Lukáš
PY  - 2023
TI  - Using Kubernetes in Academic Environment : Problems and Approaches
PB  - Springer
CY  - Cham (Switzerland)
SN  - 9783031226977
KW  - cloud;HPC;scheduling;Kubernetes;resource management
UR  - https://link.springer.com/chapter/10.1007/978-3-031-22698-4_12
N2  - In this work, we discuss our experience when utilizing the Kubernetes orchestrator (K8s) to efficiently allocate resources in a heterogeneous and dynamic academic environment. In the commercial world, the "pay per use" model is a strong regulating factor for efficient resource usage. In the academic environment, resources are usually provided "for free" to the end-users, thus they often lack a clear motivation to plan their use efficiently. In this paper, we show three major sources of inefficiencies. One is the users' requirement to have interactive computing environments, where the users need resources for their application as soon as possible. Users do not appreciate waiting for interactive environments, but constantly keeping some resources available for interactive tasks is inefficient. The second phenomenon is observable in both interactive and batch workloads; users tend to overestimate necessary limits for their computations, thus wasting resources. Finally, Kubernetes does not support fair-sharing functionality (dynamic user priorities) which hampers the efforts when developing a fair scheme for Pod/job scheduling and/or eviction. We discuss various approaches to deal with these problems such as scavenger jobs, placeholder jobs, Kubernetes-specific resource allocation policies, separate clusters, priority classes, and novel hybrid cloud approach. We also show that all these proposals open interesting scheduling-related questions that are hard to answer with existing Kubernetes tools and policies. Last but not least, we provide a real workload trace from our installation to the scheduling community which captures these phenomena.
ER  -

SPIŠAKOVÁ, Viktória, Dalibor KLUSÁČEK and Lukáš HEJTMÁNEK. Using Kubernetes in Academic Environment : Problems and Approaches. In Dalibor Klusáček, Julita Corbalán, Gonzalo P. Rodrigo. \textit{Job Scheduling Strategies for Parallel Processing}. 1st ed. Cham (Switzerland): Springer, 2023, p.~235-253. ISBN~978-3-031-22697-7. Available from: https://dx.doi.org/10.1007/978-3-031-22698-4\_{}12.

Detailed Information on Publication Record