Self-adaptive autoscaling algorithm for SLA-sensitive applications running on the Kubernetes clusters

Pozdniakova, Olesia; Cholomskis, Aurimas; Mažeika, Dalius

doi:10.1007/s10586-023-04082-y

Use this URL to cite this publication: https://hdl.handle.net/20.500.14911/209960

Self-adaptive autoscaling algorithm for SLA-sensitive applications running on the Kubernetes clusters

Details

Publication Type (CRIS)

Straipsnis Web of Science ir Scopus duomenų bazėje / Article in Web of Science and Scopus database (S1)

Publication Type (eLABa)

Straipsnis Web of Science DB / Web of Science DB article (S1)

VILNIUS TECH Research Priorities and Topics

Dirbtinio intelekto ir sprendimų priėmimo sistemos / Artificial intelligence and decision support systems (IK0303)

Lithuanian Intelligent Specialization

Transportas, logistika ir informacinės ir ryšių technologijos (IRT) / Transport, logistic and information and communication technologies (L106)

Author(s)

Author	Affiliation
Pozdniakova, Olesia	Informacinių sistemų katedra / Department of Information Systems (1046)
Cholomskis, Aurimas	Informacinių sistemų katedra / Department of Information Systems (1046)
Mažeika, Dalius	Informacinių sistemų katedra / Department of Information Systems (1046)

Title

Self-adaptive autoscaling algorithm for SLA-sensitive applications running on the Kubernetes clusters

[en]

Olesia Pozdniakova, Aurimas Cholomskis, Dalius Mažeika

Is part of

Cluster computing

Published In

Year	Volume	Start Page	End Page
2024	27	2399	2426

Publisher

New York : Springer

Publisher (trusted)

Springer

Referenced in Database(s)(DBs)

Science Citation Index Expanded (Web of Science)

SCOPUS

Dimensions

INSPEC

Extent

p. 2399-2426

URI

URI	Access Rights
https://hdl.handle.net/20.500.14911/209960
https://link.springer.com/article/10.1007/s10586-023-04082-y	Viso teksto dokumentas (atviroji prieiga) / Full Text Document (Open Access)

DOI

10.1007/s10586-023-04082-y

Cited references

Science / Art Area

Technologijos mokslai / Technological sciences (T)

Field of Science / Art

Informatikos inžinerija / Informatics engineering (T007)

Keywords (en)

Abstract (en)

Most existing autoscaling approaches help to avoid violating the performance-related Service Level Objectives (SLO). However, these solutions do not aim to recover the SLO. The proposed novel autoscaling solution covers both SLO violation avoidance and recovery. The SLO failure avoidance part of the solution aims to avoid SLO violations by adjusting autoscaling thresholds based on compliance with SLO. It also dynamically selects the required CPU threshold, cooldown intervals and the number of replicas based on load velocity. The recovery part of the solution aims to recover SLO by additional resource provisioning if SLO is violated due to a delay or resource underestimation. The proposed implementation of the solution targets embarrassingly parallel workloads. It is compared with two autoscaling solutions in five workload scenarios, evaluating the ability of the solution to operate close to the defined SLO values. The results show that the proposed solution provides sufficient resources to support or recover performance-based SLOs.