L3: Latency-aware Load Balancing in Multi-Cluster Service Mesh

Olivier Michaelis, Stefan Schmid, Habib Mostafaei

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    7 Downloads (Pure)

    Abstract

    Microservice architectures and service meshes have become highly popular and face increasingly stringent scalability and dependability requirements. To achieve low-latency service execution and maximize performance, service providers of large-scale distributed systems deploy microservices geographically closer to their users in multi-cluster service mesh environments. However, inter-cluster service dependencies introduce additional latency, and effective load balancing across multiple replicas distributed across clusters is crucial. Addressing this challenge, we present L3, an adaptive latency-aware load-balancing mechanism for multi-cluster service meshes. We conduct extensive simulations on Amazon EC2, and our results of using the microservices of the DeathStarBench suite for three clusters report that L3 reduces the 99th percentile latency by 26% and 22% compared with round-robin and C3.
    Original languageEnglish
    Title of host publicationMiddleware '24
    Subtitle of host publicationProceedings of the 25th International Middleware Conference
    Place of PublicationNew York
    PublisherAssociation for Computing Machinery, Inc
    Pages49-61
    Number of pages13
    ISBN (Electronic)979-8-4007-0623-3
    DOIs
    Publication statusPublished - 2 Dec 2024
    Event25th International Middleware Conference, Middleware 2024 - Hong Kong, Hong Kong
    Duration: 2 Dec 20246 Dec 2024

    Conference

    Conference25th International Middleware Conference, Middleware 2024
    Abbreviated titleMiddleware 2024
    Country/TerritoryHong Kong
    CityHong Kong
    Period2/12/246/12/24

    Keywords

    • Latency
    • Load Balancing
    • Microservices
    • Multi-cluster Service Mesh

    Fingerprint

    Dive into the research topics of 'L3: Latency-aware Load Balancing in Multi-Cluster Service Mesh'. Together they form a unique fingerprint.
    • Best Student Paper Award

      Michaelis, O. (Recipient), Schmid, S. (Recipient) & Mostafaei, H. (Recipient), 4 Dec 2024

      Prize: OtherCareer, activity or publication related prizes (lifetime, best paper, poster etc.)Scientific

    Cite this