DNS-embedded service endpoint registry for distributed e-Infrastructures

Andrii Salnikov, Balázs Kónya

Research output: Contribution to journalArticlepeer-review

Abstract

Distributed e-Infrastructure is a key component of modern BIG Science. Service discovery in e-Science environments, such as Worldwide LHC Computing Grid (WLCG), is a crucial functionality that relies on service registry. In this paper we re-formulate the requirements for the service endpoint registry based on our more than 10 years experience with many systems designed or used within the WLCG e-Infrastructure. To satisfy those requirements the paper proposes a novel idea to use the existing well-established Domain Name System (DNS) infrastructure together with a suitable data model as a service endpoint registry. The presented ARC Hierarchical Endpoints Registry (ARCHERY) system consists of a minimalistic data model representing services and their endpoints within e-Infrastructures, a rendering of the data model embedded into DNS-records, a lightweight software layer for DNS-record management and client-side data discovery. Our approach for the ARCHERY registry required minimal software development and inherits all the benefits of one of the most reliable distributed information discovery source of the internet, the DNS infrastructure. In particular, deployment, management and operation of ARCHERY is fully relying on DNS. Results of ARCHERY deployment use-cases are provided together with performance analysis.

Original languageEnglish
Pages (from-to)1645-1664
JournalCluster Computing
Volume25
Issue number3
Early online date2021
DOIs
Publication statusPublished - 2022

Subject classification (UKÄ)

  • Computer Science

Free keywords

  • Advanced resource connector
  • ARCHERY
  • Distributed computing
  • Domain Name System
  • e-Science
  • Information system
  • Service endpoint registry
  • WLCG

Fingerprint

Dive into the research topics of 'DNS-embedded service endpoint registry for distributed e-Infrastructures'. Together they form a unique fingerprint.

Cite this