BEGIN:VCALENDAR VERSION:2.0 PRODID:-//pretalx//pretalx.adass.org//adass2026//speaker//MWNYTK BEGIN:VTIMEZONE TZID:AWST BEGIN:STANDARD DTSTART:20000101T000000 RRULE:FREQ=YEARLY;BYMONTH=1;UNTIL=20051231T160000Z TZNAME:AWST TZOFFSETFROM:+0800 TZOFFSETTO:+0800 END:STANDARD BEGIN:STANDARD DTSTART:20070325T040000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:AWST TZOFFSETFROM:+0900 TZOFFSETTO:+0800 END:STANDARD BEGIN:DAYLIGHT DTSTART:20071028T030000 RRULE:FREQ=YEARLY;BYDAY=4SU;BYMONTH=10;UNTIL=20081025T190000Z TZNAME:AWDT TZOFFSETFROM:+0800 TZOFFSETTO:+0900 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:pretalx-adass2026-CTG9SR@pretalx.adass.org DTSTART;TZID=AWST:20261104T134500 DTEND;TZID=AWST:20261104T140000 DESCRIPTION:# Bridging Kubernetes and Slurm for Transparent HPC Job Offload ing\n\n**Authors:**\nS. Borra1\, U. Canbolat1\, M. Drobek1\, L. Haupt1\n\n**Affiliation:**\n 1 German Center for Astroph ysics (DZA)\, Görlitz\, Germany\n\n**Date:**\nJuly 30\, 2026\n\n**Abstrac t:**\nKubernetes has emerged as a control plane for modern scientific plat forms\, supporting reproducible and high-throughput computing workflows. A dditionally\, high-performance computing (HPC) systems managed by Slurm re main essential for large-scale\, compute-intensive processing. Despite the ir complementary roles\, these environments are typically disconnected\, r equiring manual workload transitions and resulting in fragmented observabi lity and control.\n\nSeveral approaches were explored to bridging this gap \, including systems such as interLink\, Volcano\, REANA (Reusable Analyse s) and Slinky. In this work\, we present interLink\, a lightweight integra tion that extends Kubernetes orchestration into a Slurm-managed HPC cluste r. By representing HPC resources within Kubernetes\, workloads can be offl oaded directly and executed as Slurm jobs without requiring changes to use r workflows or tooling. A Kubernetes pod\, the smallest deployable unit in Kubernetes\, encapsulating one or more containers and their execution con text\, acts as the interface through which users submit and monitor jobs. interLink ensures that job state\, logs\, and execution progress are conti nuously reflected back into this originating pod\, preserving a consistent operational view.\n\nThis approach enables Kubernetes to function as a un ified control plane for both service-oriented and batch-oriented workloads . In particular\, a remote user can use Jupyter notebooks interactively\, for example\, in preparation of batch jobs to be run on large datasets sto red in the HPC center. This presentation explains how interLink reduces op erational friction\, maintains end-to-end observability across system boun daries\, and enables seamless integration of high-throughput and HPC workf lows within a single environment. DTSTAMP:20261001T101754Z LOCATION:Banquet Hall SUMMARY:Bridging Kubernetes and Slurm for Transparent HPC Job Offloading - Sagar Borra URL:https://pretalx.adass.org/adass2026/talk/CTG9SR/ END:VEVENT END:VCALENDAR