Ceph Scientific Users Working Group BoF
summary
Community-run Ceph Scientific Users BoF convenes a mix of research sites exchanging concrete practices: running RBD with three replicas and CephFS as backends for OpenStack and Kubernetes, juggling aging hardware by phasing out out-of-warranty nodes and reusing them for scratch or backups, and integrating object lifecycles into tape archives via S3 lifecycle to tape (IBM examples). Participants report scale: 10 PB science cluster, 25 PB legacy with 45 PB coming online, and ~300 PB on tape, plus practical failure-domain and capacity-planning tips.
AI-written summary · about
chapters (7)
- 0:00Introduction and setup
- 3:34Community structure and goals
- 9:50Reusing out-of-warranty hardware
- 16:49Expanding Ceph use cases
- 21:04Ceph vs tape for archiving
- 32:04Giving back to the Ceph project
- 37:45Wrap-up and next steps
related talks
01h 02mIntroduction to Ceph and Architectural Overview
29mCeph and the future of Open Source Storage
13mKeynote: Getting to Know Ceph
29mCeph's journey at SUSE
36mTesting Ceph: Status, Development, & Opportunities
29mCeph, Xen, and CloudStack: Semper Melior
32mDeploying Stand-alone Ceph and Integrating with K8/OpenShift and OpenStack
08mKeynote: A Wonderful Journey On Ceph
