Longhorn: Intro, Deep Dive and Q&A
summary
Longhorn is a CNCF-incubating distributed block store for Kubernetes that runs replicas per volume with an engine collocated to the consumer, offers incremental S3 backups and in-cluster snapshots, and supports one‑click install and live upgrades with no detach downtime. Community numbers show ~3.8k GitHub stars and 53k+ nodes reporting. Upcoming 1.3 adds CSI snapshot support, a dedicated storage network, backing‑image downloads and secure control/data comms; an SPDK engine prototype shows near‑local throughput with ~20µs added latency.
AI-written summary · about
chapters (17)
- 0:00Introduction to Longhorn
- 0:35Longhorn mission and goals
- 1:20Design principles
- 2:24Usability and management
- 3:19Maintainability and upgrades
- 3:50How Longhorn works
- 6:42Management plane overview
- 8:12Community update
- 9:12Upcoming 1.3 release
- 10:34Future roadmap
- 11:52Production demo
- 13:53Auto scaling and node pools
- 16:51Storage scheduling rules
- 20:07Adding storage capacity
- 21:00SPDK engine performance
- 22:46Architecture change details
- 24:52Q&A session
related talks
38mLonghorn: Intro, Deep Dive And Q+A
47mLonghorn: Intro, Deep Dive and Q+A
32mLonghorn: Intro, Deep Dive and Q&A
48mIntro to Longhorn: Open Source Cloud-Native Distributed Block Storage Built On and For K8s
31mLonghorn: Intro, Deep Dive and Q&A
37mBuild a Kubernetes Based Cloud Native Storage Solution From Scratch
35mImproving Longhorn Performance With SPDK
24mSheng Liang, Rancher Labs & Murli Thirumale, Portworx | KubeCon + CloudNativeCon Europe - Virtual