~/talk

From ISCSI to NVMe-of: A Comparative Look on Storage Protocol Advantages & Challenges

on YouTube 30m
Talkat Cephalocon 2024 · 2024-12-04..12-05· [networking]

speaker

name:A. Muthmann
links:none on file

resources

video:https://youtu.be/GtjmgDccrJc
slides:none on file

summary

Direct comparison shows RBD usually wins for throughput/IOPS/latency, with NVMe-oF typically faster than iSCSI but slower than raw RBD except in small‐dataset cachey cases; benchmarks and customer migrations confirm improved stability and latency after moving from iSCSI. NVMe-oF deployments require SPDK/ RDMA and careful CPU pinning, plus clustered gateways and multipath tooling to avoid out‑of‑order writes and consistency hazards. Expect higher CPU use, limited Windows initiator support today, and slow vSphere-driven adoption. RBD usually wins for throughput/IOPS/latency NVMe-oF uses SPDK and RDMA, polling and core pinning iSCSI is in maintenance since Nov 2022

AI-written summary · about

chapters (14)

  1. 0:00Introduction and company overview
  2. 2:33Overview of Ceph storage protocols
  3. 3:43History and architectural background
  4. 7:30Underlying technical implementation
  5. 9:36Deployment, network, and complexity
  6. 13:34Featureset comparison
  7. 14:24Compatibility and scalability
  8. 16:48Reliability and network tolerance
  9. 17:43Cost and security considerations
  10. 18:24Use cases and practical applications
  11. 19:03Performance benchmarks
  12. 22:16Challenges and limitations
  13. 25:49Customer insights and adoption
  14. 27:29Conclusion and Q&A

related talks

~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.