~/talk

Empowering Azure Storage with RDMA

Talkat NSDI 2023 · 2023-04-17..04-19· [networking]
name:Wei Bai
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
name:Lei Cao
links:none on file
links:none on file
links:none on file
linkedin:codeteacher
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
name:Erica Lan
links:none on file
name:Ivan Lee
links:none on file
name:Avi Levy
links:none on file
links:none on file
name:Xin Liu
linkedin:fbxin
name:Chen Liu
links:none on file
name:Guohan Lu
links:none on file
name:Yuemin Lu
links:none on file
name:Xiakun Lu
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
links:none on file
name:Ying Xie
links:none on file
name:Joyce Yom
links:none on file
links:none on file
links:none on file
links:none on file
slides:none on file

Azure replaces TCP with RoCEv2-based RDMA at regional scale, moving roughly 70% of traffic to RDMA and handling exabytes per day over 100+ Gbps links up to ~100 km. The deployment adds RDMA e‑stats for fine-grained latency and synchronized NIC/CPU timestamps, an automatic TCP fallback for lossy links, and tuned storage libraries that translate socket APIs to RDMA verbs. Key protocols and fixes include PFC tuning, ECN-based congestion control like DCQCN, extensive testing, and interoperability work across diverse NICs.

AI-written summary · about

  1. 0:00Introduction to Azure RDMA
  2. 1:32The problem with TCP
  3. 3:13Importance and benefits
  4. 4:22The RDMA solution
  5. 5:57RDMA evolution and RoCE
  6. 7:24Challenges of implementation
  7. 8:41Enabling RoCE at scale
  8. 11:08Congestion and blocking
  9. 12:27Congestion control protocols
  10. 14:29Software and driver support
  11. 16:09Performance monitoring
  12. 17:52Lessons and best practices
  13. 19:14Open research problems
  14. 19:41Conclusion
~/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.