~/talk

MD cluster raid

on YouTube 24m
Talkat DevConf.CZ 2020 · 2020-01-24..01-26· [linux-and-operating-systems]

speaker

name:Xiao Ni
links:none on file

resources

video:https://youtu.be/Bf6rzqJQ2p4
slides:none on file

summary

MD Cluster RAID is a host‑based shared‑storage RAID that avoids a single point of failure and provides HA for active/active setups (examples: GFS). It uses per-node bitmaps and a resync window so each node tracks local writes, and relies on a cluster lock manager (DLM/PLM) to choose a resync owner and serialize recovery. Tradeoffs: disables read balancing during resync, needs coordination to avoid inconsistent reads; demo and history compare to cmirror.

AI-written summary · about

chapters (11)

  1. 0:00Virtual Storage Team
  2. 0:19Overview
  3. 0:43RAID concepts
  4. 2:24Cluster Basics
  5. 3:27A Word About Data Consistency
  6. 4:48Shared Storage Cluster RAID
  7. 8:09Single cluster node failure
  8. 11:43Coordinating cluster actions
  9. 13:57Resync
  10. 16:02Summary
  11. 16:52Questions and Resources

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.