~/talk

Kubernetes Scalability Definition Evolution

on YouTube 39m
Talkat KubeCon + CloudNativeCon Europe 2019 · on Thursday, 2019-05-23· at 14:00· Hall 8.0 F5· [kubernetes]

speakers

name:Wojciech Tyczyński
website:https://tykus160.github.io
name:Andrzej Wasylkowski
links:none on file

resources

video:https://youtu.be/7j76n21Pn-4
slides:none on file

summary

Kubernetes starts with a 100-node claim in 2015 but proves it insufficient, replacing vague thresholds with explicit SLIs/SLOs: original rules (API responsiveness 99% <1s, pod startup 99% <5s) expose poor coverage and precision, so a 2017 product-surface doc and the concepts of scalability dimensions and scalability envelope emerge. Current official SLOs cover mutating/read API latency and pod startup with a 5,000-node limit, use per-resource streams and 99th percentile over 5 minutes, and several networking/storage SLIs remain "working progress" measured in synthetic benchmarks.

AI-written summary · about

chapters (12)

  1. 0:00Intro
  2. 0:20Scalability - what does it mean?
  3. 4:10Scalability - how to define it?
  4. 6:11Definition drawbacks
  5. 8:48Scalability SLOs - coverage
  6. 10:52Scalability - SLOs coverage
  7. 12:58SLISLO principles
  8. 16:27How to provide SLOs?
  9. 17:53Defining Kubernetes limits
  10. 18:50Scalability SLO framework
  11. 26:48Defining Scalability
  12. 29:02Current state

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.