Twine - A Unified Cluster Management System for Shared Infrastructure

Twine - A Unified Cluster Management System for Shared Infrastructure

USENIX via YouTube Direct link

Intro

1 of 24

1 of 24

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Twine - A Unified Cluster Management System for Shared Infrastructure

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Data center geographic regions
  3. 3 What design decisions did Twine make differently?
  4. 4 What if we used Kubernetes?
  5. 5 How does Twine avoid stranded capacity?
  6. 6 How does Twine perform fleet-wide optimization?
  7. 7 How does Twine perform fleet-wide optimization fo. entire geographic region?
  8. 8 How well does the Twine scheduler scale?
  9. 9 How do we mitigate risks with 1M machines per deployment?
  10. 10 Private pools or shared infrastructure?
  11. 11 What is host customization?
  12. 12 What is the overhead for host profile switches?
  13. 13 What drives host profile changes?
  14. 14 What are the challenges with supporting ubiquitous shared infrastructure?
  15. 15 Challenge: Tasks are not homogenous
  16. 16 How does Twine collaborate with applications?
  17. 17 What is our shared infrastructure adoption?
  18. 18 How easy is it to migrate onto shared infrastructure.
  19. 19 Power is our most constrained resource
  20. 20 Big machines or small machines?
  21. 21 Why use small machines?
  22. 22 How much do we save by using small machines?
  23. 23 What lessons did we learn using small machines?
  24. 24 Conclusion

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.