1 / 24

Automated Bandwidth Allocation Problems in Data Centers

Automated Bandwidth Allocation Problems in Data Centers. Y ifei Yuan, Anduo Wang, Rajeev Alur , Boon Thau Loo U niversity of Pennsylvania. M otivation. Managing network resources is the key computational problem in Data Centers.

louisa
Télécharger la présentation

Automated Bandwidth Allocation Problems in Data Centers

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Automated Bandwidth Allocation Problems in Data Centers Yifei Yuan, Anduo Wang, Rajeev Alur, Boon ThauLoo University of Pennsylvania

  2. Motivation • Managing network resources is the key computational problem in Data Centers. • Applying verification/synthesis tool to network resource management? • Benefits: exact solutions, correctness guarantees • Challenges: efficiency • This work: bandwidth allocation by SAT/SMT solvers

  3. Bandwidth Allocation Problem

  4. Bandwidth Allocation Problem Data Center’s Network X1 10G bps 10G bps X2 X3 1G bps 600M bps 500M bps 450M bps S1 S2 S3 S4

  5. Bandwidth Allocation Problem Data Center’s Network Virtual Network X1 V1 10G bps 10G bps 400M bps 400M bps X2 X3 V2 V3 1G bps 600M bps 500M bps 450M bps S1 S2 S3 S4

  6. Bandwidth Allocation Problem Data Center’s Network Virtual Network X1 V1 10G bps 10G bps 400M bps 400M bps X2 X3 V2 V3 1G bps 600M bps 500M bps 450M bps S1 S2 S3 S4

  7. Bandwidth Allocation Problem Data Center’s Network Virtual Network X1 V1 10G bps 10G bps 400M bps 400M bps X2 X3 V2 V3 1G bps 600M bps 500M bps 450M bps v1 v3 v2 S1 S2 S3 S4

  8. Bandwidth Allocation Problem Data Center’s Network Virtual Network X1 V1 10G bps 10G bps 400M bps 400M bps X2 X3 V2 V3 1G bps 600M bps 500M bps 450M bps v1 v3 v2 S1 S2 S3 S4

  9. BAP: Facts • Complexity: • NP-complete: tree for physical network & virtual network • Existing heuristics: • Pros: efficient • Cons: no guarantee • Alternative approach: SAT/SMT solving

  10. SAT/SMT Encoding: A Glimpse • X(v,s): VM v is mapped to server s • Y(l,e): physical link l is reserved bandwidth virtual link e • R(l,e,k): physical link l is the k-th edge on the routing path for virtual link e • Server capacity: • ∑vX(v,s) < c(s), for every server s • Link capacity: • ∑eY(l,e) < b(l), for every physical link l

  11. Abstraction and Refinement • Observation: Hierarchical physical network topology in data centers • Tree • Fat-tree • Idea: • Abstract physical network: small size • Refine subgraphs

  12. Abstraction 4 2 1 2

  13. Abstraction 4 2 1 2

  14. Abstraction 3 6 4 2 1 2

  15. Abstraction 3 6

  16. Abstraction 3 6

  17. Refinement 3 6 4 2 1 2

  18. Refinement 4 2 1 2

  19. Evaluation: Set up • Physical network topology: tree with 200 servers: 200 20 4 4 4 4

  20. Evaluation: Set up • Virtual network topology: connected cliques 2 1 1

  21. Evaluation: Set up • Experiment: • Run allocation algorithm • Keep mapping the VN to the PN • Stop when no more VN can be mapped

  22. Evaluation: Server Utilization

  23. Evaluation: Running Time per VN

  24. Summary • Alternative approach solving network resource allocation problem: using SAT/SMT solvers • Abstract&refinement for scalability • Strength: optimal solution • Weakness: efficiency • Possible scenario: Optimal reallocation

More Related