1 / 19

Dynamo

Dynamo. Kay Ousterhout. Goals. Small files Always writeable Low latency Measured at 99.9 th percentile. Non-goals. Untrusted nodes Relational schema Hierarchical namespace. Key-Value Store. Big (Old?) Ideas. Replication: Store every object on N nodes. N = 3. Consistent Hashing.

ehren
Download Presentation

Dynamo

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. Dynamo Kay Ousterhout

  2. Goals • Small files • Always writeable • Low latency • Measured at 99.9th percentile

  3. Non-goals • Untrusted nodes • Relational schema • Hierarchical namespace Key-Value Store

  4. Big (Old?) Ideas

  5. Replication: Store every object on N nodes N = 3

  6. Consistent Hashing A B G Key C F E D

  7. Consistent Hashing A H B G Key C F E D

  8. Consistent Hashing + Virtual Nodes A H B G Key C F E D

  9. Conflict Resolution: Vector Clocks

  10. Basic put() N = 3, W = 2 k:v ([G, 1]) A H k:v B G Coordinator C F E D

  11. get() with Sloppy Quorum N = 3, W = 2, R = 2 k? A H k? B G k:v ([G, 1]) k:v ([G, 1]) Coordinator C F E D

  12. Takeaway: Tunable! Change N,R,W for desired consistency, availability

  13. Antientropy: Merkle Trees Node A Node B Hash of children Object hashes at leaves

  14. More Ideas • Hinted handoff • Explicit join/leave mechanism (gossip-based) • Seed nodes • Local notion of failure

  15. Comments

  16. System Scope “…the system needs to have scalable and robust solutions for load balancing, membership and failure detection, failure recovery, replica synchronization, overload handling, state transfer, concurrency and job scheduling, request marshaling, request routing, system monitoring and alarming, and configuration management.”

  17. Triggers • Client registers to be notified when key changes • Challenging with eventual consistency! • Solution: sloppy triggers

  18. Setting N,R,W • …is annoying! • Can we auto-configure R? • What about W?

  19. Supporting Multiple N,R,W • Different availability/consistency tradeoffs for each object • …without making multiple systems

More Related