Dynamo (storage system)
Dynamo is the name given to a set of techniques that when taken together can form a highly available key-value structured storage system[1] or a distributed data store.[2] It has properties of both databases and distributed hash tables (DHTs). Amazon DynamoDB is "built on the principles of Dynamo" [3] (apparently with some improvements) and is a hosted service within the AWS infrastructure. It was created to help address some scalability issues that Amazon.com's website experienced during the holiday season of 2004.[4] By 2007 it was used in Amazon Web Services, such as its Simple Storage Service (S3).[5]
Principles
- Incremental scalability: Dynamo should be able to scale out one storage host (henceforth, referred to as “node”) at a time, with minimal impact on both operators of the system and the system itself.
- Symmetry: Every node in Dynamo should have the same set of responsibilities as its peers; there should be no distinguished node or nodes that take special roles or extra set of responsibilities.
- Decentralization: An extension of symmetry, the design should favor decentralized peer-to-peer techniques over centralized control.
- Heterogeneity: The system needs to be able to exploit heterogeneity in the infrastructure it runs on. e.g. the work distribution must be proportional to the capabilities of the individual servers. This is essential in adding new nodes with higher capacity without having to upgrade all hosts at once.
Techniques used
| Problem | Technique | Advantage |
|---|---|---|
| Dataset partitioning | Consistent Hashing | Incremental, possibly linear scalability in proportion to the number of collaborating nodes. |
| Highly available writes | Vector Clock or Dotted-Version-Vector Sets, reconciliation during reads | Version size is decoupled from update rates. |
| Handling temporary failures | Sloppy Quorum and Hinted Handoff | Provides high availability and durability guarantee when some of the replicas are not available. |
| Recovering from permanent failures | anti-entropy using Merkle tree | Can be used to identify differences between replica owners and synchronize divergent replicas pro-actively. |
| Membership and failure detection | gossip-based membership protocol and failure detection | Avoids having a centralized registry for storing membership and node liveness information, preserving symmetry. |
Implementation History
Amazon published the paper on Dynamo, but never released their implementation. The index layer of Amazon S3 implements and extends many of the core features of a Dynamo. Since then, several implementations have been created based on the paper. The paper also inspired many other NoSQL database implementations.[6] Here are some projects that implement it or were inspired by it.
See also
References
- ↑ Dynamo: Amazon’s Highly Available Key-value Store, SOSP 2007
- ↑ Decandia, G.; Hastorun, D.; Jampani, M.; Kakulapati, G.; Lakshman, A.; Pilchin, A.; Sivasubramanian, S.; Vosshall, P.; Vogels, W. (2007). "Dynamo". Proceedings of twenty-first ACM SIGOPS symposium on Operating systems principles - SOSP '07. p. 205. doi:10.1145/1294261.1294281. ISBN 9781595935915.
- ↑ http://www.allthingsdistributed.com/2012/01/amazon-dynamodb.html
- ↑ http://readwrite.com/2012/01/18/amazon-enters-the-nosql-market
- ↑ Werner Vogels (October 2, 2007). "Amazon's Dynamo". Retrieved September 21, 2016.
- ↑ http://readwrite.com/2012/01/18/amazon-enters-the-nosql-market "launched a thousand NoSQL databases"