Srinath Perera has put together a strong list of architecture patterns based on three meta patterns: distribution, caching, and asynchronous processing. He contends these three are the primal patterns and the following patterns are but different combinations:
- LB (Load Balancers) + Shared nothing Units. Units that do not share anything with each other fronted with a load balancer that routes incoming messages to a unit based on some criteria.
- LB + Stateless Nodes + Scalable Storage. Several stateless nodes talking to a scalable storage, and a load balancer distributes load among the nodes.
- Peer to Peer Architectures (Distributed Hash Table (DHT) and Content Addressable Networks (CAN)). Algorithm for scaling up logarithmically.
- Distributed Queues. Queue implementation (FIFO delivery) implemented as a network service.
- Publish/Subscribe Paradigm. Network publish subscribe brokers that route messages to each other.
- Gossip and Nature-inspired Architectures. Each node randomly pick and exchange information with follow nodes.
- Map Reduce/ Data flows. Scalable pattern to describe and execute Jobs.
- Tree of responsibility. Break the problem down recursively and assign to a tree, each parent node delegating work to children nodes.
- Stream processing. Process data streams, data that is keeps coming.
- Scalable Storages. Ranges from Databases, NoSQL storages, Service Registries, to File systems.
Please read the original article, List of Known Scalable Architecture Templates, for more details.