Examines Facebook’s use of Memcache, a distributed, scalable in-memory key-value store caching data to reduce backend load and improve performance. Discusses architecture, consistency challenges, caching policies, failure handling, and optimizations for high throughput and low latency.
Dynamo is a highly available, scalable distributed key-value store designed for fault tolerance and elasticity. It uses consistent hashing for data partitioning, vector clocks for conflict resolution, and quorum protocols to balance availability and consistency, making it ideal for services like shopping carts where eventual consistency suffices.
Details Facebook’s memcached architecture handling billions of requests and trillions of items. Covers distributed key-value store design, latency reduction using UDP/TCP, incast congestion control, leases mechanism, memory pools, and regional replication.
Lecture on distributed systems design covering stateful vs stateless server architectures, distributed data stores (Dynamo key-value store, Bigtable, Cassandra), Google File System, reliability engineering, replication, partitioning, and e-commerce system architecture.