Dynamo: Amazon’s Highly Available Key-value Store

Шынназар’s task from previous lecture: read about the Amazon’s Dynamo

Dynamo: The P2P context

Chord and DHash intended for wide-area P2P systems (individual nodes at Internet’s edge, file sharing)

Central challenge: low-latency key lookup with high availability (trades off consistency for availability and latency)

Techniques:

• Consistent hashing to map keys to nodes
• Vector clocks for conflict resolution
• Gossip for node membership
• Replication at successor for availability under failure

add slides here

Dynamo Requirements

• Highly available writes despite failure
  • Despite disks failing, network routes flapping, “data centers destroyed by tornadoes”
  • Always respond quickly, even during the failures → replication
• Low request-response latency: focus on 99.99% Service Level Agreement
• Incrementally scalable as servers grow to workload (adding “nodes” should be seamless)
• Comprehensible conflict resolution (high availability in above sense implies conflicts)

add slides here