Distributed Caching in Real-Time Payment Systems
summary
Built an active‑active distributed cache that supports thousands of TPS with sub‑second responses and five nines availability, switching from server to client‑side failover via a configuration‑driven library that implements a sliding window circuit breaker and quorum checks (odd‑node math shown). Recovery is automated through ServiceNow Orchestrator + Ansible calling a cache management API to force failover, restart clusters, and failback, backed by chaos/resiliency tests and dashboards that cut MTTR to minutes.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 7:04Business critical apps
- 10:17Failover design
- 27:25Cost of downtime
- 34:28Key takeaways
- 50:03Q&A
related talks
53mLeveraging Caching For Cloud Native Applications
21mDistCache: Provable Load Balancing for Large-Scale Storage Systems with Distributed Caching
44mAvailability, Latency and Cost: Withstanding Outages
25mDistCache: Provable Load Balancing for Large-Scale Storage Systems with Distributed...
38mSecuring Distributed Cache: Achieving Secure-by-Default with Key Challenges &...
32mHow does your application behaves when everything goes wrong?
29mOracle TimesTen: extreme performance for latency-critical applications
18mEngineering Resilience at Scale; Lessons from a Distributed Systems Transformation