High Throughput and/or Low Latency
summary
A case study of reworking a real production system to multiply throughput on existing hardware while also reducing response latency. It describes diagnosing bottlenecks and applying practical optimization techniques for high-load systems to achieve both higher capacity and lower latency.
AI-written summary · about
chapters (20)
- 0:00Introduction
- 0:26Load goals and criteria
- 1:51Interdepartmental system description
- 3:19Pre-transformation architecture
- 5:27Project tasks and constraints
- 6:28Bottleneck identification methodology
- 8:15Performance tactics
- 10:44Query scheduler optimization
- 12:32Cryptoprocessing issues
- 13:38Network optimization
- 15:51Message broker replacement
- 17:20Guaranteed message delivery
- 18:24System scaling
- 20:12Load balancing issues
- 21:37Amdahl's Law implications
- 23:02System mathematical modeling
- 24:31Scaling risks and penalties
- 26:18Architecture transformation results
- 27:24Next steps and optimizations
- 29:39Q&A
