SBShantanu Badmanjiinshantanubadmanji.hashnode.dev·Aug 13 · 10 min readAurora Optimization: How Storage Cleanup, Replica Removal, and Right-Sizing Cut RDS Costs by 84%The Database Was the Culprit When we started the cost optimization journey, the database looked bulletproof. It handled production traffic reliably. It had reader replicas for scale. It had headroom f00
SBShantanu Badmanjiinshantanubadmanji.hashnode.dev·Aug 4 · 11 min readFrom $4,200 to $800/month: Our AWS Cost Optimization Journey — 81% Cost Reduction With Zero DowntimeOpening: The Problem and the Proof We were paying $4,200 a month for infrastructure we didn't need to use. That sounds hyperbolic. It's not. Our primary database was 75% idle. Our containerized servic20
SBShantanu Badmanjiinshantanubadmanji.hashnode.dev·May 5 · 11 min readWhy I Used PostgreSQL Advisory Locks Instead of RedisThe moment you say "race condition across concurrent tasks," every engineer in the room reaches for Redis. It's the default. It's what the internet recommends. It's what that one architecture post wit00
SBShantanu Badmanjiinshantanubadmanji.hashnode.dev·Apr 20 · 7 min readWhy DATE(updated_at) Broke Timezones and Killed PostgreSQL Index PerformanceI recently resolved two separate production bugs that turned out to share the same root cause — a seemingly innocent DATE() call wrapped around a timestamptz column. What made it worse: the pattern ha00
