X-Raying Your Redis App: SDK Tuning with a Performance Engineer’s Eye
summary
Starts with a Flask app that issues 100+ Redis round trips per feed request and shows concrete fixes: use pipelining to collapse 100 RTTs into one — latency drops from ~1s to ~23ms, collocate app and Redis — that falls to ~5ms. Moves to Redis Cluster to scale throughput (roughly 80k → 150k ops/s on three shards) and replaces per-cat SETs with HyperLogLog to cut a 1GB key to ~12KB (≈1% error), all measured with OpenTelemetry and benchmarks.
AI-written summary · about
related talks
41mHigh Volume Ratelimiting with Redis
56mRedis Application Patterns in Rails
59mUsing Redis beyond caching
36mBuild a Cloud Native Asynchronous Messaging System For Scale With Redis
33mIntroduction to Redis
34mScaling Redis writes with cluster mode
50mScaling Postgres With Some Help from Redis
20mHow to Build a High Performance App Using Cloud Foundry and Redis