Database Performance in High Traffic Environments
summary
Pepper runs a high‑traffic platform with 500 million page views, 25 million users and 70,000 user‑submitted deals per month and keeps responsiveness by splitting databases per market across about 11 locations so each site is isolated, using automation with the same codebase to deploy and reduce operational overhead, and performing regular audits plus team rotations to catch regressions. This yields ~75–80% returning visitors and local failures that affect only one market, preserving uptime and web responsiveness.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 3:55Market gap and platform purpose
- 5:31Database performance factors
- 6:14Database distribution strategy
- 9:22Performance optimization battles
- 10:17System audits importance
related talks
50mBuilding and Operating Online Shops under Extreme Load
51mLarge-scale fault-tolerant on prem deployments powering 100M+ transactions a day
44mIntroduction to application scaling
34mZero Downtime Database Migrations and Deployments
18mHigh-Load Systems: Challenges in Social Network Development
47mScaling: from 0 to 25 million users
27mScaling for the Expected and Unex
45mSpeeding up Code, Webpages and Teams