Scale By the Bay 2021 intro video by Eynav Mass
summary
Claims that auto-scaling is not enough and that incremental growth plus sudden peaks created unexpected failure modes at Oribi, which handles billions of events a day. Describes replacing Ruby with its "successor" and the concrete changes to deployment, monitoring and capacity planning, recounts specific incidents called scale bumpers, the mitigations applied, and which fixes actually reduced outage frequency and peak latency.
AI-written summary · about
related talks
07mFrom Scaling APIs to Scaling Data to Scaling Your Team
29mCapacity Planning with the Universal Scalability Law
20mScale By The Bay 2019: Sharanya Santhanam & Shiv Toolsidass
30mInfrastructure scale issues
29mBlueprints for Scaling: Practical Steps for Scaling Your Data Platform to Handle Exponential Growth
48mEvolution of the Metrics Pipeline: How the Architecture Scaled with Load
10mImpacting Business as it Happens
36mTelemetry Analysis for Scaling
