Using Serverless and ARM64 for Real-Time Observability

Explore how to leverage serverless computing and ARM64 architecture for real-time observability in this 41-minute conference talk from GOTO Chicago 2024 by Liz Fong-Jones, Field CTO at Honeycomb.io. Learn about extending a sub-second latency query engine from RAM-only operations to querying months of data using cloud object storage and serverless functions. Discover the challenges of managing AWS Lambda at scale, including concurrency limits, runtime configuration, hardware architecture experimentation, and the price/performance considerations when utilizing thousands of parallel workers. The presentation includes a practical demonstration of Honeycomb's capabilities for interactive investigation of production behavior, dynamic aggregation across any time range, and how to purchase compute resources in 1ms units. Fong-Jones also discusses power efficiency considerations, software optimization techniques, and provides guidance on implementing similar approaches in your own systems.