Systems @Scale 2019 recap
This post is a recap of the Systems @Scale 2019 conference, featuring presentations on various large-scale systems engineering topics. Key contributions include discussions on Apache ZooKeeper's genesis, Apache Hive's evolution to enterprise-grade warehousing, Delos as a storage system for Facebook's control plane, Accordion for memory organization in LSM key-value stores, distributed tracing systems (Jaeger and Canopy) for observability, continuous deployment at Facebook scale, Affirm's observability infrastructure, LinkedIn's PYMK recommendation service and its reliance on Venice, Facebook's cluster management system Tupperware, preemption algorithms in Nomad, and disaster recovery strategies at Facebook scale. The post highlights trade-offs in system design, performance optimizations, and lessons learned from building and operating these systems.
More from the Scalability and Large-Scale Systems Engineering trail
- Open-Sourcing Rebalancer: A Generic, High-Performance Library for Solving Assignment Problems
- ZGateway: Learnings from Putting a Proxy in Front of ZippyDB
- MTIA 300: Meta’s First Training Chip with Built-in NICs and Communication-Offloading Engines
- From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking
- GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model