Current State and the Future of Cortex
Talkat KubeCon + CloudNativeCon North America 2022 · on Friday, 2022-10-28· at 11:55· 252 AB, Huntington Place: 1 Washington Blvd·
summary
Cortex now ships an OpenTelemetry bridge so traces can be exported to Jaeger, Zipkin, Kafka or AWS X‑Ray for real‑time bottleneck hunting, and a partitioning compactor that cuts compaction time by ~50% in lab runs on 200M series while avoiding the 64GB index limit. A vertical query sharding mode yields 30%+ query speedups for instant queries, streaming query→ingester traffic reduces memory spikes, and existing deployments report stable operation at ~150M series. Call for more maintainers and doc help.
AI-written summary · about
chapters (8)
- 0:00Introduction to speakers
- 2:08Agenda overview
- 3:02What is Cortex?
- 5:45Architectural deep dive
- 13:35Key features and innovations
- 25:14Release lookback and users
- 27:42Community roadmap and goals
- 31:49Q&A session
related talks
20mCortex: Intro and Production Tips
39mDeep Dive: Cortex
30mCortex: Insights, U...
25mCortex: Ingesting and Querying 100s of Billions of Samples Per Day
45mScaling Prometheus with Cortex, one time series at a time
37mIntro: Cortex
41mWeave Cortex: Horizontally Scalable, Multitenant Prometheus as a Service
20mIntro to Scaling Prometheus with Cortex