Cortex: Insights, U...
summary
Cortex is a horizontally scalable, multi-tenant long‑term store for Prometheus with an active 1.19 release: OpenStack Swift moves from experimental to supported, ruler gains experimental HA with primary/non‑primary ownership, and ruler can evaluate rules via the existing query path to reuse caching. A live Helm microservices demo changes a tenant limit from 25,000 → 2,000 runtime rate limit without restarts and scales ingesters 3→4 with immediate rebalancing. Perf work shows ~20% CPU savings from push‑worker reuse and posting‑cache tweaks plus a read‑only ingester state for safer scale‑down.
AI-written summary · about
chapters (7)
- 0:00Introduction and agenda
- 2:43Cortex architecture overview
- 6:38Live demonstration
- 12:52Team and community updates
- 13:38New features in version 1.19
- 23:46Roadmap and future work
- 25:36Graduation goals and Q&A
related talks
37mIntro: Cortex
20mCortex: Intro and Production Tips
25mCortex: Ingesting and Querying 100s of Billions of Samples Per Day
37mCurrent State and the Future of Cortex
45mScaling Prometheus with Cortex, one time series at a time
39mDeep Dive: Cortex
41mWeave Cortex: Horizontally Scalable, Multitenant Prometheus as a Service
20mIntro to Scaling Prometheus with Cortex