Prometheus Intro and Deep Dive
Talkat KubeCon + CloudNativeCon + Open Source Summit China 2023 · on Wednesday, 2023-09-27· at 14:45· 3夹层 3M3会议室 | 3M Room 3M3·
summary
Prometheus is a metrics engine that now ships native histograms for high-resolution latency buckets, a native OpenTelemetry ingestion endpoint, and exemplar retention so trace IDs attach to metric buckets. Recent server work yields about a 50% memory reduction in large installs by deduplicating label storage. Remote_write v2 moves to stateful, streaming transfers to cut bandwidth, and vanilla Prometheus targets up to 100 million active series before recommending Thanos/Mimir. Update recommended.
AI-written summary · about
chapters (14)
- 0:00Prometheus overview
- 1:45Core features
- 3:33Prometheus history
- 5:39Community growth
- 6:01How Prometheus works
- 10:22Recent updates
- 16:56Future roadmap
- 18:00Q&A
- 24:17High-cardinality metrics
- 26:04Scaling Prometheus
- 26:47Remote write performance
- 33:38Contributing to Prometheus
- 39:55Development process
- 42:03Closing remarks
related talks
32mPrometheus Intro and Deep Dive
36mPrometheus - Intro, Deep Dive, And Open Q+A
03mPrometheus Project Updates
33mPrometheus Project Intro
01h 19mIntro + Deep Dive: Prometheus
23mPrometheus – What it is, What is New, and What is Coming
28mPrometheus 3.0 Overview
36mObservability with Prometheus and Beyond: Leveraging Cloud-native Technologies Outside of Cloud