Building scalable OSS observability with Mimir, Loki, Tempo, and Pyroscope | ObservabilityCON 2023

In this video, we cover the latest and greatest news about the scalability and performance of the open source telemetry backends that make up the Grafana LGTM Stack: Grafana Mimir for Prometheus metrics, Grafana Loki for logs, and Grafana Tempo for traces.

Learn about our newest OSS database, Grafana Pyroscope for continuous profiling, which provides insights into resource usage and latency down to the code level. You'll also find out what to expect from Loki 3.0. Finally, find out how to correlate profiles with metrics, logs, and traces for a more holistic view of system health and performance.

Chapters
0:00: Introduction: Hello world!
2:10: The cost of siloed observability at scale
3:30: The "true" definition of observability
5:00 Using the full observability toolkit
6:07 How to find anomalies in metrics trends
9:33 The history of Loki
11:38 Loki 3.0 is coming - here's what to expect
15:07 Query acceleration (flagship feature of Loki 3.0)
20:45 How to find where latency and errors originate across many services with traces
29:55 How to find root causes of issues at the code level
37:20 Profiling: Debugging an incident (Demo)