22 lines
1.2 KiB
Markdown
22 lines
1.2 KiB
Markdown
# Logging
|
|
|
|
Applies to a service that writes logs.
|
|
|
|
## Levels
|
|
|
|
Log levels have a standard, RFC5424: { emerg: 0, alert: 1, crit: 2, error: 3, warning: 4, notice: 5, info: 6, debug: 7 }.
|
|
|
|
We follow a simplified variant:
|
|
|
|
* **0: Error** - Crash or equivalent catastrophe that needs fairly immediate action.
|
|
* **1: Warning** - The app works, for now, but something is wrong and needs to be fixed.
|
|
* **2: Info** - Nothing is wrong, but this is important information that should be possible to find in a production system.
|
|
* **3: Verbose** - Somewhat more detailed information than Info, suitable level to enable in a production system where more information is needed for a limited time.
|
|
* **4: Debug** - Suitable level for development. If enabled in production, the logs will be flooded.
|
|
|
|
## Infrastructure
|
|
|
|
All logging in our applications goes to OTLP or stdout.
|
|
|
|
In our server environments, every log, trace and metric ends up in the environment's remote observability platform, such as Grafana Cloud or a self-hosted Grafana. A file on the server's disk is fine on the way there, such as a log a shipper tails, as long as it is bounded in size. It is never the only place a record lives.
|