metrics.md 483 B

Metrics - Prometheus / Graphana

Goal: understanding of where exactly the time is being spent when executing queries (e.g. in Hue database, in interpreter, RPC call to warehouse...)

TODO

  • Alerting: when is alive wrong more than X seconds
  • Number of active users
  • Resource usage: CPU, DB calls, memory, IOs
  • Slowness: percentiles times of requests
  • Number of queries

  • Provide default Graphana dashboard & alerting