Prometheus Patterns

PromQL Essentials

Rate and Error Calculations

# Request rate (per second, 5m window)
rate(http_requests_total[5m])

# Error rate percentage
sum(rate(http_requests_total{status=~"5.."}[5m]))
/ sum(rate(http_requests_total[5m])) * 100

# P99 latency from histogram
histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))

# P50 latency by endpoint
histogram_quantile(0.50,
  sum(rate(http_request_duration_seconds_bucket[5m])) by (le, handler)
)

# Saturation: CPU usage per pod
sum(rate(container_cpu_usage_seconds_total[5m])) by (pod)
/ sum(kube_pod_container_resource_limits{resource="cpu"}) by (pod) * 100

SLO: Error Budget

# SLO: 99.9% availability over 30 days
# Error budget = 0.1% = 43.2 minutes/month

# Current burn rate (how fast consuming budget)
1 - (
  sum(rate(http_requests_total{status!~"5.."}[1h]))
  / sum(rate(http_requests_total[1h]))
) / (1 - 0.999)

# Remaining error budget (percentage)
1 - (
  sum(increase(http_requests_total{status=~"5.."}[30d]))
  / (sum(increase(http_requests_total[30d])) * 0.001)
)