poimen-memory/docs/slo/latency.yaml

# SLO: Latency
# Targets:
#   - Query p99: < 200ms
#   - Version lookup p99: < 500ms
#   - Audit trail p99: < 100ms

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: memory-latency
  namespace: monitoring
spec:
  groups:
    - name: latency
      interval: 1m
      rules:
        # Query latency p99
        - record: memory:query:latency:p99
          expr: |
            histogram_quantile(0.99,
              sum(rate(http_request_duration_seconds_bucket{
                service="memory",
                endpoint="/memory/query"
              }[5m])) by (le)
            )

        # Query latency alert
        - alert: MemoryQueryLatencyHigh
          expr: |
            memory:query:latency:p99 > 0.2
          for: 5m
          labels:
            severity: warning
            slo: latency
          annotations:
            summary: "Memory query p99 latency > 200ms"
            description: "Current: {{ $value | humanizeDuration }}"

        # Version lookup latency p99
        - record: memory:version:latency:p99
          expr: |
            histogram_quantile(0.99,
              sum(rate(http_request_duration_seconds_bucket{
                service="memory",
                endpoint=~"/memory/entities/.*/versions.*"
              }[5m])) by (le)
            )

        # Version lookup latency alert
        - alert: MemoryVersionLatencyHigh
          expr: |
            memory:version:latency:p99 > 0.5
          for: 5m
          labels:
            severity: warning
            slo: latency
          annotations:
            summary: "Memory version lookup p99 latency > 500ms"
            description: "Current: {{ $value | humanizeDuration }}"

        # Audit trail latency p99
        - record: memory:audit:latency:p99
          expr: |
            histogram_quantile(0.99,
              sum(rate(http_request_duration_seconds_bucket{
                service="memory",
                endpoint=~"/memory/audit.*"
              }[5m])) by (le)
            )

        # Audit latency alert
        - alert: MemoryAuditLatencyHigh
          expr: |
            memory:audit:latency:p99 > 0.1
          for: 5m
          labels:
            severity: info
            slo: latency
          annotations:
            summary: "Memory audit p99 latency > 100ms"
            description: "Current: {{ $value | humanizeDuration }}"