- Loki log aggregation (MinIO backed, 10-day retention) - Promtail daemonset (pod + talos journal logs) - Prometheus + kube-state-metrics - Grafana dashboards (6-row template per service)
46 lines
1.0 KiB
YAML
46 lines
1.0 KiB
YAML
service: vault
|
|
display_name: "Vault"
|
|
namespace: storage
|
|
service_type: stateful-store
|
|
folder: "Vault"
|
|
jobs: [vault]
|
|
metrics:
|
|
prefix: vault
|
|
up_selector: 'job="vault"'
|
|
rate:
|
|
metric: vault_core_handle_request_total
|
|
labels: [method, path]
|
|
duration:
|
|
metric: vault_core_handle_request_duration_seconds
|
|
type: histogram
|
|
unit: s
|
|
error:
|
|
metric: vault_core_handle_request_total
|
|
filter: 'error="true"'
|
|
domain:
|
|
- metric: vault_core_unsealed
|
|
kind: gauge
|
|
- metric: vault_core_active
|
|
kind: gauge
|
|
- metric: vault_core_replication_primary
|
|
kind: gauge
|
|
- metric: vault_token_total
|
|
kind: gauge
|
|
- metric: vault_database_connection_close_total
|
|
kind: counter
|
|
correlation_ids: []
|
|
logs:
|
|
loki_namespace_selector: 'namespace="iam"'
|
|
alerts:
|
|
- name: HighErrorRate
|
|
expr_template: rate_error_ratio
|
|
threshold: 0.05
|
|
for: 10m
|
|
severity: warning
|
|
- name: VaultSealed
|
|
expr_template: gauge_below_threshold
|
|
metric: vault_core_unsealed
|
|
threshold: 1
|
|
for: 1m
|
|
severity: critical
|