Files
homelab/k8s/monitoring/dashboards/services/minio.descriptor.yaml
T
Story Crater Bot 63d7256b9e k8s/monitoring: add prometheus grafana loki observability
- 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)
2026-07-11 19:17:28 -07:00

69 lines
1.6 KiB
YAML

# minio.descriptor.yaml
# Build input for generating svc-minio.yaml dashboard ConfigMap
# and svc-minio-rules.yaml PrometheusRule.
service: minio
display_name: "MinIO"
namespace: storage
service_type: stateful-store
folder: "MinIO"
jobs:
- minio
metrics:
prefix: minio
up_selector: 'job="minio"'
rate:
metric: minio_s3_requests_total
labels: [method, bucket]
duration:
metric: minio_s3_requests_duration_seconds
type: histogram
unit: s
error:
metric: minio_s3_requests_total
filter: 'error="true"'
domain:
- metric: minio_cluster_capacity_usable_bytes
kind: gauge
- metric: minio_cluster_capacity_raw_total_bytes
kind: gauge
- metric: minio_replication_metrics_failed_byte_count
kind: gauge
- metric: minio_replication_metrics_replicating_byte_count
kind: gauge
- metric: minio_cluster_health_drives_online
kind: gauge
- metric: minio_cluster_health_drives_offline
kind: gauge
correlation_ids: []
logs:
loki_namespace_selector: 'namespace="storage"'
alerts:
- name: HighErrorRate
expr_template: rate_error_ratio
threshold: 0.05
for: 10m
severity: warning
- name: DiskSpaceLow
expr_template: gauge_below_percentage
metric: minio_cluster_capacity_usable_bytes
threshold: 0.1
base_metric: minio_cluster_capacity_raw_total_bytes
for: 5m
severity: critical
- name: ReplicationLag
expr_template: gauge_above_threshold
metric: minio_replication_metrics_replicating_byte_count
threshold: 1073741824
for: 15m
severity: warning