refactor(k8s): consolidate to infra/+apps/ single-source tree, dedicated per-app CNPG (authentik-db/temporal-db), wire monitoring-config, forgejo→cicd ns, drop orphan/stale (data-schemas, ollama, story-crater, sqs/argocd, key-rotation)
This commit is contained in:
Story Crater Bot
@@ -0,0 +1,34 @@
|
||||
# k8s/monitoring/ingress-alerts.yaml
|
||||
# ingress-nginx's chart has no built-in PrometheusRule block, so these rules are
|
||||
# a standalone CRD instance. Applied via the prometheus release's postsync hook
|
||||
# (after the operator/CRDs are confirmed up) — see helmfile.yaml.gotmpl.
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
name: ingress-nginx-rules
|
||||
namespace: ingress-nginx
|
||||
spec:
|
||||
groups:
|
||||
- name: ingress-nginx.rules
|
||||
rules:
|
||||
- alert: IngressHighErrorRate
|
||||
expr: |
|
||||
sum(rate(nginx_ingress_controller_requests{status=~"5.."}[5m])) by (ingress)
|
||||
/ sum(rate(nginx_ingress_controller_requests[5m])) by (ingress) > 0.05
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High 5xx rate on {{ $labels.ingress }}"
|
||||
description: "More than 5% of requests to {{ $labels.ingress }} have returned 5xx for 10 minutes."
|
||||
- alert: IngressHighLatencyP95
|
||||
expr: |
|
||||
histogram_quantile(0.95,
|
||||
sum(rate(nginx_ingress_controller_request_duration_seconds_bucket[5m])) by (ingress, le)
|
||||
) > 1
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "p95 latency > 1s on {{ $labels.ingress }}"
|
||||
description: "95th percentile request latency for {{ $labels.ingress }} has exceeded 1s for 10 minutes."
|
||||
@@ -0,0 +1,33 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
name: argocd-rules
|
||||
namespace: argocd
|
||||
spec:
|
||||
groups:
|
||||
- name: argocd.rules
|
||||
interval: 15s
|
||||
rules:
|
||||
- alert: ArgoCDHighErrorRate
|
||||
expr: |
|
||||
(
|
||||
sum(rate(argocd_http_request_total{status=~"5.."}[5m]))
|
||||
/
|
||||
sum(rate(argocd_http_request_total[5m]))
|
||||
) > 0.05
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High error rate on Argo CD"
|
||||
description: "5xx error rate exceeded 5% for 10 minutes. Value: {{ $value | humanizePercentage }}"
|
||||
|
||||
- alert: ArgoCDApplicationSyncFailure
|
||||
expr: |
|
||||
argocd_app_health_degraded_total > 0
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Argo CD applications in degraded state"
|
||||
description: "{{ $value | humanize }} application(s) have been degraded for 10 minutes"
|
||||
@@ -0,0 +1,33 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
name: authentik-rules
|
||||
namespace: iam
|
||||
spec:
|
||||
groups:
|
||||
- name: authentik.rules
|
||||
interval: 15s
|
||||
rules:
|
||||
- alert: AuthentikHighErrorRate
|
||||
expr: |
|
||||
(
|
||||
sum(rate(authentik_http_requests_total{status=~"5.."}[5m]))
|
||||
/
|
||||
sum(rate(authentik_http_requests_total[5m]))
|
||||
) > 0.05
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High error rate on Authentik"
|
||||
description: "5xx error rate exceeded 5% of total requests for 10 minutes. Value: {{ $value | humanizePercentage }}"
|
||||
|
||||
- alert: AuthentikOutpostDown
|
||||
expr: |
|
||||
authentik_outpost_total_up == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Authentik outpost is down"
|
||||
description: "Outpost {{ $labels.outpost_name }} (type: {{ $labels.outpost_type }}) has been offline for 5 minutes"
|
||||
@@ -0,0 +1,23 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
name: forgejo-rules
|
||||
namespace: forgejo
|
||||
spec:
|
||||
groups:
|
||||
- name: forgejo.rules
|
||||
interval: 15s
|
||||
rules:
|
||||
- alert: ForgejoHighErrorRate
|
||||
expr: |
|
||||
(
|
||||
sum(rate(forgejo_http_request_total{status=~"5.."}[5m]))
|
||||
/
|
||||
sum(rate(forgejo_http_request_total[5m]))
|
||||
) > 0.05
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High error rate on Forgejo"
|
||||
description: "5xx error rate exceeded 5% for 10 minutes. Value: {{ $value | humanizePercentage }}"
|
||||
@@ -0,0 +1,23 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
name: grafana-rules
|
||||
namespace: logging
|
||||
spec:
|
||||
groups:
|
||||
- name: grafana.rules
|
||||
interval: 15s
|
||||
rules:
|
||||
- alert: GrafanaHighErrorRate
|
||||
expr: |
|
||||
(
|
||||
sum(rate(grafana_http_request_total{status=~"5.."}[5m]))
|
||||
/
|
||||
sum(rate(grafana_http_request_total[5m]))
|
||||
) > 0.05
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High error rate on Grafana"
|
||||
description: "5xx error rate exceeded 5% for 10 minutes. Value: {{ $value | humanizePercentage }}"
|
||||
@@ -0,0 +1,57 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
name: minio-rules
|
||||
namespace: storage
|
||||
spec:
|
||||
groups:
|
||||
- name: minio.rules
|
||||
interval: 15s
|
||||
rules:
|
||||
- alert: MinIOHighErrorRate
|
||||
expr: |
|
||||
(
|
||||
sum(rate(minio_s3_requests_total{error="true"}[5m]))
|
||||
/
|
||||
sum(rate(minio_s3_requests_total[5m]))
|
||||
) > 0.05
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High error rate on MinIO"
|
||||
description: "S3 request error rate exceeded 5% for 10 minutes. Value: {{ $value | humanizePercentage }}"
|
||||
|
||||
- alert: MinIODiskSpaceLow
|
||||
expr: |
|
||||
(
|
||||
minio_cluster_capacity_usable_bytes
|
||||
/
|
||||
minio_cluster_capacity_raw_total_bytes
|
||||
) < 0.1
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "MinIO disk space critically low"
|
||||
description: "Usable capacity < 10% of raw capacity. Free space: {{ $value | humanizePercentage }}"
|
||||
|
||||
- alert: MinIOReplicationLag
|
||||
expr: |
|
||||
minio_replication_metrics_replicating_byte_count > 1073741824
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "MinIO replication lag detected"
|
||||
description: "Bytes pending replication > 1GB for 15 minutes. Value: {{ $value | humanize1024 }}B"
|
||||
|
||||
- alert: MinIODriveOffline
|
||||
expr: |
|
||||
minio_cluster_health_drives_offline > 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "MinIO drive offline"
|
||||
description: "{{ $value | humanize }} drive(s) offline in MinIO cluster"
|
||||
@@ -0,0 +1,33 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
name: vault-rules
|
||||
namespace: storage
|
||||
spec:
|
||||
groups:
|
||||
- name: vault.rules
|
||||
interval: 15s
|
||||
rules:
|
||||
- alert: VaultHighErrorRate
|
||||
expr: |
|
||||
(
|
||||
sum(rate(vault_core_handle_request_total{error="true"}[5m]))
|
||||
/
|
||||
sum(rate(vault_core_handle_request_total[5m]))
|
||||
) > 0.05
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High error rate on Vault"
|
||||
description: "Error rate exceeded 5% for 10 minutes. Value: {{ $value | humanizePercentage }}"
|
||||
|
||||
- alert: VaultSealed
|
||||
expr: |
|
||||
vault_core_unsealed == 0
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Vault is sealed"
|
||||
description: "Vault has been sealed for 1 minute. Immediate attention required."
|
||||
@@ -0,0 +1,75 @@
|
||||
# k8s/monitoring/blackbox-exporter-values.yaml
|
||||
# Active black-box HTTP probing of every ingress-exposed service — gives an
|
||||
# uptime/availability signal independent of real traffic. Homelab services
|
||||
# like Vault/MinIO/Longhorn UI get almost no organic requests, so ingress RED
|
||||
# metrics alone can't tell "idle" from "down"; this closes that gap.
|
||||
|
||||
config:
|
||||
modules:
|
||||
http_2xx:
|
||||
prober: http
|
||||
timeout: 5s
|
||||
http:
|
||||
valid_http_versions: ["HTTP/1.1", "HTTP/2.0"]
|
||||
valid_status_codes: [] # any 2xx
|
||||
follow_redirects: true
|
||||
preferred_ip_protocol: "ip4"
|
||||
tls_config:
|
||||
insecure_skip_verify: true # homelab-ca is a private CA; skip verify for simplicity
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 20m
|
||||
memory: 32Mi
|
||||
limits:
|
||||
cpu: 100m
|
||||
memory: 64Mi
|
||||
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Exists
|
||||
effect: NoSchedule
|
||||
|
||||
serviceMonitor:
|
||||
enabled: true
|
||||
selfMonitor:
|
||||
enabled: true
|
||||
defaults:
|
||||
interval: 30s
|
||||
scrapeTimeout: 10s
|
||||
module: http_2xx
|
||||
targets:
|
||||
- name: grafana
|
||||
url: https://grafana.riotpiao.com/
|
||||
- name: loki
|
||||
url: https://loki.riotpiao.com/ready
|
||||
- name: authentik
|
||||
url: https://authentik.riotpiao.com/-/health/ready/
|
||||
- name: vault
|
||||
url: https://vault.riotpiao.com/v1/sys/health
|
||||
- name: minio-console
|
||||
url: https://minio.riotpiao.com/
|
||||
- name: minio-api
|
||||
url: https://minio-api.riotpiao.com/minio/health/live
|
||||
- name: prometheus
|
||||
url: https://prometheus.riotpiao.com/-/healthy
|
||||
- name: portainer
|
||||
url: https://portainer.riotpiao.com/
|
||||
- name: forgejo
|
||||
url: https://forgejo.riotpiao.com/api/healthz
|
||||
- name: argocd
|
||||
url: https://argocd.riotpiao.com/healthz
|
||||
- name: longhorn
|
||||
url: https://longhorn.riotpiao.com/
|
||||
|
||||
prometheusRule:
|
||||
enabled: true
|
||||
rules:
|
||||
- alert: ServiceProbeDown
|
||||
expr: probe_success == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Probe failing for {{ $labels.instance }}"
|
||||
description: "Blackbox probe for {{ $labels.instance }} has failed for more than 5 minutes."
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,55 @@
|
||||
# k8s/monitoring/dashboards/control-plane-logs.yaml
|
||||
# Surfaces controller/control-plane logs that are already in Loki today
|
||||
# (Promtail scrapes every namespace with no filter) — this dashboard is the
|
||||
# "make it visible" piece, not new log collection.
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: control-plane-logs-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
data:
|
||||
control-plane-logs.json: |
|
||||
{
|
||||
"title": "Cluster Control Plane & Controllers (Logs)",
|
||||
"uid": "control-plane-logs",
|
||||
"schemaVersion": 39,
|
||||
"timezone": "browser",
|
||||
"time": { "from": "now-1h", "to": "now" },
|
||||
"refresh": "30s",
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
"title": "Error rate by namespace",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 6, "w": 24, "x": 0, "y": 0 },
|
||||
"datasource": { "type": "loki", "uid": "loki" },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (namespace) (count_over_time({namespace=~\"kube-system|cert-manager|ingress-nginx|longhorn-system\"} |= \"error\" [5m]))"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"title": "Control plane (kube-apiserver, controller-manager, scheduler)",
|
||||
"type": "logs",
|
||||
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 6 },
|
||||
"datasource": { "type": "loki", "uid": "loki" },
|
||||
"targets": [
|
||||
{ "expr": "{namespace=\"kube-system\"}" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"title": "Cluster add-ons (cert-manager, ingress-nginx, longhorn)",
|
||||
"type": "logs",
|
||||
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 16 },
|
||||
"datasource": { "type": "loki", "uid": "loki" },
|
||||
"targets": [
|
||||
{ "expr": "{namespace=~\"cert-manager|ingress-nginx|longhorn-system\"}" }
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,121 @@
|
||||
# k8s/monitoring/dashboards/hardware-overview.yaml
|
||||
# Trimmed operator at-a-glance view across all nodes — node-exporter already
|
||||
# powers the deep-dive "Node Exporter Full" (#1860, see grafana-values.yaml),
|
||||
# this is the quick health-check version, not a replacement for it.
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: hardware-overview-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
data:
|
||||
hardware-overview.json: |
|
||||
{
|
||||
"title": "Hardware Statistics (Operator Overview)",
|
||||
"uid": "hardware-overview",
|
||||
"schemaVersion": 39,
|
||||
"timezone": "browser",
|
||||
"time": { "from": "now-6h", "to": "now" },
|
||||
"refresh": "30s",
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
"title": "Nodes up / down",
|
||||
"type": "stat",
|
||||
"gridPos": { "h": 5, "w": 24, "x": 0, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [
|
||||
{ "type": "value", "options": { "0": { "text": "DOWN", "color": "red" } } },
|
||||
{ "type": "value", "options": { "1": { "text": "UP", "color": "green" } } }
|
||||
]
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{ "expr": "up{job=~\".*node-exporter.*\"}", "legendFormat": "{{instance}}" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"title": "CPU usage % by node",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 5 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "max": 100, "min": 0 } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(1 - avg(rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) by (instance)) * 100",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"title": "Memory usage % by node",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 5 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "max": 100, "min": 0 } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"title": "Root filesystem usage % by node",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 13 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "max": 100, "min": 0 } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(1 - node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"}) * 100",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"title": "Root filesystem space remaining",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 13 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "node_filesystem_avail_bytes{mountpoint=\"/\"}",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"title": "Network errors/drops by node",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 21 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "rate(node_network_receive_errs_total[5m])", "legendFormat": "{{instance}} rx errs" },
|
||||
{ "expr": "rate(node_network_transmit_errs_total[5m])", "legendFormat": "{{instance}} tx errs" },
|
||||
{ "expr": "rate(node_network_receive_drop_total[5m])", "legendFormat": "{{instance}} rx drops" },
|
||||
{ "expr": "rate(node_network_transmit_drop_total[5m])", "legendFormat": "{{instance}} tx drops" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"title": "Load average (1m / 5m) by node",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 21 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "node_load1", "legendFormat": "{{instance}} load1" },
|
||||
{ "expr": "node_load5", "legendFormat": "{{instance}} load5" }
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,185 @@
|
||||
# k8s/monitoring/dashboards/kube-controller-health.yaml
|
||||
# Talos binds controller-manager/scheduler/etcd to 127.0.0.1, so Prometheus
|
||||
# can't scrape them directly (see prometheus-values.yaml). kube-apiserver is
|
||||
# the one control-plane component that's still reachable (its ServiceMonitor
|
||||
# targets the in-cluster `kubernetes` service, not localhost) — paired with
|
||||
# kube-state-metrics signals as a proxy for controller/scheduler health.
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: kube-controller-health-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
data:
|
||||
kube-controller-health.json: |
|
||||
{
|
||||
"title": "Kube-Controller Health",
|
||||
"uid": "kube-controller-health",
|
||||
"schemaVersion": 39,
|
||||
"timezone": "browser",
|
||||
"time": { "from": "now-6h", "to": "now" },
|
||||
"refresh": "30s",
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
"title": "API server — up",
|
||||
"type": "stat",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [
|
||||
{ "type": "value", "options": { "0": { "text": "DOWN", "color": "red" } } },
|
||||
{ "type": "value", "options": { "1": { "text": "UP", "color": "green" } } }
|
||||
]
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{ "expr": "min(up{job=\"apiserver\"})", "legendFormat": "apiserver" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"title": "API server — request rate by verb/code",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 18, "x": 6, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(apiserver_request_total[5m])) by (verb, code)",
|
||||
"legendFormat": "{{verb}} {{code}}"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"title": "API server — error rate % (5xx)",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(apiserver_request_total{code=~\"5..\"}[5m])) / sum(rate(apiserver_request_total[5m])) * 100",
|
||||
"legendFormat": "5xx %"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"title": "API server — latency p95 / p99",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "s" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, sum(rate(apiserver_request_duration_seconds_bucket[5m])) by (le))",
|
||||
"legendFormat": "p95"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket[5m])) by (le))",
|
||||
"legendFormat": "p99"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"title": "Pods stuck Pending",
|
||||
"type": "stat",
|
||||
"gridPos": { "h": 5, "w": 8, "x": 0, "y": 16 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "value": 0, "color": "green" },
|
||||
{ "value": 1, "color": "yellow" },
|
||||
{ "value": 5, "color": "red" }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{ "expr": "sum(kube_pod_status_phase{phase=\"Pending\"}) OR on() vector(0)", "legendFormat": "pending" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"title": "CrashLoopBackOff containers",
|
||||
"type": "stat",
|
||||
"gridPos": { "h": 5, "w": 8, "x": 8, "y": 16 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "value": 0, "color": "green" },
|
||||
{ "value": 1, "color": "red" }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{ "expr": "sum(kube_pod_container_status_waiting_reason{reason=\"CrashLoopBackOff\"}) OR on() vector(0)", "legendFormat": "crashlooping" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"title": "Nodes NotReady",
|
||||
"type": "stat",
|
||||
"gridPos": { "h": 5, "w": 8, "x": 16, "y": 16 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "value": 0, "color": "green" },
|
||||
{ "value": 1, "color": "red" }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{ "expr": "count(kube_node_status_condition{condition=\"Ready\", status=\"true\"} == 0) OR on() vector(0)", "legendFormat": "not ready" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"title": "Failed Jobs",
|
||||
"type": "table",
|
||||
"gridPos": { "h": 7, "w": 12, "x": 0, "y": 21 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "kube_job_status_failed > 0", "format": "table", "instant": true }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"title": "Deployments with unavailable replicas",
|
||||
"type": "table",
|
||||
"gridPos": { "h": 7, "w": 12, "x": 12, "y": 21 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "kube_deployment_status_replicas_unavailable > 0", "format": "table", "instant": true }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"title": "Container restart rate by pod",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 28 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(kube_pod_container_status_restarts_total[15m])) by (namespace, pod)",
|
||||
"legendFormat": "{{namespace}}/{{pod}}"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,172 @@
|
||||
# k8s/monitoring/dashboards/service-availability.yaml
|
||||
# Active uptime/availability from blackbox-exporter probes — the signal that
|
||||
# covers low-traffic services (Vault, MinIO, Longhorn UI) where RED metrics
|
||||
# alone can't distinguish "idle" from "down".
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: service-availability-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
data:
|
||||
service-availability.json: |
|
||||
{
|
||||
"title": "Service Availability & Certificate Expiration",
|
||||
"uid": "svc-availability",
|
||||
"schemaVersion": 39,
|
||||
"timezone": "browser",
|
||||
"time": { "from": "now-24h", "to": "now" },
|
||||
"refresh": "30s",
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
"title": "Up / Down — all probed services",
|
||||
"type": "stat",
|
||||
"gridPos": { "h": 6, "w": 24, "x": 0, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [
|
||||
{ "type": "value", "options": { "0": { "text": "DOWN", "color": "red" } } },
|
||||
{ "type": "value", "options": { "1": { "text": "UP", "color": "green" } } }
|
||||
],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "value": 0, "color": "red" },
|
||||
{ "value": 1, "color": "green" }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{ "expr": "probe_success", "legendFormat": "{{instance}}" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"title": "Uptime % trend",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 6 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "max": 100, "min": 0 } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "avg_over_time(probe_success[$__rate_interval]) * 100",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"title": "Probe latency",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "s" } },
|
||||
"targets": [
|
||||
{ "expr": "probe_duration_seconds", "legendFormat": "{{instance}}" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"title": "7-day SLO (% successful probes)",
|
||||
"type": "table",
|
||||
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 14 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percent",
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "value": 0, "color": "red" },
|
||||
{ "value": 99, "color": "yellow" },
|
||||
{ "value": 99.9, "color": "green" }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "avg_over_time(probe_success[7d]) * 100",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"title": "Services DOWN right now",
|
||||
"type": "stat",
|
||||
"gridPos": { "h": 4, "w": 12, "x": 0, "y": 22 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "value": 0, "color": "green" },
|
||||
{ "value": 1, "color": "red" }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{ "expr": "count(probe_success == 0) OR on() vector(0)", "legendFormat": "down" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"title": "Certs expiring in < 14 days",
|
||||
"type": "stat",
|
||||
"gridPos": { "h": 4, "w": 12, "x": 12, "y": 22 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "value": 0, "color": "green" },
|
||||
{ "value": 1, "color": "red" }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "count((certmanager_certificate_expiration_timestamp_seconds - time()) / 86400 < 14) OR on() vector(0)",
|
||||
"legendFormat": "expiring"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"title": "Certificate expiry — days remaining",
|
||||
"type": "table",
|
||||
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 26 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "value": 0, "color": "red" },
|
||||
{ "value": 14, "color": "yellow" },
|
||||
{ "value": 30, "color": "green" }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(certmanager_certificate_expiration_timestamp_seconds - time()) / 86400",
|
||||
"legendFormat": "{{name}}",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,141 @@
|
||||
# k8s/monitoring/dashboards/service-golden-signals.yaml
|
||||
# RED metrics (rate/errors/duration) for every service fronted by ingress-nginx.
|
||||
# Picked up automatically by Grafana's sidecar (grafana_dashboard=1 label) — see
|
||||
# sidecar.dashboards in k8s/logging/grafana-values.yaml.
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: service-golden-signals-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
data:
|
||||
service-golden-signals.json: |
|
||||
{
|
||||
"title": "Latency & Golden Signals (Ingress RED)",
|
||||
"uid": "svc-golden-signals",
|
||||
"schemaVersion": 39,
|
||||
"timezone": "browser",
|
||||
"time": { "from": "now-6h", "to": "now" },
|
||||
"refresh": "30s",
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "ingress",
|
||||
"type": "query",
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"query": "label_values(nginx_ingress_controller_requests, ingress)",
|
||||
"refresh": 2,
|
||||
"includeAll": false
|
||||
}
|
||||
]
|
||||
},
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
"title": "Request rate by status — $ingress",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(nginx_ingress_controller_requests{ingress=\"$ingress\"}[5m])) by (status)",
|
||||
"legendFormat": "{{status}}"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"title": "Error rate % (4xx / 5xx) — $ingress",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(nginx_ingress_controller_requests{ingress=\"$ingress\", status=~\"5..\"}[5m])) / sum(rate(nginx_ingress_controller_requests{ingress=\"$ingress\"}[5m])) * 100",
|
||||
"legendFormat": "5xx"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(nginx_ingress_controller_requests{ingress=\"$ingress\", status=~\"4..\"}[5m])) / sum(rate(nginx_ingress_controller_requests{ingress=\"$ingress\"}[5m])) * 100",
|
||||
"legendFormat": "4xx"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"title": "Latency p50 / p95 / p99 — $ingress",
|
||||
"type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "s" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress=\"$ingress\"}[5m])) by (le))",
|
||||
"legendFormat": "p50"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress=\"$ingress\"}[5m])) by (le))",
|
||||
"legendFormat": "p95"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress=\"$ingress\"}[5m])) by (le))",
|
||||
"legendFormat": "p99"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"title": "All services — traffic overview",
|
||||
"type": "table",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk(11, sum(rate(nginx_ingress_controller_requests[5m])) by (ingress))",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"title": "Customer-facing failures (5xx count, window total)",
|
||||
"type": "stat",
|
||||
"gridPos": { "h": 5, "w": 12, "x": 0, "y": 16 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "value": 0, "color": "green" },
|
||||
{ "value": 1, "color": "yellow" },
|
||||
{ "value": 50, "color": "red" }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(increase(nginx_ingress_controller_requests{status=~\"5..\"}[$__range])) OR on() vector(0)",
|
||||
"legendFormat": "5xx total"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"title": "Top 5 error-contributing services",
|
||||
"type": "table",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 16 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk(5, sum(rate(nginx_ingress_controller_requests{status=~\"5..\"}[5m])) by (ingress))",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,109 @@
|
||||
# k8s/monitoring/dashboards/service-internals.yaml
|
||||
# Native per-service metrics — the "why" layer behind the ingress RED/uptime
|
||||
# dashboards (e.g. ingress shows MinIO is slow; this shows disk offline).
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: service-internals-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
data:
|
||||
service-internals.json: |
|
||||
{
|
||||
"title": "Service Internals (MinIO / Forgejo / Argo CD / cert-manager / Vault / Longhorn)",
|
||||
"uid": "svc-internals",
|
||||
"schemaVersion": 39,
|
||||
"timezone": "browser",
|
||||
"time": { "from": "now-6h", "to": "now" },
|
||||
"refresh": "30s",
|
||||
"panels": [
|
||||
{ "id": 1, "title": "MinIO — disk/node offline", "type": "timeseries",
|
||||
"gridPos": { "h": 6, "w": 12, "x": 0, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "minio_cluster_disk_offline_total", "legendFormat": "disks offline" },
|
||||
{ "expr": "minio_cluster_nodes_offline_total", "legendFormat": "nodes offline" }
|
||||
]
|
||||
},
|
||||
{ "id": 2, "title": "MinIO — S3 request errors", "type": "timeseries",
|
||||
"gridPos": { "h": 6, "w": 12, "x": 12, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "sum(rate(minio_s3_requests_errors_total[5m])) by (api)", "legendFormat": "{{api}}" }
|
||||
]
|
||||
},
|
||||
{ "id": 3, "title": "MinIO — S3 TTFB latency", "type": "timeseries",
|
||||
"gridPos": { "h": 6, "w": 12, "x": 0, "y": 6 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "s" } },
|
||||
"targets": [
|
||||
{ "expr": "minio_s3_time_ttfb_seconds_distribution", "legendFormat": "{{api}}" }
|
||||
]
|
||||
},
|
||||
{ "id": 4, "title": "Forgejo — repos / orgs", "type": "stat",
|
||||
"gridPos": { "h": 6, "w": 12, "x": 12, "y": 6 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "gitea_repositories", "legendFormat": "repos" },
|
||||
{ "expr": "gitea_organizations", "legendFormat": "orgs" }
|
||||
]
|
||||
},
|
||||
{ "id": 5, "title": "Forgejo — process health (CPU/mem)", "type": "timeseries",
|
||||
"gridPos": { "h": 6, "w": 12, "x": 0, "y": 12 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "rate(process_cpu_seconds_total{job=~\".*forgejo.*|.*gitea.*\"}[5m])", "legendFormat": "cpu" },
|
||||
{ "expr": "process_resident_memory_bytes{job=~\".*forgejo.*|.*gitea.*\"}", "legendFormat": "mem" }
|
||||
]
|
||||
},
|
||||
{ "id": 6, "title": "Argo CD — app sync/health status", "type": "table",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "argocd_app_info", "format": "table", "instant": true }
|
||||
]
|
||||
},
|
||||
{ "id": 7, "title": "cert-manager — days to cert expiry", "type": "stat",
|
||||
"gridPos": { "h": 6, "w": 12, "x": 0, "y": 18 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "value": 0, "color": "red" },
|
||||
{ "value": 14, "color": "yellow" },
|
||||
{ "value": 30, "color": "green" }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{ "expr": "(certmanager_certificate_expiration_timestamp_seconds - time()) / 86400", "legendFormat": "{{name}}" }
|
||||
]
|
||||
},
|
||||
{ "id": 8, "title": "Vault — sealed/unsealed", "type": "stat",
|
||||
"gridPos": { "h": 6, "w": 6, "x": 12, "y": 20 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [
|
||||
{ "type": "value", "options": { "0": { "text": "SEALED", "color": "red" } } },
|
||||
{ "type": "value", "options": { "1": { "text": "UNSEALED", "color": "green" } } }
|
||||
]
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{ "expr": "vault_core_unsealed", "legendFormat": "vault" }
|
||||
]
|
||||
},
|
||||
{ "id": 9, "title": "Longhorn — volume robustness", "type": "table",
|
||||
"gridPos": { "h": 6, "w": 6, "x": 18, "y": 20 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "longhorn_volume_robustness", "format": "table", "instant": true }
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,12 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: svc-argocd-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
annotations:
|
||||
grafana_folder: "Argo CD"
|
||||
data:
|
||||
svc-argocd.json: |
|
||||
{"title":"Argo CD — Service Overview","uid":"svc-argocd","schemaVersion":39,"timezone":"browser","time":{"from":"now-6h","to":"now"},"refresh":"30s","panels":[{"id":1,"title":"Row: Availability","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":0},"panels":[{"id":2,"title":"Up","type":"stat","gridPos":{"h":4,"w":6,"x":0,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"}}},"targets":[{"expr":"min(up{job=~\"argocd-.*\"})"}]},{"id":3,"title":"HTTP requests","type":"timeseries","gridPos":{"h":8,"w":9,"x":6,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(argocd_http_request_total[5m])) by (status)","legendFormat":"{{status}}"}]},{"id":4,"title":"Error rate %","type":"timeseries","gridPos":{"h":8,"w":9,"x":15,"y":1},"fieldConfig":{"defaults":{"unit":"percent"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(argocd_http_request_total{status=~\"5..\"}[5m])) / sum(rate(argocd_http_request_total[5m])) * 100"}]},{"id":5,"title":"Request latency","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":9},"fieldConfig":{"defaults":{"unit":"s"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"histogram_quantile(0.95, sum(rate(argocd_http_request_duration_seconds_bucket[5m])) by (le))","legendFormat":"p95"}]}]},{"id":10,"title":"Row: Resources","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":1},"panels":[{"id":11,"title":"CPU","type":"timeseries","gridPos":{"h":8,"w":8,"x":0,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(container_cpu_usage_seconds_total{namespace=\"argocd\"}[5m])) by (pod)","legendFormat":"{{pod}}"}]},{"id":12,"title":"Memory","type":"timeseries","gridPos":{"h":8,"w":8,"x":8,"y":2},"fieldConfig":{"defaults":{"unit":"bytes"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(container_memory_working_set_bytes{namespace=\"argocd\"}) by (pod)","legendFormat":"{{pod}}"}]},{"id":13,"title":"Restarts","type":"timeseries","gridPos":{"h":8,"w":8,"x":16,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(kube_pod_container_status_restarts_total{namespace=\"argocd\"}[15m])) by (pod)","legendFormat":"{{pod}}"}]}]},{"id":20,"title":"Row: Applications & Sync","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":2},"panels":[{"id":21,"title":"Applications","type":"stat","gridPos":{"h":6,"w":6,"x":0,"y":3},"fieldConfig":{"defaults":{"unit":"short"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"argocd_app_total"}]},{"id":22,"title":"Sync by status","type":"timeseries","gridPos":{"h":6,"w":9,"x":6,"y":3},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(argocd_app_sync_total[5m])) by (sync_status)","legendFormat":"{{sync_status}}"}]},{"id":23,"title":"Degraded apps","type":"stat","gridPos":{"h":6,"w":6,"x":15,"y":3},"fieldConfig":{"defaults":{"unit":"short"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"argocd_app_health_degraded_total"}]},{"id":24,"title":"Git sync ops","type":"timeseries","gridPos":{"h":6,"w":12,"x":0,"y":9},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(argocd_git_sync_total[5m])) by (git_operation,git_status)","legendFormat":"{{git_operation}}/{{git_status}}"}]}]},{"id":30,"title":"Row: Logs","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":3},"panels":[{"id":31,"title":"Recent logs","type":"logs","gridPos":{"h":10,"w":24,"x":0,"y":4},"datasource":{"type":"loki","uid":"loki"},"targets":[{"expr":"{namespace=\"argocd\"}"}]}]}]}
|
||||
@@ -0,0 +1,143 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: svc-authentik-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
annotations:
|
||||
grafana_folder: "Authentik"
|
||||
data:
|
||||
svc-authentik.json: |
|
||||
{
|
||||
"title": "Authentik — Service Overview",
|
||||
"uid": "svc-authentik",
|
||||
"schemaVersion": 39,
|
||||
"timezone": "browser",
|
||||
"time": { "from": "now-6h", "to": "now" },
|
||||
"refresh": "30s",
|
||||
"panels": [
|
||||
{
|
||||
"id": 1, "title": "Row: Availability & Golden Signals", "type": "row",
|
||||
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
|
||||
"panels": [
|
||||
{
|
||||
"id": 2, "title": "Up", "type": "stat",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 1 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [
|
||||
{ "type": "value", "options": { "0": { "text": "DOWN", "color": "red" }, "1": { "text": "UP", "color": "green" } } }
|
||||
],
|
||||
"thresholds": { "mode": "absolute", "steps": [ { "value": null, "color": "red" }, { "value": 1, "color": "green" } ] }
|
||||
}
|
||||
},
|
||||
"targets": [{ "expr": "min(up{job=\"authentik-server\"})" }]
|
||||
},
|
||||
{
|
||||
"id": 3, "title": "HTTP request rate by status", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 9, "x": 6, "y": 1 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "sum(rate(authentik_flows_execution_stage_time_count[5m])) by (flow_slug)", "legendFormat": "{{flow_slug}}" }]
|
||||
},
|
||||
{
|
||||
"id": 4, "title": "Error rate % (5xx)", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 9, "x": 15, "y": 1 },
|
||||
"fieldConfig": { "defaults": { "unit": "percent" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "(1 - (authentik_flows_cached / authentik_flows_execution_stage_time_count)) * 100" }]
|
||||
},
|
||||
{
|
||||
"id": 5, "title": "Request duration p50/p95/p99", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 9 },
|
||||
"fieldConfig": { "defaults": { "unit": "s" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "histogram_quantile(0.50, sum(rate(authentik_main_request_duration_seconds_bucket[5m])) by (le))", "legendFormat": "p50" },
|
||||
{ "expr": "histogram_quantile(0.95, sum(rate(authentik_main_request_duration_seconds_bucket[5m])) by (le))", "legendFormat": "p95" },
|
||||
{ "expr": "histogram_quantile(0.99, sum(rate(authentik_main_request_duration_seconds_bucket[5m])) by (le))", "legendFormat": "p99" }
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 10, "title": "Row: Resource Usage", "type": "row",
|
||||
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 1 },
|
||||
"panels": [
|
||||
{
|
||||
"id": 11, "title": "CPU by pod", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 8, "x": 0, "y": 2 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"iam\",pod=~\"authentik.*\"}[5m])) by (pod)", "legendFormat": "{{pod}}" }]
|
||||
},
|
||||
{
|
||||
"id": 12, "title": "Memory by pod", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 8, "x": 8, "y": 2 },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "sum(container_memory_working_set_bytes{namespace=\"iam\",pod=~\"authentik.*\"}) by (pod)", "legendFormat": "{{pod}}" }]
|
||||
},
|
||||
{
|
||||
"id": 13, "title": "Restart rate by pod", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 8, "x": 16, "y": 2 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "sum(rate(kube_pod_container_status_restarts_total{namespace=\"iam\",pod=~\"authentik.*\"}[15m])) by (pod)", "legendFormat": "{{pod}}" }]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 20, "title": "Row: Identity Provider (OIDC / OAuth2)", "type": "row",
|
||||
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 2 },
|
||||
"panels": [
|
||||
{
|
||||
"id": 21, "title": "Outpost connections", "type": "stat",
|
||||
"gridPos": { "h": 7, "w": 6, "x": 0, "y": 3 },
|
||||
"fieldConfig": { "defaults": { "unit": "short" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "authentik_outposts_connected" }]
|
||||
},
|
||||
{
|
||||
"id": 22, "title": "Flows cached", "type": "stat",
|
||||
"gridPos": { "h": 7, "w": 6, "x": 6, "y": 3 },
|
||||
"fieldConfig": { "defaults": { "unit": "short" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "authentik_flows_cached" }]
|
||||
},
|
||||
{
|
||||
"id": 23, "title": "Policies cached", "type": "stat",
|
||||
"gridPos": { "h": 7, "w": 6, "x": 12, "y": 3 },
|
||||
"fieldConfig": { "defaults": { "unit": "short" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "authentik_policies_cached" }]
|
||||
},
|
||||
{
|
||||
"id": 24, "title": "Queued tasks", "type": "stat",
|
||||
"gridPos": { "h": 7, "w": 6, "x": 18, "y": 3 },
|
||||
"fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "unit": "short" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "authentik_tasks_queued" }]
|
||||
},
|
||||
{
|
||||
"id": 25, "title": "Admin workers", "type": "timeseries",
|
||||
"gridPos": { "h": 7, "w": 12, "x": 0, "y": 10 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "authentik_admin_workers" }]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 30, "title": "Row: Logs", "type": "row",
|
||||
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 3 },
|
||||
"panels": [
|
||||
{
|
||||
"id": 31, "title": "Recent logs", "type": "logs",
|
||||
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 4 },
|
||||
"datasource": { "type": "loki", "uid": "loki" },
|
||||
"targets": [{ "expr": "{namespace=\"iam\"}" }]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,12 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: svc-forgejo-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
annotations:
|
||||
grafana_folder: "Forgejo"
|
||||
data:
|
||||
svc-forgejo.json: |
|
||||
{"title":"Forgejo — Service Overview","uid":"svc-forgejo","schemaVersion":39,"timezone":"browser","time":{"from":"now-6h","to":"now"},"refresh":"30s","panels":[{"id":1,"title":"Row: Availability","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":0},"panels":[{"id":2,"title":"Up","type":"stat","gridPos":{"h":4,"w":6,"x":0,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"}}},"targets":[{"expr":"min(up{job=\"forgejo\"})"}]},{"id":3,"title":"HTTP requests by method","type":"timeseries","gridPos":{"h":8,"w":9,"x":6,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(forgejo_http_request_total[5m])) by (method)","legendFormat":"{{method}}"}]},{"id":4,"title":"Error rate %","type":"timeseries","gridPos":{"h":8,"w":9,"x":15,"y":1},"fieldConfig":{"defaults":{"unit":"percent"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(forgejo_http_request_total{status=~\"5..\"}[5m])) / sum(rate(forgejo_http_request_total[5m])) * 100"}]},{"id":5,"title":"Request latency","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":9},"fieldConfig":{"defaults":{"unit":"s"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"histogram_quantile(0.95, sum(rate(forgejo_http_request_duration_seconds_bucket[5m])) by (le))","legendFormat":"p95"}]}]},{"id":10,"title":"Row: Resources","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":1},"panels":[{"id":11,"title":"CPU","type":"timeseries","gridPos":{"h":8,"w":8,"x":0,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(container_cpu_usage_seconds_total{namespace=\"forgejo\"}[5m])) by (pod)","legendFormat":"{{pod}}"}]},{"id":12,"title":"Memory","type":"timeseries","gridPos":{"h":8,"w":8,"x":8,"y":2},"fieldConfig":{"defaults":{"unit":"bytes"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(container_memory_working_set_bytes{namespace=\"forgejo\"}) by (pod)","legendFormat":"{{pod}}"}]},{"id":13,"title":"Restarts","type":"timeseries","gridPos":{"h":8,"w":8,"x":16,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(kube_pod_container_status_restarts_total{namespace=\"forgejo\"}[15m])) by (pod)","legendFormat":"{{pod}}"}]}]},{"id":20,"title":"Row: Git Operations","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":2},"panels":[{"id":21,"title":"Repositories","type":"stat","gridPos":{"h":6,"w":6,"x":0,"y":3},"fieldConfig":{"defaults":{"unit":"short"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"forgejo_repositories_total"}]},{"id":22,"title":"Users","type":"stat","gridPos":{"h":6,"w":6,"x":6,"y":3},"fieldConfig":{"defaults":{"unit":"short"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"forgejo_users_total"}]},{"id":23,"title":"Git ops rate","type":"timeseries","gridPos":{"h":6,"w":12,"x":12,"y":3},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(forgejo_git_operations_total[5m])) by (operation_type)","legendFormat":"{{operation_type}}"}]},{"id":24,"title":"Runner tasks","type":"timeseries","gridPos":{"h":6,"w":12,"x":0,"y":9},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(forgejo_runner_tasks_total[5m])) by (status)","legendFormat":"{{status}}"}]}]},{"id":30,"title":"Row: Logs","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":3},"panels":[{"id":31,"title":"Recent logs","type":"logs","gridPos":{"h":10,"w":24,"x":0,"y":4},"datasource":{"type":"loki","uid":"loki"},"targets":[{"expr":"{namespace=\"forgejo\"}"}]}]}]}
|
||||
@@ -0,0 +1,12 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: svc-grafana-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
annotations:
|
||||
grafana_folder: "Grafana"
|
||||
data:
|
||||
svc-grafana.json: |
|
||||
{"title":"Grafana — Service Overview","uid":"svc-grafana","schemaVersion":39,"timezone":"browser","time":{"from":"now-6h","to":"now"},"refresh":"30s","panels":[{"id":1,"title":"Row: Availability","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":0},"panels":[{"id":2,"title":"Up","type":"stat","gridPos":{"h":4,"w":6,"x":0,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"},"mappings":[{"type":"value","options":{"0":{"text":"DOWN","color":"red"},"1":{"text":"UP","color":"green"}}}]}},"targets":[{"expr":"min(up{job=\"grafana\"})"}]},{"id":3,"title":"HTTP requests","type":"timeseries","gridPos":{"h":8,"w":9,"x":6,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(grafana_http_request_total[5m])) by (status)","legendFormat":"{{status}}"}]},{"id":4,"title":"Error rate %","type":"timeseries","gridPos":{"h":8,"w":9,"x":15,"y":1},"fieldConfig":{"defaults":{"unit":"percent"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(grafana_http_request_total{status=~\"5..\"}[5m])) / sum(rate(grafana_http_request_total[5m])) * 100"}]},{"id":5,"title":"Request latency","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":9},"fieldConfig":{"defaults":{"unit":"s"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"histogram_quantile(0.95, sum(rate(grafana_http_request_duration_seconds_bucket[5m])) by (le))","legendFormat":"p95"}]}]},{"id":10,"title":"Row: Resources","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":1},"panels":[{"id":11,"title":"CPU","type":"timeseries","gridPos":{"h":8,"w":8,"x":0,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(container_cpu_usage_seconds_total{namespace=\"logging\",pod=~\"grafana.*\"}[5m])) by (pod)","legendFormat":"{{pod}}"}]},{"id":12,"title":"Memory","type":"timeseries","gridPos":{"h":8,"w":8,"x":8,"y":2},"fieldConfig":{"defaults":{"unit":"bytes"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(container_memory_working_set_bytes{namespace=\"logging\",pod=~\"grafana.*\"}) by (pod)","legendFormat":"{{pod}}"}]},{"id":13,"title":"Restarts","type":"timeseries","gridPos":{"h":8,"w":8,"x":16,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(kube_pod_container_status_restarts_total{namespace=\"logging\",pod=~\"grafana.*\"}[15m])) by (pod)","legendFormat":"{{pod}}"}]}]},{"id":20,"title":"Row: Dashboards & Users","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":2},"panels":[{"id":21,"title":"Total dashboards","type":"stat","gridPos":{"h":6,"w":6,"x":0,"y":3},"fieldConfig":{"defaults":{"unit":"short"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"grafana_dashboard_total"}]},{"id":22,"title":"Total users","type":"stat","gridPos":{"h":6,"w":6,"x":6,"y":3},"fieldConfig":{"defaults":{"unit":"short"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"grafana_user_total"}]},{"id":23,"title":"Total alerts","type":"stat","gridPos":{"h":6,"w":6,"x":12,"y":3},"fieldConfig":{"defaults":{"unit":"short"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"grafana_alerts_total"}]}]},{"id":30,"title":"Row: Logs","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":3},"panels":[{"id":31,"title":"Recent logs","type":"logs","gridPos":{"h":10,"w":24,"x":0,"y":4},"datasource":{"type":"loki","uid":"loki"},"targets":[{"expr":"{namespace=\"logging\",container=\"grafana\"}"}]}]}]}
|
||||
@@ -0,0 +1,143 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: svc-minio-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
annotations:
|
||||
grafana_folder: "MinIO"
|
||||
data:
|
||||
svc-minio.json: |
|
||||
{
|
||||
"title": "MinIO — Service Overview",
|
||||
"uid": "svc-minio",
|
||||
"schemaVersion": 39,
|
||||
"timezone": "browser",
|
||||
"time": { "from": "now-6h", "to": "now" },
|
||||
"refresh": "30s",
|
||||
"panels": [
|
||||
{
|
||||
"id": 1, "title": "Row: Availability & Golden Signals", "type": "row",
|
||||
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
|
||||
"panels": [
|
||||
{
|
||||
"id": 2, "title": "Up", "type": "stat",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 1 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [
|
||||
{ "type": "value", "options": { "0": { "text": "DOWN", "color": "red" }, "1": { "text": "UP", "color": "green" } } }
|
||||
],
|
||||
"thresholds": { "mode": "absolute", "steps": [ { "value": null, "color": "red" }, { "value": 1, "color": "green" } ] }
|
||||
}
|
||||
},
|
||||
"targets": [{ "expr": "min(up{job=\"minio\"})" }]
|
||||
},
|
||||
{
|
||||
"id": 3, "title": "S3 request rate by method", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 9, "x": 6, "y": 1 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "sum(rate(minio_s3_requests_total[5m])) by (method)", "legendFormat": "{{method}}" }]
|
||||
},
|
||||
{
|
||||
"id": 4, "title": "Error rate %", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 9, "x": 15, "y": 1 },
|
||||
"fieldConfig": { "defaults": { "unit": "percent" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "sum(rate(minio_s3_requests_total{error=\"true\"}[5m])) / sum(rate(minio_s3_requests_total[5m])) * 100" }]
|
||||
},
|
||||
{
|
||||
"id": 5, "title": "Request duration p50/p95/p99", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 9 },
|
||||
"fieldConfig": { "defaults": { "unit": "s" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "histogram_quantile(0.50, sum(rate(minio_s3_requests_duration_seconds_bucket[5m])) by (le))", "legendFormat": "p50" },
|
||||
{ "expr": "histogram_quantile(0.95, sum(rate(minio_s3_requests_duration_seconds_bucket[5m])) by (le))", "legendFormat": "p95" },
|
||||
{ "expr": "histogram_quantile(0.99, sum(rate(minio_s3_requests_duration_seconds_bucket[5m])) by (le))", "legendFormat": "p99" }
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 10, "title": "Row: Resource Usage", "type": "row",
|
||||
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 1 },
|
||||
"panels": [
|
||||
{
|
||||
"id": 11, "title": "CPU by pod", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 8, "x": 0, "y": 2 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"storage\",pod=~\"minio.*\"}[5m])) by (pod)", "legendFormat": "{{pod}}" }]
|
||||
},
|
||||
{
|
||||
"id": 12, "title": "Memory by pod", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 8, "x": 8, "y": 2 },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "sum(container_memory_working_set_bytes{namespace=\"storage\",pod=~\"minio.*\"}) by (pod)", "legendFormat": "{{pod}}" }]
|
||||
},
|
||||
{
|
||||
"id": 13, "title": "Restart rate by pod", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 8, "x": 16, "y": 2 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "sum(rate(kube_pod_container_status_restarts_total{namespace=\"storage\",pod=~\"minio.*\"}[15m])) by (pod)", "legendFormat": "{{pod}}" }]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 20, "title": "Row: Storage & Replication", "type": "row",
|
||||
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 2 },
|
||||
"panels": [
|
||||
{
|
||||
"id": 21, "title": "Usable vs Raw capacity", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 3 },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes", "custom": { "lineWidth": 2 } } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "minio_cluster_capacity_usable_bytes", "legendFormat": "Usable" },
|
||||
{ "expr": "minio_cluster_capacity_raw_total_bytes", "legendFormat": "Raw Total" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 22, "title": "Drive health (online/offline)", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 3 },
|
||||
"fieldConfig": { "defaults": { "unit": "short" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [
|
||||
{ "expr": "minio_cluster_health_drives_online", "legendFormat": "Online" },
|
||||
{ "expr": "minio_cluster_health_drives_offline", "legendFormat": "Offline" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 23, "title": "Replication lag (bytes pending)", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 11 },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "minio_replication_metrics_replicating_byte_count", "legendFormat": "Pending replication" }]
|
||||
},
|
||||
{
|
||||
"id": 24, "title": "Replication failures (bytes)", "type": "timeseries",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 11 },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes" } },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"targets": [{ "expr": "minio_replication_metrics_failed_byte_count", "legendFormat": "Failed replication" }]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 30, "title": "Row: Logs", "type": "row",
|
||||
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 3 },
|
||||
"panels": [
|
||||
{
|
||||
"id": 31, "title": "Recent logs", "type": "logs",
|
||||
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 4 },
|
||||
"datasource": { "type": "loki", "uid": "loki" },
|
||||
"targets": [{ "expr": "{namespace=\"storage\"}" }]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,12 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: svc-vault-dashboard
|
||||
namespace: logging
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
annotations:
|
||||
grafana_folder: "Vault"
|
||||
data:
|
||||
svc-vault.json: |
|
||||
{"title":"Vault — Service Overview","uid":"svc-vault","schemaVersion":39,"timezone":"browser","time":{"from":"now-6h","to":"now"},"refresh":"30s","panels":[{"id":1,"title":"Row: Availability & Golden Signals","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":0},"panels":[{"id":2,"title":"Up","type":"stat","gridPos":{"h":4,"w":6,"x":0,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"},"mappings":[{"type":"value","options":{"0":{"text":"DOWN","color":"red"},"1":{"text":"UP","color":"green"}}}],"thresholds":{"mode":"absolute","steps":[{"value":null,"color":"red"},{"value":1,"color":"green"}]}}},"targets":[{"expr":"min(up{job=\"vault\"})"}]},{"id":3,"title":"Request rate by status","type":"timeseries","gridPos":{"h":8,"w":9,"x":6,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(vault_core_handle_request_total[5m])) by (method)","legendFormat":"{{method}}"}]},{"id":4,"title":"Error rate %","type":"timeseries","gridPos":{"h":8,"w":9,"x":15,"y":1},"fieldConfig":{"defaults":{"unit":"percent"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(vault_core_handle_request_total{error=\"true\"}[5m])) / sum(rate(vault_core_handle_request_total[5m])) * 100"}]},{"id":5,"title":"Request duration p50/p95/p99","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":9},"fieldConfig":{"defaults":{"unit":"s"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"histogram_quantile(0.50, sum(rate(vault_core_handle_request_duration_seconds_bucket[5m])) by (le))","legendFormat":"p50"},{"expr":"histogram_quantile(0.95, sum(rate(vault_core_handle_request_duration_seconds_bucket[5m])) by (le))","legendFormat":"p95"},{"expr":"histogram_quantile(0.99, sum(rate(vault_core_handle_request_duration_seconds_bucket[5m])) by (le))","legendFormat":"p99"}]}]},{"id":10,"title":"Row: Resource Usage","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":1},"panels":[{"id":11,"title":"CPU by pod","type":"timeseries","gridPos":{"h":8,"w":8,"x":0,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(container_cpu_usage_seconds_total{namespace=\"iam\",pod=~\"vault.*\"}[5m])) by (pod)","legendFormat":"{{pod}}"}]},{"id":12,"title":"Memory by pod","type":"timeseries","gridPos":{"h":8,"w":8,"x":8,"y":2},"fieldConfig":{"defaults":{"unit":"bytes"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(container_memory_working_set_bytes{namespace=\"iam\",pod=~\"vault.*\"}) by (pod)","legendFormat":"{{pod}}"}]},{"id":13,"title":"Restart rate","type":"timeseries","gridPos":{"h":8,"w":8,"x":16,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(kube_pod_container_status_restarts_total{namespace=\"iam\",pod=~\"vault.*\"}[15m])) by (pod)","legendFormat":"{{pod}}"}]}]},{"id":20,"title":"Row: Vault Seal State","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":2},"panels":[{"id":21,"title":"Sealed","type":"stat","gridPos":{"h":6,"w":6,"x":0,"y":3},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"},"mappings":[{"type":"value","options":{"0":{"text":"UNSEALED","color":"green"},"1":{"text":"SEALED","color":"red"}}}],"thresholds":{"mode":"absolute","steps":[{"value":null,"color":"green"},{"value":1,"color":"red"}]}}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"vault_core_unsealed"}]},{"id":22,"title":"Active","type":"stat","gridPos":{"h":6,"w":6,"x":6,"y":3},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"},"mappings":[{"type":"value","options":{"0":{"text":"INACTIVE","color":"red"},"1":{"text":"ACTIVE","color":"green"}}}],"thresholds":{"mode":"absolute","steps":[{"value":null,"color":"red"},{"value":1,"color":"green"}]}}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"vault_core_active"}]},{"id":23,"title":"Replication (Primary)","type":"stat","gridPos":{"h":6,"w":6,"x":12,"y":3},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"},"mappings":[{"type":"value","options":{"0":{"text":"SECONDARY","color":"orange"},"1":{"text":"PRIMARY","color":"green"}}}],"thresholds":{"mode":"absolute","steps":[{"value":null,"color":"orange"},{"value":1,"color":"green"}]}}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"vault_core_replication_primary"}]},{"id":24,"title":"Active tokens","type":"stat","gridPos":{"h":6,"w":6,"x":18,"y":3},"fieldConfig":{"defaults":{"unit":"short"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"vault_token_total"}]}]},{"id":30,"title":"Row: Logs","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":3},"panels":[{"id":31,"title":"Recent logs","type":"logs","gridPos":{"h":10,"w":24,"x":0,"y":4},"datasource":{"type":"loki","uid":"loki"},"targets":[{"expr":"{namespace=\"iam\",container=\"vault\"}"}]}]}]}
|
||||
@@ -0,0 +1,30 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
# Single source for cluster monitoring config (alerts, servicemonitors, dashboards).
|
||||
# NO top-level `namespace:` transformer — PrometheusRules deliberately live in
|
||||
# per-app namespaces (forgejo, iam, argocd, storage, ...); a transformer would
|
||||
# wrongly rewrite them all to one ns.
|
||||
resources:
|
||||
- alerts/ingress-alerts.yaml
|
||||
- alerts/svc-argocd-rules.yaml
|
||||
- alerts/svc-authentik-rules.yaml
|
||||
- alerts/svc-forgejo-rules.yaml
|
||||
- alerts/svc-grafana-rules.yaml
|
||||
- alerts/svc-minio-rules.yaml
|
||||
- alerts/svc-vault-rules.yaml
|
||||
- servicemonitors/argocd.yaml
|
||||
- servicemonitors/authentik.yaml
|
||||
- servicemonitors/forgejo.yaml
|
||||
- servicemonitors/minio.yaml
|
||||
- dashboards/control-plane-logs.yaml
|
||||
- dashboards/hardware-overview.yaml
|
||||
- dashboards/kube-controller-health.yaml
|
||||
- dashboards/service-availability.yaml
|
||||
- dashboards/service-golden-signals.yaml
|
||||
- dashboards/service-internals.yaml
|
||||
- dashboards/svc-argocd.yaml
|
||||
- dashboards/svc-authentik.yaml
|
||||
- dashboards/svc-forgejo.yaml
|
||||
- dashboards/svc-grafana.yaml
|
||||
- dashboards/svc-minio.yaml
|
||||
- dashboards/svc-vault.yaml
|
||||
@@ -0,0 +1,140 @@
|
||||
# monitoring/prometheus-values.yaml
|
||||
# Chart: prometheus-community/kube-prometheus-stack
|
||||
# Release name: prometheus (affects all generated resource names)
|
||||
#
|
||||
# What this installs:
|
||||
# - Prometheus Operator (manages the Prometheus CRD)
|
||||
# - Prometheus StatefulSet (scrapes metrics, stores on Longhorn PVC)
|
||||
# - node-exporter DaemonSet (kernel CPU/RAM/disk/network per node)
|
||||
# - kube-state-metrics Deployment (K8s object state — pod resource requests, phases)
|
||||
#
|
||||
# What this deliberately omits:
|
||||
# - Grafana: already deployed in the logging namespace
|
||||
# - Alertmanager: enable later when you want Slack/PagerDuty routing
|
||||
# - kubeControllerManager / kubeScheduler / kubeEtcd: Talos only binds these
|
||||
# on 127.0.0.1 — the default ServiceMonitors can't reach them
|
||||
# - kubeProxy: removed cluster-wide; Cilium handles routing instead
|
||||
|
||||
# ── Grafana ───────────────────────────────────────────────────────────────────
|
||||
grafana:
|
||||
enabled: false
|
||||
|
||||
# ── Alertmanager ──────────────────────────────────────────────────────────────
|
||||
alertmanager:
|
||||
enabled: false
|
||||
|
||||
# ── Prometheus ────────────────────────────────────────────────────────────────
|
||||
prometheus:
|
||||
prometheusSpec:
|
||||
retention: 15d
|
||||
retentionSize: "18GB"
|
||||
|
||||
# scrapeTimeout MUST be <= scrapeInterval or the operator refuses to generate
|
||||
# the Prometheus config ("scrapeTimeout greater than scrapeInterval") and no
|
||||
# STS is created. Use a larger interval to keep the 60s timeout headroom.
|
||||
scrapeInterval: 60s
|
||||
scrapeTimeout: 60s
|
||||
evaluationInterval: 30s
|
||||
|
||||
# Pin to az-a (talos-cp-1) — sole Longhorn node; else the RWO PVC can't
|
||||
# attach on cp-2/cp-3 (CSINode lacks driver.longhorn.io).
|
||||
nodeSelector:
|
||||
topology.kubernetes.io/zone: az-a
|
||||
|
||||
# Persistent storage — metrics survive node reboots and pod restarts.
|
||||
# longhorn-wffc (WaitForFirstConsumer) binds after scheduling so the volume
|
||||
# lands on the node the pod runs on.
|
||||
storageSpec:
|
||||
volumeClaimTemplate:
|
||||
spec:
|
||||
storageClassName: longhorn-wffc
|
||||
accessModes: ["ReadWriteOnce"]
|
||||
resources:
|
||||
requests:
|
||||
storage: 20Gi
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 200m
|
||||
memory: 512Mi
|
||||
limits:
|
||||
cpu: 1000m
|
||||
memory: 1Gi
|
||||
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Exists
|
||||
effect: NoSchedule
|
||||
|
||||
# Match ServiceMonitors/PodMonitors from all namespaces, not just the ones
|
||||
# the chart itself creates. Required to scrape workloads in other namespaces.
|
||||
serviceMonitorSelectorNilUsesHelmValues: false
|
||||
podMonitorSelectorNilUsesHelmValues: false
|
||||
ruleSelectorNilUsesHelmValues: false
|
||||
|
||||
# ── Prometheus Operator ────────────────────────────────────────────────────────
|
||||
prometheusOperator:
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Exists
|
||||
effect: NoSchedule
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
limits:
|
||||
cpu: 200m
|
||||
memory: 256Mi
|
||||
|
||||
# ── node-exporter ─────────────────────────────────────────────────────────────
|
||||
# DaemonSet: one pod per node, reads /proc and /sys directly via hostPID.
|
||||
# These filesystem excludes prevent scrape errors on Talos's read-only overlayfs
|
||||
# mounts and containerd's ephemeral snapshot filesystems.
|
||||
nodeExporter:
|
||||
enabled: true
|
||||
|
||||
prometheus-node-exporter:
|
||||
extraArgs:
|
||||
- --collector.filesystem.mount-points-exclude=^/(dev|proc|run/credentials/.+|sys|var/lib/containerd/.+|var/lib/kubelet/.+|run/.+)($|/)
|
||||
- --collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$
|
||||
tolerations:
|
||||
- operator: Exists # schedule on every node regardless of taints
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 64Mi
|
||||
limits:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
|
||||
# ── kube-state-metrics ────────────────────────────────────────────────────────
|
||||
# Watches the K8s API; surfaces pod CPU/memory requests, deployment replica
|
||||
# counts, pod phase, etc. — the "are my workloads healthy?" layer.
|
||||
kubeStateMetrics:
|
||||
enabled: true
|
||||
|
||||
kube-state-metrics:
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Exists
|
||||
effect: NoSchedule
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 64Mi
|
||||
limits:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
|
||||
# ── Disable unreachable control-plane scrape targets ──────────────────────────
|
||||
kubeControllerManager:
|
||||
enabled: false
|
||||
|
||||
kubeScheduler:
|
||||
enabled: false
|
||||
|
||||
kubeEtcd:
|
||||
enabled: false
|
||||
|
||||
kubeProxy:
|
||||
enabled: false
|
||||
@@ -0,0 +1,37 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: argocd
|
||||
namespace: monitoring
|
||||
labels:
|
||||
release: kube-prometheus-stack
|
||||
spec:
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- cicd
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: argocd-metrics
|
||||
endpoints:
|
||||
- port: metrics
|
||||
interval: 30s
|
||||
scrapeTimeout: 10s
|
||||
---
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: argocd-server
|
||||
namespace: monitoring
|
||||
labels:
|
||||
release: kube-prometheus-stack
|
||||
spec:
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- cicd
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: argocd-server-metrics
|
||||
endpoints:
|
||||
- port: metrics
|
||||
interval: 30s
|
||||
scrapeTimeout: 10s
|
||||
@@ -0,0 +1,18 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: authentik
|
||||
namespace: monitoring
|
||||
labels:
|
||||
release: kube-prometheus-stack
|
||||
spec:
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- iam
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: authentik
|
||||
endpoints:
|
||||
- port: metrics
|
||||
interval: 30s
|
||||
scrapeTimeout: 10s
|
||||
@@ -0,0 +1,19 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: forgejo
|
||||
namespace: monitoring
|
||||
labels:
|
||||
release: kube-prometheus-stack
|
||||
spec:
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- cicd
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: gitea
|
||||
endpoints:
|
||||
- port: http
|
||||
path: /metrics
|
||||
interval: 30s
|
||||
scrapeTimeout: 10s
|
||||
@@ -0,0 +1,19 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: minio
|
||||
namespace: monitoring
|
||||
labels:
|
||||
release: kube-prometheus-stack
|
||||
spec:
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- storage
|
||||
selector:
|
||||
matchLabels:
|
||||
app: minio
|
||||
endpoints:
|
||||
- port: minio-api
|
||||
path: /minio/v2/metrics/cluster
|
||||
interval: 30s
|
||||
scrapeTimeout: 10s
|
||||
Reference in New Issue
Block a user