fluxcd: add prometheus
This commit is contained in:
Márcio Fernandes
@@ -1,8 +1,6 @@
|
||||
# Prometheus Setup
|
||||
|
||||
- <https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack>
|
||||
- <https://github.com/prometheus-community/helm-charts/blob/main/charts/kube-prometheus-stack/values.yaml>
|
||||
|
||||
|
||||
## helm chart
|
||||
|
||||
```bash
|
||||
|
||||
@@ -1,55 +0,0 @@
|
||||
# values.yaml to install only Prometheus Operator and CRDs
|
||||
|
||||
# Disable all components except the operator
|
||||
defaultRules:
|
||||
create: false
|
||||
|
||||
alertmanager:
|
||||
enabled: false
|
||||
|
||||
grafana:
|
||||
enabled: false
|
||||
|
||||
kubeStateMetrics:
|
||||
enabled: false
|
||||
|
||||
nodeExporter:
|
||||
enabled: false
|
||||
|
||||
prometheus:
|
||||
enabled: false
|
||||
|
||||
coreDns:
|
||||
enabled: false
|
||||
|
||||
kubeControllerManager:
|
||||
enabled: false
|
||||
|
||||
kubeEtcd:
|
||||
enabled: false
|
||||
|
||||
kubeProxy:
|
||||
enabled: false
|
||||
|
||||
kubeScheduler:
|
||||
enabled: false
|
||||
|
||||
prometheusOperator:
|
||||
enabled: true
|
||||
createCustomResource: true
|
||||
tls:
|
||||
enabled: false
|
||||
admissionWebhooks:
|
||||
enabled: false
|
||||
cleanupCustomResource: false
|
||||
serviceMonitor:
|
||||
selfMonitor: false
|
||||
kubeletService:
|
||||
enabled: true
|
||||
# requires manual creation of service #prom-kublet-service
|
||||
nodeSelector:
|
||||
role: worker-node
|
||||
|
||||
# global:
|
||||
# nodeSelector:
|
||||
# dedicated: worker-node
|
||||
@@ -1,36 +0,0 @@
|
||||
kubeStateMetrics:
|
||||
enabled: true
|
||||
|
||||
kube-state-metrics: # ok tested!
|
||||
podLabels:
|
||||
role: worker-node
|
||||
nodeSelector:
|
||||
role: worker-node
|
||||
prometheus:
|
||||
monitor:
|
||||
interval: "60s"
|
||||
relabelings:
|
||||
- targetLabel: cluster
|
||||
replacement: casa
|
||||
additionalLabels:
|
||||
app.kubernetes.io/name: prometheus-kube-state-metrics # !important: selector used by agent
|
||||
|
||||
|
||||
coreDns: # ok tested!
|
||||
enabled: true
|
||||
serviceMonitor:
|
||||
relabelings:
|
||||
- targetLabel: cluster
|
||||
replacement: casa
|
||||
additionalLabels:
|
||||
app.kubernetes.io/name: prometheus-stack-coredns # !important: selector used by agent
|
||||
|
||||
kubeApiServer: # ok tested!
|
||||
enabled: true
|
||||
serviceMonitor:
|
||||
relabelings:
|
||||
- targetLabel: cluster
|
||||
replacement: casa
|
||||
additionalLabels:
|
||||
app.kubernetes.io/name: prometheus-stack-apiserver # !important: selector used by agent
|
||||
|
||||
@@ -1,25 +0,0 @@
|
||||
# Deploy node exporter as a daemonset to all nodes
|
||||
nodeExporter:
|
||||
enabled: true
|
||||
|
||||
|
||||
# job node exporter
|
||||
prometheus-node-exporter:
|
||||
prometheus:
|
||||
monitor:
|
||||
enabled: true
|
||||
interval: "60s"
|
||||
relabelings:
|
||||
# https://github.com/dotdc/grafana-dashboards-kubernetes
|
||||
- action: replace
|
||||
sourceLabels: [__meta_kubernetes_pod_node_name]
|
||||
targetLabel: nodename
|
||||
|
||||
# identification of cluster
|
||||
- targetLabel: cluster
|
||||
replacement: casa
|
||||
|
||||
# it seams to be an timestamp can not be an label!
|
||||
- action: labeldrop
|
||||
regex: __meta_kubernetes_endpoints_annotation_endpoints_kubernetes_io_last_change_trigger_time
|
||||
|
||||
@@ -1,78 +0,0 @@
|
||||
# Used file to testing new options and configurations
|
||||
# Should be the laste file to be loaded
|
||||
kubelet:
|
||||
enabled: true
|
||||
namespace: kube-system
|
||||
serviceMonitor:
|
||||
interval: 60s #WARN: Error on ingesting out-of-order samples. https://github.com/prometheus-community/helm-charts/issues/5483
|
||||
enabled: true
|
||||
## Enable scraping /metrics from kubelet's service
|
||||
kubelet: true
|
||||
cAdvisor: true
|
||||
additionalLabels:
|
||||
app.kubernetes.io/name: prometheus-kubelet # !important: selector used by agent
|
||||
|
||||
probesMetricRelabelings:
|
||||
- targetLabel: cluster
|
||||
replacement: casa
|
||||
|
||||
- sourceLabels: [__name__, image]
|
||||
separator: ;
|
||||
regex: container_([a-z_]+);
|
||||
replacement: $1
|
||||
action: drop
|
||||
- sourceLabels: [__name__]
|
||||
separator: ;
|
||||
regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s)
|
||||
replacement: $1
|
||||
action: drop
|
||||
|
||||
|
||||
# # RelabelConfigs to apply to samples before scraping
|
||||
# # ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
|
||||
# #
|
||||
# # metrics_path is required to match upstream rules and charts
|
||||
cAdvisorRelabelings:
|
||||
|
||||
- targetLabel: cluster
|
||||
replacement: casa
|
||||
|
||||
- action: replace
|
||||
sourceLabels: [__metrics_path__]
|
||||
targetLabel: metrics_path
|
||||
- sourceLabels: [__meta_kubernetes_pod_node_name]
|
||||
separator: ;
|
||||
regex: ^(.*)$
|
||||
targetLabel: nodename
|
||||
replacement: $1
|
||||
action: replace
|
||||
|
||||
# # RelabelConfigs to apply to samples before scraping
|
||||
# # ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
|
||||
# #
|
||||
probesRelabelings:
|
||||
|
||||
|
||||
- targetLabel: cluster
|
||||
replacement: casa
|
||||
|
||||
- action: replace
|
||||
sourceLabels: [__metrics_path__]
|
||||
targetLabel: metrics_path
|
||||
|
||||
- sourceLabels: [__meta_kubernetes_pod_node_name]
|
||||
separator: ;
|
||||
regex: ^(.*)$
|
||||
targetLabel: nodename
|
||||
replacement: $1
|
||||
action: replace
|
||||
|
||||
resourceRelabelings:
|
||||
|
||||
- targetLabel: cluster
|
||||
replacement: casa
|
||||
|
||||
- action: replace
|
||||
sourceLabels: [__metrics_path__]
|
||||
targetLabel: metrics_path
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
# use for testing
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,72 +0,0 @@
|
||||
|
||||
apiVersion: monitoring.coreos.com/v1alpha1
|
||||
kind: PrometheusAgent
|
||||
metadata:
|
||||
name: prometheus-agent
|
||||
namespace: monitoring
|
||||
spec:
|
||||
|
||||
podMonitorSelector: null
|
||||
podMonitorNamespaceSelector: null
|
||||
serviceMonitorNamespaceSelector:
|
||||
matchLabels:
|
||||
prometheus-monitoring: enabled
|
||||
|
||||
serviceMonitorSelector:
|
||||
matchLabels:
|
||||
release: prometheus-stack
|
||||
|
||||
replicas: 1
|
||||
remoteWrite:
|
||||
- url: https://prometheus.monitoring.limbosolutions.com/api/v1/write
|
||||
scrapeInterval: 60s
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
limits:
|
||||
cpu: 200m
|
||||
memory: 300Mi
|
||||
serviceAccountName: prometheus-agent
|
||||
nodeSelector:
|
||||
role: worker-node
|
||||
---
|
||||
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
name: prometheus-agent
|
||||
rules:
|
||||
- apiGroups: [""]
|
||||
resources: ["nodes", "nodes/metrics", "nodes/proxy", "services", "endpoints", "pods"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
- apiGroups: ["monitoring.coreos.com"]
|
||||
resources: ["servicemonitors", "podmonitors"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
- nonResourceURLs:
|
||||
- /metrics
|
||||
- /metrics/cadvisor
|
||||
- /metrics/probes
|
||||
verbs: ["get"]
|
||||
---
|
||||
|
||||
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
name: prometheus-agent-monitoring
|
||||
roleRef:
|
||||
kind: ClusterRole
|
||||
name: prometheus-agent
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-agent
|
||||
namespace: monitoring
|
||||
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: prometheus-agent
|
||||
namespace: monitoring
|
||||
Reference in New Issue
Block a user