fluxcd : adding repo example with some apps
This commit is contained in:
@@ -0,0 +1,18 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
labels:
|
||||
release: prometheus
|
||||
name: alerts-flux.rules
|
||||
namespace: monitoring
|
||||
spec:
|
||||
groups:
|
||||
- name: Flux
|
||||
rules:
|
||||
- alert: ReconciliationFailure
|
||||
expr: max(gotk_reconcile_condition{status="False",type="Ready"}) by (exported_namespace, name, kind) + on(exported_namespace, name, kind) (max(gotk_reconcile_condition{status="Deleted"}) by (exported_namespace, name, kind)) * 2 == 1
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: '{{ $labels.kind }} {{ $labels.exported_namespace }}/{{ $labels.name }} reconciliation has been failing for more than ten minutes.'
|
||||
@@ -0,0 +1,397 @@
|
||||
---
|
||||
apiVersion: helm.toolkit.fluxcd.io/v2
|
||||
kind: HelmRelease
|
||||
metadata:
|
||||
name: prometheus
|
||||
spec:
|
||||
upgrade:
|
||||
remediation:
|
||||
retries: -1
|
||||
chart:
|
||||
spec:
|
||||
chart: kube-prometheus-stack
|
||||
version: "54.x.x"
|
||||
sourceRef:
|
||||
kind: HelmRepository
|
||||
name: prometheus-community
|
||||
namespace: infrastructure
|
||||
interval: 30m0s
|
||||
values:
|
||||
fullnameOverride: "prometheus"
|
||||
|
||||
## Create default rules for monitoring the cluster
|
||||
##
|
||||
defaultRules:
|
||||
create: true
|
||||
rules:
|
||||
etcd: false
|
||||
kubernetesSystem: false
|
||||
kubeScheduler: false
|
||||
kubeProxy: false
|
||||
configReloaders: true
|
||||
general: true
|
||||
k8s: true
|
||||
kubeApiserverAvailability: true
|
||||
kubeApiserverBurnrate: true
|
||||
kubeApiserverHistogram: true
|
||||
kubeApiserverSlos: true
|
||||
kubeControllerManager: true
|
||||
kubelet: true
|
||||
kubePrometheusGeneral: true
|
||||
kubePrometheusNodeRecording: true
|
||||
kubernetesApps: true
|
||||
kubernetesResources: true
|
||||
kubernetesStorage: true
|
||||
kubeSchedulerAlerting: true
|
||||
kubeSchedulerRecording: true
|
||||
kubeStateMetrics: true
|
||||
network: true
|
||||
node: true
|
||||
nodeExporterAlerting: true
|
||||
nodeExporterRecording: true
|
||||
prometheus: true
|
||||
prometheusOperator: true
|
||||
|
||||
global:
|
||||
rbac:
|
||||
create: true
|
||||
|
||||
alertmanager:
|
||||
enabled: true
|
||||
|
||||
config:
|
||||
global:
|
||||
resolve_timeout: 5m
|
||||
route:
|
||||
group_by:
|
||||
- job
|
||||
- alertname
|
||||
receiver: 'null'
|
||||
routes:
|
||||
- receiver: 'null'
|
||||
matchers:
|
||||
- alertname =~ "InfoInhibitor|Watchdog"
|
||||
receivers:
|
||||
- name: 'null'
|
||||
templates:
|
||||
- '/etc/alertmanager/config/*.tmpl'
|
||||
|
||||
serviceMonitor:
|
||||
interval: ""
|
||||
selfMonitor: true
|
||||
|
||||
|
||||
alertmanagerSpec:
|
||||
replicas: 1
|
||||
retention: 120h
|
||||
|
||||
storage: {}
|
||||
# volumeClaimTemplate:
|
||||
# spec:
|
||||
# storageClassName: gluster
|
||||
# accessModes: ["ReadWriteOnce"]
|
||||
# resources:
|
||||
# requests:
|
||||
# storage: 50Gi
|
||||
# selector: {}
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 64Mi
|
||||
limits:
|
||||
cpu: 501m
|
||||
memory: 64Mi
|
||||
|
||||
podAntiAffinity: "soft"
|
||||
podAntiAffinityTopologyKey: kubernetes.io/hostname
|
||||
|
||||
|
||||
grafana:
|
||||
enabled: false
|
||||
|
||||
kubeApiServer:
|
||||
enabled: true
|
||||
tlsConfig:
|
||||
# serverName: kubernetes
|
||||
insecureSkipVerify: true
|
||||
serviceMonitor:
|
||||
interval: ""
|
||||
proxyUrl: ""
|
||||
|
||||
kubelet:
|
||||
enabled: true
|
||||
namespace: kube-system
|
||||
|
||||
serviceMonitor:
|
||||
additionalLabels: {}
|
||||
cAdvisor: true
|
||||
cAdvisorMetricRelabelings:
|
||||
- action: drop
|
||||
regex: >-
|
||||
container_cpu_(load_average_10s|system_seconds_total|user_seconds_total)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: >-
|
||||
container_fs_(io_current|io_time_seconds_total|io_time_weighted_seconds_total|reads_merged_total|sector_reads_total|sector_writes_total|writes_merged_total)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: container_memory_(mapped_file|swap)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: container_(file_descriptors|tasks_state|threads_max)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: container_spec.*
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: .+;
|
||||
sourceLabels:
|
||||
- id
|
||||
- pod
|
||||
cAdvisorRelabelings:
|
||||
- sourceLabels:
|
||||
- __metrics_path__
|
||||
targetLabel: metrics_path
|
||||
https: true
|
||||
interval: ''
|
||||
metricRelabelings: []
|
||||
probes: true
|
||||
probesMetricRelabelings: []
|
||||
probesRelabelings:
|
||||
- sourceLabels:
|
||||
- __metrics_path__
|
||||
targetLabel: metrics_path
|
||||
proxyUrl: ''
|
||||
relabelings:
|
||||
- sourceLabels:
|
||||
- __metrics_path__
|
||||
targetLabel: metrics_path
|
||||
resource: false
|
||||
|
||||
kubeControllerManager:
|
||||
enabled: false
|
||||
|
||||
serviceMonitor:
|
||||
enabled: false
|
||||
interval: ""
|
||||
proxyUrl: ""
|
||||
https: null
|
||||
insecureSkipVerify: null
|
||||
serverName: null
|
||||
|
||||
coreDns:
|
||||
enabled: true
|
||||
service:
|
||||
port: 9153
|
||||
targetPort: 9153
|
||||
# selector:
|
||||
# k8s-app: kube-dns
|
||||
serviceMonitor:
|
||||
interval: ""
|
||||
|
||||
kubeDns:
|
||||
enabled: false
|
||||
|
||||
kubeEtcd:
|
||||
enabled: false
|
||||
|
||||
serviceMonitor:
|
||||
enabled: false
|
||||
interval: ""
|
||||
proxyUrl: ""
|
||||
scheme: http
|
||||
insecureSkipVerify: false
|
||||
|
||||
kubeScheduler:
|
||||
enabled: false
|
||||
|
||||
serviceMonitor:
|
||||
enabled: false
|
||||
interval: ""
|
||||
https: null
|
||||
insecureSkipVerify: null
|
||||
|
||||
kubeProxy:
|
||||
enabled: false
|
||||
|
||||
serviceMonitor:
|
||||
enabled: false
|
||||
interval: ""
|
||||
https: false
|
||||
|
||||
kubeStateMetrics:
|
||||
enabled: true
|
||||
|
||||
kube-state-metrics:
|
||||
prometheus:
|
||||
monitor:
|
||||
enabled: true
|
||||
interval: ""
|
||||
|
||||
selfMonitor:
|
||||
enabled: true
|
||||
|
||||
nodeExporter:
|
||||
enabled: true
|
||||
|
||||
prometheus-node-exporter:
|
||||
extraArgs:
|
||||
- --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/)
|
||||
- --collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$
|
||||
prometheus:
|
||||
monitor:
|
||||
enabled: true
|
||||
interval: ""
|
||||
|
||||
prometheusOperator:
|
||||
enabled: true
|
||||
|
||||
serviceMonitor:
|
||||
interval: ""
|
||||
scrapeTimeout: ""
|
||||
selfMonitor: true
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 125m
|
||||
memory: 128Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 128Mi
|
||||
|
||||
# Required for use in managed kubernetes clusters (such as AWS EKS) with custom CNI (such as calico),
|
||||
# because control-plane managed by AWS cannot communicate with pods' IP CIDR and admission webhooks are not working
|
||||
##
|
||||
hostNetwork: false
|
||||
|
||||
dnsConfig: {}
|
||||
# nameservers:
|
||||
# - 1.2.3.4
|
||||
# searches:
|
||||
# - ns1.svc.cluster-domain.example
|
||||
# - my.dns.search.suffix
|
||||
# options:
|
||||
# - name: ndots
|
||||
# value: "2"
|
||||
# - name: edns0
|
||||
|
||||
# Enable vertical pod autoscaler support for prometheus-operator
|
||||
verticalPodAutoscaler:
|
||||
enabled: false
|
||||
# List of resources that the vertical pod autoscaler can control. Defaults to cpu and memory
|
||||
controlledResources: []
|
||||
|
||||
# Define the max allowed resources for the pod
|
||||
maxAllowed: {}
|
||||
# cpu: 200m
|
||||
# memory: 100Mi
|
||||
# Define the min allowed resources for the pod
|
||||
minAllowed: {}
|
||||
# cpu: 200m
|
||||
# memory: 100Mi
|
||||
|
||||
updatePolicy:
|
||||
# Specifies whether recommended updates are applied when a Pod is started and whether recommended updates
|
||||
# are applied during the life of a Pod. Possible values are "Off", "Initial", "Recreate", and "Auto".
|
||||
updateMode: Auto
|
||||
|
||||
prometheusConfigReloader:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 35Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 1024Mi
|
||||
|
||||
prometheus:
|
||||
enabled: true
|
||||
|
||||
thanosService:
|
||||
enabled: false
|
||||
|
||||
thanosServiceMonitor:
|
||||
enabled: false
|
||||
interval: ""
|
||||
|
||||
thanosServiceExternal:
|
||||
enabled: false
|
||||
|
||||
podDisruptionBudget:
|
||||
enabled: true
|
||||
minAvailable: 1
|
||||
maxUnavailable: ""
|
||||
|
||||
ingress:
|
||||
enabled: false
|
||||
ingressClassName: nginx
|
||||
# hosts:
|
||||
# - prometheus.domain.com
|
||||
hosts: []
|
||||
|
||||
## Paths to use for ingress rules - one path should match the prometheusSpec.routePrefix
|
||||
##
|
||||
paths: []
|
||||
# - /
|
||||
|
||||
pathType: Prefix
|
||||
|
||||
serviceMonitor:
|
||||
interval: ""
|
||||
selfMonitor: true
|
||||
|
||||
prometheusSpec:
|
||||
## If true, pass --storage.tsdb.max-block-duration=2h to prometheus. This is already done if using Thanos
|
||||
##
|
||||
disableCompaction: false
|
||||
scrapeInterval: "15s"
|
||||
scrapeTimeout: "10s"
|
||||
evaluationInterval: "1m"
|
||||
enableAdminAPI: false
|
||||
priorityClassName: "system-cluster-critical"
|
||||
|
||||
remoteWrite:
|
||||
- url: https://mimir.example.com/api/v1/push
|
||||
ruleNamespaceSelector: {}
|
||||
ruleSelectorNilUsesHelmValues: false
|
||||
ruleSelector: {}
|
||||
serviceMonitorSelectorNilUsesHelmValues: false
|
||||
serviceMonitorSelector: {}
|
||||
serviceMonitorNamespaceSelector: {}
|
||||
podMonitorSelectorNilUsesHelmValues: false
|
||||
podMonitorSelector: {}
|
||||
podMonitorNamespaceSelector: {}
|
||||
probeSelectorNilUsesHelmValues: true
|
||||
probeSelector: {}
|
||||
probeNamespaceSelector: {}
|
||||
|
||||
retention: 1d
|
||||
retentionSize: "25GiB"
|
||||
|
||||
## Enable compression of the write-ahead log using Snappy.
|
||||
##
|
||||
walCompression: false
|
||||
|
||||
replicas: 1
|
||||
|
||||
podAntiAffinity: "soft"
|
||||
podAntiAffinityTopologyKey: kubernetes.io/hostname
|
||||
|
||||
resources:
|
||||
limits:
|
||||
cpu: 2000m
|
||||
memory: 6000Mi
|
||||
requests:
|
||||
cpu: 900m
|
||||
memory: 6000Mi
|
||||
|
||||
thanos: {}
|
||||
# objectStorageConfig:
|
||||
# key: objstore.yml
|
||||
# name: thanos-objstore-config
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: infrastructure
|
||||
resources:
|
||||
- hr-kube-prometheus-stack.yaml
|
||||
34
fluxcd/repo/infrastructure/base/prometheus/dependencies.yaml
Normal file
34
fluxcd/repo/infrastructure/base/prometheus/dependencies.yaml
Normal file
@@ -0,0 +1,34 @@
|
||||
apiVersion: kustomize.toolkit.fluxcd.io/v1
|
||||
kind: Kustomization
|
||||
metadata:
|
||||
name: inf-prometheus-core
|
||||
namespace: infrastructure
|
||||
spec:
|
||||
interval: 5m
|
||||
path: ./infrastructure/base/prometheus/core
|
||||
prune: true
|
||||
sourceRef:
|
||||
kind: GitRepository
|
||||
name: flux-system
|
||||
namespace: flux-system
|
||||
healthChecks:
|
||||
- apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
name: prometheus-operator
|
||||
namespace: infrastructure
|
||||
---
|
||||
apiVersion: kustomize.toolkit.fluxcd.io/v1
|
||||
kind: Kustomization
|
||||
metadata:
|
||||
name: inf-prometheus-resources
|
||||
namespace: infrastructure
|
||||
spec:
|
||||
dependsOn:
|
||||
- name: inf-prometheus-core
|
||||
interval: 5m
|
||||
path: ./infrastructure/base/prometheus/resources
|
||||
prune: true
|
||||
sourceRef:
|
||||
kind: GitRepository
|
||||
name: flux-system
|
||||
namespace: flux-system
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: infrastructure
|
||||
resources:
|
||||
- dependencies.yaml
|
||||
@@ -0,0 +1,24 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PodMonitor
|
||||
metadata:
|
||||
name: flux-system
|
||||
labels:
|
||||
app.kubernetes.io/part-of: flux
|
||||
release: prometheus
|
||||
spec:
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- flux-system
|
||||
selector:
|
||||
matchExpressions:
|
||||
- key: app
|
||||
operator: In
|
||||
values:
|
||||
- helm-controller
|
||||
- source-controller
|
||||
- kustomize-controller
|
||||
- notification-controller
|
||||
- image-automation-controller
|
||||
- image-reflector-controller
|
||||
podMetricsEndpoints:
|
||||
- port: http-prom
|
||||
@@ -0,0 +1,15 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: http-broadcaster
|
||||
spec:
|
||||
endpoints:
|
||||
- interval: 30s
|
||||
port: web
|
||||
scheme: http
|
||||
scrapeTimeout: 29s
|
||||
namespaceSelector:
|
||||
any: true
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: "http-broadcaster"
|
||||
@@ -0,0 +1,10 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: infrastructure
|
||||
resources:
|
||||
- flux-podmonitor.yaml
|
||||
- php-fpm-exporters-servicemonitor.yaml
|
||||
- rabbitmq-servicemonitor.yaml
|
||||
- python-metrics-servicemonitor.yaml
|
||||
- php-metrics-servicemonitor.yaml
|
||||
- http-broadcaster-servicemonitor.yaml
|
||||
@@ -0,0 +1,15 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: php-fpm-exporters
|
||||
spec:
|
||||
endpoints:
|
||||
- interval: 15s
|
||||
port: php-fpm-exporter
|
||||
scheme: http
|
||||
scrapeTimeout: 14s
|
||||
namespaceSelector:
|
||||
any: true
|
||||
selector:
|
||||
matchLabels:
|
||||
k8s.example.com/php-fpm-exporter-scrape: 'true'
|
||||
@@ -0,0 +1,16 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: php-metrics
|
||||
spec:
|
||||
endpoints:
|
||||
- interval: 15s
|
||||
port: php-metrics
|
||||
path: /metrics
|
||||
scheme: http
|
||||
scrapeTimeout: 14s
|
||||
namespaceSelector:
|
||||
any: true
|
||||
selector:
|
||||
matchLabels:
|
||||
k8s.example.com/php-metrics-scrape: 'true'
|
||||
@@ -0,0 +1,16 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: python-metrics
|
||||
spec:
|
||||
endpoints:
|
||||
- interval: 15s
|
||||
port: metrics
|
||||
path: /metrics
|
||||
scheme: http
|
||||
scrapeTimeout: 14s
|
||||
namespaceSelector:
|
||||
any: true
|
||||
selector:
|
||||
matchLabels:
|
||||
k8s.example.com/python-metrics-scrape: 'true'
|
||||
@@ -0,0 +1,42 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: rabbitmq
|
||||
namespace: rabbitmq-operator
|
||||
spec:
|
||||
endpoints:
|
||||
- port: prometheus
|
||||
scheme: http
|
||||
interval: 15s
|
||||
scrapeTimeout: 14s
|
||||
- port: prometheus-tls
|
||||
scheme: https
|
||||
interval: 15s
|
||||
scrapeTimeout: 14s
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
- port: prometheus
|
||||
scheme: http
|
||||
path: /metrics/detailed
|
||||
params:
|
||||
family:
|
||||
- queue_coarse_metrics
|
||||
- queue_metrics
|
||||
interval: 15s
|
||||
scrapeTimeout: 14s
|
||||
- port: prometheus-tls
|
||||
scheme: https
|
||||
path: /metrics/detailed
|
||||
params:
|
||||
family:
|
||||
- queue_coarse_metrics
|
||||
- queue_metrics
|
||||
interval: 15s
|
||||
scrapeTimeout: 14s
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: rabbitmq
|
||||
namespaceSelector:
|
||||
any: true
|
||||
Reference in New Issue
Block a user