jhlim
/
nd002test
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

prometheus, nfs-provisioner add

This commit is contained in:
sdjo 2024-10-08 17:10:19 +09:00
parent 4692a443c5
commit ef3be802c6
20 changed files with 3095 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

101
on-premise/nfs-provisioner/1.configuration/init_add_ns.yaml Normal file
View File

@ -0,0 +1,101 @@
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
name: provision
name: nfs-pod-provisioner-sa
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
labels:
name: provision
name: nfs-pod-provisioner-otherRoles
namespace: kube-system
rules:
- apiGroups:
- ""
resources:
- endpoints
verbs:
- get
- list
- watch
- create
- update
- patch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
name: provision
name: nfs-provisioner-clusterRole
rules:
- apiGroups:
- ""
resources:
- persistentvolumes
verbs:
- get
- list
- watch
- create
- delete
- apiGroups:
- ""
resources:
- persistentvolumeclaims
verbs:
- get
- list
- watch
- update
- apiGroups:
- storage.k8s.io
resources:
- storageclasses
verbs:
- get
- list
- watch
- apiGroups:
- ""
resources:
- events
verbs:
- create
- update
- patch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
labels:
name: provision
name: nfs-pod-provisioner-otherRoles
namespace: kube-system
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: nfs-pod-provisioner-otherRoles
subjects:
- kind: ServiceAccount
name: nfs-pod-provisioner-sa
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
name: provision
name: nfs-provisioner-rolebinding
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: nfs-provisioner-clusterRole
subjects:
- kind: ServiceAccount
name: nfs-pod-provisioner-sa
namespace: kube-system

38
on-premise/nfs-provisioner/3.deploy/sample-deploy.yaml Normal file
View File

@ -0,0 +1,38 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: vm-nfs
namespace: kube-system
labels:
name: provision
spec:
replicas: 1
selector:
matchLabels:
app: vm-nfs
strategy:
type: Recreate
template:
metadata:
labels:
app: vm-nfs
spec:
serviceAccountName: nfs-pod-provisioner-sa
containers:
- name: nfs-client-provisioner
image: k8s.gcr.io/sig-storage/nfs-subdir-external-provisioner:v4.0.2 # provisioner를 구성하는 image
volumeMounts:
- name: nfs-provisioner
mountPath: /persistentvolumes
env:
- name: PROVISIONER_NAME
value: vm-nfs # SC에서 provisioner의 이름으로 사용
- name: NFS_SERVER
value: 192.168.0.211
- name: NFS_PATH
value: /nfs # nfs 연결 주소
volumes:
- name: nfs-provisioner
nfs:
server: 192.168.0.211
path: /nfs

15
on-premise/nfs-provisioner/4.postSettings/sc-vm.yaml Normal file
View File

@ -0,0 +1,15 @@
apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
name: vm-nfs # pvc에서 사용할 SC Name
annotations:
storageclass.kubernetes.io/is-default-class: "true"
labels:
name: provision
provisioner: vm-nfs # provisioner에서 생성한 PROVISIONER_NAME
parameters:
#pathPattern: "${.PVC.namespace}/${.PVC.annotations.nfs.io/storage-path}" # waits for nfs.io/storage-path annotation, if not specified will accept as empty string.
onDelete: Retain
#onDelete: delete
archiveOnDelete: "false"
reclaimPolicy: Retain

13
on-premise/prometheusAlertManager/1_configuration/init.yaml Normal file
View File

@ -0,0 +1,13 @@
# Source: prometheus/charts/alertmanager/templates/serviceaccount.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: prometheus-alertmanager
labels:
helm.sh/chart: alertmanager-1.12.0
app.kubernetes.io/name: alertmanager
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "v0.27.0"
app.kubernetes.io/managed-by: Helm
namespace: monitoring
automountServiceAccountToken: true

17
on-premise/prometheusAlertManager/1_configuration/pvc.yaml Normal file
View File

@ -0,0 +1,17 @@
# Source: prometheus/templates/pvc.yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
labels:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
app.kubernetes.io/part-of: prometheus
name: prometheus-alert
namespace: monitoring
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: "2Gi"

24
on-premise/prometheusAlertManager/2_config/default.yaml Normal file
View File

@ -0,0 +1,24 @@
# Source: prometheus/charts/alertmanager/templates/configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-alertmanager
labels:
helm.sh/chart: alertmanager-1.12.0
app.kubernetes.io/name: alertmanager
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "v0.27.0"
app.kubernetes.io/managed-by: Helm
namespace: monitoring
data:
alertmanager.yml: |
global: {}
receivers:
- name: default-receiver
route:
group_interval: 5m
group_wait: 10s
receiver: default-receiver
repeat_interval: 3h
templates:
- /etc/alertmanager/*.tmpl

99
on-premise/prometheusAlertManager/3_deploy/deploy.yaml Normal file
View File

@ -0,0 +1,99 @@
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app.kubernetes.io/instance: prometheus
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/name: alertmanager
app.kubernetes.io/version: v0.27.0
helm.sh/chart: alertmanager-1.12.0
name: prometheus-alertmanager
namespace: monitoring
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/instance: prometheus
app.kubernetes.io/name: alertmanager
template:
metadata:
labels:
app.kubernetes.io/instance: prometheus
app.kubernetes.io/name: alertmanager
spec:
automountServiceAccountToken: true
containers:
- args:
- --storage.path=/alertmanager
- --config.file=/etc/alertmanager/alertmanager.yml
env:
- name: POD_IP
valueFrom:
fieldRef:
apiVersion: v1
fieldPath: status.podIP
image: quay.io/prometheus/alertmanager:v0.27.0
imagePullPolicy: IfNotPresent
livenessProbe:
httpGet:
path: /
port: http
name: alertmanager
ports:
- containerPort: 9093
name: http
protocol: TCP
readinessProbe:
httpGet:
path: /
port: http
resources:
limits:
cpu: 200m
memory: 512Mi
securityContext:
runAsGroup: 65534
runAsNonRoot: true
runAsUser: 65534
volumeMounts:
- mountPath: /etc/alertmanager
name: config
- mountPath: /alertmanager
name: storage
securityContext:
fsGroup: 65534
runAsGroup: 65534
runAsNonRoot: true
runAsUser: 65534
serviceAccountName: prometheus-alertmanager
volumes:
- configMap:
defaultMode: 420
name: prometheus-alertmanager
name: config
- name: storage
persistentVolumeClaim:
claimName: prometheus-alert
---
# Source: prometheus/charts/alertmanager/templates/services.yaml
apiVersion: v1
kind: Service
metadata:
name: prometheus-alertmanager
labels:
helm.sh/chart: alertmanager-1.12.0
app.kubernetes.io/name: alertmanager
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "v0.27.0"
app.kubernetes.io/managed-by: Helm
namespace: monitoring
spec:
type: ClusterIP
ports:
- port: 9093
targetPort: http
protocol: TCP
name: http
selector:
app.kubernetes.io/name: alertmanager
app.kubernetes.io/instance: prometheus

26
on-premise/prometheusAlertManager/3_deploy/ing.yaml Normal file
View File

@ -0,0 +1,26 @@
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: ing-alertmanager
namespace: monitoring
annotations:
# 인증 방법 설정: basic auth
nginx.ingress.kubernetes.io/auth-type: basic
# basic auth 사용자가 들어있는 secret 설정
nginx.ingress.kubernetes.io/auth-secret: basic-auth
# 인증 요청시 나오는 메세지 설정
nginx.ingress.kubernetes.io/auth-realm: 'Authentication Required - admin'
spec:
ingressClassName: nginx
rules:
- host: alert.icurfer.com
http:
paths:
- backend:
service:
name: prometheus-alertmanager
port:
number: 9093
path: /
pathType: Prefix

313
on-premise/prometheus_2.54.1/1_configuration/init.yaml Normal file
View File

@ -0,0 +1,313 @@
# Source: prometheus/charts/kube-state-metrics/templates/serviceaccount.yaml
apiVersion: v1
kind: ServiceAccount
automountServiceAccountToken: true
metadata:
labels:
helm.sh/chart: kube-state-metrics-5.25.1
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: metrics
app.kubernetes.io/part-of: kube-state-metrics
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "2.13.0"
name: prometheus-kube-state-metrics
namespace: monitoring
---
# Source: prometheus/charts/prometheus-node-exporter/templates/serviceaccount.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: prometheus-prometheus-node-exporter
namespace: monitoring
labels:
helm.sh/chart: prometheus-node-exporter-4.39.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: metrics
app.kubernetes.io/part-of: prometheus-node-exporter
app.kubernetes.io/name: prometheus-node-exporter
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "1.8.2"
automountServiceAccountToken: false
---
# Source: prometheus/charts/prometheus-pushgateway/templates/serviceaccount.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
helm.sh/chart: prometheus-pushgateway-2.14.0
app.kubernetes.io/name: prometheus-pushgateway
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "v1.9.0"
app.kubernetes.io/managed-by: Helm
name: prometheus-prometheus-pushgateway
namespace: monitoring
automountServiceAccountToken: true
---
# Source: prometheus/templates/serviceaccount.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: v2.54.1
helm.sh/chart: prometheus-25.27.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/part-of: prometheus
name: prometheus-server
namespace: monitoring
annotations:
{}
---
# Source: prometheus/charts/kube-state-metrics/templates/role.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
helm.sh/chart: kube-state-metrics-5.25.1
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: metrics
app.kubernetes.io/part-of: kube-state-metrics
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "2.13.0"
name: prometheus-kube-state-metrics
rules:
- apiGroups: ["certificates.k8s.io"]
resources:
- certificatesigningrequests
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- configmaps
verbs: ["list", "watch"]
- apiGroups: ["batch"]
resources:
- cronjobs
verbs: ["list", "watch"]
- apiGroups: ["extensions", "apps"]
resources:
- daemonsets
verbs: ["list", "watch"]
- apiGroups: ["extensions", "apps"]
resources:
- deployments
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- endpoints
verbs: ["list", "watch"]
- apiGroups: ["autoscaling"]
resources:
- horizontalpodautoscalers
verbs: ["list", "watch"]
- apiGroups: ["extensions", "networking.k8s.io"]
resources:
- ingresses
verbs: ["list", "watch"]
- apiGroups: ["batch"]
resources:
- jobs
verbs: ["list", "watch"]
- apiGroups: ["coordination.k8s.io"]
resources:
- leases
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- limitranges
verbs: ["list", "watch"]
- apiGroups: ["admissionregistration.k8s.io"]
resources:
- mutatingwebhookconfigurations
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- namespaces
verbs: ["list", "watch"]
- apiGroups: ["networking.k8s.io"]
resources:
- networkpolicies
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- nodes
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- persistentvolumeclaims
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- persistentvolumes
verbs: ["list", "watch"]
- apiGroups: ["policy"]
resources:
- poddisruptionbudgets
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- pods
verbs: ["list", "watch"]
- apiGroups: ["extensions", "apps"]
resources:
- replicasets
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- replicationcontrollers
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- resourcequotas
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- secrets
verbs: ["list", "watch"]
- apiGroups: [""]
resources:
- services
verbs: ["list", "watch"]
- apiGroups: ["apps"]
resources:
- statefulsets
verbs: ["list", "watch"]
- apiGroups: ["storage.k8s.io"]
resources:
- storageclasses
verbs: ["list", "watch"]
- apiGroups: ["admissionregistration.k8s.io"]
resources:
- validatingwebhookconfigurations
verbs: ["list", "watch"]
- apiGroups: ["storage.k8s.io"]
resources:
- volumeattachments
verbs: ["list", "watch"]
---
# Source: prometheus/templates/clusterrole.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: v2.54.1
helm.sh/chart: prometheus-25.27.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/part-of: prometheus
name: prometheus-server
rules:
- apiGroups:
- ""
resources:
- nodes
- nodes/proxy
- nodes/metrics
- services
- endpoints
- pods
- ingresses
- configmaps
verbs:
- get
- list
- watch
- apiGroups:
- "extensions"
- "networking.k8s.io"
resources:
- ingresses/status
- ingresses
verbs:
- get
- list
- watch
- apiGroups:
- "discovery.k8s.io"
resources:
- endpointslices
verbs:
- get
- list
- watch
- nonResourceURLs:
- "/metrics"
verbs:
- get
---
# Source: prometheus/charts/kube-state-metrics/templates/clusterrolebinding.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
helm.sh/chart: kube-state-metrics-5.25.1
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: metrics
app.kubernetes.io/part-of: kube-state-metrics
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "2.13.0"
name: prometheus-kube-state-metrics
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: prometheus-kube-state-metrics
subjects:
- kind: ServiceAccount
name: prometheus-kube-state-metrics
namespace: monitoring
---
# Source: prometheus/templates/clusterrolebinding.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: v2.54.1
helm.sh/chart: prometheus-25.27.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/part-of: prometheus
name: prometheus-server
subjects:
- kind: ServiceAccount
name: prometheus-server
namespace: monitoring
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: prometheus-server

20
on-premise/prometheus_2.54.1/1_configuration/pvc.yaml Normal file
View File

@ -0,0 +1,20 @@
# Source: prometheus/templates/pvc.yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
labels:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: v2.54.1
helm.sh/chart: prometheus-25.27.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/part-of: prometheus
name: prometheus-server
namespace: monitoring
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: "8Gi"

194
on-premise/prometheus_2.54.1/2_config/cm_prometheus-rulefiles-default.yaml Normal file
View File

@ -0,0 +1,194 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-rulefiles
namespace: monitoring
data:
# Awesome Prometheus alerts
################################################################################
# Basic resource monitoring prometheus self-monitoring
################################################################################
prometheus-self-monitoring.yaml: |
groups:
- name: prometheus-self-monitoring
rules:
- alert: Watchdog
annotations:
description: |
This is an alert meant to ensure that the entire alerting pipeline is functional.
This alert is always firing, therefore it should always be firing in Alertmanager
and always fire against a receiver. There are integrations with various notification
mechanisms that send a notification when this alert is not firing. For example the
"DeadMansSnitch" integration in PagerDuty.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog
summary: An alert that should always be firing to certify that Alertmanager
is working properly.
expr: vector(1)
labels:
severity: none
# Awesome Prometheus alerts
################################################################################
# Basic resource monitoring host and hardware (node-export)
################################################################################
prometheus-host-hardware.yaml: |
groups:
- name: prometheus-host-hardware
rules:
- alert: HostOutOfMemory (1.2.01)
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
for: 2m
labels:
severity: warning
annotations:
summary: Host out of memory (instance {{ $labels.instance }})
description: "Node memory is filling up (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostOutOfDiskSpace (1.2.07)
expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
for: 2m
labels:
severity: warning
annotations:
summary: Host out of disk space (instance {{ $labels.instance }})
description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Please add ignored mountpoints in node_exporter parameters like
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
# Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
- alert: HostHighCpuLoad (1.2.13)
expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80
for: 0m
labels:
severity: warning
annotations:
summary: Host high CPU load (instance {{ $labels.instance }})
description: "CPU load is > 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostOomKillDetected (1.2.24)
expr: increase(node_vmstat_oom_kill[1m]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Host OOM kill detected (instance {{ $labels.instance }})
description: "OOM kill detected\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Awesome Prometheus alerts
################################################################################
# Basic resource monitoring docker container (google/cAdvisor)
################################################################################
Prometheus-docker-containers.yaml: |
groups:
- name: prometheus-docker-containers
rules:
# This rule can be very noisy in dynamic infra with legitimate container start/stop/deployment.
- alert: ContainerKilled (1.3.1)
expr: time() - container_last_seen > 60
for: 0m
labels:
severity: warning
annotations:
summary: Container killed (instance {{ $labels.instance }})
description: "A container has disappeared\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# This rule can be very noisy in dynamic infra with legitimate container start/stop/deployment.
- alert: ContainerCpuUsage (1.3.3)
expr: (sum(rate(container_cpu_usage_seconds_total{name!=""}[3m])) BY (instance, name) * 100) > 80
for: 2m
labels:
severity: warning
annotations:
summary: Container CPU usage (instance {{ $labels.instance }})
description: "Container CPU usage is above 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# See https://medium.com/faun/how-much-is-too-much-the-linux-oomkiller-and-used-memory-d32186f29c9d
- alert: ContainerMemoryUsage (1.3.4)
expr: (sum(container_memory_working_set_bytes{name!=""}) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) > 80
for: 2m
labels:
severity: warning
annotations:
summary: Container Memory usage (instance {{ $labels.instance }})
description: "Container Memory usage is above 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Awesome Prometheus alerts
################################################################################
# Orchestrators kubernetes (kube-state-metrics)
################################################################################
prometheus-kubernetes.yaml: |
groups:
- name: prometheus-kubernetes
rules:
- alert: KubernetesNodeReady (5.1.01)
expr: kube_node_status_condition{condition="Ready",status="true"} == 0
for: 10m
labels:
severity: critical
annotations:
summary: Kubernetes Node ready (instance {{ $labels.instance }})
description: "Node {{ $labels.node }} has been unready for a long time\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesOutOfDisk (5.1.04)
expr: kube_node_status_condition{condition="OutOfDisk",status="true"} == 1
for: 2m
labels:
severity: critical
annotations:
summary: Kubernetes out of disk (instance {{ $labels.instance }})
description: "{{ $labels.node }} has OutOfDisk condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesContainerOomKiller (5.1.06)
expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m]) == 1
for: 0m
labels:
severity: warning
annotations:
summary: Kubernetes container oom killer (instance {{ $labels.instance }})
description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesVolumeOutOfDiskSpace (5.1.10)
expr: kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10
for: 2m
labels:
severity: warning
annotations:
summary: Kubernetes Volume out of disk space (instance {{ $labels.instance }})
description: "Volume is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesPersistentvolumeError (5.1.12)
expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending", job="kube-state-metrics"} > 0
for: 0m
labels:
severity: critical
annotations:
summary: Kubernetes PersistentVolume error (instance {{ $labels.instance }})
description: "Persistent volume is in bad state\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesHpaScaleCapability (5.1.16)
expr: kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas
for: 2m
labels:
severity: info
annotations:
summary: Kubernetes HPA scale capability (instance {{ $labels.instance }})
description: "The maximum number of desired Pods has been hit\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesPodNotHealthy (5.1.17)
expr: min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[15m:1m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Kubernetes Pod not healthy (instance {{ $labels.instance }})
description: "Pod has been in a non-ready state for longer than 15 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesPodCrashLooping (5.1.18)
expr: increase(kube_pod_container_status_restarts_total[1m]) > 3
for: 2m
labels:
severity: warning
annotations:
summary: Kubernetes pod crash looping (instance {{ $labels.instance }})
description: "Pod {{ $labels.pod }} is crash looping\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesApiServerErrors (5.1.29)
expr: sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[1m])) / sum(rate(apiserver_request_total{job="apiserver"}[1m])) * 100 > 3
for: 2m
labels:
severity: critical
annotations:
summary: Kubernetes API server errors (instance {{ $labels.instance }})
description: "Kubernetes API server is experiencing high error rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesClientCertificateExpiresSoon (5.1.32)
expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 24*60*60
for: 0m
labels:
severity: critical
annotations:
summary: Kubernetes client certificate expires soon (instance {{ $labels.instance }})
description: "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"

354
on-premise/prometheus_2.54.1/2_config/default.yaml Normal file
View File

@ -0,0 +1,354 @@
# Source: prometheus/templates/cm.yaml
apiVersion: v1
kind: ConfigMap
metadata:
labels:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: v2.54.1
helm.sh/chart: prometheus-25.27.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/part-of: prometheus
name: prometheus-server
namespace: monitoring
data:
allow-snippet-annotations: "false"
alerting_rules.yml: |
{}
alerts: |
{}
prometheus.yml: |
global:
evaluation_interval: 1m
scrape_interval: 1m
scrape_timeout: 10s
rule_files:
- /etc/config/recording_rules.yml
- /etc/config/alerting_rules.yml
- /etc/config/rules
- /etc/config/alerts
scrape_configs:
- job_name: prometheus
static_configs:
- targets:
- localhost:9090
- bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
job_name: kubernetes-apiservers
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- action: keep
regex: default;kubernetes;https
source_labels:
- __meta_kubernetes_namespace
- __meta_kubernetes_service_name
- __meta_kubernetes_endpoint_port_name
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
insecure_skip_verify: true
- bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
job_name: kubernetes-nodes
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- replacement: kubernetes.default.svc:443
target_label: __address__
- regex: (.+)
replacement: /api/v1/nodes/$1/proxy/metrics
source_labels:
- __meta_kubernetes_node_name
target_label: __metrics_path__
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
insecure_skip_verify: true
- bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
job_name: kubernetes-nodes-cadvisor
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- replacement: kubernetes.default.svc:443
target_label: __address__
- regex: (.+)
replacement: /api/v1/nodes/$1/proxy/metrics/cadvisor
source_labels:
- __meta_kubernetes_node_name
target_label: __metrics_path__
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
insecure_skip_verify: true
- honor_labels: true
job_name: kubernetes-service-endpoints
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- action: keep
regex: true
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_scrape
- action: drop
regex: true
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_scrape_slow
- action: replace
regex: (https?)
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_scheme
target_label: __scheme__
- action: replace
regex: (.+)
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_path
target_label: __metrics_path__
- action: replace
regex: (.+?)(?::\d+)?;(\d+)
replacement: $1:$2
source_labels:
- __address__
- __meta_kubernetes_service_annotation_prometheus_io_port
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_service_annotation_prometheus_io_param_(.+)
replacement: __param_$1
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: namespace
- action: replace
source_labels:
- __meta_kubernetes_service_name
target_label: service
- action: replace
source_labels:
- __meta_kubernetes_pod_node_name
target_label: node
- honor_labels: true
job_name: kubernetes-service-endpoints-slow
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- action: keep
regex: true
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_scrape_slow
- action: replace
regex: (https?)
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_scheme
target_label: __scheme__
- action: replace
regex: (.+)
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_path
target_label: __metrics_path__
- action: replace
regex: (.+?)(?::\d+)?;(\d+)
replacement: $1:$2
source_labels:
- __address__
- __meta_kubernetes_service_annotation_prometheus_io_port
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_service_annotation_prometheus_io_param_(.+)
replacement: __param_$1
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: namespace
- action: replace
source_labels:
- __meta_kubernetes_service_name
target_label: service
- action: replace
source_labels:
- __meta_kubernetes_pod_node_name
target_label: node
scrape_interval: 5m
scrape_timeout: 30s
- honor_labels: true
job_name: prometheus-pushgateway
kubernetes_sd_configs:
- role: service
relabel_configs:
- action: keep
regex: pushgateway
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_probe
- honor_labels: true
job_name: kubernetes-services
kubernetes_sd_configs:
- role: service
metrics_path: /probe
params:
module:
- http_2xx
relabel_configs:
- action: keep
regex: true
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_probe
- source_labels:
- __address__
target_label: __param_target
- replacement: blackbox
target_label: __address__
- source_labels:
- __param_target
target_label: instance
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels:
- __meta_kubernetes_namespace
target_label: namespace
- source_labels:
- __meta_kubernetes_service_name
target_label: service
- honor_labels: true
job_name: kubernetes-pods
kubernetes_sd_configs:
- role: pod
relabel_configs:
- action: keep
regex: true
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_scrape
- action: drop
regex: true
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_scrape_slow
- action: replace
regex: (https?)
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_scheme
target_label: __scheme__
- action: replace
regex: (.+)
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_path
target_label: __metrics_path__
- action: replace
regex: (\d+);(([A-Fa-f0-9]{1,4}::?){1,7}[A-Fa-f0-9]{1,4})
replacement: '[$2]:$1'
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_port
- __meta_kubernetes_pod_ip
target_label: __address__
- action: replace
regex: (\d+);((([0-9]+?)(\.|$)){4})
replacement: $2:$1
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_port
- __meta_kubernetes_pod_ip
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_annotation_prometheus_io_param_(.+)
replacement: __param_$1
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: namespace
- action: replace
source_labels:
- __meta_kubernetes_pod_name
target_label: pod
- action: drop
regex: Pending|Succeeded|Failed|Completed
source_labels:
- __meta_kubernetes_pod_phase
- action: replace
source_labels:
- __meta_kubernetes_pod_node_name
target_label: node
- honor_labels: true
job_name: kubernetes-pods-slow
kubernetes_sd_configs:
- role: pod
relabel_configs:
- action: keep
regex: true
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_scrape_slow
- action: replace
regex: (https?)
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_scheme
target_label: __scheme__
- action: replace
regex: (.+)
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_path
target_label: __metrics_path__
- action: replace
regex: (\d+);(([A-Fa-f0-9]{1,4}::?){1,7}[A-Fa-f0-9]{1,4})
replacement: '[$2]:$1'
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_port
- __meta_kubernetes_pod_ip
target_label: __address__
- action: replace
regex: (\d+);((([0-9]+?)(\.|$)){4})
replacement: $2:$1
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_port
- __meta_kubernetes_pod_ip
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_annotation_prometheus_io_param_(.+)
replacement: __param_$1
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: namespace
- action: replace
source_labels:
- __meta_kubernetes_pod_name
target_label: pod
- action: drop
regex: Pending|Succeeded|Failed|Completed
source_labels:
- __meta_kubernetes_pod_phase
- action: replace
source_labels:
- __meta_kubernetes_pod_node_name
target_label: node
scrape_interval: 5m
scrape_timeout: 30s
alerting:
alertmanagers:
- kubernetes_sd_configs:
- role: pod
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- source_labels: [__meta_kubernetes_namespace]
regex: monitoring
action: keep
- source_labels: [__meta_kubernetes_pod_label_app_kubernetes_io_instance]
regex: prometheus
action: keep
- source_labels: [__meta_kubernetes_pod_label_app_kubernetes_io_name]
regex: alertmanager
action: keep
- source_labels: [__meta_kubernetes_pod_container_port_number]
regex: "9093"
action: keep
recording_rules.yml: |
{}
rules: |
{}

115
on-premise/prometheus_2.54.1/3_deploy/daemonset.yaml Normal file
View File

@ -0,0 +1,115 @@
# Source: prometheus/charts/prometheus-node-exporter/templates/daemonset.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: prometheus-prometheus-node-exporter
namespace: monitoring
labels:
helm.sh/chart: prometheus-node-exporter-4.39.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: metrics
app.kubernetes.io/part-of: prometheus-node-exporter
app.kubernetes.io/name: prometheus-node-exporter
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "1.8.2"
spec:
selector:
matchLabels:
app.kubernetes.io/name: prometheus-node-exporter
app.kubernetes.io/instance: prometheus
revisionHistoryLimit: 10
updateStrategy:
rollingUpdate:
maxUnavailable: 1
type: RollingUpdate
template:
metadata:
annotations:
cluster-autoscaler.kubernetes.io/safe-to-evict: "true"
labels:
helm.sh/chart: prometheus-node-exporter-4.39.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: metrics
app.kubernetes.io/part-of: prometheus-node-exporter
app.kubernetes.io/name: prometheus-node-exporter
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "1.8.2"
spec:
automountServiceAccountToken: false
securityContext:
fsGroup: 65534
runAsGroup: 65534
runAsNonRoot: true
runAsUser: 65534
serviceAccountName: prometheus-prometheus-node-exporter
containers:
- name: node-exporter
image: quay.io/prometheus/node-exporter:v1.8.2
imagePullPolicy: IfNotPresent
args:
- --path.procfs=/host/proc
- --path.sysfs=/host/sys
- --path.rootfs=/host/root
- --path.udev.data=/host/root/run/udev/data
- --web.listen-address=[$(HOST_IP)]:9100
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
env:
- name: HOST_IP
value: 0.0.0.0
ports:
- name: metrics
containerPort: 9100
protocol: TCP
livenessProbe:
failureThreshold: 3
httpGet:
httpHeaders:
path: /
port: 9100
scheme: HTTP
initialDelaySeconds: 0
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 1
readinessProbe:
failureThreshold: 3
httpGet:
httpHeaders:
path: /
port: 9100
scheme: HTTP
initialDelaySeconds: 0
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 1
volumeMounts:
- name: proc
mountPath: /host/proc
readOnly: true
- name: sys
mountPath: /host/sys
readOnly: true
- name: root
mountPath: /host/root
mountPropagation: HostToContainer
readOnly: true
hostNetwork: true
hostPID: true
hostIPC: false
nodeSelector:
kubernetes.io/os: linux
tolerations:
- effect: NoSchedule
operator: Exists
volumes:
- name: proc
hostPath:
path: /proc
- name: sys
hostPath:
path: /sys
- name: root
hostPath:
path: /

267
on-premise/prometheus_2.54.1/3_deploy/deploy.yaml Normal file
View File

@ -0,0 +1,267 @@
# Source: prometheus/charts/kube-state-metrics/templates/deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: prometheus-kube-state-metrics
namespace: monitoring
labels:
helm.sh/chart: kube-state-metrics-5.25.1
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: metrics
app.kubernetes.io/part-of: kube-state-metrics
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "2.13.0"
spec:
selector:
matchLabels:
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/instance: prometheus
replicas: 1
strategy:
type: RollingUpdate
revisionHistoryLimit: 10
template:
metadata:
labels:
helm.sh/chart: kube-state-metrics-5.25.1
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: metrics
app.kubernetes.io/part-of: kube-state-metrics
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "2.13.0"
spec:
automountServiceAccountToken: true
hostNetwork: false
serviceAccountName: prometheus-kube-state-metrics
securityContext:
fsGroup: 65534
runAsGroup: 65534
runAsNonRoot: true
runAsUser: 65534
seccompProfile:
type: RuntimeDefault
containers:
- name: kube-state-metrics
args:
- --port=8080
- --resources=certificatesigningrequests,configmaps,cronjobs,daemonsets,deployments,endpoints,horizontalpodautoscalers,ingresses,jobs,leases,limitranges,mutatingwebhookconfigurations,namespaces,networkpolicies,nodes,persistentvolumeclaims,persistentvolumes,poddisruptionbudgets,pods,replicasets,replicationcontrollers,resourcequotas,secrets,services,statefulsets,storageclasses,validatingwebhookconfigurations,volumeattachments
imagePullPolicy: IfNotPresent
image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.13.0
ports:
- containerPort: 8080
name: "http"
livenessProbe:
failureThreshold: 3
httpGet:
httpHeaders:
path: /livez
port: 8080
scheme: HTTP
initialDelaySeconds: 5
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 5
readinessProbe:
failureThreshold: 3
httpGet:
httpHeaders:
path: /readyz
port: 8080
scheme: HTTP
initialDelaySeconds: 5
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 5
resources:
{}
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
---
# Source: prometheus/charts/prometheus-pushgateway/templates/deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
helm.sh/chart: prometheus-pushgateway-2.14.0
app.kubernetes.io/name: prometheus-pushgateway
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "v1.9.0"
app.kubernetes.io/managed-by: Helm
name: prometheus-prometheus-pushgateway
namespace: monitoring
spec:
replicas: 1
strategy:
type: Recreate
selector:
matchLabels:
app.kubernetes.io/name: prometheus-pushgateway
app.kubernetes.io/instance: prometheus
template:
metadata:
labels:
helm.sh/chart: prometheus-pushgateway-2.14.0
app.kubernetes.io/name: prometheus-pushgateway
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "v1.9.0"
app.kubernetes.io/managed-by: Helm
spec:
serviceAccountName: prometheus-prometheus-pushgateway
automountServiceAccountToken: true
containers:
- name: pushgateway
image: "quay.io/prometheus/pushgateway:v1.9.0"
imagePullPolicy: IfNotPresent
ports:
- name: metrics
containerPort: 9091
protocol: TCP
livenessProbe:
httpGet:
path: /-/healthy
port: 9091
initialDelaySeconds: 10
timeoutSeconds: 10
readinessProbe:
httpGet:
path: /-/ready
port: 9091
initialDelaySeconds: 10
timeoutSeconds: 10
volumeMounts:
- name: storage-volume
mountPath: "/data"
subPath: ""
securityContext:
fsGroup: 65534
runAsNonRoot: true
runAsUser: 65534
volumes:
- name: storage-volume
emptyDir: {}
---
# Source: prometheus/templates/deploy.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: v2.54.1
helm.sh/chart: prometheus-25.27.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/part-of: prometheus
name: prometheus-server
namespace: monitoring
spec:
selector:
matchLabels:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
replicas: 1
revisionHistoryLimit: 10
strategy:
type: Recreate
rollingUpdate: null
template:
metadata:
labels:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: v2.54.1
helm.sh/chart: prometheus-25.27.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/part-of: prometheus
spec:
enableServiceLinks: true
serviceAccountName: prometheus-server
containers:
- name: prometheus-server-configmap-reload
image: "quay.io/prometheus-operator/prometheus-config-reloader:v0.76.0"
imagePullPolicy: "IfNotPresent"
args:
- --watched-dir=/etc/config
- --listen-address=0.0.0.0:8080
- --reload-url=http://127.0.0.1:9090/-/reload
ports:
- containerPort: 8080
name: metrics
livenessProbe:
httpGet:
path: /healthz
port: metrics
scheme: HTTP
initialDelaySeconds: 2
periodSeconds: 10
readinessProbe:
httpGet:
path: /healthz
port: metrics
scheme: HTTP
periodSeconds: 10
volumeMounts:
- name: config-volume
mountPath: /etc/config
readOnly: true
- name: prometheus-server
image: "quay.io/prometheus/prometheus:v2.54.1"
imagePullPolicy: "IfNotPresent"
args:
- --storage.tsdb.retention.time=15d
- --config.file=/etc/config/prometheus.yml
- --storage.tsdb.path=/data
- --web.console.libraries=/etc/prometheus/console_libraries
- --web.console.templates=/etc/prometheus/consoles
- --web.enable-lifecycle
ports:
- containerPort: 9090
readinessProbe:
httpGet:
path: /-/ready
port: 9090
scheme: HTTP
initialDelaySeconds: 30
periodSeconds: 5
timeoutSeconds: 4
failureThreshold: 3
successThreshold: 1
livenessProbe:
httpGet:
path: /-/healthy
port: 9090
scheme: HTTP
initialDelaySeconds: 30
periodSeconds: 15
timeoutSeconds: 10
failureThreshold: 3
successThreshold: 1
volumeMounts:
- name: config-volume
mountPath: /etc/config
- name: storage-volume
mountPath: /data
subPath: ""
dnsPolicy: ClusterFirst
securityContext:
fsGroup: 65534
runAsGroup: 65534
runAsNonRoot: true
runAsUser: 65534
terminationGracePeriodSeconds: 300
volumes:
- name: config-volume
configMap:
name: prometheus-server
- name: storage-volume
persistentVolumeClaim:
claimName: prometheus-server

25
on-premise/prometheus_2.54.1/3_deploy/ing.yaml Normal file
View File

@ -0,0 +1,25 @@
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: ing-prometheus
namespace: monitoring
annotations:
# 인증 방법 설정: basic auth
nginx.ingress.kubernetes.io/auth-type: basic
# basic auth 사용자가 들어있는 secret 설정
nginx.ingress.kubernetes.io/auth-secret: basic-auth
# 인증 요청시 나오는 메세지 설정
nginx.ingress.kubernetes.io/auth-realm: 'Authentication Required - admin'
spec:
ingressClassName: nginx
rules:
- host: prometheus.icurfer.com
http:
paths:
- backend:
service:
name: prometheus-prometheus-server
port:
number: 80
path: /
pathType: Prefix

106
on-premise/prometheus_2.54.1/3_deploy/service.yaml Normal file
View File

@ -0,0 +1,106 @@
# Source: prometheus/charts/kube-state-metrics/templates/service.yaml
apiVersion: v1
kind: Service
metadata:
name: prometheus-kube-state-metrics
namespace: monitoring
labels:
helm.sh/chart: kube-state-metrics-5.25.1
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: metrics
app.kubernetes.io/part-of: kube-state-metrics
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "2.13.0"
annotations:
prometheus.io/scrape: 'true'
spec:
type: "ClusterIP"
ports:
- name: "http"
protocol: TCP
port: 8080
targetPort: 8080
selector:
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/instance: prometheus
---
# Source: prometheus/charts/prometheus-node-exporter/templates/service.yaml
apiVersion: v1
kind: Service
metadata:
name: prometheus-prometheus-node-exporter
namespace: monitoring
labels:
helm.sh/chart: prometheus-node-exporter-4.39.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: metrics
app.kubernetes.io/part-of: prometheus-node-exporter
app.kubernetes.io/name: prometheus-node-exporter
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "1.8.2"
annotations:
prometheus.io/scrape: "true"
spec:
type: ClusterIP
ports:
- port: 9100
targetPort: 9100
protocol: TCP
name: metrics
selector:
app.kubernetes.io/name: prometheus-node-exporter
app.kubernetes.io/instance: prometheus
---
# Source: prometheus/charts/prometheus-pushgateway/templates/service.yaml
apiVersion: v1
kind: Service
metadata:
annotations:
prometheus.io/probe: pushgateway
labels:
helm.sh/chart: prometheus-pushgateway-2.14.0
app.kubernetes.io/name: prometheus-pushgateway
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: "v1.9.0"
app.kubernetes.io/managed-by: Helm
name: prometheus-prometheus-pushgateway
namespace: monitoring
spec:
type: ClusterIP
ports:
- port: 9091
targetPort: 9091
protocol: TCP
name: http
selector:
app.kubernetes.io/name: prometheus-pushgateway
app.kubernetes.io/instance: prometheus
---
# Source: prometheus/templates/service.yaml
apiVersion: v1
kind: Service
metadata:
labels:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
app.kubernetes.io/version: v2.54.1
helm.sh/chart: prometheus-25.27.0
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/part-of: prometheus
name: prometheus-server
namespace: monitoring
spec:
ports:
- name: http
port: 80
protocol: TCP
targetPort: 9090
selector:
app.kubernetes.io/component: server
app.kubernetes.io/name: prometheus
app.kubernetes.io/instance: prometheus
sessionAffinity: None
type: "ClusterIP"

6
on-premise/prometheus_2.54.1/create.md Normal file
View File

@ -0,0 +1,6 @@
helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
helm search repo prometheus-community
helm pull prometheus-community/prometheus --untar
helm template . > demo.yaml
다음 kustomize로 네임스페이스 추가.

6
on-premise/prometheus_2.54.1/imageList.txt Normal file
View File

@ -0,0 +1,6 @@
"quay.io/prometheus/alertmanager:v0.27.0",
"quay.io/prometheus/node-exporter:v1.8.2",
"quay.io/prometheus-operator/prometheus-config-reloader:v0.76.0",
"quay.io/prometheus/prometheus:v2.54.1",
"quay.io/prometheus/pushgateway:v1.9.0",
"registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.13.0",

4
on-premise/prometheus_2.54.1/kustomization.yaml Normal file
View File

@ -0,0 +1,4 @@
namespace: monitoring
resources:
- prometheus_all_2.54.1.yaml

1352
on-premise/prometheus_2.54.1/prometheus_all_2.54.1.yaml Normal file
View File

File diff suppressed because it is too large Load Diff