k8s全方位监控-prometheus-alertmanager部署-配置第一条告警邮件
1、alertmanager告警插件部署
[root@VM_0_48_centos prometheus]# cat alertmanager-pvc.yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: alertmanager
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: EnsureExists
spec:
storageClassName: managed-nfs-storage #必须动态PV，需要改为自己的名字
accessModes:
- ReadWriteOnce
resources:
requests:
[root@VM_0_48_centos prometheus]# cat alertmanager-deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: alertmanager
namespace: kube-system
labels:
k8s-app: alertmanager
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
version: v0.14.0
spec:
replicas: 1
selector:
matchLabels:
k8s-app: alertmanager
version: v0.14.0
template:
metadata:
labels:
k8s-app: alertmanager
version: v0.14.0
annotations:
scheduler.alpha.kubernetes.io/critical-pod: ''
spec:
priorityClassName: system-cluster-critical
containers:
- name: prometheus-alertmanager
image: "prom/alertmanager:v0.14.0"
imagePullPolicy: "IfNotPresent"
args:
- --config.file=/etc/config/alertmanager.yml
- --storage.path=/data
- --web.external-url=/
ports:
- containerPort: 9093
readinessProbe:
httpGet:
path: /#/status
port: 9093
initialDelaySeconds: 30
timeoutSeconds: 30
volumeMounts:
- name: config-volume
mountPath: /etc/config
- name: storage-volume
mountPath: "/data"
subPath: ""
resources:
limits:
cpu: 10m
memory: 50Mi
requests:
cpu: 10m
memory: 50Mi
- name: prometheus-alertmanager-configmap-reload
image: "jimmidyson/configmap-reload:v0.1"
imagePullPolicy: "IfNotPresent"
args:
- --volume-dir=/etc/config
- --webhook-url=http://localhost:9093/-/reload
volumeMounts:
- name: config-volume
mountPath: /etc/config
readOnly: true
resources:
limits:
cpu: 10m
memory: 10Mi
requests:
cpu: 10m
memory: 10Mi
volumes:
- name: config-volume
configMap:
name: alertmanager-config
- name: storage-volume
persistentVolumeClaim:
claimName: alertmanager
[root@VM_0_48_centos prometheus]# cat alertmanager-service.yaml
apiVersion: v1
kind: Service
metadata:
name: alertmanager
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
kubernetes.io/name: "Alertmanager"
spec:
ports:
- name: http
port: 80
protocol: TCP
targetPort: 9093
selector:
k8s-app: alertmanager
type: "ClusterIP"
2、prometheus 查看服务是否正常
查看alertmanager服务是否正常
[root@VM_0_48_centos prometheus]# kubectl get svc -n kube-system
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
alertmanager ClusterIP 10.0.0.176 <none> 80/TCP 46h
3、 prometheus 配置告警规则和调用altermanager
[root@VM_0_48_centos prometheus]# cat prometheus-configmap.yaml
# Prometheus configuration format https://prometheus.io/docs/prometheus/latest/configuration/configuration/
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-config
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: EnsureExists
data:
prometheus.yml: |
scrape_configs:
- job_name: prometheus
static_configs:
- targets:
- localhost:9090 - 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-kubelet
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
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_(.+)
- target_label: __metrics_path__
replacement: /metrics/cadvisor
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-service-endpoints
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- action: keep
regex: true
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_scrape
- 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_label_(.+)
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: kubernetes_namespace
- action: replace
source_labels:
- __meta_kubernetes_service_name
target_label: kubernetes_name - 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: kubernetes_namespace
- source_labels:
- __meta_kubernetes_service_name
target_label: kubernetes_name - 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: replace
regex: (.+)
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_path
target_label: __metrics_path__
- action: replace
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
source_labels:
- __address__
- __meta_kubernetes_pod_annotation_prometheus_io_port
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: kubernetes_namespace
- action: replace
source_labels:
- __meta_kubernetes_pod_name
target_label: kubernetes_pod_name
alerting:
alertmanagers:
- static_configs:
- targets: ["alertmanager:80"] ####需要修改alertmanger服务名字，集群内部通过服务名调用
4、配置告警规则-创建告警规则的configmap
[root@VM_0_48_centos prometheus]# cat prometheus-rules.yaml
# Prometheus configuration format https://prometheus.io/docs/prometheus/latest/configuration/configuration/
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-rules-config
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: EnsureExists
data:
rules.yml: |
groups:
- name: node
rules:
- alert: memory_use
expr: 100-(node_memory_MemFree_bytes+node_memory_Cached_bytes+node_memory_Buffers_bytes)/node_memory_MemTotal_bytes*100 >= 90
for: 10s
annotations:
summary: "机器 {{ $labels.instance }} 内存使用的率超过90%" expr: 100-(node_memory_MemFree_bytes+node_memory_Cached_bytes+node_memory_Buffers_bytes)/node_memory_MemTotal_bytes*100 >= 80
for: 10s
annotations:
summary: "机器 {{ $labels.instance }} 内存使用的率超过80%"
5、配置告警规则-将告警规则挂载到promethues中
[root@VM_0_48_centos prometheus]# cat prometheus-statefulset.yaml
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: prometheus
namespace: kube-system
labels:
k8s-app: prometheus
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
version: v2.2.1
spec:
serviceName: "prometheus"
replicas: 1
podManagementPolicy: "Parallel"
updateStrategy:
type: "RollingUpdate"
selector:
matchLabels:
k8s-app: prometheus
template:
metadata:
labels:
k8s-app: prometheus
annotations:
scheduler.alpha.kubernetes.io/critical-pod: ''
spec:
priorityClassName: system-cluster-critical
serviceAccountName: prometheus
initContainers:
- name: "init-chown-data"
image: "busybox:latest"
imagePullPolicy: "IfNotPresent"
command: ["chown", "-R", "65534:65534", "/data"]
volumeMounts:
- name: prometheus-data
mountPath: /data
subPath: ""
containers:
- name: prometheus-server-configmap-reload
image: "jimmidyson/configmap-reload:v0.1"
imagePullPolicy: "IfNotPresent"
args:
- --volume-dir=/etc/config
- --webhook-url=http://localhost:9090/-/reload
volumeMounts:
- name: config-volume
mountPath: /etc/config
readOnly: true
resources:
limits:
cpu: 10m
memory: 10Mi
requests:
cpu: 10m
memory: 10Mi - name: prometheus-server
image: "prom/prometheus:v2.2.1"
imagePullPolicy: "IfNotPresent"
args:
- --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
initialDelaySeconds: 30
timeoutSeconds: 30
livenessProbe:
httpGet:
path: /-/healthy
port: 9090
initialDelaySeconds: 30
timeoutSeconds: 30
# based on 10 running nodes with 30 pods each
resources:
limits:
cpu: 200m
memory: 1000Mi
requests:
cpu: 200m
memory: 1000Mi volumeMounts:
- name: config-volume
mountPath: /etc/config
- name: prometheus-data
mountPath: /data
subPath: ""
- name: rules-volume
mountPath: /etc/config/alert_rules
terminationGracePeriodSeconds: 300
volumes:
- name: config-volume
configMap:
name: prometheus-config
- name: rules-volume
configMap:
name: prometheus-rules-config ####挂载规则到服务目录下
- name: prometheus-data
persistentVolumeClaim:
claimName: prometheus-claim
6、配置告警规则 配置 prometheus启用告警规则
[root@VM_0_48_centos prometheus]# cat prometheus-configmap.yaml
# Prometheus configuration format https://prometheus.io/docs/prometheus/latest/configuration/configuration/
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-config
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: EnsureExists
data:
prometheus.yml: |
scrape_configs:
- job_name: prometheus
static_configs:
- targets:
- localhost:9090
- job_name: node
static_configs:
- targets:
- 172.19.0.48:9100
- 172.19.0.14:9100
- 172.19.0.9:9100
- 172.19.0.2:9100 - 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-kubelet
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
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_(.+)
- target_label: __metrics_path__
replacement: /metrics/cadvisor
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-service-endpoints
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- action: keep
regex: true
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_scrape
- 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_label_(.+)
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: kubernetes_namespace
- action: replace
source_labels:
- __meta_kubernetes_service_name
target_label: kubernetes_name - 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: kubernetes_namespace
- source_labels:
- __meta_kubernetes_service_name
target_label: kubernetes_name - 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: replace
regex: (.+)
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_path
target_label: __metrics_path__
- action: replace
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
source_labels:
- __address__
- __meta_kubernetes_pod_annotation_prometheus_io_port
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: kubernetes_namespace
- action: replace
source_labels:
- __meta_kubernetes_pod_name
target_label: kubernetes_pod_name
alerting:
alertmanagers:
- static_configs:
- targets: ["alertmanager:80"]
rule_files:
- "/etc/config/alert_rules/*.yml" ####启用挂载的规则文件
5、配置告警媒介
[root@VM_0_48_centos prometheus]# cat alertmanager-configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
name: alertmanager-config
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: EnsureExists
data:
alertmanager.yml: |
global:
resolve_timeout: 5m
smtp_smarthost: 'smtp.163.com:25'
smtp_from: 'xjq18125012766@163.com'
smtp_auth_username: '********@163.com'
smtp_auth_password: '*******'
smtp_require_tls: false route:
group_by: ['alertname']
group_wait: 10s
group_interval: 30s
repeat_interval: 10s
receiver: 'mail' receivers:
- name: 'mail'
email_configs:
- to: '2654071080@qq.com'
6、告警结果展示
k8s全方位监控-prometheus-alertmanager部署-配置第一条告警邮件的更多相关文章
- k8s全方位监控-prometheus部署
1.k8s 监控资源对象 2. prometheus简单介绍. https://github.com/prometheus •多维数据模型:由度量名称和键值对标识的时间序列数据•PromSQL:一种灵 ...
- k8s全方位监控 -prometheus实现短信告警接口编写（python）
1.prometheus短信告警接口实现(python)源码如下: import subprocess from flask import Flask from flask import reques ...
- k8s全方位监控中-常用rules配置
[root@VM_0_48_centos prometheus]# cat alertmanager-configmap.yaml apiVersion: v1 kind: ConfigMap met ...
- Alertmanager 部署配置
目录 前言 源码安装 配置 启动 配置prometheus监控Alertmanager 修改prometheus配置 重新加载配置文件 配置测试告警 修改prometheus配置 重新加载配置文件 测 ...
- Longhorn，企业级云原生容器分布式存储 - 监控(Prometheus+AlertManager+Grafana)
内容来源于官方 Longhorn 1.1.2 英文技术手册. 系列 Longhorn 是什么? Longhorn 企业级云原生容器分布式存储解决方案设计架构和概念 Longhorn 企业级云原生容器分 ...
- k8s全方位监控-prometheus-配置文件介绍以及基于文件服务发现
1.scrape_configs 参数介绍 # 默认的全局配置 global: scrape_interval: 15s # 采集间隔15s,默认为1min一次 evaluation_interval ...
- 容器编排系统K8s之Prometheus监控系统+Grafana部署
前文我们聊到了k8s的apiservice资源结合自定义apiserver扩展原生apiserver功能的相关话题,回顾请参考:https://www.cnblogs.com/qiuhom-1874/ ...
- K8S(13)监控实战-部署prometheus
k8s监控实战-部署prometheus 目录 k8s监控实战-部署prometheus 1 prometheus前言相关 1.1 Prometheus的特点 1.2 基本原理 1.2.1 原理说明 ...
- 【集群监控】Docker上部署Prometheus+Alertmanager+Grafana实现集群监控
Docker部署 下载 sudo yum-config-manager --add-repo https://download.docker.com/linux/centos/docker-ce.re ...
随机推荐
- 010 Linux 文本统计与去重 (wc 和 uniq)
wc 命令一般是作为组合命令的一员与其他命令一同起到统计的作用.而一般情况下使用wc -l 命令较多. uniq 可检查文本文件中重复出现的行,一般与 sort 命令结合使用.一起组合搭配使用完成统计 ...
- Visual Studio 中快速创建方法 Generate a method in Visual Studio
2020-04-04 https://docs.microsoft.com/en-us/visualstudio/ide/reference/generate-method?view=vs-2019 ...
- Thread的打断
常用方法 public void interrupt() t.interrupt() 打断t线程(设置t线程某给标志位f=true,并不是打断线程的运行),不能打断正在竞争锁的线程. public b ...
- Linux中3个文件查找相关命令详解
源于:https://mp.weixin.qq.com/s/VPs-IXY6RoxbltHIxtIbng which命令 我们经常在linux要查找某个文件,但不知道放在哪里了,可以使用下面的一些命令 ...
- ReactiveCocoa 学习资料
之前就有听说,感觉很强大,ReactiveCocoa更加被Mattt Thompson大神称为开启一个新Objective-C纪元.所以觉得非常有学习的必要了. 一些很好的学习资料: Reactive ...
- nvidia-smi
内容转自:https://blog.csdn.net/handsome_bear/article/details/80903477 nvidia-smi 显示 说明 Fan 风扇转速(0%--100% ...
- python基础——异常处理、递归
异常处理 while True: try: num1 = int(input('num1:')) num2 = int(input('num2:')) result = num1 + num2 exc ...
- [技术干货-算子使用] mindspore.scipy 入门使用指导
1. MindSpore框架的SciPy模块 SciPy 是基于NumPy实现的科学计算库,主要用于数学.物理学.生物学等科学以及工程学领域.诸如高阶迭代,线性代数求解等都会需要用到SicPy.Sci ...
- Solution -「六省联考 2017」「洛谷 P3750」分手是祝愿
\(\mathcal{Description}\) Link. 有 \(n\) 盏编号为 \(1\sim n\),已知初始状态的灯,每次操作选取 \(x\in[1,n]\),使得所有编号为 \ ...
- CentOS7搭建ntp时钟服务器
文章目录 服务器配置 远程客户端配置 服务器配置 # 关闭防火墙,selinux=disabled 1.# 服务器部署 [root@localhost ~]# yum -y install ntp n ...