准备docker镜像
```
docker pull docker.io/prom/alertmanager:v0.14.0
docker tag 23744b2d645c harbor.od.com/infra/alertmanager:v0.14.0
docker push harbor.od.com/infra/alertmanager:v0.14.0
```
准备目录
```
mkdir /data/k8s-yaml/alertmanager
cd /data/k8s-yaml/alertmanager
```
准备资源清单
cm.yaml
```
cat >cm.yaml <<'EOF'
apiVersion: v1
kind: ConfigMap
metadata:
name: alertmanager-config
namespace: infra
data:
config.yml: |-
global:
# 在没有报警的情况下声明为已解决的时间
resolve_timeout: 5m
# 配置邮件发送信息
smtp_smarthost: 'smtp.163.com:25'
smtp_from: 'xxx@163.com'
smtp_auth_username: 'xxx@163.com'
smtp_auth_password: 'xxxxxx'
smtp_require_tls: false
templates:
- '/etc/alertmanager/*.tmpl'
# 所有报警信息进入后的根路由，用来设置报警的分发策略
route:
# 这里的标签列表是接收到报警信息后的重新分组标签，例如，接收到的报警信息里面有许多具有 cluster=A 和 alertname=LatncyHigh 这样的标签的报警信息将会批量被聚合到一个分组里面
group_by: ['alertname', 'cluster']
# 当一个新的报警分组被创建后，需要等待至少group_wait时间来初始化通知，这种方式可以确保您能有足够的时间为同一分组来获取多个警报，然后一起触发这个报警信息。
group_wait: 30s
# 当第一个报警发送后，等待'group_interval'时间来发送新的一组报警信息。
group_interval: 5m
# 如果一个报警信息已经发送成功了，等待'repeat_interval'时间来重新发送他们
repeat_interval: 5m
# 默认的receiver：如果一个报警没有被一个route匹配，则发送给默认的接收器
receiver: default
receivers:
- name: 'default'
email_configs:
- to: 'xxxx@qq.com'
send_resolved: true
html: '{{ template "email.to.html" . }}'
headers: { Subject: " {{ .CommonLabels.instance }} {{ .CommonAnnotations.summary }}" }
email.tmpl: |
{{ define "email.to.html" }}
{{- if gt (len .Alerts.Firing) 0 -}}
{{ range .Alerts }}
告警程序: prometheus_alert <br>
告警级别: {{ .Labels.severity }} <br>
告警类型: {{ .Labels.alertname }} <br>
故障主机: {{ .Labels.instance }} <br>
告警主题: {{ .Annotations.summary }} <br>
触发时间: {{ .StartsAt.Format "2006-01-02 15:04:05" }} <br>
{{ end }}{{ end -}}
{{- if gt (len .Alerts.Resolved) 0 -}}
{{ range .Alerts }}
告警程序: prometheus_alert <br>
告警级别: {{ .Labels.severity }} <br>
告警类型: {{ .Labels.alertname }} <br>
故障主机: {{ .Labels.instance }} <br>
告警主题: {{ .Annotations.summary }} <br>
触发时间: {{ .StartsAt.Format "2006-01-02 15:04:05" }} <br>
恢复时间: {{ .EndsAt.Format "2006-01-02 15:04:05" }} <br>
{{ end }}{{ end -}}
{{- end }}
EOF
```
dp.yaml
```
cat >dp.yaml <<'EOF'
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: alertmanager
namespace: infra
spec:
replicas: 1
selector:
matchLabels:
app: alertmanager
template:
metadata:
labels:
app: alertmanager
spec:
containers:
- name: alertmanager
image: harbor.zq.com/infra/alertmanager:v0.14.0
args:
- "--config.file=/etc/alertmanager/config.yml"
- "--storage.path=/alertmanager"
ports:
- name: alertmanager
containerPort: 9093
volumeMounts:
- name: alertmanager-cm
mountPath: /etc/alertmanager
volumes:
- name: alertmanager-cm
configMap:
name: alertmanager-config
imagePullSecrets:
- name: harbor
EOF
```
svc.yaml
```
cat ><<'EOF'
apiVersion: v1
kind: Service
metadata:
name: alertmanager
namespace: infra
spec:
selector:
app: alertmanager
ports:
- port: 80
targetPort: 9093
EOF
```
应用资源配置清单
```
kubectl apply -f http://k8s-yaml.od.com/alertmanager/cm.yaml
kubectl apply -f http://k8s-yaml.od.com/alertmanager/dp.yaml
kubectl apply -f http://k8s-yaml.od.com/alertmanager/svc.yaml
```
k8s创建基础报警规则文件
```
cat >/data/nfs-volume/prometheus/etc/rules.yml <<'EOF'
groups:
- name: hostStatsAlert
rules:
- alert: hostCpuUsageAlert
expr: sum(avg without (cpu)(irate(node_cpu{mode!='idle'}[5m]))) by (instance) > 0.85
for: 5m
labels:
severity: warning
annotations:
summary: "{{ $labels.instance }} CPU usage above 85% (current value: {{ $value }}%)"
- alert: hostMemUsageAlert
expr: (node_memory_MemTotal - node_memory_MemAvailable)/node_memory_MemTotal > 0.85
for: 5m
labels:
severity: warning
annotations:
summary: "{{ $labels.instance }} MEM usage above 85% (current value: {{ $value }}%)"
- alert: OutOfInodes
expr: node_filesystem_free{fstype="overlay",mountpoint ="/"} / node_filesystem_size{fstype="overlay",mountpoint ="/"} * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: "Out of inodes (instance {{ $labels.instance }})"
description: "Disk is almost running out of available inodes (< 10% left) (current value: {{ $value }})"
- alert: OutOfDiskSpace
expr: node_filesystem_free{fstype="overlay",mountpoint ="/rootfs"} / node_filesystem_size{fstype="overlay",mountpoint ="/rootfs"} * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: "Out of disk space (instance {{ $labels.instance }})"
description: "Disk is almost full (< 10% left) (current value: {{ $value }})"
- alert: UnusualNetworkThroughputIn
expr: sum by (instance) (irate(node_network_receive_bytes[2m])) / 1024 / 1024 > 100
for: 5m
labels:
severity: warning
annotations:
summary: "Unusual network throughput in (instance {{ $labels.instance }})"
description: "Host network interfaces are probably receiving too much data (> 100 MB/s) (current value: {{ $value }})"
- alert: UnusualNetworkThroughputOut
expr: sum by (instance) (irate(node_network_transmit_bytes[2m])) / 1024 / 1024 > 100
for: 5m
labels:
severity: warning
annotations:
summary: "Unusual network throughput out (instance {{ $labels.instance }})"
description: "Host network interfaces are probably sending too much data (> 100 MB/s) (current value: {{ $value }})"
- alert: UnusualDiskReadRate
expr: sum by (instance) (irate(node_disk_bytes_read[2m])) / 1024 / 1024 > 50
for: 5m
labels:
severity: warning
annotations:
summary: "Unusual disk read rate (instance {{ $labels.instance }})"
description: "Disk is probably reading too much data (> 50 MB/s) (current value: {{ $value }})"
- alert: UnusualDiskWriteRate
expr: sum by (instance) (irate(node_disk_bytes_written[2m])) / 1024 / 1024 > 50
for: 5m
labels:
severity: warning
annotations:
summary: "Unusual disk write rate (instance {{ $labels.instance }})"
description: "Disk is probably writing too much data (> 50 MB/s) (current value: {{ $value }})"
- alert: UnusualDiskReadLatency
expr: rate(node_disk_read_time_ms[1m]) / rate(node_disk_reads_completed[1m]) > 100
for: 5m
labels:
severity: warning
annotations:
summary: "Unusual disk read latency (instance {{ $labels.instance }})"
description: "Disk latency is growing (read operations > 100ms) (current value: {{ $value }})"
- alert: UnusualDiskWriteLatency
expr: rate(node_disk_write_time_ms[1m]) / rate(node_disk_writes_completedl[1m]) > 100
for: 5m
labels:
severity: warning
annotations:
summary: "Unusual disk write latency (instance {{ $labels.instance }})"
description: "Disk latency is growing (write operations > 100ms) (current value: {{ $value }})"
- name: http_status
rules:
- alert: ProbeFailed
expr: probe_success == 0
for: 1m
labels:
severity: error
annotations:
summary: "Probe failed (instance {{ $labels.instance }})"
description: "Probe failed (current value: {{ $value }})"
- alert: StatusCode
expr: probe_http_status_code <= 199 OR probe_http_status_code >= 400
for: 1m
labels:
severity: error
annotations:
summary: "Status Code (instance {{ $labels.instance }})"
description: "HTTP status code is not 200-399 (current value: {{ $value }})"
- alert: SslCertificateWillExpireSoon
expr: probe_ssl_earliest_cert_expiry - time() < 86400 * 30
for: 5m
labels:
severity: warning
annotations:
summary: "SSL certificate will expire soon (instance {{ $labels.instance }})"
description: "SSL certificate expires in 30 days (current value: {{ $value }})"
- alert: SslCertificateHasExpired
expr: probe_ssl_earliest_cert_expiry - time() <= 0
for: 5m
labels:
severity: error
annotations:
summary: "SSL certificate has expired (instance {{ $labels.instance }})"
description: "SSL certificate has expired already (current value: {{ $value }})"
- alert: BlackboxSlowPing
expr: probe_icmp_duration_seconds > 2
for: 5m
labels:
severity: warning
annotations:
summary: "Blackbox slow ping (instance {{ $labels.instance }})"
description: "Blackbox ping took more than 2s (current value: {{ $value }})"
- alert: BlackboxSlowRequests
expr: probe_http_duration_seconds > 2
for: 5m
labels:
severity: warning
annotations:
summary: "Blackbox slow requests (instance {{ $labels.instance }})"
description: "Blackbox request took more than 2s (current value: {{ $value }})"
- alert: PodCpuUsagePercent
expr: sum(sum(label_replace(irate(container_cpu_usage_seconds_total[1m]),"pod","$1","container_label_io_kubernetes_pod_name", "(.*)"))by(pod) / on(pod) group_right kube_pod_container_resource_limits_cpu_cores *100 )by(container,namespace,node,pod,severity) > 80
for: 5m
labels:
severity: warning
annotations:
summary: "Pod cpu usage percent has exceeded 80% (current value: {{ $value }}%)"
EOF
```
在prometheus配置文件中追加配置：
```
cat >>/data/nfs-volume/prometheus/etc/prometheus.yml <<'EOF'
alerting:
alertmanagers:
- static_configs:
- targets: ["alertmanager"]
rule_files:
- "/data/etc/rules.yml"
EOF
```
重载配置：
```
curl -X POST http://prometheus.od.com/-/reload
```
- 空白目录
- k8s
- k8s介绍和架构图
- 硬件环境和准备工作
- bind9-DNS服务部署
- 私有仓库harbor部署
- k8s-etcd部署
- api-server部署
- 配置apiserver L4代理
- controller-manager部署
- kube-scheduler部署
- node节点kubelet 部署
- node节点kube-proxy部署
- cfss-certinfo使用
- k8s网络-Flannel部署
- k8s网络优化
- CoreDNS部署
- k8s服务暴露之ingress
- 常用命令记录
- k8s-部署dashboard服务
- K8S平滑升级
- k8s服务交付
- k8s交付dubbo服务
- 服务架构图
- zookeeper服务部署
- Jenkins服务+共享存储nfs部署
- 安装配置maven和java运行时环境的底包镜像
- 使用blue ocean流水线构建镜像
- K8S生态--交付prometheus监控
- 介绍
- 部署4个exporter
- 部署prometheus server
- 部署grafana
- alert告警部署
- 日志收集ELK
- 制作Tomcat镜像
- 部署ElasticSearch
- 部署kafka和kafka-manager
- filebeat镜像制作
- 部署logstash
- 部署Kibana
- Apollo交付到Kubernetes集群
- Apollo简介
- 交付apollo-configservice
- 交付apollo-adminservice
- 交付apollo-portal
- k8s-CICD
- 集群整体架构
- 集群安装
- harbor仓库和nfs部署
- nginx-ingress-controller服务部署
- gitlab服务部署
- gitlab服务优化
- gitlab-runner部署
- dind服务部署
- CICD自动化服务devops演示
- k8s上服务日志收集