# 1. 安装Prometheus
$ wget https://github.com/prometheus/prometheus/releases/download/v2.37.0/prometheus-2.37.0.linux-amd64.tar.gz
$ tar -xzf prometheus-2.37.0.linux-amd64.tar.gz
$ cd prometheus-2.37.0.linux-amd64
$ sudo cp prometheus /usr/local/bin/
$ sudo cp promtool /usr/local/bin/

# 2. 安装Grafana
$ sudo yum install -y grafana

# 3. 安装PostgreSQL exporters
$ wget https://github.com/prometheus-community/postgres_exporter/releases/download/v0.15.0/postgres_exporter-0.15.0.linux-amd64.tar.gz
$ tar -xzf postgres_exporter-0.15.0.linux-amd64.tar.gz
$ cd postgres_exporter-0.15.0.linux-amd64
$ sudo cp postgres_exporter /usr/local/bin/

# 4. 配置PostgreSQL exporters
$ sudo vi /etc/postgres_exporter.yml
data_source_name: “postgresql://fgedu:password@fgedu.localhost:5432/fgedudb?sslmode=disable”

# 5. 配置Prometheus
$ sudo vi /etc/prometheus/prometheus.yml

global:
scrape_interval: 15s
evaluation_interval: 15s

rule_files:
– “/etc/prometheus/rules/*.yml”

alerting:
alertmanagers:
– static_configs:
– targets:
– fgedu.localhost:9093

scrape_configs:
– job_name: ‘postgres’
static_configs:
– targets: [‘fgedu.localhost:9187’]
labels:
instance: ‘postgres’

# 6. 配置Alertmanager
$ wget https://github.com/prometheus/alertmanager/releases/download/v0.24.0/alertmanager-0.24.0.linux-amd64.tar.gz
$ tar -xzf alertmanager-0.24.0.linux-amd64.tar.gz
$ cd alertmanager-0.24.0.linux-amd64
$ sudo cp alertmanager /usr/local/bin/
$ sudo cp amtool /usr/local/bin/

# 7. 配置Alertmanager
$ sudo vi /etc/alertmanager/alertmanager.yml

global:
smtp_smarthost: ‘smtp.fgedu.net.cn:587’
smtp_from: ‘alertmanager@fgedu.net.cn’
smtp_auth_username: ‘alertmanager’
smtp_auth_password: ‘password’

route:
group_by: [‘alertname’]
group_wait: 30s
group_interval: 5m
repeat_interval: 1h
receiver: ’email’

receivers:
– name: ’email’
email_configs:
– to: ‘dba@fgedu.net.cn’

# 8. 启动服务
$ sudo systemctl start postgres_exporter
$ sudo systemctl enable postgres_exporter
$ sudo systemctl start prometheus
$ sudo systemctl enable prometheus
$ sudo systemctl start alertmanager
$ sudo systemctl enable alertmanager
$ sudo systemctl start grafana-server
$ sudo systemctl enable grafana-server

# 9. 验证服务
$ curl http://fgedu.localhost:9090/targets
$ curl http://fgedu.localhost:9093/status
$ curl http://fgedu.localhost:3000

# 1. 配置系统预警规则
$ sudo vi /etc/prometheus/rules/system_alerts.yml
groups:
– name: system_alerts
rules:
– alert: HighCpuUsage
expr: 100 – (avg by(instance) (irate(node_cpu_seconds_total{mode=”idle”}[5m])) * 100) > 80
for: 5m
labels:
severity: warning
annotations:
summary: “High CPU usage on {{ $labels.instance }}”
description: “CPU usage is {{ $value }}%”

– alert: HighMemoryUsage
expr: (node_memory_MemTotal_bytes – node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100 > 80
for: 5m
labels:
severity: warning
annotations:
summary: “High memory usage on {{ $labels.instance }}”
description: “Memory usage is {{ $value }}%”

# 2. 配置数据库预警规则
$ sudo vi /etc/prometheus/rules/postgres_alerts.yml
groups:
– name: postgres_alerts
rules:
– alert: PostgresqlDown
expr: pg_up == 0
for: 5m
labels:
severity: critical
annotations:
summary: “PostgreSQL down on {{ $labels.instance }}”
description: “PostgreSQL instance {{ $labels.instance }} has been down for 5 minutes”

– alert: HighConnectionCount
expr: pg_stat_activity_count > 100
for: 5m
labels:
severity: warning
annotations:
summary: “High connection count on {{ $labels.instance }}”
description: “Connection count is {{ $value }}”

– alert: SlowQueries
expr: pg_stat_statements_max_duration > 10000
for: 5m
labels:
severity: warning
annotations:
summary: “Slow queries on {{ $labels.instance }}”
description: “Maximum query duration is {{ $value }}ms”

– alert: HighTableSpaceUsage
expr: (pg_tablespace_size_bytes / pg_tablespace_size_max_bytes) * 100 > 80
for: 5m
labels:
severity: warning
annotations:
summary: “High tablespace usage on {{ $labels.instance }}”
description: “Tablespace usage is {{ $value }}%”

# 3. 配置性能预警规则
$ sudo vi /etc/prometheus/rules/performance_alerts.yml
groups:
– name: performance_alerts
rules:
– alert: HighIoWait
expr: (avg by(instance) (irate(node_cpu_seconds_total{mode=”iowait”}[5m])) * 100) > 30
for: 5m
labels:
severity: warning
annotations:
summary: “High IO wait on {{ $labels.instance }}”
description: “IO wait is {{ $value }}%”

– alert: HighNetworkTraffic
expr: ((sum by(instance) (irate(node_network_transmit_bytes_total[5m])) + sum by(instance) (irate(node_network_receive_bytes_total[5m]))) / 1024 / 1024 > 100
for: 5m
labels:
severity: warning
annotations:
summary: “High network traffic on {{ $labels.instance }}”
description: “Network traffic is {{ $value }} MB/s”

# 4. 重启Prometheus
$ sudo systemctl restart prometheus

# 5. 验证预警规则
$ curl http://fgedu.localhost:9090/rules

# 1. 配置邮件通知
$ sudo vi /etc/alertmanager/alertmanager.yml

global:
smtp_smarthost: ‘smtp.fgedu.net.cn:587’
smtp_from: ‘alertmanager@fgedu.net.cn’
smtp_auth_username: ‘alertmanager’
smtp_auth_password: ‘password’
smtp_require_tls: true

route:
group_by: [‘alertname’]
group_wait: 30s
group_interval: 5m
repeat_interval: 1h
receiver: ’email’
routes:
– match:
severity: critical
receiver: ’email’
continue: true
– match:
severity: warning
receiver: ’email’

receivers:
– name: ’email’
email_configs:
– to: ‘dba@fgedu.net.cn’
send_resolved: true

# 2. 配置微信通知
$ sudo vi /etc/alertmanager/alertmanager.yml

global:
smtp_smarthost: ‘smtp.fgedu.net.cn:587’
smtp_from: ‘alertmanager@fgedu.net.cn’
smtp_auth_username: ‘alertmanager’
smtp_auth_password: ‘password’
smtp_require_tls: true

route:
group_by: [‘alertname’]
group_wait: 30s
group_interval: 5m
repeat_interval: 1h
receiver: ‘wechat’
routes:
– match:
severity: critical
receiver: ‘wechat’
continue: true

receivers:
– name: ‘wechat’
wechat_configs:
– corp_id: ‘your_corp_id’
api_url: ‘https://qyapi.weixin.qq.com/cgi-bin/’
to_party: ‘your_party_id’
agent_id: ‘your_agent_id’
api_secret: ‘your_api_secret’
message: ‘{{ template “wechat.default.message” . }}’

# 3. 配置短信通知
$ sudo vi /etc/alertmanager/alertmanager.yml

global:
smtp_smarthost: ‘smtp.fgedu.net.cn:587’
smtp_from: ‘alertmanager@fgedu.net.cn’
smtp_auth_username: ‘alertmanager’
smtp_auth_password: ‘password’
smtp_require_tls: true

route:
group_by: [‘alertname’]
group_wait: 30s
group_interval: 5m
repeat_interval: 1h
receiver: ‘sms’
routes:
– match:
severity: critical
receiver: ‘sms’
continue: true

receivers:
– name: ‘sms’
webhook_configs:
– url: ‘http://sms-gateway:8080/send’
send_resolved: true

# 4. 重启Alertmanager
$ sudo systemctl restart alertmanager

# 5. 验证通知配置
$ curl http://fgedu.localhost:9093/status

# 1. 配置Grafana dashboard
# 登录Grafana界面：http://fgedu.localhost:3000
# 导入PostgreSQL监控面板

# 2. 配置预警面板
$ sudo vi /etc/grafana/provisioning/dashboards/postgres_alerts.json
{
“annotations”: {
“list”: [
{
“builtIn”: 1,
“datasource”: “– Grafana –“,
“enable”: true,
“hide”: true,
“iconColor”: “rgba(0, 211, 255, 1)”,
“name”: “Annotations & Alerts”,
“type”: “dashboard”
}
]
},
“editable”: true,
“gnetId”: null,
“graphTooltip”: 0,
“id”: 1,
“links”: [],
“panels”: [
{
“alert”: {
“alertRuleTags”: {},
“conditions”: [
{
“evaluator”: {
“params”: [
80
],
“type”: “gt”
},
“operator”: {
“type”: “and”
},
“query”: {
“params”: [
“A”,
“5m”,
“now”
]
},
“reducer”: {
“params”: [],
“type”: “avg”
},
“type”: “query”
}
],
“executionErrorState”: “alerting”,
“for”: “5m”,
“frequency”: “1m”,
“handler”: 1,
“name”: “High CPU Usage”,
“noDataState”: “no_data”,
“notifications”: []
},
“aliasColors”: {},
“bars”: false,
“dashLength”: 10,
“dashes”: false,
“datasource”: “Prometheus”,
“fieldConfig”: {
“defaults”: {
“custom”: {}
},
“overrides”: []
},
“fill”: 1,
“fillGradient”: 0,
“gridPos”: {
“h”: 8,
“w”: 12,
“x”: 0,
“y”: 0
},
“hiddenSeries”: false,
“id”: 2,
“legend”: {
“avg”: false,
“current”: false,
“max”: false,
“min”: false,
“show”: true,
“total”: false,
“values”: false
},
“lines”: true,
“linewidth”: 1,
“nullPointMode”: “null”,
“options”: {
“alertThreshold”: true
},
“percentage”: false,
“pluginVersion”: “7.5.10”,
“pointradius”: 2,
“points”: false,
“renderer”: “flot”,
“seriesOverrides”: [],
“spaceLength”: 10,
“stack”: false,
“steppedLine”: false,
“targets”: [
{
“expr”: “100 – (avg by(instance) (irate(node_cpu_seconds_total{mode=\”idle\”}[5m])) * 100)”,
“interval”: “”,
“legendFormat”: “{{instance}}”,
“refId”: “A”
}
],
“thresholds”: [
{
“colorMode”: “critical”,
“fill”: true,
“line”: true,
“op”: “gt”,
“value”: 80,
“yaxis”: “left”
}
],
“timeFrom”: null,
“timeRegions”: [],
“timeShift”: null,
“title”: “CPU Usage”,
“tooltip”: {
“shared”: true,
“sort”: 0,
“value_type”: “individual”
},
“type”: “graph”,
“xaxis”: {
“buckets”: null,
“mode”: “time”,
“name”: null,
“show”: true,
“values”: []
},
“yaxes”: [
{
“format”: “percentunit”,
“label”: null,
“logBase”: 1,
“max”: null,
“min”: null,
“show”: true
},
{
“format”: “short”,
“label”: null,
“logBase”: 1,
“max”: null,
“min”: null,
“show”: true
}
],
“yaxis”: {
“align”: false,
“alignLevel”: null
}
}
],
“refresh”: “5s”,
“schemaVersion”: 26,
“style”: “dark”,
“tags”: [],
“templating”: {
“list”: []
},
“time”: {
“from”: “now-6h”,
“to”: “now”
},
“timepicker”: {},
“timezone”: “”,
“title”: “PostgreSQL Alerts”,
“uid”: “postgres-alerts”,
“version”: 1
}

# 3. 重启Grafana
$ sudo systemctl restart grafana-server

# 4. 验证监控配置
$ curl http://fgedu.localhost:3000