# 查看EC2实例的CPU利用率
$ aws cloudwatch get-metric-statistics \
–namespace AWS/EC2 \
–metric-name CPUUtilization \
–dimensions Name=InstanceId,Value=i-1234567890abcdef0 \
–start-time 2026-04-03T00:00:00Z \
–end-time 2026-04-03T12:00:00Z \
–period 3600 \
–statistics Average

# 查看S3存储桶的请求数
$ aws cloudwatch get-metric-statistics \
–namespace AWS/S3 \
–metric-name NumberOfObjects \
–dimensions Name=BucketName,Value=my-bucket Name=StorageType,Value=AllStorageTypes \
–start-time 2026-04-03T00:00:00Z \
–end-time 2026-04-03T12:00:00Z \
–period 3600 \
–statistics Average

# 创建EC2 CPU告警
$ aws cloudwatch put-metric-alarm \
–alarm-name EC2-CPU-High \
–alarm-description “Alarm when EC2 CPU exceeds 80%” \
–metric-name CPUUtilization \
–namespace AWS/EC2 \
–statistic Average \
–period 300 \
–threshold 80 \
–comparison-operator GreaterThanThreshold \
–dimensions Name=InstanceId,Value=i-1234567890abcdef0 \
–evaluation-periods 2 \
–alarm-actions arn:aws:sns:us-west-2:123456789012:MyTopic \
–unit Percent

# 创建S3存储告警
$ aws cloudwatch put-metric-alarm \
–alarm-name S3-Storage-High \
–alarm-description “Alarm when S3 storage exceeds 90%” \
–metric-name BucketSizeBytes \
–namespace AWS/S3 \
–statistic Average \
–period 86400 \
–threshold 900000000000 \
–comparison-operator GreaterThanThreshold \
–dimensions Name=BucketName,Value=my-bucket Name=StorageType,Value=StandardStorage \
–evaluation-periods 1 \
–alarm-actions arn:aws:sns:us-west-2:123456789012:MyTopic \
–unit Bytes

风哥风哥提示：告警阈值的设置应该根据实际业务需求和资源特性进行调整，避免过多的误报。

3. Azure云监控与告警

3.1 Azure Monitor

Azure Monitor是Azure的综合监控服务，提供了对Azure资源和应用程序的监控能力。

3.2 监控指标

# 查看VM的CPU利用率
$ az monitor metrics list \
–resource /subscriptions/12345678-1234-1234-1234-123456789012/resourceGroups/myResourceGroup/providers/Microsoft.Compute/virtualMachines/myVM \
–metric “Percentage CPU” \
–interval PT1H \
–start-time 2026-04-03T00:00:00Z \
–end-time 2026-04-03T12:00:00Z

# 查看存储账户的使用情况
$ az monitor metrics list \
–resource /subscriptions/12345678-1234-1234-1234-123456789012/resourceGroups/myResourceGroup/providers/Microsoft.Storage/storageAccounts/mystorageaccount \
–metric “UsedCapacity” \
–interval PT1H \
–start-time 2026-04-03T00:00:00Z \
–end-time 2026-04-03T12:00:00Z

# 创建VM CPU告警
$ az monitor metrics alert create \
–name VM-CPU-High \
–resource-group myResourceGroup \
–scopes /subscriptions/12345678-1234-1234-1234-123456789012/resourceGroups/myResourceGroup/providers/Microsoft.Compute/virtualMachines/myVM \
–condition “avg Percentage CPU > 80″ \
–window-size 5m \
–evaluation-frequency 1m \
–action-groups ” /subscriptions/12345678-1234-1234-1234-123456789012/resourceGroups/myResourceGroup/providers/microsoft.insights/actiongroups/myActionGroup”

# 创建存储账户告警
$ az monitor metrics alert create \
–name Storage-Usage-High \
–resource-group myResourceGroup \
–scopes /subscriptions/12345678-1234-1234-1234-123456789012/resourceGroups/myResourceGroup/providers/Microsoft.Storage/storageAccounts/mystorageaccount \
–condition “avg UsedCapacity > 900000000000″ \
–window-size 1h \
–evaluation-frequency 15m \
–action-groups ” /subscriptions/12345678-1234-1234-1234-123456789012/resourceGroups/myResourceGroup/providers/microsoft.insights/actiongroups/myActionGroup”

学习交流加群风哥微信: itpux-com

4. 阿里云监控与告警

4.1 云监控

阿里云监控是阿里云的综合监控服务，提供了对阿里云资源和应用程序的监控能力。

4.2 监控指标

# 查看ECS实例的CPU利用率
$ aliyun cloudmonitor DescribeMetricList \
–Project acs_ecs_dashboard \
–Metric cpu_total \
–Dimensions [{“instanceId”:”i-2ze1234567890″}] \
–StartTime “2026-04-03T00:00:00Z” \
–EndTime “2026-04-03T12:00:00Z” \
–Period 3600

# 查看OSS存储桶的使用情况
$ aliyun cloudmonitor DescribeMetricList \
–Project acs_oss \
–Metric storage \
–Dimensions [{“bucket”:”my-bucket”}] \
–StartTime “2026-04-03T00:00:00Z” \
–EndTime “2026-04-03T12:00:00Z” \
–Period 3600

# 创建ECS CPU告警
$ aliyun cloudmonitor CreateAlarm \
–Project acs_ecs_dashboard \
–Metric cpu_total \
–Dimensions [{“instanceId”:”i-2ze1234567890″}] \
–AlarmName ECS-CPU-High \
–Expression “$1>80” \
–Period 60 \
–Statistics average \
–ComparisonOperator GreaterThanThreshold \
–Threshold 80 \
–EvaluationCount 2 \
–ContactGroups “MyContactGroup”

# 创建OSS存储告警
$ aliyun cloudmonitor CreateAlarm \
–Project acs_oss \
–Metric storage \
–Dimensions [{“bucket”:”my-bucket”}] \
–AlarmName OSS-Storage-High \
–Expression “$1>900000000000” \
–Period 3600 \
–Statistics average \
–ComparisonOperator GreaterThanThreshold \
–Threshold 900000000000 \
–EvaluationCount 1 \
–ContactGroups “MyContactGroup”

学习交流加群风哥QQ113257174

5. Prometheus监控

5.1 Prometheus概述

Prometheus是一个开源的监控系统，特别适合容器环境的监控。它提供了强大的时序数据收集和查询能力。

5.2 Prometheus安装

# 使用Docker安装Prometheus
$ docker run -d \
–name prometheus \
-p 9090:9090 \
-v /path/to/prometheus.yml:/etc/prometheus/prometheus.yml \
prom/prometheus

# prometheus.yml配置示例
$ cat /path/to/prometheus.yml
global:
scrape_interval: 15s

scrape_configs:
– job_name: ‘node’
static_configs:
– targets: [‘node-exporter:9100’]

– job_name: ‘docker’
static_configs:
– targets: [‘cadvisor:8080’]

– job_name: ‘kubernetes’
kubernetes_sd_configs:
– role: pod
relabel_configs:
– source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
action: keep
regex: true

# 查询CPU使用率
node_cpu_seconds_total{mode=”idle”}

# 查询内存使用情况
node_memory_MemTotal_bytes – node_memory_MemFree_bytes

# 查询磁盘使用情况
node_filesystem_size_bytes{mountpoint=”/”} – node_filesystem_free_bytes{mountpoint=”/”}

# 查询网络流量
rate(node_network_transmit_bytes_total[5m])

更多学习教程公众号风哥教程itpux_com

6. Grafana可视化

6.1 Grafana概述

Grafana是一个开源的可视化平台，支持多种数据源，包括Prometheus、CloudWatch、Azure Monitor等。

6.2 Grafana安装

# 使用Docker安装Grafana
$ docker run -d \
–name grafana \
-p 3000:3000 \
grafana/grafana

# 登录Grafana
# 访问 http://fgedudb:3000
# 默认fgedu: admin
# 默认密码: admin

# 配置Prometheus数据源
1. 登录Grafana
2. 点击左侧菜单的”Configuration” -> “Data sources”
3. 点击”Add data source”
4. 选择”Prometheus”
5. 输入Prometheus的URL (例如: http://prometheus:9090)
6. 点击”Save & Test”

# 配置CloudWatch数据源
1. 登录Grafana
2. 点击左侧菜单的”Configuration” -> “Data sources”
3. 点击”Add data source”
4. 选择”CloudWatch”
5. 输入AWS访问密钥和区域
6. 点击”Save & Test”

# 导入预定义仪表板
1. 登录Grafana
2. 点击左侧菜单的”Create” -> “Import”
3. 输入仪表板ID (例如: 1860 for Node Exporter)
4. 选择数据源
5. 点击”Import”

# 创建自定义仪表板
1. 登录Grafana
2. 点击左侧菜单的”Create” -> “Dashboard”
3. 点击”Add new panel”
4. 选择数据源
5. 输入查询语句
6. 配置可视化选项
7. 点击”Apply”

author:www.itpux.com

7. 告警管理

7.1 告警级别

• 严重 (Critical): 需要立即处理的问题，可能导致服务中断
• 警告 (Warning): 需要关注的问题，可能会影响服务性能
• 信息 (Info): 提供信息性通知，不影响服务

7.2 告警通知渠道

# 配置Grafana告警通知渠道
1. 登录Grafana
2. 点击左侧菜单的”Alerting” -> “Notification channels”
3. 点击”Add channel”
4. 选择通知类型 (例如: Email, Slack, PagerDuty)
5. 配置通知设置
6. 点击”Save”

# 配置Prometheus告警
$ cat /path/to/alerting_rules.yml
groups:
– name: node_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 above 80% for 5 minutes”

# 启动Prometheus时加载告警规则
$ docker run -d \
–name prometheus \
-p 9090:9090 \
-v /path/to/prometheus.yml:/etc/prometheus/prometheus.yml \
-v /path/to/alerting_rules.yml:/etc/prometheus/alerting_rules.yml \
prom/prometheus \
–config.file=/etc/prometheus/prometheus.yml \
–alertmanager.url=http://alertmanager:9093