# 使用内置工具监控

## mongostat
$ /mongodb/app/bin/mongostat

## mongotop
$ /mongodb/app/bin/mongotop

## db.serverStatus()
$ /mongodb/app/bin/mongosh -u fgedu -p fgedu123 –authenticationDatabase admin
fgedu.net.cn> db.serverStatus()

## db.stats()
fgedu.net.cn> db.stats()

## db.collection.stats()
fgedu.net.cn> db.fgedu_collection.stats()

## db.currentOp()
fgedu.net.cn> db.currentOp()

## db.profile()
fgedu.net.cn> db.setProfilingLevel(1, { slowms: 100 })
fgedu.net.cn> db.system.profile.find().sort({ ts: -1 }).limit(10)

# 使用Prometheus和Grafana监控

## 安装Prometheus
$ wget https://github.com/prometheus/prometheus/releases/download/v2.37.0/prometheus-2.37.0.linux-amd64.tar.gz
$ tar -zxvf prometheus-2.37.0.linux-amd64.tar.gz
$ mv prometheus-2.37.0.linux-amd64 /usr/local/prometheus

## 配置Prometheus
$ cat > /usr/local/prometheus/prometheus.yml << EOF global: scrape_interval: 15s scrape_configs: - job_name: 'mongodb' static_configs: - targets: ['localhost:9216'] EOF ## 安装MongoDB Exporter $ wget https://github.com/percona/mongodb_exporter/releases/download/v0.20.0/mongodb_exporter-0.20.0.linux-amd64.tar.gz $ tar -zxvf mongodb_exporter-0.20.0.linux-amd64.tar.gz $ mv mongodb_exporter-0.20.0.linux-amd64/mongodb_exporter /usr/local/bin/ ## 启动MongoDB Exporter $ export MONGODB_URI="mongodb://fgedu:fgedu123@localhost:27017/admin" $ nohup mongodb_exporter --web.listen-address=:9216 & ## 启动Prometheus $ nohup /usr/local/prometheus/prometheus --config.file=/usr/local/prometheus/prometheus.yml & ## 安装Grafana $ wget https://dl.grafana.com/oss/release/grafana-8.5.6.linux-amd64.tar.gz $ tar -zxvf grafana-8.5.6.linux-amd64.tar.gz $ mv grafana-8.5.6 /usr/local/grafana ## 启动Grafana $ nohup /usr/local/grafana/bin/grafana-server & ## 配置Grafana数据源 # 访问 http://localhost:3000 # 用户名: admin, 密码: admin # 添加Prometheus数据源 # 导入MongoDB Dashboard (ID: 7353)

# 查询性能分析

## 启用慢查询日志
$ /mongodb/app/bin/mongosh -u fgedu -p fgedu123 –authenticationDatabase admin
fgedu.net.cn> db.setProfilingLevel(1, { slowms: 100 })

## 查看慢查询日志
fgedu.net.cn> db.system.profile.find().sort({ ts: -1 }).limit(10)

## 使用explain分析查询计划
fgedu.net.cn> db.fgedu_collection.find({ name: “fgedu01” }).explain(“executionStats”)

## 分析查询性能
fgedu.net.cn> db.fgedu_collection.find({ age: { $gt: 25 } }).explain(“executionStats”)

## 分析聚合查询
fgedu.net.cn> db.fgedu_collection.aggregate([
… { $match: { age: { $gt: 25 } } },
… { $group: { _id: “$age”, count: { $sum: 1 } } },
… { $sort: { count: -1 } }
… ]).explain(“executionStats”)

# 系统性能分析

## 查看系统资源使用情况
$ top
$ iostat -x
$ vmstat
$ netstat -tulpn

## 查看MongoDB资源使用情况
$ /mongodb/app/bin/mongostat
$ /mongodb/app/bin/mongotop

## 查看MongoDB实例状态
$ /mongodb/app/bin/mongosh -u fgedu -p fgedu123 –authenticationDatabase admin
fgedu.net.cn> db.serverStatus()

## 查看存储引擎状态
fgedu.net.cn> db.serverStatus().wiredTiger

## 查看连接状态
fgedu.net.cn> db.serverStatus().connections

## 查看操作统计
fgedu.net.cn> db.serverStatus().opcounters

# 配置Prometheus告警

## 创建告警规则文件
$ cat > /usr/local/prometheus/rules/mongodb_alerts.yml << EOF groups: - name: mongodb_alerts rules: - alert: MongoDBInstanceDown expr: mongodb_up == 0 for: 5m labels: severity: critical annotations: summary: "MongoDB instance down" description: "MongoDB instance {{ $labels.instance }} is down for more than 5 minutes" - alert: MongoDBHighCPU expr: (avg by(instance) (irate(process_cpu_seconds_total{job="mongodb"}[5m])) / count by(instance) (count_cpu_core{job="mongodb"}) * 100 > 80
for: 5m
labels:
severity: warning
annotations:
summary: “MongoDB high CPU usage”
description: “MongoDB instance {{ $labels.instance }} CPU usage is above 80% for more than 5 minutes”

– alert: MongoDBHighMemory
expr: (mongodb_memory_resident_bytes / mongodb_memory_virtual_bytes) * 100 > 90
for: 5m
labels:
severity: warning
annotations:
summary: “MongoDB high memory usage”
description: “MongoDB instance {{ $labels.instance }} memory usage is above 90% for more than 5 minutes”

– alert: MongoDBHighConnections
expr: mongodb_connections_current > mongodb_connections_available * 0.8
for: 5m
labels:
severity: warning
annotations:
summary: “MongoDB high connections”
description: “MongoDB instance {{ $labels.instance }} connections are above 80% of available for more than 5 minutes”

– alert: MongoDBReplicationLag
expr: mongodb_repl_lag > 30
for: 5m
labels:
severity: warning
annotations:
summary: “MongoDB replication lag”
description: “MongoDB instance {{ $labels.instance }} replication lag is above 30 seconds for more than 5 minutes”
EOF

## 修改Prometheus配置文件
$ cat > /usr/local/prometheus/prometheus.yml << EOF global: scrape_interval: 15s rule_files: - "rules/mongodb_alerts.yml" scrape_configs: - job_name: 'mongodb' static_configs: - targets: ['localhost:9216'] alerting: alertmanagers: - static_configs: - targets: ['localhost:9093'] EOF ## 安装Alertmanager $ wget https://github.com/prometheus/alertmanager/releases/download/v0.23.0/alertmanager-0.23.0.linux-amd64.tar.gz $ tar -zxvf alertmanager-0.23.0.linux-amd64.tar.gz $ mv alertmanager-0.23.0.linux-amd64 /usr/local/alertmanager ## 配置Alertmanager $ cat > /usr/local/alertmanager/alertmanager.yml << EOF global: resolve_timeout: 5m route: group_by: ['alertname'] group_wait: 30s group_interval: 5m repeat_interval: 1h receiver: 'email' receivers: - name: 'email' email_configs: - to: 'admin@fgedu.net.cn' from: 'alertmanager@fgedu.net.cn' smarthost: 'smtp.fgedu.net.cn:587' auth_username: 'alertmanager' auth_password: 'password' require_tls: true EOF ## 启动Alertmanager $ nohup /usr/local/alertmanager/alertmanager --config.file=/usr/local/alertmanager/alertmanager.yml & ## 重启Prometheus $ pkill prometheus $ nohup /usr/local/prometheus/prometheus --config.file=/usr/local/prometheus/prometheus.yml &