# 2. 实施步骤
# 步骤1：部署Prometheus
# 步骤2：部署Grafana
# 步骤3：部署Node Exporter
# 步骤4：部署Alertmanager
# 步骤5：配置监控规则
# 步骤6：配置告警规则
# 步骤7：配置Grafana面板
# 步骤8：验证监控效果

# 3. 应用效果
# 实现了对系统性能的实时监控
# 及时发现和解决性能问题
# 提高了系统的稳定性和可靠性

# 部署Prometheus
tar -xzf prometheus-2.45.0.linux-amd64.tar.gz
mv prometheus-2.45.0.linux-amd64/prometheus /usr/local/bin/
mv prometheus-2.45.0.linux-amd64/promtool /usr/local/bin/

# 部署Grafana
dnf install -y grafana

# 部署Node Exporter
for server in server1 server2 server3; do
ssh $server “wget https://github.com/prometheus/node_exporter/releases/download/v1.6.1/node_exporter-1.6.1.linux-amd64.tar.gz”
ssh $server “tar -xzf node_exporter-1.6.1.linux-amd64.tar.gz”
ssh $server “mv node_exporter-1.6.1.linux-amd64/node_exporter /usr/local/bin/”
ssh $server “cat > /etc/systemd/system/node_exporter.service << 'EOF' [Unit] Description=Node Exporter After=network.target [Service] Type=simple User=prometheus ExecStart=/usr/local/bin/node_exporter [Install] WantedBy=multi-user.target EOF" ssh $server "systemctl daemon-reload" ssh $server "systemctl start node_exporter" ssh $server "systemctl enable node_exporter" done # 配置Prometheus cat > /etc/prometheus/prometheus.yml << 'EOF' global: scrape_interval: 15s rule_files: - /etc/prometheus/rules/alert_rules.yml alerting: alertmanagers: - static_configs: - targets: ['localhost:9093'] scrape_configs: - job_name: 'node' static_configs: - targets: ['server1:9100', 'server2:9100', 'server3:9100'] EOF # 配置告警规则 cat > /etc/prometheus/rules/alert_rules.yml << 'EOF' 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”
description: “CPU usage is above 80% for 5 minutes”

– 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”
description: “Memory usage is above 80% for 5 minutes”

– alert: HighDiskUsage
expr: (node_filesystem_size_bytes{mountpoint=”/”} – node_filesystem_free_bytes{mountpoint=”/”}) / node_filesystem_size_bytes{mountpoint=”/”} * 100 > 90
for: 5m
labels:
severity: critical
annotations:
summary: “High Disk Usage”
description: “Disk usage is above 90% for 5 minutes”
EOF

# 启动服务
systemctl start prometheus
systemctl enable prometheus
systemctl start grafana-server
systemctl enable grafana-server
systemctl start alertmanager
systemctl enable alertmanager

# 验证监控效果
# 浏览器访问 http://localhost:9090
# 浏览器访问 http://localhost:3000
# 导入Node Exporter Full面板（ID: 1860）

# 2. 实施步骤
# 步骤1：部署Elasticsearch
# 步骤2：部署Logstash
# 步骤3：部署Kibana
# 步骤4：部署Filebeat
# 步骤5：配置日志收集
# 步骤6：配置日志分析
# 步骤7：配置告警
# 步骤8：验证日志分析效果

# 3. 应用效果
# 实现了对系统日志的实时收集和分析
# 及时发现和解决系统问题
# 提高了系统的可维护性

# 部署Elasticsearch
dnf install -y java-11-openjdk
wget https://artifacts.elastic.co/downloads/elasticsearch/elasticsearch-7.17.10-linux-x86_64.tar.gz
tar -xzf elasticsearch-7.17.10-linux-x86_64.tar.gz
mv elasticsearch-7.17.10 /opt/elasticsearch

# 配置Elasticsearch
cat > /opt/elasticsearch/config/elasticsearch.yml << 'EOF' cluster.name: fgedu-cluster node.name: node-1 path.data: /var/lib/elasticsearch path.logs: /var/log/elasticsearch network.host: 0.0.0.0 http.port: 9200 EOF # 创建用户和目录 useradd -m elasticsearch mkdir -p /var/lib/elasticsearch /var/log/elasticsearch chown -R elasticsearch:elasticsearch /opt/elasticsearch /var/lib/elasticsearch /var/log/elasticsearch # 创建Elasticsearch服务文件 cat > /etc/systemd/system/elasticsearch.service << 'EOF' [Unit] Description=Elasticsearch After=network.target [Service] Type=simple User=elasticsearch ExecStart=/opt/elasticsearch/bin/elasticsearch [Install] WantedBy=multi-user.target EOF # 部署Logstash wget https://artifacts.elastic.co/downloads/logstash/logstash-7.17.10-linux-x86_64.tar.gz tar -xzf logstash-7.17.10-linux-x86_64.tar.gz mv logstash-7.17.10 /opt/logstash # 配置Logstash cat > /opt/logstash/config/logstash.yml << 'EOF' path.data: /var/lib/logstash path.logs: /var/log/logstash EOF cat > /opt/logstash/pipeline/logstash.conf << 'EOF' input { beats { port => 5044
}
}

filter {
if [message] =~ /ERROR/ {
mutate {
add_field => { “severity” => “error” }
}
} else if [message] =~ /WARN/ {
mutate {
add_field => { “severity” => “warning” }
}
} else {
mutate {
add_field => { “severity” => “info” }
}
}
}

output {
elasticsearch {
hosts => [“localhost:9200”]
index => “logs-%{+YYYY.MM.dd}”
}
}
EOF

# 创建用户和目录
useradd -m logstash
mkdir -p /var/lib/logstash /var/log/logstash
chown -R logstash:logstash /opt/logstash /var/lib/logstash /var/log/logstash

# 创建Logstash服务文件
cat > /etc/systemd/system/logstash.service << 'EOF' [Unit] Description=Logstash After=network.target [Service] Type=simple User=logstash ExecStart=/opt/logstash/bin/logstash [Install] WantedBy=multi-user.target EOF # 部署Kibana wget https://artifacts.elastic.co/downloads/kibana/kibana-7.17.10-linux-x86_64.tar.gz tar -xzf kibana-7.17.10-linux-x86_64.tar.gz mv kibana-7.17.10-linux-x86_64 /opt/kibana # 配置Kibana cat > /opt/kibana/config/kibana.yml << 'EOF' server.port: 5601 server.host: "0.0.0.0" elasticsearch.hosts: ["http://localhost:9200"] EOF # 创建用户和目录 useradd -m kibana chown -R kibana:kibana /opt/kibana # 创建Kibana服务文件 cat > /etc/systemd/system/kibana.service << 'EOF' [Unit] Description=Kibana After=network.target [Service] Type=simple User=kibana ExecStart=/opt/kibana/bin/kibana [Install] WantedBy=multi-user.target EOF # 部署Filebeat for server in server1 server2 server3; do ssh $server "wget https://artifacts.elastic.co/downloads/beats/filebeat/filebeat-7.17.10-linux-x86_64.tar.gz" ssh $server "tar -xzf filebeat-7.17.10-linux-x86_64.tar.gz" ssh $server "mv filebeat-7.17.10-linux-x86_64/filebeat /usr/local/bin/" ssh $server "cat > /etc/filebeat/filebeat.yml << 'EOF' filebeat.inputs: - type: log enabled: true paths: - /var/log/*.log output.logstash: hosts: ["localhost:5044"] EOF" ssh $server "cat > /etc/systemd/system/filebeat.service << 'EOF' [Unit] Description=Filebeat After=network.target [Service] Type=simple User=root ExecStart=/usr/local/bin/filebeat -c /etc/filebeat/filebeat.yml [Install] WantedBy=multi-user.target EOF" ssh $server "systemctl daemon-reload" ssh $server "systemctl start filebeat" ssh $server "systemctl enable filebeat" done # 启动服务 systemctl daemon-reload systemctl start elasticsearch systemctl enable elasticsearch systemctl start logstash systemctl enable logstash systemctl start kibana systemctl enable kibana # 验证日志分析效果 # 浏览器访问 http://localhost:5601 # 创建索引模式 logs-* # 查看日志数据

# 2. 实施步骤
# 步骤1：部署Zabbix Server
# 步骤2：部署Zabbix Agent
# 步骤3：配置监控主机
# 步骤4：配置监控项
# 步骤5：配置告警规则
# 步骤6：配置可视化面板
# 步骤7：验证监控效果

# 3. 应用效果
# 实现了对系统性能的全面监控
# 及时发现和解决性能问题
# 提高了系统的稳定性和可靠性

# 部署Zabbix Server
dnf install -y zabbix-server-mysql zabbix-web-mysql zabbix-apache-conf zabbix-sql-scripts zabbix-agent

# 配置数据库
mysql -u root -p -e “CREATE DATABASE zabbix CHARACTER SET utf8mb4 COLLATE utf8mb4_bin;”
mysql -u root -p -e “CREATE USER ‘zabbix’@’localhost’ IDENTIFIED BY ‘password’;”
mysql -u root -p -e “GRANT ALL PRIVILEGES ON zabbix.* TO ‘zabbix’@’localhost’;”
mysql -u root -p zabbix < /usr/share/zabbix-sql-scripts/mysql/server.sql # 配置Zabbix Server cat > /etc/zabbix/zabbix_server.conf << 'EOF' DBHost=localhost DBName=zabbix DBUser=zabbix DBPassword=password EOF # 配置PHP cat > /etc/php-fpm.d/zabbix.conf << 'EOF' php_value[date.timezone] = Asia/Shanghai EOF # 启动服务 systemctl start zabbix-server systemctl enable zabbix-server systemctl start httpd systemctl enable httpd systemctl start php-fpm systemctl enable php-fpm systemctl start zabbix-agent systemctl enable zabbix-agent # 部署Zabbix Agent for server in server1 server2 server3; do ssh $server "dnf install -y zabbix-agent" ssh $server "cat > /etc/zabbix/zabbix_agentd.conf << 'EOF' Server=zabbix-server-ip ServerActive=zabbix-server-ip Hostname=server1 EOF" ssh $server "systemctl start zabbix-agent" ssh $server "systemctl enable zabbix-agent" done # 配置Zabbix # 浏览器访问 http://localhost/zabbix # 登录Zabbix（默认用户名和密码：Admin/zabbix） # 添加监控主机 # 配置监控项 # 配置告警规则 # 配置可视化面板 # 验证监控效果 # 浏览器访问 http://localhost/zabbix # 查看监控数据和告警信息