feat(监控): 添加Telegraf监控配置和磁盘监控脚本

refactor(容器): 从Docker迁移到Podman并更新Nomad配置

fix(配置): 修复代理和别名配置问题

docs(文档): 更新配置文件和脚本注释

chore(清理): 移除不再使用的Consul和Docker相关文件

configuration/templates/disk-monitoring.conf.j2

@@ -0,0 +1,68 @@
+# 硬盘监控配置
+# 监控所有挂载点的硬盘使用情况
+
+# 硬盘使用率监控
+[[inputs.disk]]
+  ## 忽略的文件系统类型
+  ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
+  
+  ## 监控所有挂载点
+  mount_points = ["/", "/var", "/tmp", "/opt", "/home"]
+  
+  ## 标签配置
+  [inputs.disk.tags]
+    service = "disk-monitoring"
+    
+# 硬盘 I/O 监控
+[[inputs.diskio]]
+  ## 监控所有设备
+  devices = ["sda", "sdb", "sdc", "sdd", "nvme0n1", "nvme1n1"]
+  
+  ## 跳过序列号收集以提高性能
+  skip_serial_number = true
+  
+  [inputs.diskio.tags]
+    service = "disk-io-monitoring"
+
+# 文件系统 inode 监控
+[[inputs.disk]]
+  ## 监控 inode 使用情况
+  ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
+  
+  ## 收集 inode 信息
+  [inputs.disk.tags]
+    service = "inode-monitoring"
+
+# 进程监控（可选，用于监控可能占用大量硬盘的进程）
+[[inputs.procstat]]
+  ## 监控 Docker 进程（如果存在）
+  pattern = "docker"
+  
+  [inputs.procstat.tags]
+    service = "docker-process"
+
+[[inputs.procstat]]
+  ## 监控 Podman 进程
+  pattern = "podman"
+  
+  [inputs.procstat.tags]
+    service = "podman-process"
+
+[[inputs.procstat]]
+  ## 监控 Nomad 进程
+  pattern = "nomad"
+  
+  [inputs.procstat.tags]
+    service = "nomad-process"
+
+# 日志文件大小监控
+[[inputs.filestat]]
+  files = [
+    "/var/log/nomad/*.log",
+    "/var/log/syslog",
+    "/var/log/kern.log",
+    "/var/log/auth.log"
+  ]
+  
+  [inputs.filestat.tags]
+    service = "log-monitoring"

configuration/templates/system-monitoring.conf.j2

@@ -0,0 +1,68 @@
+# 系统监控配置
+# CPU、内存、网络等系统资源监控
+
+# CPU 监控
+[[inputs.cpu]]
+  ## 是否收集每个 CPU 核心的信息
+  percpu = true
+  ## 是否收集总 CPU 信息
+  totalcpu = true
+  ## 收集字段
+  collect_cpu_time = false
+  ## 报告活跃的 CPU
+  report_active = false
+  
+  [inputs.cpu.tags]
+    service = "cpu-monitoring"
+
+# 内存监控
+[[inputs.mem]]
+  [inputs.mem.tags]
+    service = "memory-monitoring"
+
+# 网络接口监控
+[[inputs.net]]
+  ## 接口配置
+  interfaces = ["eth*", "en*", "tailscale*"]
+  
+  [inputs.net.tags]
+    service = "network-monitoring"
+
+# 系统负载监控
+[[inputs.system]]
+  [inputs.system.tags]
+    service = "system-load"
+
+# 内核统计
+[[inputs.kernel]]
+  [inputs.kernel.tags]
+    service = "kernel-stats"
+
+# 网络统计
+[[inputs.netstat]]
+  [inputs.netstat.tags]
+    service = "network-stats"
+
+# 交换分区监控
+[[inputs.swap]]
+  [inputs.swap.tags]
+    service = "swap-monitoring"
+
+# 服务状态监控
+[[inputs.systemd_units]]
+  ## 监控的服务
+  units = ["nomad.service", "docker.service", "podman.service", "telegraf.service", "tailscaled.service"]
+  
+  [inputs.systemd_units.tags]
+    service = "service-monitoring"
+
+# 硬盘健康状态监控（如果支持 SMART）
+[[inputs.smart]]
+  ## SMART 监控路径
+  path_smartctl = "/usr/sbin/smartctl"
+  
+  ## 超时设置
+  timeout = "30s"
+  
+  [inputs.smart.tags]
+    service = "smart-monitoring"

configuration/templates/telegraf-env.j2

@@ -0,0 +1,7 @@
+# Telegraf 环境变量配置
+# InfluxDB 2.x 认证信息
+
+INFLUX_TOKEN={{ influxdb_token }}
+INFLUX_ORG={{ influxdb_org }}
+INFLUX_BUCKET={{ influxdb_bucket }}
+INFLUX_URL={{ influxdb_url }}

configuration/templates/telegraf.conf.j2

@@ -0,0 +1,53 @@
+# Telegraf 主配置文件
+# Nomad 集群硬盘监控配置
+
+# 全局设置
+[global_tags]
+  nomad_cluster = "production"
+  node_role = "{{ nomad_role | default('unknown') }}"
+  hostname = "{{ inventory_hostname }}"
+
+# Agent 配置
+[agent]
+  interval = "{{ collection_interval | default(30) }}s"
+  round_interval = true
+  metric_batch_size = 1000
+  metric_buffer_limit = 10000
+  collection_jitter = "2s"
+  flush_interval = "10s"
+  flush_jitter = "0s"
+  precision = ""
+  hostname = "{{ inventory_hostname }}"
+  omit_hostname = false
+
+# 输出配置 - InfluxDB 2.x
+[[outputs.influxdb_v2]]
+  urls = ["{{ influxdb_url }}"]
+  token = "{{ influxdb_token }}"
+  organization = "{{ influxdb_org | default('nomad') }}"
+  bucket = "{{ influxdb_bucket | default('nomad_monitoring') }}"
+  
+  ## 连接配置
+  timeout = "10s"
+  max_retries = 3
+  retry_timeout = "5s"
+  
+  ## 数据精度
+  precision = "s"
+  
+  ## TLS 配置（如果需要）
+  # tls_ca = "/etc/telegraf/ca.pem"
+  # tls_cert = "/etc/telegraf/cert.pem"
+  # tls_key = "/etc/telegraf/key.pem"
+  # insecure_skip_verify = false
+
+# 日志配置 - 禁用本地日志以节省硬盘空间
+[log]
+  ## 只输出错误日志到 syslog，不生成本地文件
+  level = "ERROR"
+  ## 禁用本地日志文件
+  # file = "/var/log/telegraf/telegraf.log"
+  ## 使用 syslog 替代本地文件
+  logtarget = "syslog"
+  ## 禁用日志轮转
+  logrotate = false

configuration/templates/telegraf.service.j2

@@ -0,0 +1,29 @@
+[Unit]
+Description=Telegraf - 节点监控服务
+Documentation=https://github.com/influxdata/telegraf
+After=network.target
+
+[Service]
+Type=notify
+User=telegraf
+Group=telegraf
+ExecStart=/usr/bin/telegraf --config {{ telegraf_config_url }}
+ExecReload=/bin/kill -HUP $MAINPID
+KillMode=control-group
+Restart=on-failure
+RestartSec=5
+TimeoutStopSec=20
+EnvironmentFile=/etc/default/telegraf
+
+# 安全配置
+NoNewPrivileges=true
+PrivateTmp=true
+ProtectSystem=strict
+ProtectHome=true
+ReadWritePaths=/var/lib/telegraf
+ProtectKernelTunables=true
+ProtectKernelModules=true
+ProtectControlGroups=true
+
+[Install]
+WantedBy=multi-user.target