[#1] 增加部署测试prom&grafana

deploytest/docker-compose.yml

@@ -0,0 +1,41 @@
+version: "3.8"
+
+networks:
+  monitor_net:
+    driver: bridge
+
+services:
+  prometheus:
+    image: prom/prometheus:latest
+    container_name: deploytest-prometheus
+    volumes:
+      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      # - ./prometheus/alerts.yml:/etc/prometheus/alerts.yml:ro  # 可选：如需告警规则可解开
+    command:
+      - "--config.file=/etc/prometheus/prometheus.yml"
+      - "--web.enable-lifecycle"
+    ports:
+      - "19090:9090"
+    networks:
+      - monitor_net
+    extra_hosts:
+      # 兼容 Linux：让容器中的 host.docker.internal 指向宿主机
+      - "host.docker.internal:host-gateway"
+
+  grafana:
+    image: grafana/grafana:latest
+    container_name: deploytest-grafana
+    depends_on:
+      - prometheus
+    ports:
+      - "13000:3000"
+    networks:
+      - monitor_net
+    volumes:
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
+    environment:
+      - GF_SECURITY_ADMIN_USER=admin
+      - GF_SECURITY_ADMIN_PASSWORD=admin
+      - GF_USERS_ALLOW_SIGN_UP=false
+

deploytest/grafana/dashboards/netconf-transceiver-exporter.json

@@ -0,0 +1,450 @@
+{
+  "id": null,
+  "uid": "netconf-transceiver-exporter",
+  "title": "NETCONF Transceiver Exporter",
+  "tags": ["netconf", "transceiver", "exporter"],
+  "timezone": "browser",
+  "schemaVersion": 38,
+  "version": 1,
+  "refresh": "30s",
+  "panels": [
+    {
+      "type": "stat",
+      "title": "Exporter Scrape Success Ratio",
+      "description": "含义：当前选择的所有 $device 的 netconf_scrape_success 平均值，介于 0–1。用法：一眼看整体抓取健康度（≈1 表示基本都成功，<1 表示有失败）；多选多个设备时是平均值，可快速知道整体是否在抖。",
+      "id": 1,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "targets": [
+        {
+          "expr": "avg(netconf_scrape_success{job=~\"$job\", device=~\"$device\"})",
+          "legendFormat": "success_ratio",
+          "refId": "A"
+        }
+      ],
+      "options": {
+        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+        "orientation": "horizontal",
+        "textMode": "auto"
+      },
+      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 }
+    },
+    {
+      "type": "timeseries",
+      "title": "Exporter Build Info (TODO)",
+      "description": "含义：预留的 exporter_build_info{version,python_version} 指标，可查看 exporter 版本与 Python 运行环境。用法：目前 exporter 尚未实现该指标，显示 No data 属正常；未来实现后，可以用来确认线上跑的是哪个版本/解释器，排查“是不是在用最新代码”。",
+      "id": 9,
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "exporter_build_info{job=~\"$job\", device=~\"$device\"}",
+          "legendFormat": "{{version}} ({{python_version}})",
+          "refId": "A"
+        }
+      ],
+      "gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 }
+    },
+    {
+      "type": "stat",
+      "title": "Exporter Devices Total (TODO)",
+      "description": "含义：预留的 exporter_devices_total，表示 exporter 配置或注册的设备总数。用法：当前无数据属预期；未来实现后，可对比 total 与 enabled（Panel 11），例如 total=10 但 enabled=8，用来找出被禁用或注册失败的设备。",
+      "id": 10,
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "exporter_devices_total{job=~\"$job\", device=~\"$device\"}",
+          "legendFormat": "{{device}} total",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": { "defaults": { "unit": "none" }, "overrides": [] },
+      "options": {
+        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+        "orientation": "horizontal",
+        "textMode": "auto"
+      },
+      "gridPos": { "h": 4, "w": 6, "x": 12, "y": 0 }
+    },
+    {
+      "type": "stat",
+      "title": "Exporter Devices Enabled (TODO)",
+      "description": "含义：预留的 exporter_devices_enabled，表示实际启用抓取的设备数量。用法：当前无数据属预期；未来实现后，可快速判断是否有设备被标记为 disabled 或注册失败，并与 Panel 10 对比排查配置问题。",
+      "id": 11,
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "exporter_devices_enabled{job=~\"$job\", device=~\"$device\"}",
+          "legendFormat": "{{device}} enabled",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": { "defaults": { "unit": "none" }, "overrides": [] },
+      "options": {
+        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+        "orientation": "horizontal",
+        "textMode": "auto"
+      },
+      "gridPos": { "h": 4, "w": 6, "x": 18, "y": 0 }
+    },
+    {
+      "type": "timeseries",
+      "title": "Scrape Success by Device",
+      "description": "含义：每个设备的 netconf_scrape_success 随时间的 0/1 曲线（按 $device 过滤）。用法：查看“哪个设备最近在频繁失败”：曲线掉到 0 的时间段就是失败窗口；多设备同时查看时，每条线代表一个 device，可以直观看出谁最不稳定。",
+      "id": 2,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "targets": [
+        {
+          "expr": "netconf_scrape_success{job=~\"$job\", device=~\"$device\"}",
+          "legendFormat": "{{device}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "bool" },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 9, "x": 6, "y": 0 }
+    },
+    {
+      "type": "timeseries",
+      "title": "Scrape Duration per Device",
+      "description": "含义：每个设备的 netconf_scrape_duration_seconds，单位秒。用法：判断哪台设备抓取最慢（曲线越高，抓取耗时越长，可能 RPC 多或设备性能差）；观察趋势变化，例如某设备 duration 从 2s 突然升到 10s，提示设备压力或链路问题。",
+      "id": 3,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "targets": [
+        {
+          "expr": "netconf_scrape_duration_seconds{job=~\"$job\", device=~\"$device\"}",
+          "legendFormat": "{{device}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "s" },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 9, "x": 15, "y": 0 }
+    },
+    {
+      "type": "table",
+      "title": "Scrape Errors by Device & Type (5m)",
+      "description": "含义：最近 5 分钟内 netconf_scrape_errors_total 的增长量，按 (device,error_type) 聚合。用法：出现异常时优先查看 error_type（如 AuthError、RpcTimeout、UnknownError 等）；配合 Panel 2/3 使用，当某设备 success 掉、duration 拉长时，看对应的 error_type 是什么以定位问题。",
+      "id": 4,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "targets": [
+        {
+          "expr": "sum(increase(netconf_scrape_errors_total{job=~\"$job\", device=~\"$device\"}[5m])) by (device, error_type)",
+          "format": "table",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": { "defaults": {}, "overrides": [] },
+      "gridPos": { "h": 6, "w": 12, "x": 0, "y": 4 }
+    },
+    {
+      "type": "timeseries",
+      "title": "Transceiver Supply Voltage",
+      "description": "含义：transceiver_supply_voltage_volts，按 {device,port,component_name} 展示各光模块电压。用法：$port 选 All 时可对比不同端口/模块电压是否在合理区间；当某个 transceiver 电压明显过低或过高时，通过 legend 中的 device/port/component_name 精确定位异常模块。",
+      "id": 12,
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "transceiver_supply_voltage_volts{job=~\"$job\", device=~\"$device\", port=~\"$port\"}",
+          "legendFormat": "{{device}}/{{port}}/{{component_name}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "volt" },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 6 }
+    },
+    {
+      "type": "timeseries",
+      "title": "Transceiver Temperature (with vendor/serial)",
+      "description": "含义：transceiver_temperature_celsius 与 transceiver_info_info join 后的温度曲线，legend 中包含 vendor 与 serial 等元数据。用法：在同一设备下对比多个模块温度，快速发现温度显著偏高的模块；带 serial 的 legend 方便截图或记录，用于资产与维护（如“序列号为 X 的模块长期偏高”）。",
+      "id": 13,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "targets": [
+        {
+          "expr": "transceiver_temperature_celsius{job=~\"$job\", device=~\"$device\", port=~\"$port\"} * on(job, device, port, component_name) group_left(vendor, serial, part_number, hardware_rev) transceiver_info_info{job=~\"$job\", device=~\"$device\"}",
+          "legendFormat": "{{device}}/{{port}} {{vendor}}({{serial}})",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "celsius" },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 }
+    },
+    {
+      "type": "bargauge",
+      "title": "Transceiver Present & Oper Status",
+      "description": "含义：transceiver_present 表示模块是否在位 (1=在位,0=不在位)，同时预留展示 transceiver_oper_status（运行状态，例如 up/down），当前无该数据属预期。用法：快速确认某设备端口上光模块是否插着（present=1）；未来实现 oper_status 后，可在同一面板中发现“模块在位但状态为 down”这类异常。",
+      "id": 14,
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "transceiver_present{job=~\"$job\", device=~\"$device\", port=~\"$port\"}",
+          "legendFormat": "{{device}}/{{port}}/{{component_name}}",
+          "refId": "A"
+        },
+        {
+          "expr": "transceiver_oper_status{job=~\"$job\", device=~\"$device\", port=~\"$port\"}",
+          "legendFormat": "oper: {{device}}/{{port}}/{{component_name}}",
+          "refId": "B"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "bool" },
+        "overrides": []
+      },
+      "gridPos": { "h": 6, "w": 12, "x": 0, "y": 14 }
+    },
+    {
+      "type": "timeseries",
+      "title": "Channel Tx Power (dBm)",
+      "description": "含义：transceiver_channel_tx_power_dbm，按 channel 维度展示发射光功率。用法：$device + $port 指定后，$component 可选单个或多个模块，查看各通道的 TX 功率；用于对比多通道是否功率均衡，以及定位某个通道发射功率突然下降的情况。",
+      "id": 15,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "targets": [
+        {
+          "expr": "transceiver_channel_tx_power_dbm{job=~\"$job\", device=~\"$device\", port=~\"$port\", component_name=~\"$component\"}",
+          "legendFormat": "{{component_name}}:{{channel}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "dBm" },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 20 }
+    },
+    {
+      "type": "timeseries",
+      "title": "Channel Rx Power (dBm)",
+      "description": "含义：transceiver_channel_rx_power_dbm，按 channel 展示接收光功率。用法：配合 TX 面板一起查看链路健康度（TX 正常但 RX 很低可能是远端/链路问题）；多 device、多 port 对比场景下，可快速识别接收功率异常低的通道。",
+      "id": 16,
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "transceiver_channel_rx_power_dbm{job=~\"$job\", device=~\"$device\", port=~\"$port\", component_name=~\"$component\"}",
+          "legendFormat": "{{component_name}}:{{channel}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "dBm" },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 20 }
+    },
+    {
+      "type": "timeseries",
+      "title": "Channel Bias Current (mA)",
+      "description": "含义：transceiver_channel_bias_current_ma，每个 channel 对应激光器偏置电流。用法：检查不同通道的电流是否在合理范围内，识别某个通道电流特别高的情况（可能模块老化）；结合历史趋势观察电流缓慢爬升，用于预判光模块老化风险。",
+      "id": 17,
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "transceiver_channel_bias_current_ma{job=~\"$job\", device=~\"$device\", port=~\"$port\", component_name=~\"$component\"}",
+          "legendFormat": "{{component_name}}:{{channel}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "mA" },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 28 }
+    },
+    {
+      "type": "timeseries",
+      "title": "Channel Laser Temperature (C, device-dependent)",
+      "description": "含义：transceiver_channel_laser_temperature_celsius，按通道展示激光器温度。用法：当前 H3C 设备通常不返回该字段，因此本面板往往无数据，这是设备特性而非 bug；若未来设备或其他厂商实现该字段，本面板可用于更细粒度地观察每个通道的激光温度。",
+      "id": 18,
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "transceiver_channel_laser_temperature_celsius{job=~\"$job\", device=~\"$device\", port=~\"$port\", component_name=~\"$component\"}",
+          "legendFormat": "{{component_name}}:{{channel}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "celsius" },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 28 }
+    },
+    {
+      "type": "table",
+      "title": "Channel Info (Instant)",
+      "description": "含义：transceiver_channel_info_info 与 transceiver_info_info join 后形成的静态资产表，每行对应一个 channel，并附带 vendor/serial/part_number/hardware_rev 等上游光模块信息。用法：使用 Instant 查询和表格展示，仅保留 label 列；作为“光模块资产清单”，可按 port、component_name、channel_index 排序，清晰查看每个端口有哪些模块及其通道数量，并通过 vendor/serial 等字段核对现场资产或反查某个 channel 属于哪个物理模块。",
+      "id": 19,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "targets": [
+        {
+          "expr": "transceiver_channel_info_info{job=~\"$job\", device=~\"$device\"} * on(job, device, port, component_name) group_left(vendor, serial, part_number, hardware_rev) transceiver_info_info{job=~\"$job\", device=~\"$device\"}",
+          "format": "table",
+          "instant": true,
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": [
+          {
+            "matcher": { "id": "byName", "options": "Time" },
+            "properties": [
+              { "id": "custom.hidden", "value": true }
+            ]
+          },
+          {
+            "matcher": { "id": "byName", "options": "Value" },
+            "properties": [
+              { "id": "custom.hidden", "value": true }
+            ]
+          }
+        ]
+      },
+      "options": {
+        "showHeader": true
+      },
+      "gridPos": { "h": 10, "w": 24, "x": 0, "y": 36 }
+    },
+    {
+      "type": "stat",
+      "title": "Time Since Last Scrape (s)",
+      "description": "含义：time() - netconf_last_scrape_timestamp_seconds，表示每个设备距离最近一次 NETCONF 抓取已过去的秒数。用法：如果数值一直在几十秒以内，说明抓取在持续正常执行；若某设备数值突然飙高且长期不回落，说明它很久没有被成功抓取，需检查连接、认证或设备状态。",
+      "id": 20,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "targets": [
+        {
+          "expr": "time() - netconf_last_scrape_timestamp_seconds{job=~\"$job\", device=~\"$device\"}",
+          "legendFormat": "{{device}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "s" },
+        "overrides": []
+      },
+      "options": {
+        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+        "orientation": "horizontal",
+        "textMode": "auto"
+      },
+      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 46 }
+    },
+    {
+      "type": "stat",
+      "title": "Transceiver Data Staleness (TODO)",
+      "description": "含义：设计中的 transceiver_data_staleness_seconds，计划表示 Transceiver 业务数据（最近一次成功抓取）相对当前时间的滞后程度。用法：目前仅注册 metric，逻辑尚未实现，因此无数据属预期；未来实现后，将比 Panel 20 更直接地体现“业务数据本身有多旧”，用于监控数据新鲜度。",
+      "id": 21,
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "transceiver_data_staleness_seconds{job=~\"$job\", device=~\"$device\"}",
+          "legendFormat": "{{device}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": { "defaults": { "unit": "s" }, "overrides": [] },
+      "options": {
+        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+        "orientation": "horizontal",
+        "textMode": "auto"
+      },
+      "gridPos": { "h": 4, "w": 6, "x": 6, "y": 46 }
+    }
+  ],
+  "templating": {
+    "list": [
+      {
+        "name": "job",
+        "label": "Job",
+        "type": "query",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "query": "label_values(netconf_scrape_success, job)",
+        "refresh": 1,
+        "multi": true,
+        "includeAll": true,
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        }
+      },
+      {
+        "name": "device",
+        "label": "Device",
+        "type": "query",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "query": "label_values(netconf_scrape_success{job=~\"$job\"}, device)",
+        "refresh": 2,
+        "multi": true,
+        "includeAll": true
+      },
+      {
+        "name": "port",
+        "label": "Port",
+        "type": "query",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "query": "label_values(transceiver_channel_info_info{job=~\"$job\",device=~\"$device\"}, port)",
+        "refresh": 2,
+        "multi": true,
+        "includeAll": true
+      },
+      {
+        "name": "component",
+        "label": "Component",
+        "type": "query",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "query": "label_values(transceiver_channel_info_info{job=~\"$job\",device=~\"$device\",port=~\"$port\"}, component_name)",
+        "refresh": 2,
+        "multi": true,
+        "includeAll": true
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  }
+}

deploytest/grafana/provisioning/dashboards/dashboards.yml

@@ -0,0 +1,12 @@
+apiVersion: 1
+
+providers:
+  - name: "netconf-transceiver-exporter"
+    orgId: 1
+    folder: ""
+    type: file
+    disableDeletion: false
+    editable: true
+    options:
+      path: /var/lib/grafana/dashboards
+

deploytest/grafana/provisioning/datasources/datasource.yml

@@ -0,0 +1,11 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    uid: prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: false
+

deploytest/prometheus/prometheus.yml

@@ -0,0 +1,13 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 30s
+
+scrape_configs:
+  - job_name: "netconf_transceiver_exporter"
+    scrape_interval: 15s
+    static_configs:
+      - targets:
+          - "host.docker.internal:19100"
+        labels:
+          env: "deploytest"
+