feat: 方案100%匹配 — RBAC动态权限+Grafana监控+目录库独立微服务+全国目录中心+标识同步

2026-06-30 13:42:11 +08:00
parent 96e2393c50
commit 29a6b57533
40 changed files with 4159 additions and 7 deletions
@@ -0,0 +1,80 @@
+# TCS-IPTV 监控部署说明
+
+## 组件
+
+| 文件 | 说明 |
+|------|------|
+| `prometheus.yml` | Prometheus 采集配置，抓取 api-svc / chain-svc / hash-api / catalog-svc 的 `/metrics` |
+| `grafana-dashboard.json` | Grafana 面板 JSON，覆盖 4 金指标 |
+
+## 快速部署
+
+### 1. Prometheus
+
+```bash
+# 启动 Prometheus（Docker）
+docker run -d --name prometheus \
+  -p 9090:9090 \
+  -v $(pwd)/prometheus.yml:/etc/prometheus/prometheus.yml \
+  prom/prometheus
+```
+
+### 2. Grafana
+
+```bash
+# 启动 Grafana（Docker）
+docker run -d --name grafana \
+  -p 3000:3000 \
+  -v $(pwd)/grafana-dashboard.json:/etc/grafana/provisioning/dashboards/tcs-iptv.json \
+  grafana/grafana
+```
+
+### 3. 导入面板
+
+1. 打开 Grafana → http://localhost:3000
+2. Dashboards → Import → 上传 `grafana-dashboard.json`
+3. 数据源选择 Prometheus（http://prometheus:9090）
+
+## 面板指标说明
+
+| 面板 | 指标 | Prometheus Metric |
+|------|------|-------------------|
+| 请求延迟 | P50/P95/P99 | `tcs_http_request_duration_seconds` (Histogram) |
+| 请求总量 | QPS by path | `tcs_http_requests_total` (Counter) |
+| 错误率 | 4xx/5xx QPS | `tcs_http_errors_total` (Counter) |
+| 在途请求 | 并发数 | `tcs_http_in_flight_requests` (Gauge) |
+| 错误率百分比 | 错误/总请求 | 上述两个 Counter 计算 |
+| 延迟热力图 | by path | Histogram bucket 热力图 |
+
+## 告警规则建议
+
+在 Prometheus 中配置 `alerting_rules.yml`：
+
+```yaml
+groups:
+  - name: tcs-iptv-alerts
+    rules:
+      - alert: HighErrorRate
+        expr: sum(rate(tcs_http_errors_total[5m])) / sum(rate(tcs_http_requests_total[5m])) > 0.1
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "错误率超过 10%"
+
+      - alert: HighLatency
+        expr: histogram_quantile(0.95, sum(rate(tcs_http_request_duration_seconds_bucket[5m])) by (le)) > 2
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "P95 延迟超过 2 秒"
+
+      - alert: HighInFlight
+        expr: tcs_http_in_flight_requests > 100
+        for: 2m
+        labels:
+          severity: warning
+        annotations:
+          summary: "在途请求超过 100"
+```
@@ -0,0 +1,181 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": "-- Grafana --",
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "description": "TCS-IPTV MA 码系统运行监控面板 — 覆盖4金指标：Latency / Traffic / Errors / Saturation",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "title": "请求延迟 (Latency — P50/P95/P99)",
+      "type": "timeseries",
+      "datasource": "Prometheus",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "s",
+          "color": { "mode": "palette-classic" }
+        }
+      },
+      "targets": [
+        {
+          "expr": "histogram_quantile(0.50, sum(rate(tcs_http_request_duration_seconds_bucket[5m])) by (le))",
+          "legendFormat": "P50",
+          "refId": "A"
+        },
+        {
+          "expr": "histogram_quantile(0.95, sum(rate(tcs_http_request_duration_seconds_bucket[5m])) by (le))",
+          "legendFormat": "P95",
+          "refId": "B"
+        },
+        {
+          "expr": "histogram_quantile(0.99, sum(rate(tcs_http_request_duration_seconds_bucket[5m])) by (le))",
+          "legendFormat": "P99",
+          "refId": "C"
+        }
+      ]
+    },
+    {
+      "title": "请求总量 (Traffic — QPS)",
+      "type": "timeseries",
+      "datasource": "Prometheus",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps",
+          "color": { "mode": "palette-classic" }
+        }
+      },
+      "targets": [
+        {
+          "expr": "sum(rate(tcs_http_requests_total[1m])) by (method, path)",
+          "legendFormat": "{{method}} {{path}}",
+          "refId": "A"
+        }
+      ]
+    },
+    {
+      "title": "错误率 (Errors — 4xx/5xx)",
+      "type": "timeseries",
+      "datasource": "Prometheus",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps",
+          "color": { "mode": "palette-classic" }
+        }
+      },
+      "targets": [
+        {
+          "expr": "sum(rate(tcs_http_errors_total[5m])) by (method, path, status)",
+          "legendFormat": "{{method}} {{path}} {{status}}",
+          "refId": "A"
+        }
+      ]
+    },
+    {
+      "title": "在途请求 (Saturation — 并发数)",
+      "type": "stat",
+      "datasource": "Prometheus",
+      "gridPos": { "h": 8, "w": 6, "x": 12, "y": 8 },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "thresholds": {
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 50 },
+              { "color": "red", "value": 100 }
+            ]
+          }
+        }
+      },
+      "targets": [
+        {
+          "expr": "tcs_http_in_flight_requests",
+          "legendFormat": "在途请求",
+          "refId": "A"
+        }
+      ]
+    },
+    {
+      "title": "错误率百分比",
+      "type": "gauge",
+      "datasource": "Prometheus",
+      "gridPos": { "h": 8, "w": 6, "x": 18, "y": 8 },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percentunit",
+          "min": 0,
+          "max": 1,
+          "thresholds": {
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 0.05 },
+              { "color": "red", "value": 0.1 }
+            ]
+          }
+        }
+      },
+      "targets": [
+        {
+          "expr": "sum(rate(tcs_http_errors_total[5m])) / sum(rate(tcs_http_requests_total[5m]))",
+          "legendFormat": "错误率",
+          "refId": "A"
+        }
+      ]
+    },
+    {
+      "title": "按路径延迟热力图",
+      "type": "heatmap",
+      "datasource": "Prometheus",
+      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 16 },
+      "targets": [
+        {
+          "expr": "sum(rate(tcs_http_request_duration_seconds_bucket[5m])) by (le, path)",
+          "legendFormat": "{{path}}",
+          "refId": "A",
+          "format": "heatmap"
+        }
+      ],
+      "options": {
+        "calculate": false,
+        "cellGap": 1,
+        "color": {
+          "scheme": "Spectral"
+        }
+      }
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 38,
+  "style": "dark",
+  "tags": ["tcs-iptv", "ma-code"],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "TCS-IPTV MA 码系统监控",
+  "uid": "tcs-iptv-monitor",
+  "version": 1,
+  "weekStart": ""
+}
@@ -0,0 +1,39 @@
+# TCS-IPTV Prometheus 采集配置
+# 对应方案：系统管理模块 — 运行监控
+
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  # api-svc 主服务
+  - job_name: "tcs-api-svc"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["api-svc:8080"]
+        labels:
+          service: "api-svc"
+
+  # chain-svc 链服务
+  - job_name: "tcs-chain-svc"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["chain-svc:8081"]
+        labels:
+          service: "chain-svc"
+
+  # hash-api 哈希服务
+  - job_name: "tcs-hash-api"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["hash-api:8082"]
+        labels:
+          service: "hash-api"
+
+  # catalog-svc 目录库服务（独立部署时启用）
+  - job_name: "tcs-catalog-svc"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["catalog-svc:8083"]
+        labels:
+          service: "catalog-svc"