BIZ-28: deploy monitoring dashboard + alert config
Co-authored-by: multica-agent <github@multica.ai>
This commit is contained in:
@@ -0,0 +1,50 @@
|
||||
# Alertmanager 配置
|
||||
# 告警通知路由到 Feishu
|
||||
|
||||
global:
|
||||
resolve_timeout: 5m
|
||||
|
||||
route:
|
||||
receiver: "default"
|
||||
group_wait: 30s
|
||||
group_interval: 5m
|
||||
repeat_interval: 4h
|
||||
routes:
|
||||
# 严重告警 → 通知 Vincent
|
||||
- receiver: "vincent-critical"
|
||||
match:
|
||||
severity: critical
|
||||
repeat_interval: 2h
|
||||
continue: true
|
||||
|
||||
# 警告告警 → 通知 COO
|
||||
- receiver: "coo-warning"
|
||||
match:
|
||||
severity: warning
|
||||
repeat_interval: 4h
|
||||
|
||||
receivers:
|
||||
- name: "default"
|
||||
webhook_configs:
|
||||
- url: "http://host.docker.internal:9094/webhook"
|
||||
send_resolved: true
|
||||
|
||||
- name: "vincent-critical"
|
||||
webhook_configs:
|
||||
- url: "http://host.docker.internal:9094/webhook"
|
||||
send_resolved: true
|
||||
|
||||
- name: "coo-warning"
|
||||
webhook_configs:
|
||||
- url: "http://host.docker.internal:9094/webhook"
|
||||
send_resolved: true
|
||||
|
||||
# 抑制规则：严重告警自动抑制同源的警告
|
||||
inhibit_rules:
|
||||
- source_match:
|
||||
severity: critical
|
||||
target_match:
|
||||
severity: warning
|
||||
equal:
|
||||
- alertname
|
||||
- instance
|
||||
@@ -0,0 +1,288 @@
|
||||
{
|
||||
"title": "OpenClaw Agent Health Dashboard",
|
||||
"uid": "agent-health",
|
||||
"version": 1,
|
||||
"tags": ["openclaw", "agent", "monitoring"],
|
||||
"timezone": "browser",
|
||||
"editable": true,
|
||||
"refresh": "30s",
|
||||
"panels": [
|
||||
{
|
||||
"title": "系统资源概览",
|
||||
"type": "row",
|
||||
"gridPos": {"h": 1, "w": 24, "x": 0, "y": 0}
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"title": "CPU 使用率",
|
||||
"type": "gauge",
|
||||
"gridPos": {"h": 8, "w": 6, "x": 0, "y": 1},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
],
|
||||
"options": {
|
||||
"reduceOptions": {"calcs": ["lastNotNull"]},
|
||||
"showThresholdLabels": false,
|
||||
"showThresholdMarkers": true
|
||||
},
|
||||
"thresholds": [
|
||||
{"color": "green", "value": null},
|
||||
{"color": "yellow", "value": 70},
|
||||
{"color": "red", "value": 90}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"title": "内存使用率",
|
||||
"type": "gauge",
|
||||
"gridPos": {"h": 8, "w": 6, "x": 6, "y": 1},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
],
|
||||
"options": {
|
||||
"reduceOptions": {"calcs": ["lastNotNull"]},
|
||||
"showThresholdLabels": false,
|
||||
"showThresholdMarkers": true
|
||||
},
|
||||
"thresholds": [
|
||||
{"color": "green", "value": null},
|
||||
{"color": "yellow", "value": 80},
|
||||
{"color": "red", "value": 95}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"title": "磁盘使用率",
|
||||
"type": "gauge",
|
||||
"gridPos": {"h": 8, "w": 6, "x": 12, "y": 1},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by(instance) ((node_filesystem_size_bytes - node_filesystem_free_bytes) / node_filesystem_size_bytes * 100)",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
],
|
||||
"options": {
|
||||
"reduceOptions": {"calcs": ["lastNotNull"]},
|
||||
"showThresholdLabels": false,
|
||||
"showThresholdMarkers": true
|
||||
},
|
||||
"thresholds": [
|
||||
{"color": "green", "value": null},
|
||||
{"color": "yellow", "value": 80},
|
||||
{"color": "red", "value": 95}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"title": "系统负载",
|
||||
"type": "stat",
|
||||
"gridPos": {"h": 8, "w": 6, "x": 18, "y": 1},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "node_load1",
|
||||
"legendFormat": "1min"
|
||||
},
|
||||
{
|
||||
"expr": "node_load5",
|
||||
"legendFormat": "5min"
|
||||
},
|
||||
{
|
||||
"expr": "node_load15",
|
||||
"legendFormat": "15min"
|
||||
}
|
||||
],
|
||||
"options": {
|
||||
"reduceOptions": {"calcs": ["lastNotNull"]},
|
||||
"colorMode": "background",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"textMode": "auto"
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Agent 健康状态",
|
||||
"type": "row",
|
||||
"gridPos": {"h": 1, "w": 24, "x": 0, "y": 9}
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"title": "Agent 心跳状态",
|
||||
"type": "table",
|
||||
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 10},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "agent_heartbeat_status",
|
||||
"legendFormat": "{{agent_label}}"
|
||||
}
|
||||
],
|
||||
"transformations": [
|
||||
{"id": "organize", "options": {"excludeByName": {}, "indexByName": {}, "renameByName": {"Value": "状态"}}}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"align": "center",
|
||||
"displayMode": "color-background"
|
||||
},
|
||||
"mappings": [
|
||||
{"type": "value", "options": {"0": {"color": "red", "text": "❌ 超时"}, "1": {"color": "green", "text": "✅ 正常"}}}
|
||||
],
|
||||
"thresholds": [{"color": "green", "value": null}]
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"title": "任务停滞时长",
|
||||
"type": "bargauge",
|
||||
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 10},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "agent_task_stagnation_seconds",
|
||||
"legendFormat": "{{agent_label}}"
|
||||
}
|
||||
],
|
||||
"options": {
|
||||
"orientation": "horizontal",
|
||||
"displayMode": "gradient",
|
||||
"showUnfilled": true
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "s",
|
||||
"thresholds": [
|
||||
{"color": "green", "value": null},
|
||||
{"color": "yellow", "value": 3600},
|
||||
{"color": "red", "value": 14400}
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"title": "待办任务数",
|
||||
"type": "stat",
|
||||
"gridPos": {"h": 4, "w": 6, "x": 0, "y": 18},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "agent_workboard_pending",
|
||||
"legendFormat": "待办任务"
|
||||
}
|
||||
],
|
||||
"options": {
|
||||
"reduceOptions": {"calcs": ["lastNotNull"]},
|
||||
"colorMode": "background",
|
||||
"graphMode": "area",
|
||||
"textMode": "auto"
|
||||
},
|
||||
"thresholds": [
|
||||
{"color": "green", "value": null},
|
||||
{"color": "yellow", "value": 5},
|
||||
{"color": "red", "value": 10}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"title": "429 错误计数",
|
||||
"type": "stat",
|
||||
"gridPos": {"h": 4, "w": 6, "x": 6, "y": 18},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "agent_429_error_rate",
|
||||
"legendFormat": "429 错误"
|
||||
}
|
||||
],
|
||||
"options": {
|
||||
"reduceOptions": {"calcs": ["lastNotNull"]},
|
||||
"colorMode": "background",
|
||||
"graphMode": "area",
|
||||
"textMode": "auto"
|
||||
},
|
||||
"thresholds": [
|
||||
{"color": "green", "value": null},
|
||||
{"color": "yellow", "value": 10},
|
||||
{"color": "red", "value": 50}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"title": "Prometheus 目标状态",
|
||||
"type": "table",
|
||||
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 18},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "up",
|
||||
"legendFormat": "{{job}} ({{instance}})"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {"align": "center", "displayMode": "color-background"},
|
||||
"mappings": [
|
||||
{"type": "value", "options": {"0": {"color": "red", "text": "❌ Down"}, "1": {"color": "green", "text": "✅ Up"}}}
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "告警状态",
|
||||
"type": "row",
|
||||
"gridPos": {"h": 1, "w": 24, "x": 0, "y": 26}
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"title": "活跃告警",
|
||||
"type": "table",
|
||||
"gridPos": {"h": 8, "w": 24, "x": 0, "y": 27},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "ALERTS{alertstate=\"firing\"}",
|
||||
"legendFormat": "{{alertname}}"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {"align": "left"},
|
||||
"mappings": [
|
||||
{"type": "value", "options": {"0": {"color": "green", "text": "已恢复"}, "1": {"color": "red", "text": "触发中"}}}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"schemaVersion": 38,
|
||||
"style": "dark",
|
||||
"tags": ["openclaw", "agent", "monitoring"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "datasource",
|
||||
"type": "datasource",
|
||||
"query": "prometheus",
|
||||
"current": {"value": "Prometheus"}
|
||||
}
|
||||
]
|
||||
},
|
||||
"annotations": {
|
||||
"list": [
|
||||
{
|
||||
"name": "告警事件",
|
||||
"type": "dashboard",
|
||||
"builtIn": 1,
|
||||
"datasource": {"type": "prometheus", "uid": "PBFA97CFB590B2093"},
|
||||
"enable": true,
|
||||
"hide": true,
|
||||
"iconColor": "rgba(255, 96, 96, 1)",
|
||||
"expr": "ALERTS",
|
||||
"step": "60s"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,12 @@
|
||||
apiVersion: 1
|
||||
|
||||
providers:
|
||||
- name: "Agent Health"
|
||||
orgId: 1
|
||||
folder: "OpenClaw"
|
||||
type: file
|
||||
disableDeletion: false
|
||||
editable: true
|
||||
updateIntervalSeconds: 10
|
||||
options:
|
||||
path: /etc/grafana/provisioning/dashboards
|
||||
@@ -0,0 +1,42 @@
|
||||
global:
|
||||
scrape_interval: 15s
|
||||
evaluation_interval: 15s
|
||||
|
||||
# Alertmanager 配置
|
||||
alerting:
|
||||
alertmanagers:
|
||||
- static_configs:
|
||||
- targets:
|
||||
- alertmanager:9093
|
||||
|
||||
# 规则文件
|
||||
rule_files:
|
||||
- "agent_alerts.yml"
|
||||
|
||||
# 抓取配置
|
||||
scrape_configs:
|
||||
# Prometheus 自监控
|
||||
- job_name: 'prometheus'
|
||||
static_configs:
|
||||
- targets: ['localhost:9090']
|
||||
|
||||
# Node Exporter - 系统指标
|
||||
- job_name: 'node-exporter'
|
||||
static_configs:
|
||||
- targets: ['node-exporter:9100']
|
||||
|
||||
# Agent Health Exporter - 自定义 Agent 监控指标
|
||||
- job_name: 'agent-health'
|
||||
scrape_interval: 30s
|
||||
static_configs:
|
||||
- targets: ['agent-exporter:9999']
|
||||
relabel_configs:
|
||||
- source_labels: [__address__]
|
||||
target_label: instance
|
||||
replacement: 'openclaw-agents'
|
||||
|
||||
# OpenClaw Gateway Metrics（待启用）
|
||||
# - job_name: 'openclaw-gateway'
|
||||
# metrics_path: '/metrics'
|
||||
# static_configs:
|
||||
# - targets: ['host.docker.internal:18789']
|
||||
Reference in New Issue
Block a user