1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
|
import asyncio
import aiohttp
import json
from datetime import datetime, timedelta
from dataclasses import dataclass
from typing import List, Dict, Optional
import smtplib
from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart
@dataclass
class AlertRule:
"""告警规则定义"""
name: str
metric: str
threshold: float
operator: str
severity: str
cooldown_minutes: int = 15
class RPAMonitoringSystem:
"""RPA智能监控系统"""
def __init__(self, config: dict):
self.config = config
self.orchestrator_url = config['orchestrator_url']
self.api_key = config['api_key']
self.alert_rules = self._load_alert_rules()
self.alert_history = {}
def _load_alert_rules(self) -> List[AlertRule]:
"""加载告警规则"""
return [
AlertRule("机器人故障率过高", "robot_fault_rate", 0.2, ">", "high"),
AlertRule("作业失败率过高", "job_failure_rate", 0.15, ">", "medium"),
AlertRule("API响应时间过长", "api_response_time", 5.0, ">", "medium"),
AlertRule("系统CPU使用率过高", "cpu_usage", 80.0, ">", "high"),
AlertRule("系统内存使用率过高", "memory_usage", 85.0, ">", "high"),
AlertRule("数据库连接数过多", "db_connections", 150, ">", "critical"),
AlertRule("队列积压过多", "queue_backlog", 100, ">", "medium")
]
async def collect_metrics(self) -> Dict[str, float]:
"""收集系统指标"""
metrics = {}
async with aiohttp.ClientSession() as session:
tasks = [
self._collect_robot_metrics(session),
self._collect_job_metrics(session),
self._collect_system_metrics(),
self._collect_queue_metrics(session)
]
results = await asyncio.gather(*tasks, return_exceptions=True)
for result in results:
if isinstance(result, dict):
metrics.update(result)
return metrics
async def _collect_robot_metrics(self, session: aiohttp.ClientSession) -> Dict[str, float]:
"""收集机器人指标"""
try:
headers = {"Authorization": f"Bearer {self.api_key}"}
async with session.get(
f"{self.orchestrator_url}/odata/Robots",
headers=headers
) as response:
if response.status != 200:
return {}
data = await response.json()
robots = data.get('value', [])
total_robots = len(robots)
faulted_robots = len([r for r in robots if r.get('State') == 'Faulted'])
return {
"total_robots": total_robots,
"faulted_robots": faulted_robots,
"robot_fault_rate": faulted_robots / total_robots if total_robots > 0 else 0
}
except Exception:
return {}
async def _collect_job_metrics(self, session: aiohttp.ClientSession) -> Dict[str, float]:
"""收集作业指标"""
try:
headers = {"Authorization": f"Bearer {self.api_key}"}
end_time = datetime.now()
start_time = end_time - timedelta(hours=1)
filter_query = f"CreationTime ge {start_time.isoformat()}Z"
async with session.get(
f"{self.orchestrator_url}/odata/Jobs",
headers=headers,
params={"$filter": filter_query}
) as response:
if response.status != 200:
return {}
data = await response.json()
jobs = data.get('value', [])
total_jobs = len(jobs)
failed_jobs = len([j for j in jobs if j.get('State') == 'Faulted'])
running_jobs = len([j for j in jobs if j.get('State') == 'Running'])
return {
"total_jobs_1h": total_jobs,
"failed_jobs_1h": failed_jobs,
"running_jobs": running_jobs,
"job_failure_rate": failed_jobs / total_jobs if total_jobs > 0 else 0
}
except Exception:
return {}
async def _collect_system_metrics(self) -> Dict[str, float]:
"""收集系统指标"""
try:
import psutil
return {
"cpu_usage": psutil.cpu_percent(interval=1),
"memory_usage": psutil.virtual_memory().percent,
"disk_usage": psutil.disk_usage('/').percent
}
except Exception:
return {}
async def _collect_queue_metrics(self, session: aiohttp.ClientSession) -> Dict[str, float]:
"""收集队列指标"""
try:
headers = {"Authorization": f"Bearer {self.api_key}"}
async with session.get(
f"{self.orchestrator_url}/odata/QueueItems",
headers=headers,
params={"$filter": "Status eq 'New'"}
) as response:
if response.status != 200:
return {}
data = await response.json()
queue_items = data.get('value', [])
return {
"queue_backlog": len(queue_items)
}
except Exception:
return {}
def check_alerts(self, metrics: Dict[str, float]) -> List[Dict]:
"""检查告警条件"""
alerts = []
current_time = datetime.now()
for rule in self.alert_rules:
if rule.metric not in metrics:
continue
metric_value = metrics[rule.metric]
if self._evaluate_condition(metric_value, rule.threshold, rule.operator):
last_alert_time = self.alert_history.get(rule.name)
if last_alert_time:
time_diff = (current_time - last_alert_time).total_seconds() / 60
if time_diff < rule.cooldown_minutes:
continue
alert = {
"rule_name": rule.name,
"metric": rule.metric,
"current_value": metric_value,
"threshold": rule.threshold,
"severity": rule.severity,
"timestamp": current_time.isoformat(),
"message": f"{rule.name}: {rule.metric}当前值{metric_value}超过阈值{rule.threshold}"
}
alerts.append(alert)
self.alert_history[rule.name] = current_time
return alerts
def _evaluate_condition(self, value: float, threshold: float, operator: str) -> bool:
"""评估告警条件"""
if operator == ">":
return value > threshold
elif operator == "<":
return value < threshold
elif operator == ">=":
return value >= threshold
elif operator == "<=":
return value <= threshold
elif operator == "==":
return value == threshold
return False
async def send_alert(self, alert: Dict) -> bool:
"""发送告警通知"""
try:
await self._send_email_alert(alert)
return True
except Exception as e:
print(f"发送告警失败: {e}")
return False
async def _send_email_alert(self, alert: Dict):
"""发送邮件告警"""
smtp_config = self.config.get('smtp', {})
msg = MIMEMultipart()
msg['From'] = smtp_config.get('from_email')
msg['To'] = ', '.join(smtp_config.get('to_emails', []))
msg['Subject'] = f"[RPA告警] {alert['severity'].upper()} - {alert['rule_name']}"
body = f"""
告警详情：
规则名称: {alert['rule_name']}
指标名称: {alert['metric']}
当前值: {alert['current_value']}
阈值: {alert['threshold']}
严重程度: {alert['severity']}
触发时间: {alert['timestamp']}
详细信息: {alert['message']}
请及时处理！
"""
msg.attach(MIMEText(body, 'plain', 'utf-8'))
async def run_monitoring_loop(self, interval_seconds: int = 60):
"""运行监控循环"""
print(f"RPA监控系统启动，监控间隔: {interval_seconds}秒")
while True:
try:
metrics = await self.collect_metrics()
print(f"收集到指标: {metrics}")
alerts = self.check_alerts(metrics)
for alert in alerts:
print(f"触发告警: {alert['message']}")
await self.send_alert(alert)
await asyncio.sleep(interval_seconds)
except Exception as e:
print(f"监控循环异常: {e}")
await asyncio.sleep(interval_seconds)
if __name__ == "__main__":
config = {
"orchestrator_url": "https://your-orchestrator.com",
"api_key": "your-api-key",
"smtp": {
"host": "smtp.company.com",
"port": 587,
"from_email": "rpa-monitor@company.com",
"to_emails": ["admin@company.com", "ops@company.com"]
}
}
monitor = RPAMonitoringSystem(config)
asyncio.run(monitor.run_monitoring_loop(60))
|
