File size: 11,410 Bytes
8b7b267 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 |
#!/usr/bin/env python3
"""
Health Monitoring System
Continuous health monitoring for all API endpoints
"""
import schedule
import time
import requests
import json
import logging
from datetime import datetime
from typing import Dict, List, Optional
from pathlib import Path
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
class HealthMonitor:
"""Continuous health monitoring for all endpoints"""
def __init__(self, base_url: str = "http://localhost:7860"):
self.base_url = base_url
self.endpoints = self.load_endpoints()
self.health_history = []
self.alert_threshold = 3 # Number of consecutive failures before alert
self.failure_counts = {} # Track consecutive failures per endpoint
def load_endpoints(self) -> List[Dict]:
"""Load endpoints from service registry"""
registry_file = Path("config/service_registry.json")
if not registry_file.exists():
logger.warning("⚠ Service registry not found, using default endpoints")
return self._get_default_endpoints()
try:
with open(registry_file, 'r') as f:
registry = json.load(f)
endpoints = []
for service in registry.get("services", []):
for endpoint in service.get("endpoints", []):
endpoints.append({
"path": endpoint.get("path", ""),
"method": endpoint.get("method", "GET"),
"category": service.get("category", "unknown"),
"service_id": service.get("id", "unknown"),
"base_url": self.base_url
})
return endpoints
except Exception as e:
logger.error(f"❌ Failed to load endpoints: {e}")
return self._get_default_endpoints()
def _get_default_endpoints(self) -> List[Dict]:
"""Get default endpoints for monitoring"""
return [
{"path": "/api/health", "method": "GET", "category": "system", "base_url": self.base_url},
{"path": "/api/ohlcv/BTC", "method": "GET", "category": "market_data", "base_url": self.base_url},
{"path": "/api/v1/ohlcv/BTC", "method": "GET", "category": "market_data", "base_url": self.base_url},
{"path": "/api/market/ohlcv", "method": "GET", "category": "market_data", "base_url": self.base_url, "params": {"symbol": "BTC", "interval": "1d", "limit": 30}},
]
def check_endpoint_health(self, endpoint: Dict) -> Dict:
"""Check health of single endpoint"""
path = endpoint["path"]
method = endpoint.get("method", "GET").upper()
params = endpoint.get("params", {})
try:
start_time = time.time()
url = f"{endpoint['base_url']}{path}"
if method == "GET":
response = requests.get(url, params=params, timeout=10)
elif method == "POST":
response = requests.post(url, json=params, timeout=10)
else:
response = requests.request(method, url, json=params, timeout=10)
response_time = (time.time() - start_time) * 1000
is_healthy = response.status_code in [200, 201]
result = {
"endpoint": path,
"status": "healthy" if is_healthy else "degraded",
"status_code": response.status_code,
"response_time_ms": round(response_time, 2),
"timestamp": datetime.now().isoformat(),
"method": method
}
# Update failure count
if is_healthy:
self.failure_counts[path] = 0
else:
self.failure_counts[path] = self.failure_counts.get(path, 0) + 1
result["consecutive_failures"] = self.failure_counts[path]
return result
except requests.exceptions.Timeout:
self.failure_counts[path] = self.failure_counts.get(path, 0) + 1
return {
"endpoint": path,
"status": "down",
"error": "timeout",
"timestamp": datetime.now().isoformat(),
"method": method,
"consecutive_failures": self.failure_counts[path]
}
except Exception as e:
self.failure_counts[path] = self.failure_counts.get(path, 0) + 1
return {
"endpoint": path,
"status": "down",
"error": str(e),
"timestamp": datetime.now().isoformat(),
"method": method,
"consecutive_failures": self.failure_counts[path]
}
def check_all_endpoints(self):
"""Check health of all registered endpoints"""
results = []
logger.info(f"🔍 Checking {len(self.endpoints)} endpoints...")
for endpoint in self.endpoints:
health = self.check_endpoint_health(endpoint)
results.append(health)
# Check if alert needed
if health['status'] != "healthy":
self.handle_unhealthy_endpoint(health)
# Store in history
self.health_history.append({
"check_time": datetime.now().isoformat(),
"results": results,
"summary": {
"total": len(results),
"healthy": sum(1 for r in results if r['status'] == "healthy"),
"degraded": sum(1 for r in results if r['status'] == "degraded"),
"down": sum(1 for r in results if r['status'] == "down")
}
})
# Keep only last 100 checks
if len(self.health_history) > 100:
self.health_history = self.health_history[-100:]
# Save to file
self.save_health_report(results)
return results
def handle_unhealthy_endpoint(self, health: Dict):
"""Handle unhealthy endpoint detection"""
path = health["endpoint"]
consecutive_failures = health.get("consecutive_failures", 0)
if consecutive_failures >= self.alert_threshold:
self.send_alert(health)
def send_alert(self, health: Dict):
"""Send alert about failing endpoint"""
alert_message = f"""
⚠️ ALERT: Endpoint Health Issue
Endpoint: {health['endpoint']}
Status: {health['status']}
Error: {health.get('error', 'N/A')}
Time: {health['timestamp']}
Consecutive Failures: {health.get('consecutive_failures', 0)}
"""
logger.error(alert_message)
# Save alert to file
alerts_file = Path("monitoring/alerts.json")
alerts_file.parent.mkdir(parents=True, exist_ok=True)
try:
if alerts_file.exists():
with open(alerts_file, 'r') as f:
alerts = json.load(f)
else:
alerts = []
alerts.append({
"timestamp": datetime.now().isoformat(),
"endpoint": health["endpoint"],
"status": health["status"],
"error": health.get("error"),
"consecutive_failures": health.get("consecutive_failures", 0)
})
# Keep only last 50 alerts
alerts = alerts[-50:]
with open(alerts_file, 'w') as f:
json.dump(alerts, f, indent=2)
except Exception as e:
logger.error(f"Failed to save alert: {e}")
def save_health_report(self, results: List[Dict]):
"""Save health check results to file"""
reports_dir = Path("monitoring/reports")
reports_dir.mkdir(parents=True, exist_ok=True)
report_file = reports_dir / f"health_report_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
report = {
"timestamp": datetime.now().isoformat(),
"total_endpoints": len(results),
"healthy": sum(1 for r in results if r['status'] == "healthy"),
"degraded": sum(1 for r in results if r['status'] == "degraded"),
"down": sum(1 for r in results if r['status'] == "down"),
"results": results
}
try:
with open(report_file, 'w') as f:
json.dump(report, f, indent=2)
# Also update latest report
latest_file = reports_dir / "health_report_latest.json"
with open(latest_file, 'w') as f:
json.dump(report, f, indent=2)
except Exception as e:
logger.error(f"Failed to save health report: {e}")
def get_health_summary(self) -> Dict:
"""Get summary of health status"""
if not self.health_history:
return {
"status": "unknown",
"message": "No health checks performed yet"
}
latest = self.health_history[-1]
summary = latest["summary"]
total = summary["total"]
healthy = summary["healthy"]
health_percentage = (healthy / total * 100) if total > 0 else 0
return {
"status": "healthy" if health_percentage >= 95 else "degraded" if health_percentage >= 80 else "unhealthy",
"health_percentage": round(health_percentage, 2),
"total_endpoints": total,
"healthy": healthy,
"degraded": summary["degraded"],
"down": summary["down"],
"last_check": latest["check_time"]
}
def start_monitoring(self, interval_minutes: int = 5):
"""Start continuous monitoring"""
logger.info(f"🔍 Health monitoring started (checking every {interval_minutes} minutes)")
logger.info(f"📊 Monitoring {len(self.endpoints)} endpoints")
# Run initial check
self.check_all_endpoints()
# Schedule periodic checks
schedule.every(interval_minutes).minutes.do(self.check_all_endpoints)
try:
while True:
schedule.run_pending()
time.sleep(1)
except KeyboardInterrupt:
logger.info("🛑 Health monitoring stopped")
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(description="Health Monitoring System")
parser.add_argument("--base-url", default="http://localhost:7860", help="Base URL for API")
parser.add_argument("--interval", type=int, default=5, help="Check interval in minutes")
parser.add_argument("--once", action="store_true", help="Run once and exit")
args = parser.parse_args()
monitor = HealthMonitor(base_url=args.base_url)
if args.once:
results = monitor.check_all_endpoints()
summary = monitor.get_health_summary()
print("\n" + "="*50)
print("HEALTH SUMMARY")
print("="*50)
print(json.dumps(summary, indent=2))
print("="*50)
else:
monitor.start_monitoring(interval_minutes=args.interval)
|