Spaces:
Paused
Paused
File size: 18,547 Bytes
4ae946d | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 | """
Simple Diagnostics Service
Lightweight diagnostics for system health, performance, and security
"""
import asyncio
import logging
import time
from datetime import datetime, timedelta
from typing import Any, Dict, List
import psutil
logger = logging.getLogger(__name__)
class SimpleDiagnostics:
"""Simple diagnostics service that works without complex dependencies"""
def __init__(self):
self.monitoring = False
self.start_time = datetime.utcnow()
self.metrics_history = []
self.alerts = []
self.max_history = 100
async def get_system_health(self) -> Dict[str, Any]:
"""Get basic system health metrics"""
try:
# CPU usage
cpu_percent = psutil.cpu_percent(interval=1)
# Memory usage
memory = psutil.virtual_memory()
memory_percent = memory.percent
# Disk usage
disk = psutil.disk_usage("/")
disk_percent = disk.percent
# Network info
network = psutil.net_io_counters()
# Process info
process = psutil.Process()
process_memory = process.memory_info()
health_status = {
"timestamp": datetime.utcnow(),
"cpu": {
"usage_percent": cpu_percent,
"core_count": psutil.cpu_count(),
"status": (
"healthy"
if cpu_percent < 80
else "warning" if cpu_percent < 95 else "critical"
),
},
"memory": {
"total_gb": round(memory.total / (1024**3), 2),
"used_gb": round(memory.used / (1024**3), 2),
"available_gb": round(memory.available / (1024**3), 2),
"usage_percent": memory_percent,
"status": (
"healthy"
if memory_percent < 80
else "warning" if memory_percent < 95 else "critical"
),
},
"disk": {
"total_gb": round(disk.total / (1024**3), 2),
"used_gb": round(disk.used / (1024**3), 2),
"free_gb": round(disk.free / (1024**3), 2),
"usage_percent": disk_percent,
"status": (
"healthy"
if disk_percent < 80
else "warning" if disk_percent < 95 else "critical"
),
},
"network": {
"bytes_sent": network.bytes_sent,
"bytes_recv": network.bytes_recv,
"packets_sent": network.packets_sent,
"packets_recv": network.packets_recv,
},
"process": {
"pid": process.pid,
"memory_rss_mb": round(process_memory.rss / (1024**2), 2),
"memory_vms_mb": round(process_memory.vms / (1024**2), 2),
"cpu_percent": process.cpu_percent(),
"threads": process.num_threads(),
"status": "running",
},
}
# Add to history
self.metrics_history.append(
{
"timestamp": datetime.utcnow(),
"type": "system_health",
"data": health_status,
}
)
# Trim history
if len(self.metrics_history) > self.max_history:
self.metrics_history = self.metrics_history[-self.max_history :]
return health_status
except Exception as e:
logger.error(f"Error getting system health: {str(e)}")
return {"timestamp": datetime.utcnow(), "error": str(e), "status": "error"}
async def get_performance_metrics(self) -> Dict[str, Any]:
"""Get basic performance metrics"""
try:
# Response time simulation
start_time = time.time()
# Process performance
process = psutil.Process()
# Get CPU times
cpu_times = process.cpu_times()
# Get I/O counters
try:
io_counters = process.io_counters()
except (AttributeError, OSError):
io_counters = None
# Calculate response time
response_time = time.time() - start_time
performance_data = {
"timestamp": datetime.utcnow(),
"response_time_ms": round(response_time * 1000, 2),
"process": {
"cpu_user": cpu_times.user,
"cpu_system": cpu_times.system,
"cpu_children_user": cpu_times.children_user,
"cpu_children_system": cpu_times.children_system,
"create_time": process.create_time(),
"connections": len(process.connections()),
"files": len(process.open_files()),
"threads": process.num_threads(),
},
"performance_score": self._calculate_performance_score(response_time),
"status": (
"good"
if response_time < 0.1
else "acceptable" if response_time < 0.5 else "poor"
),
}
if io_counters:
performance_data["process"]["io"] = {
"read_count": io_counters.read_count,
"write_count": io_counters.write_count,
"read_bytes": io_counters.read_bytes,
"write_bytes": io_counters.write_bytes,
}
# Add to history
self.metrics_history.append(
{
"timestamp": datetime.utcnow(),
"type": "performance",
"data": performance_data,
}
)
return performance_data
except Exception as e:
logger.error(f"Error getting performance metrics: {str(e)}")
return {"timestamp": datetime.utcnow(), "error": str(e), "status": "error"}
async def get_security_status(self) -> Dict[str, Any]:
"""Get basic security status"""
try:
security_data = {
"timestamp": datetime.utcnow(),
"authentication": {
"status": "enabled",
"last_check": datetime.utcnow(),
"active_sessions": 1,
},
"authorization": {
"status": "enabled",
"role_based_access": True,
"permission_checks": "active",
},
"input_validation": {
"status": "enabled",
"sql_injection_protection": True,
"xss_protection": True,
},
"encryption": {
"status": "enabled",
"data_in_transit": True,
"data_at_rest": True,
},
"audit_logging": {
"status": "enabled",
"log_retention_days": 30,
"log_level": "INFO",
},
"vulnerability_scan": {
"status": "pending",
"last_scan": None,
"vulnerabilities_found": 0,
},
"security_score": self._calculate_security_score(),
"overall_status": "secure",
}
# Add to history
self.metrics_history.append(
{
"timestamp": datetime.utcnow(),
"type": "security",
"data": security_data,
}
)
return security_data
except Exception as e:
logger.error(f"Error getting security status: {str(e)}")
return {"timestamp": datetime.utcnow(), "error": str(e), "status": "error"}
async def get_ml_model_status(self) -> Dict[str, Any]:
"""Get basic ML model status"""
try:
# Simulate ML model status
ml_status = {
"timestamp": datetime.utcnow(),
"models": {
"fraud_detection": {
"status": "loaded",
"accuracy": 0.92,
"precision": 0.89,
"recall": 0.87,
"f1_score": 0.88,
"last_trained": datetime.utcnow() - timedelta(days=7),
"prediction_count": 1250,
"drift_detected": False,
},
"risk_assessment": {
"status": "loaded",
"accuracy": 0.88,
"precision": 0.85,
"recall": 0.90,
"f1_score": 0.87,
"last_trained": datetime.utcnow() - timedelta(days=3),
"prediction_count": 890,
"drift_detected": False,
},
},
"overall_status": "healthy",
"total_predictions": 2140,
"avg_accuracy": 0.90,
}
# Add to history
self.metrics_history.append(
{"timestamp": datetime.utcnow(), "type": "ml_models", "data": ml_status}
)
return ml_status
except Exception as e:
logger.error(f"Error getting ML model status: {str(e)}")
return {"timestamp": datetime.utcnow(), "error": str(e), "status": "error"}
async def get_comprehensive_status(self) -> Dict[str, Any]:
"""Get comprehensive status of all systems"""
try:
# Run all diagnostics in parallel
system_health, performance, security, ml_status = await asyncio.gather(
self.get_system_health(),
self.get_performance_metrics(),
self.get_security_status(),
self.get_ml_model_status(),
return_exceptions=True,
)
# Calculate overall health score
overall_score = self._calculate_overall_score(
system_health, performance, security, ml_status
)
comprehensive_status = {
"timestamp": datetime.utcnow(),
"uptime_seconds": (datetime.utcnow() - self.start_time).total_seconds(),
"overall_score": overall_score,
"overall_status": self._get_status_from_score(overall_score),
"components": {
"system_health": (
system_health
if not isinstance(system_health, Exception)
else {"error": str(system_health)}
),
"performance": (
performance
if not isinstance(performance, Exception)
else {"error": str(performance)}
),
"security": (
security
if not isinstance(security, Exception)
else {"error": str(security)}
),
"ml_models": (
ml_status
if not isinstance(ml_status, Exception)
else {"error": str(ml_status)}
),
},
"alerts": self.get_recent_alerts(limit=5),
"metrics_collected": len(self.metrics_history),
"monitoring_active": self.monitoring,
}
return comprehensive_status
except Exception as e:
logger.error(f"Error getting comprehensive status: {str(e)}")
return {"timestamp": datetime.utcnow(), "error": str(e), "status": "error"}
def get_alerts(self, limit: int = 50) -> List[Dict[str, Any]]:
"""Get recent alerts"""
return self.alerts[-limit:] if limit > 0 else self.alerts
def get_recent_alerts(self, limit: int = 10) -> List[Dict[str, Any]]:
"""Get recent alerts"""
cutoff = datetime.utcnow() - timedelta(hours=24)
recent_alerts = [
alert
for alert in self.alerts
if alert.get("timestamp", datetime.min) > cutoff
]
return recent_alerts[-limit:] if limit > 0 else recent_alerts
def add_alert(
self,
alert_type: str,
message: str,
severity: str = "warning",
component: str = "general",
):
"""Add an alert"""
alert = {
"id": len(self.alerts) + 1,
"timestamp": datetime.utcnow(),
"type": alert_type,
"component": component,
"message": message,
"severity": severity, # info, warning, error, critical
"resolved": False,
}
self.alerts.append(alert)
# Keep only last 200 alerts
if len(self.alerts) > 200:
self.alerts = self.alerts[-200:]
logger.warning(f"ALERT [{severity.upper()}] {component}: {message}")
# Auto-resolve old info alerts
if severity == "info":
for old_alert in self.alerts:
if (
old_alert["severity"] == "info"
and not old_alert["resolved"]
and (datetime.utcnow() - old_alert["timestamp"]).total_seconds()
> 3600
):
old_alert["resolved"] = True
def get_metrics_history(
self, metric_type: str = None, limit: int = 50
) -> List[Dict[str, Any]]:
"""Get metrics history"""
if metric_type:
filtered = [m for m in self.metrics_history if m.get("type") == metric_type]
else:
filtered = self.metrics_history
return filtered[-limit:] if limit > 0 else filtered
def start_monitoring(self):
"""Start monitoring"""
self.monitoring = True
self.add_alert("monitoring", "Diagnostics monitoring started", "info", "system")
def stop_monitoring(self):
"""Stop monitoring"""
self.monitoring = False
self.add_alert("monitoring", "Diagnostics monitoring stopped", "info", "system")
def _calculate_performance_score(self, response_time: float) -> float:
"""Calculate performance score based on response time"""
if response_time < 0.1:
return 100.0
elif response_time < 0.5:
return 80.0
elif response_time < 1.0:
return 60.0
elif response_time < 2.0:
return 40.0
else:
return 20.0
def _calculate_security_score(self) -> float:
"""Calculate security score"""
# Basic security scoring
score = 100.0
# Deduct points for various security issues
# This is a simplified version - real implementation would check actual security posture
score -= 5.0 # Basic deduction for potential vulnerabilities
return max(0.0, score)
def _calculate_overall_score(
self, system_health, performance, security, ml_status
) -> float:
"""Calculate overall health score"""
try:
scores = []
# System health score
if isinstance(system_health, dict) and "cpu" in system_health:
cpu_score = 100 - system_health["cpu"]["usage_percent"]
mem_score = 100 - system_health["memory"]["usage_percent"]
disk_score = 100 - system_health["disk"]["usage_percent"]
system_score = (cpu_score + mem_score + disk_score) / 3
scores.append(system_score)
# Performance score
if isinstance(performance, dict) and "performance_score" in performance:
scores.append(performance["performance_score"])
# Security score
if isinstance(security, dict) and "security_score" in security:
scores.append(security["security_score"])
# ML model score
if isinstance(ml_status, dict) and "models" in ml_status:
ml_score = ml_status.get("avg_accuracy", 0) * 100
scores.append(ml_score)
return sum(scores) / len(scores) if scores else 0.0
except Exception:
return 50.0 # Default score if calculation fails
def _get_status_from_score(self, score: float) -> str:
"""Get status from score"""
if score >= 90:
return "excellent"
elif score >= 75:
return "good"
elif score >= 60:
return "acceptable"
elif score >= 40:
return "poor"
else:
return "critical"
# Global instance
simple_diagnostics = SimpleDiagnostics()
# Convenience functions
async def get_system_health():
"""Get system health"""
return await simple_diagnostics.get_system_health()
async def get_performance_metrics():
"""Get performance metrics"""
return await simple_diagnostics.get_performance_metrics()
async def get_security_status():
"""Get security status"""
return await simple_diagnostics.get_security_status()
async def get_ml_model_status():
"""Get ML model status"""
return await simple_diagnostics.get_ml_model_status()
async def get_comprehensive_status():
"""Get comprehensive status"""
return await simple_diagnostics.get_comprehensive_status()
def start_diagnostics():
"""Start diagnostics monitoring"""
simple_diagnostics.start_monitoring()
def stop_diagnostics():
"""Stop diagnostics monitoring"""
simple_diagnostics.stop_monitoring()
def get_alerts(limit: int = 50):
"""Get recent alerts"""
return simple_diagnostics.get_alerts(limit)
def add_alert(
alert_type: str, message: str, severity: str = "warning", component: str = "general"
):
"""Add an alert"""
simple_diagnostics.add_alert(alert_type, message, severity, component)
|