File size: 15,758 Bytes
b190b45 |
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 |
#!/usr/bin/env python3
"""
Master Resource Orchestrator
Orchestrates ALL 86+ resources hierarchically - NO IDLE RESOURCES
مدیریت سلسلهمراتبی همه 86+ منبع - هیچ منبعی بیکار نمیماند
"""
import httpx
import logging
import asyncio
from typing import Dict, Any, List, Optional, Tuple
from datetime import datetime
from enum import Enum
from backend.services.hierarchical_fallback_config import (
hierarchical_config,
Priority,
ResourceConfig
)
logger = logging.getLogger(__name__)
class ResourceStatus(Enum):
"""Status of resource attempt"""
SUCCESS = "success"
FAILED = "failed"
SKIPPED = "skipped"
TIMEOUT = "timeout"
class MasterResourceOrchestrator:
"""
Master orchestrator for ALL resources
تمام 86+ منبع را به صورت سلسلهمراتبی مدیریت میکند
"""
def __init__(self):
self.config = hierarchical_config
self.timeout = 10.0
# Statistics tracking
self.usage_stats = {
"total_requests": 0,
"successful_requests": 0,
"failed_requests": 0,
"resource_usage": {}, # Track usage per resource
"priority_distribution": { # Track which priority level succeeded
Priority.CRITICAL: 0,
Priority.HIGH: 0,
Priority.MEDIUM: 0,
Priority.LOW: 0,
Priority.EMERGENCY: 0
}
}
async def fetch_with_hierarchy(
self,
resource_list: List[ResourceConfig],
fetch_function: callable,
max_concurrent: int = 3
) -> Tuple[Any, Dict[str, Any]]:
"""
Fetch data using hierarchical fallback
دریافت داده با فالبک سلسلهمراتبی
Args:
resource_list: List of resources in priority order
fetch_function: Async function to fetch data from a resource
max_concurrent: Max concurrent attempts within same priority
Returns:
(data, metadata) - Data and information about which resource succeeded
"""
self.usage_stats["total_requests"] += 1
# Group resources by priority
priority_groups = self._group_by_priority(resource_list)
# Try each priority level
for priority in [Priority.CRITICAL, Priority.HIGH, Priority.MEDIUM, Priority.LOW, Priority.EMERGENCY]:
resources_in_priority = priority_groups.get(priority, [])
if not resources_in_priority:
continue
logger.info(f"🔄 Trying {len(resources_in_priority)} resources at {priority.name} priority")
# Try resources in this priority level
# If max_concurrent > 1, try multiple resources in parallel
if max_concurrent > 1 and len(resources_in_priority) > 1:
result = await self._try_concurrent(
resources_in_priority[:max_concurrent],
fetch_function,
priority
)
else:
result = await self._try_sequential(
resources_in_priority,
fetch_function,
priority
)
if result:
data, metadata = result
self.usage_stats["successful_requests"] += 1
self.usage_stats["priority_distribution"][priority] += 1
logger.info(f"✅ SUCCESS at {priority.name} priority: {metadata['resource_name']}")
return data, metadata
# All resources failed
self.usage_stats["failed_requests"] += 1
logger.error(f"❌ ALL {len(resource_list)} resources failed")
raise Exception(f"All {len(resource_list)} resources failed across all priority levels")
def _group_by_priority(
self,
resources: List[ResourceConfig]
) -> Dict[Priority, List[ResourceConfig]]:
"""Group resources by priority level"""
groups = {
Priority.CRITICAL: [],
Priority.HIGH: [],
Priority.MEDIUM: [],
Priority.LOW: [],
Priority.EMERGENCY: []
}
for resource in resources:
groups[resource.priority].append(resource)
return groups
async def _try_sequential(
self,
resources: List[ResourceConfig],
fetch_function: callable,
priority: Priority
) -> Optional[Tuple[Any, Dict[str, Any]]]:
"""Try resources sequentially"""
for idx, resource in enumerate(resources, 1):
try:
logger.info(f" 📡 [{idx}/{len(resources)}] Trying {resource.name}...")
# Track usage
if resource.name not in self.usage_stats["resource_usage"]:
self.usage_stats["resource_usage"][resource.name] = {
"attempts": 0,
"successes": 0,
"failures": 0
}
self.usage_stats["resource_usage"][resource.name]["attempts"] += 1
# Attempt to fetch data
start_time = datetime.utcnow()
data = await fetch_function(resource)
end_time = datetime.utcnow()
if data:
self.usage_stats["resource_usage"][resource.name]["successes"] += 1
metadata = {
"resource_name": resource.name,
"priority": priority.name,
"base_url": resource.base_url,
"response_time_ms": int((end_time - start_time).total_seconds() * 1000),
"timestamp": int(end_time.timestamp() * 1000)
}
logger.info(f" ✅ {resource.name} succeeded in {metadata['response_time_ms']}ms")
return data, metadata
logger.warning(f" ⚠️ {resource.name} returned no data")
self.usage_stats["resource_usage"][resource.name]["failures"] += 1
except asyncio.TimeoutError:
logger.warning(f" ⏱️ {resource.name} timeout")
self.usage_stats["resource_usage"][resource.name]["failures"] += 1
continue
except Exception as e:
logger.warning(f" ❌ {resource.name} failed: {e}")
self.usage_stats["resource_usage"][resource.name]["failures"] += 1
continue
return None
async def _try_concurrent(
self,
resources: List[ResourceConfig],
fetch_function: callable,
priority: Priority
) -> Optional[Tuple[Any, Dict[str, Any]]]:
"""Try multiple resources concurrently (race condition - first success wins)"""
logger.info(f" 🏁 Racing {len(resources)} resources in parallel...")
tasks = []
for resource in resources:
task = self._try_single_resource(resource, fetch_function, priority)
tasks.append(task)
# Wait for first success or all failures
for completed_task in asyncio.as_completed(tasks):
try:
result = await completed_task
if result:
# Cancel remaining tasks
for task in tasks:
if not task.done():
task.cancel()
return result
except Exception:
continue
return None
async def _try_single_resource(
self,
resource: ResourceConfig,
fetch_function: callable,
priority: Priority
) -> Optional[Tuple[Any, Dict[str, Any]]]:
"""Try a single resource (used in concurrent mode)"""
try:
# Track usage
if resource.name not in self.usage_stats["resource_usage"]:
self.usage_stats["resource_usage"][resource.name] = {
"attempts": 0,
"successes": 0,
"failures": 0
}
self.usage_stats["resource_usage"][resource.name]["attempts"] += 1
start_time = datetime.utcnow()
data = await fetch_function(resource)
end_time = datetime.utcnow()
if data:
self.usage_stats["resource_usage"][resource.name]["successes"] += 1
metadata = {
"resource_name": resource.name,
"priority": priority.name,
"base_url": resource.base_url,
"response_time_ms": int((end_time - start_time).total_seconds() * 1000),
"timestamp": int(end_time.timestamp() * 1000)
}
logger.info(f" 🏆 {resource.name} won the race! ({metadata['response_time_ms']}ms)")
return data, metadata
self.usage_stats["resource_usage"][resource.name]["failures"] += 1
return None
except Exception as e:
logger.warning(f" ❌ {resource.name} failed: {e}")
self.usage_stats["resource_usage"][resource.name]["failures"] += 1
return None
def get_usage_statistics(self) -> Dict[str, Any]:
"""
Get comprehensive usage statistics
آمار کامل استفاده از منابع
"""
total_resources = len(self.usage_stats["resource_usage"])
used_resources = sum(
1 for stats in self.usage_stats["resource_usage"].values()
if stats["attempts"] > 0
)
successful_resources = sum(
1 for stats in self.usage_stats["resource_usage"].values()
if stats["successes"] > 0
)
# Calculate success rate per priority
priority_success_rates = {}
total_priority_requests = sum(self.usage_stats["priority_distribution"].values())
if total_priority_requests > 0:
for priority, count in self.usage_stats["priority_distribution"].items():
priority_success_rates[priority.name] = {
"count": count,
"percentage": round((count / total_priority_requests) * 100, 2)
}
# Find most used resources
most_used = sorted(
self.usage_stats["resource_usage"].items(),
key=lambda x: x[1]["attempts"],
reverse=True
)[:10]
# Find most successful resources
most_successful = sorted(
self.usage_stats["resource_usage"].items(),
key=lambda x: x[1]["successes"],
reverse=True
)[:10]
return {
"overview": {
"total_requests": self.usage_stats["total_requests"],
"successful_requests": self.usage_stats["successful_requests"],
"failed_requests": self.usage_stats["failed_requests"],
"success_rate": round(
(self.usage_stats["successful_requests"] / self.usage_stats["total_requests"] * 100)
if self.usage_stats["total_requests"] > 0 else 0,
2
)
},
"resource_utilization": {
"total_resources_in_system": total_resources,
"resources_used": used_resources,
"resources_successful": successful_resources,
"utilization_rate": round((used_resources / total_resources * 100) if total_resources > 0 else 0, 2)
},
"priority_distribution": priority_success_rates,
"top_10_most_used": [
{
"resource": name,
"attempts": stats["attempts"],
"successes": stats["successes"],
"failures": stats["failures"],
"success_rate": round((stats["successes"] / stats["attempts"] * 100) if stats["attempts"] > 0 else 0, 2)
}
for name, stats in most_used
],
"top_10_most_successful": [
{
"resource": name,
"successes": stats["successes"],
"attempts": stats["attempts"],
"success_rate": round((stats["successes"] / stats["attempts"] * 100) if stats["attempts"] > 0 else 0, 2)
}
for name, stats in most_successful
]
}
def get_resource_health_report(self) -> Dict[str, Any]:
"""
Get health report for all resources
گزارش سلامت همه منابع
"""
healthy_resources = []
degraded_resources = []
failed_resources = []
unused_resources = []
for resource_name, stats in self.usage_stats["resource_usage"].items():
if stats["attempts"] == 0:
unused_resources.append(resource_name)
elif stats["successes"] == 0:
failed_resources.append({
"name": resource_name,
"attempts": stats["attempts"],
"failures": stats["failures"]
})
else:
success_rate = (stats["successes"] / stats["attempts"]) * 100
if success_rate >= 80:
healthy_resources.append({
"name": resource_name,
"success_rate": round(success_rate, 2),
"attempts": stats["attempts"]
})
else:
degraded_resources.append({
"name": resource_name,
"success_rate": round(success_rate, 2),
"attempts": stats["attempts"],
"failures": stats["failures"]
})
return {
"healthy_resources": {
"count": len(healthy_resources),
"resources": healthy_resources
},
"degraded_resources": {
"count": len(degraded_resources),
"resources": degraded_resources
},
"failed_resources": {
"count": len(failed_resources),
"resources": failed_resources
},
"unused_resources": {
"count": len(unused_resources),
"resources": unused_resources
},
"overall_health": "Healthy" if len(healthy_resources) > len(failed_resources) else "Degraded"
}
# Global instance
master_orchestrator = MasterResourceOrchestrator()
__all__ = ["MasterResourceOrchestrator", "master_orchestrator", "ResourceStatus"]
|