grabowski
96fedb3991
CI/CD Pipeline - Northern Thailand Ping River Monitor / Test Suite (3.11) (push) Failing after 25s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Build Docker Image (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Integration Test with Services (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Deploy to Staging (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Deploy to Production (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Performance Test (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Code Quality (push) Successful in 13s
Documentation / Generate API Documentation (push) Successful in 10s
Documentation / Build Sphinx Documentation (push) Successful in 16s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Cleanup (push) Successful in 1s
Documentation / Documentation Summary (push) Successful in 4s
Documentation / Validate Documentation (push) Failing after 8s
The on-box rerun after the inline fast path showed the cached endpoints healthy (latest p50 72-160ms, HII ~100ms) but /api/stats at 81% timeouts and /health at 33%: stats had a cache but NO single-flight, so every concurrent miss ran the heavy whole-DB counts (~1.7M rows) in parallel, re-jamming Postgres and the executor — which also dragged uncached history windows into 60s timeouts. /api/stats now computes through _ttl_cached_stale (one computation per 5min TTL, stale served on failure). The health API probe fails fast (5s instead of 30s) and its cache TTL rises to 30s, so a slow upstream can no longer pin executor threads longer than the cache lifetime.
288 lines
9.3 KiB
Python
288 lines
9.3 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Health check system for water monitoring application
|
|
"""
|
|
|
|
import logging
|
|
import threading
|
|
import time
|
|
from dataclasses import dataclass
|
|
from datetime import datetime, timedelta
|
|
from enum import Enum
|
|
from typing import Any, Callable, Dict, List, Optional
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class HealthStatus(Enum):
|
|
HEALTHY = "healthy"
|
|
DEGRADED = "degraded"
|
|
UNHEALTHY = "unhealthy"
|
|
|
|
|
|
@dataclass
|
|
class HealthCheckResult:
|
|
"""Result of a health check"""
|
|
|
|
name: str
|
|
status: HealthStatus
|
|
message: str
|
|
timestamp: datetime
|
|
response_time_ms: Optional[float] = None
|
|
details: Optional[Dict[str, Any]] = None
|
|
|
|
|
|
class HealthCheck:
|
|
"""Base health check class"""
|
|
|
|
def __init__(self, name: str, timeout_seconds: int = 30):
|
|
self.name = name
|
|
self.timeout_seconds = timeout_seconds
|
|
|
|
def check(self) -> HealthCheckResult:
|
|
"""Perform the health check"""
|
|
start_time = time.time()
|
|
|
|
try:
|
|
result = self._perform_check()
|
|
response_time = (time.time() - start_time) * 1000
|
|
|
|
return HealthCheckResult(
|
|
name=self.name,
|
|
status=result.get("status", HealthStatus.HEALTHY),
|
|
message=result.get("message", "OK"),
|
|
timestamp=datetime.now(),
|
|
response_time_ms=response_time,
|
|
details=result.get("details"),
|
|
)
|
|
|
|
except Exception as e:
|
|
response_time = (time.time() - start_time) * 1000
|
|
logger.error(f"Health check {self.name} failed: {e}")
|
|
|
|
return HealthCheckResult(
|
|
name=self.name,
|
|
status=HealthStatus.UNHEALTHY,
|
|
message=f"Check failed: {str(e)}",
|
|
timestamp=datetime.now(),
|
|
response_time_ms=response_time,
|
|
)
|
|
|
|
def _perform_check(self) -> Dict[str, Any]:
|
|
"""Override this method to implement the actual check"""
|
|
raise NotImplementedError
|
|
|
|
|
|
class DatabaseHealthCheck(HealthCheck):
|
|
"""Health check for database connectivity"""
|
|
|
|
def __init__(self, db_adapter, name: str = "database"):
|
|
super().__init__(name)
|
|
self.db_adapter = db_adapter
|
|
|
|
def _perform_check(self) -> Dict[str, Any]:
|
|
if not self.db_adapter:
|
|
return {
|
|
"status": HealthStatus.UNHEALTHY,
|
|
"message": "Database adapter not initialized",
|
|
}
|
|
|
|
try:
|
|
# Try to connect
|
|
if hasattr(self.db_adapter, "connect"):
|
|
connected = self.db_adapter.connect()
|
|
if not connected:
|
|
return {
|
|
"status": HealthStatus.UNHEALTHY,
|
|
"message": "Database connection failed",
|
|
}
|
|
|
|
# Try to get latest data
|
|
latest_data = self.db_adapter.get_latest_measurements(limit=1)
|
|
|
|
if latest_data:
|
|
latest_timestamp = latest_data[0].get("timestamp")
|
|
if isinstance(latest_timestamp, str):
|
|
latest_timestamp = datetime.fromisoformat(
|
|
latest_timestamp.replace("Z", "+00:00")
|
|
)
|
|
|
|
# Check if data is recent (within last 2 hours)
|
|
if datetime.now() - latest_timestamp.replace(tzinfo=None) > timedelta(
|
|
hours=2
|
|
):
|
|
return {
|
|
"status": HealthStatus.DEGRADED,
|
|
"message": f"Latest data is old: {latest_timestamp}",
|
|
"details": {"latest_data_timestamp": str(latest_timestamp)},
|
|
}
|
|
|
|
return {
|
|
"status": HealthStatus.HEALTHY,
|
|
"message": "Database connection OK",
|
|
"details": {
|
|
"latest_data_count": len(latest_data),
|
|
"latest_timestamp": str(latest_data[0].get("timestamp"))
|
|
if latest_data
|
|
else None,
|
|
},
|
|
}
|
|
|
|
except Exception as e:
|
|
return {
|
|
"status": HealthStatus.UNHEALTHY,
|
|
"message": f"Database check failed: {str(e)}",
|
|
}
|
|
|
|
|
|
class APIHealthCheck(HealthCheck):
|
|
"""Health check for external API connectivity"""
|
|
|
|
def __init__(self, api_url: str, session, name: str = "api"):
|
|
super().__init__(name)
|
|
# A liveness probe should fail fast: the default 30s timeout meant a
|
|
# slow upstream pinned executor threads for longer than the /health
|
|
# cache TTL, so the pool never drained under load.
|
|
self.timeout_seconds = 5
|
|
self.api_url = api_url
|
|
self.session = session
|
|
|
|
def _perform_check(self) -> Dict[str, Any]:
|
|
try:
|
|
# Simple GET request to check API availability
|
|
response = self.session.get(self.api_url, timeout=self.timeout_seconds)
|
|
|
|
if response.status_code == 200:
|
|
return {
|
|
"status": HealthStatus.HEALTHY,
|
|
"message": "API connection OK",
|
|
"details": {
|
|
"status_code": response.status_code,
|
|
"response_size": len(response.content),
|
|
},
|
|
}
|
|
else:
|
|
return {
|
|
"status": HealthStatus.DEGRADED,
|
|
"message": f"API returned status {response.status_code}",
|
|
"details": {"status_code": response.status_code},
|
|
}
|
|
|
|
except Exception as e:
|
|
return {
|
|
"status": HealthStatus.UNHEALTHY,
|
|
"message": f"API check failed: {str(e)}",
|
|
}
|
|
|
|
|
|
class MemoryHealthCheck(HealthCheck):
|
|
"""Health check for memory usage"""
|
|
|
|
def __init__(self, max_memory_mb: int = 1000, name: str = "memory"):
|
|
super().__init__(name)
|
|
self.max_memory_mb = max_memory_mb
|
|
|
|
def _perform_check(self) -> Dict[str, Any]:
|
|
try:
|
|
import psutil
|
|
|
|
process = psutil.Process()
|
|
memory_info = process.memory_info()
|
|
memory_mb = memory_info.rss / 1024 / 1024
|
|
|
|
if memory_mb > self.max_memory_mb:
|
|
return {
|
|
"status": HealthStatus.DEGRADED,
|
|
"message": f"High memory usage: {memory_mb:.1f}MB",
|
|
"details": {
|
|
"memory_mb": memory_mb,
|
|
"max_memory_mb": self.max_memory_mb,
|
|
},
|
|
}
|
|
|
|
return {
|
|
"status": HealthStatus.HEALTHY,
|
|
"message": f"Memory usage OK: {memory_mb:.1f}MB",
|
|
"details": {"memory_mb": memory_mb},
|
|
}
|
|
|
|
except ImportError:
|
|
return {
|
|
"status": HealthStatus.HEALTHY,
|
|
"message": "Memory check skipped (psutil not available)",
|
|
}
|
|
except Exception as e:
|
|
return {
|
|
"status": HealthStatus.UNHEALTHY,
|
|
"message": f"Memory check failed: {str(e)}",
|
|
}
|
|
|
|
|
|
class HealthCheckManager:
|
|
"""Manages multiple health checks"""
|
|
|
|
def __init__(self):
|
|
self.checks: List[HealthCheck] = []
|
|
self.last_results: Dict[str, HealthCheckResult] = {}
|
|
self._lock = threading.Lock()
|
|
|
|
def add_check(self, health_check: HealthCheck):
|
|
"""Add a health check"""
|
|
with self._lock:
|
|
self.checks.append(health_check)
|
|
|
|
def run_all_checks(self) -> Dict[str, HealthCheckResult]:
|
|
"""Run all health checks"""
|
|
results = {}
|
|
|
|
for check in self.checks:
|
|
try:
|
|
result = check.check()
|
|
results[check.name] = result
|
|
|
|
with self._lock:
|
|
self.last_results[check.name] = result
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error running health check {check.name}: {e}")
|
|
results[check.name] = HealthCheckResult(
|
|
name=check.name,
|
|
status=HealthStatus.UNHEALTHY,
|
|
message=f"Check execution failed: {str(e)}",
|
|
timestamp=datetime.now(),
|
|
)
|
|
|
|
return results
|
|
|
|
def get_overall_status(self) -> HealthStatus:
|
|
"""Get overall system health status"""
|
|
if not self.last_results:
|
|
return HealthStatus.UNHEALTHY
|
|
|
|
statuses = [result.status for result in self.last_results.values()]
|
|
|
|
if any(status == HealthStatus.UNHEALTHY for status in statuses):
|
|
return HealthStatus.UNHEALTHY
|
|
elif any(status == HealthStatus.DEGRADED for status in statuses):
|
|
return HealthStatus.DEGRADED
|
|
else:
|
|
return HealthStatus.HEALTHY
|
|
|
|
def get_health_summary(self) -> Dict[str, Any]:
|
|
"""Get a summary of system health"""
|
|
overall_status = self.get_overall_status()
|
|
|
|
return {
|
|
"overall_status": overall_status.value,
|
|
"timestamp": datetime.now().isoformat(),
|
|
"checks": {
|
|
name: {
|
|
"status": result.status.value,
|
|
"message": result.message,
|
|
"response_time_ms": result.response_time_ms,
|
|
"timestamp": result.timestamp.isoformat(),
|
|
}
|
|
for name, result in self.last_results.items()
|
|
},
|
|
}
|