Files
bakery-ia/services/data/shared/monitoring/metrics.py
2025-07-17 13:09:24 +02:00

112 lines
2.9 KiB
Python

"""
Metrics collection for microservices
"""
import time
import logging
from typing import Dict, Any
from prometheus_client import Counter, Histogram, Gauge, start_http_server
from functools import wraps
logger = logging.getLogger(__name__)
# Prometheus metrics
REQUEST_COUNT = Counter(
'http_requests_total',
'Total HTTP requests',
['method', 'endpoint', 'status_code', 'service']
)
REQUEST_DURATION = Histogram(
'http_request_duration_seconds',
'HTTP request duration in seconds',
['method', 'endpoint', 'service']
)
ACTIVE_CONNECTIONS = Gauge(
'active_connections',
'Active database connections',
['service']
)
TRAINING_JOBS = Counter(
'training_jobs_total',
'Total training jobs',
['status', 'service']
)
FORECASTS_GENERATED = Counter(
'forecasts_generated_total',
'Total forecasts generated',
['service']
)
class MetricsCollector:
"""Metrics collector for microservices"""
def __init__(self, service_name: str):
self.service_name = service_name
self.start_time = time.time()
def start_metrics_server(self, port: int = 8080):
"""Start Prometheus metrics server"""
try:
start_http_server(port)
logger.info(f"Metrics server started on port {port}")
except Exception as e:
logger.error(f"Failed to start metrics server: {e}")
def record_request(self, method: str, endpoint: str, status_code: int, duration: float):
"""Record HTTP request metrics"""
REQUEST_COUNT.labels(
method=method,
endpoint=endpoint,
status_code=status_code,
service=self.service_name
).inc()
REQUEST_DURATION.labels(
method=method,
endpoint=endpoint,
service=self.service_name
).observe(duration)
def record_training_job(self, status: str):
"""Record training job metrics"""
TRAINING_JOBS.labels(
status=status,
service=self.service_name
).inc()
def record_forecast_generated(self):
"""Record forecast generation metrics"""
FORECASTS_GENERATED.labels(
service=self.service_name
).inc()
def set_active_connections(self, count: int):
"""Set active database connections"""
ACTIVE_CONNECTIONS.labels(
service=self.service_name
).set(count)
def metrics_middleware(metrics_collector: MetricsCollector):
"""Middleware to collect metrics"""
def middleware(request, call_next):
start_time = time.time()
response = call_next(request)
duration = time.time() - start_time
metrics_collector.record_request(
method=request.method,
endpoint=request.url.path,
status_code=response.status_code,
duration=duration
)
return response
return middleware