39 lines
1.2 KiB
Python
39 lines
1.2 KiB
Python
"""
|
|
Model Manager Metrics Module
|
|
|
|
This module defines all Prometheus metrics used by the Sientia DataOps Model Manager system
|
|
for monitoring and observability. The metrics provide insights into system performance,
|
|
training operations, and operational health.
|
|
|
|
The metrics are designed to be scraped by Prometheus and can be visualized in
|
|
Grafana or other monitoring dashboards to provide real-time visibility into
|
|
the system's operation.
|
|
|
|
Key Metric Categories:
|
|
- Application Health: Overall system status and availability
|
|
|
|
Metric Labels:
|
|
- pod_id: Kubernetes pod identifier for multi-instance deployments
|
|
"""
|
|
|
|
from prometheus_client import Counter, Gauge
|
|
|
|
# Application health metric
|
|
APP_UP = Gauge(
|
|
'app_up',
|
|
'Indicates if the application is running (1) or shutting down (0)',
|
|
['pod_id'],
|
|
)
|
|
|
|
WORKFLOW_EXECUTION_TOTAL = Counter(
|
|
'model_manager_workflow_executions_total',
|
|
'Total number of workflow executions',
|
|
['pod_id', 'workflow_name', 'status'], # status: success, error
|
|
)
|
|
|
|
ACTIVITY_EXECUTION_TOTAL = Counter(
|
|
'model_manager_activity_executions_total',
|
|
'Total number of activity executions',
|
|
['pod_id', 'activity_name', 'status'], # status: success, error
|
|
)
|