SIENTIAPDE-1773
Enhance environment configuration and update dependencies - Added new environment variables for PluginStore and MLflow configuration in `.env.example`, including `RUNTIME`, `STORE_BASE_URL`, `STORE_OWNER`, `STORE_REPO`, `STORE_BRANCH`, `STORE_USERNAME`, `STORE_PASSWORD`, `STORE_CACHE_TTL_SECONDS`, `PYPI_SERVER`, `PYPI_USERNAME`, and `PYPI_PASSWORD`. - Updated `git-requirements-mapping.txt` to reflect changes in repository names. - Modified `requirements-light.txt` and `requirements.txt` to upgrade `sientia-dataops-library` to version 1.12.0 and `sientia-mlops-library` to version 0.8.1. - Updated `values.yaml` to include new environment variables for worker runtime and PluginStore configuration. - Refactored E2E tests to utilize new MLflow repository stubs and PluginStore mocks for improved testing accuracy.
This commit is contained in:
@@ -1,32 +1,32 @@
|
||||
"""
|
||||
Laborious Worker Module
|
||||
|
||||
This module provides the main worker implementation for the Sientia DataOps Laborious system.
|
||||
It orchestrates Temporal workers, manages task queues, and handles the lifecycle of
|
||||
prediction and retraining workflows.
|
||||
Entry process that connects to Temporal, registers Laborious activities, and runs four workers in
|
||||
parallel. Each worker shares the same ``Activities`` instance (single Postgres pool, single MLflow
|
||||
repository, single PluginStore handle) but polls a different task queue.
|
||||
|
||||
The worker supports multiple task queues:
|
||||
- predictions_batch-queue: Handles batch prediction workflows (heavy workload)
|
||||
Includes activities for MLFlow, data quality gates, OPC export, PI Web API export, and PostgreSQL
|
||||
- minimal_retrain-queue: Handles model retraining workflows
|
||||
- drift-queue: Handles drift detection workflows
|
||||
- simple_metrics-queue: Handles simple metrics calculation workflows
|
||||
Task queues (see ``sientia_do.temporal.worker.prepare_worker``):
|
||||
- ``predictions_batch-{runtime}-queue`` + sub-workflows on the same queue (ML-heavy path).
|
||||
- ``minimal_retrain-{runtime}-queue`` (retrain + promote + export).
|
||||
- ``drift-queue`` and ``simple_metrics-queue`` without a runtime suffix so existing schedulers
|
||||
keep stable queue names.
|
||||
|
||||
Key Features:
|
||||
- Resource-based scaling with WorkerTuner (CPU and memory aware)
|
||||
- Automatic polling scaling with PollerBehaviorAutoscaling
|
||||
- Prometheus metrics integration
|
||||
- Comprehensive error handling and logging
|
||||
- Graceful shutdown with cleanup
|
||||
- Multiple worker instances for different workflow types
|
||||
Bootstrap order:
|
||||
1. Prometheus app metrics and Mongo-backed notification handler.
|
||||
2. ``RUNTIME`` validation and ``PluginStore.install_runtime`` so ``SientiaModel`` code is importable.
|
||||
3. ``Activities`` construction (builds ``SientiaMLflowRepository`` internally from env).
|
||||
4. OPC client initialization inside activities.
|
||||
5. Temporal ``Runtime`` with SDK Prometheus bind, client connect, then ``prepare_worker`` per workflow.
|
||||
|
||||
Shutdown closes workers, notifications, activities (pools + OPC), and clears ``app_up``.
|
||||
|
||||
Environment Variables:
|
||||
- TEMPORAL_HOST: Temporal server address (default: localhost:7233)
|
||||
- TEMPORAL_NAMESPACE: Temporal namespace (default: laborious)
|
||||
- POD_ID: Kubernetes pod identifier for metrics
|
||||
- HTTP_METRICS_PORT: Prometheus metrics server port (default: 9090)
|
||||
- HTTP_SDK_METRICS_PORT: Temporal SDK metrics port (default: 9091)
|
||||
- PROJECT_NAME: Project name for notifications (default: laborious)
|
||||
- RUNTIME: Required non-empty string passed to ``install_runtime``.
|
||||
- STORE_* / PYPI_*: Plugin store and private index (see ``build_plugin_store_config``).
|
||||
- TEMPORAL_HOST, TEMPORAL_NAMESPACE: Cluster connection.
|
||||
- POD_ID, HTTP_METRICS_PORT, HTTP_SDK_METRICS_PORT: Observability.
|
||||
- PROJECT_NAME, MONGODB_*: Notifications (via ``build_mongodb_config`` in handler).
|
||||
- POSTGRES_*, MINIO_*, OPC_*, PI_WEB_API_*, MLFLOW_*: Passed through ``Activities`` helpers.
|
||||
"""
|
||||
|
||||
from temporalio import client, workflow
|
||||
@@ -40,20 +40,22 @@ with workflow.unsafe.imports_passed_through():
|
||||
from prometheus_client import start_http_server
|
||||
from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
|
||||
from sientia_do.observability.logger import get_logger
|
||||
from sientia_do.observability.metrics_controller import MetricsController
|
||||
from sientia_do.temporal.worker.prepare_worker import prepare_worker
|
||||
from sientia_do.utils.connectors_config import (
|
||||
build_api_config,
|
||||
build_mongodb_config,
|
||||
build_postgres_config,
|
||||
)
|
||||
from sientia_model.model_repository.plugin_store import PluginStore
|
||||
|
||||
from laborious import metrics
|
||||
from laborious.activities.activities import Activities
|
||||
from laborious.utils.connectors_config import (
|
||||
build_minio_config,
|
||||
build_mlflow_config,
|
||||
build_opc_config,
|
||||
build_plugin_store_config,
|
||||
)
|
||||
from laborious.worker.prepare_worker import prepare_worker
|
||||
from laborious.workflows.drift import Drift
|
||||
from laborious.workflows.minimal_retrain import MinimalRetrain
|
||||
from laborious.workflows.predictions_batch import PredictionsBatch
|
||||
@@ -69,23 +71,18 @@ SDK_METRICS_PORT = int(os.getenv('HTTP_SDK_METRICS_PORT', '9091'))
|
||||
|
||||
async def main():
|
||||
"""
|
||||
Main entry point for the Laborious worker application.
|
||||
Run the full worker lifecycle: metrics, notifications, runtime install, workers, gather.
|
||||
|
||||
This function initializes and starts all components of the worker:
|
||||
1. Sets up logging and metadata
|
||||
2. Starts Prometheus metrics server
|
||||
3. Initializes notification handler
|
||||
4. Creates and configures activities
|
||||
5. Initializes OPC connections
|
||||
6. Starts Temporal client and workers
|
||||
7. Manages worker lifecycle and graceful shutdown
|
||||
|
||||
The function runs indefinitely until interrupted or an error occurs.
|
||||
On error, it performs cleanup and exits with a non-zero status code.
|
||||
Exits the process with code 0 on normal completion of all worker tasks, or 1 after logging
|
||||
if any worker raises. ``finally`` always shuts down notifications and activities and sets
|
||||
``app_up`` to 0 before ``sys.exit``.
|
||||
|
||||
Raises:
|
||||
Exception: Any unhandled exception during worker execution
|
||||
SystemExit: On graceful shutdown or error conditions
|
||||
Exception: Propagated from ``asyncio.gather`` only before ``finally`` handling; typically
|
||||
workers run until cancelled.
|
||||
|
||||
Return:
|
||||
None (process terminates via ``sys.exit`` from the ``finally`` block).
|
||||
"""
|
||||
host = os.getenv('TEMPORAL_HOST', 'localhost:7233')
|
||||
logger = get_logger(__name__)
|
||||
@@ -113,16 +110,55 @@ async def main():
|
||||
project_name=os.getenv('PROJECT_NAME', 'laborious'),
|
||||
)
|
||||
|
||||
metrics_controller = MetricsController(logger=logger)
|
||||
|
||||
runtime = os.getenv('RUNTIME', '').strip()
|
||||
if not runtime:
|
||||
logger.custom_critical(
|
||||
'RUNTIME environment variable is required and must be non-empty',
|
||||
metadata,
|
||||
)
|
||||
metrics.APP_UP.labels(pod_id=POD_ID).set(0)
|
||||
sys.exit(1)
|
||||
|
||||
metadata_runtime = {**metadata, 'runtime': runtime}
|
||||
logger.custom_info(f'Installing PluginStore runtime: {runtime}', metadata_runtime)
|
||||
|
||||
ps_cfg = build_plugin_store_config()
|
||||
plugin_store = PluginStore(
|
||||
base_url=ps_cfg['base_url'],
|
||||
owner=ps_cfg['owner'],
|
||||
repo=ps_cfg['repo'],
|
||||
username=ps_cfg['username'],
|
||||
password=ps_cfg['password'],
|
||||
branch=ps_cfg['branch'],
|
||||
cache_ttl_seconds=ps_cfg['cache_ttl_seconds'],
|
||||
pypi_index_url=ps_cfg['pypi_index_url'],
|
||||
pypi_username=ps_cfg['pypi_username'],
|
||||
pypi_password=ps_cfg['pypi_password'],
|
||||
logger=logger,
|
||||
notification_handler=notification_handler,
|
||||
metrics_controller=metrics_controller,
|
||||
)
|
||||
|
||||
try:
|
||||
await plugin_store.install_runtime(runtime_name=runtime, metadata=metadata_runtime)
|
||||
except Exception as exc:
|
||||
logger.custom_critical(f'Failed to install runtime {runtime}: {exc}', metadata_runtime)
|
||||
metrics.APP_UP.labels(pod_id=POD_ID).set(0)
|
||||
sys.exit(1)
|
||||
|
||||
logger.custom_info('Starting Activities...', metadata)
|
||||
|
||||
activities = Activities(
|
||||
postgres_config=build_postgres_config(),
|
||||
mlflow_config=build_mlflow_config(),
|
||||
plugin_store=plugin_store,
|
||||
minio_config=build_minio_config(),
|
||||
opc_config=build_opc_config(),
|
||||
pi_web_api_config=build_api_config(),
|
||||
logger=logger,
|
||||
notification_handler=notification_handler,
|
||||
metrics_controller=metrics_controller,
|
||||
)
|
||||
|
||||
logger.custom_info('Initializing OPC...', metadata)
|
||||
@@ -159,6 +195,7 @@ async def main():
|
||||
activities.export_data_to_postgres,
|
||||
],
|
||||
logger=logger,
|
||||
runtime=runtime,
|
||||
),
|
||||
prepare_worker(
|
||||
temporal_client=temporal_client,
|
||||
@@ -210,6 +247,7 @@ async def main():
|
||||
activities.write_pi_web_api_data,
|
||||
],
|
||||
logger=logger,
|
||||
runtime=runtime,
|
||||
),
|
||||
]
|
||||
|
||||
@@ -221,8 +259,6 @@ async def main():
|
||||
|
||||
exit_code = 0
|
||||
try:
|
||||
# This will run the workers and wait for them to complete.
|
||||
# If an exception occurs in any of the worker handlers, it will be propagated here.
|
||||
await asyncio.gather(*handlers)
|
||||
except BaseException as e: # NOSONAR
|
||||
logger.custom_error(f'An unhandled exception occurred: {e}', metadata)
|
||||
|
||||
Reference in New Issue
Block a user