SIENTIAPDE-1712
Implement MinIO Offload and Retention Features - Added configuration options for MinIO retention hours and offload threshold in README. - Introduced MinIO payload offloading for large DataFrame-derived payloads, storing them as parquet files. - Updated activities to utilize MinIO for data loading and cleanup, including new methods for offloading and retention management. - Refactored existing activities to integrate MinIO functionality, ensuring compatibility with previous workflows. - Removed the legacy MinioRepository class, consolidating MinIO operations under a new manager structure. - Updated requirements to use the latest version of the sientia-dataops-library.
This commit is contained in:
vitor-aignosi
@@ -1,8 +1,15 @@
|
||||
import json
|
||||
from temporalio import activity, workflow
|
||||
|
||||
from laborious.utils.repository.minio_manager import MinioManager
|
||||
|
||||
with workflow.unsafe.imports_passed_through():
|
||||
# Extend the Temporal Postgres activities for convenient query -> MinIO export
|
||||
import pickle
|
||||
import traceback
|
||||
from datetime import timedelta
|
||||
from io import BytesIO
|
||||
from os import getenv
|
||||
from typing import Any
|
||||
|
||||
import pandas as pd
|
||||
@@ -13,15 +20,20 @@ with workflow.unsafe.imports_passed_through():
|
||||
from sientia_do.temporal.activities.postgres import Postgres
|
||||
from sientia_do.temporal.constants import DATETIME_FORMAT_FILENAME, now
|
||||
|
||||
from laborious.utils.repository.minio_repository import MinioRepository
|
||||
from laborious.utils.models.minio_dataframe_payload import MinioDataFramePayload
|
||||
from sientia_do.repository.minio_repository import MinioRepository
|
||||
|
||||
_LOAD_QUERY_OFFLOAD_SKIP_KEYS = frozenset({'model_name', 'key_prefix', 'size_threshold_bytes'})
|
||||
|
||||
|
||||
class Storage(Postgres):
|
||||
class Storage(Postgres, MinioManager):
|
||||
"""
|
||||
Extensions for Postgres activities with a helper to export query results
|
||||
directly to MinIO as Parquet and return the object name.
|
||||
"""
|
||||
|
||||
minio_repository: MinioRepository | None = None
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
host: str,
|
||||
@@ -31,12 +43,15 @@ class Storage(Postgres):
|
||||
dbname: str,
|
||||
min_connections: int,
|
||||
max_connections: int,
|
||||
minio_config: dict[str, Any],
|
||||
logger: Logger,
|
||||
notification_handler: NotificationHandler,
|
||||
metrics_controller: MetricsController,
|
||||
retention_hours: int = 24,
|
||||
minio_repository: MinioRepository | None = None,
|
||||
logger: Logger | None = None,
|
||||
notification_handler: NotificationHandler | None = None,
|
||||
metrics_controller: MetricsController | None = None,
|
||||
):
|
||||
super().__init__(
|
||||
self.retention_hours = retention_hours
|
||||
Postgres.__init__(
|
||||
self,
|
||||
host=host,
|
||||
port=port,
|
||||
user=user,
|
||||
@@ -49,20 +64,144 @@ class Storage(Postgres):
|
||||
metrics_controller=metrics_controller,
|
||||
)
|
||||
|
||||
if not hasattr(self, 'minio_repository'):
|
||||
self.minio_repository: MinioRepository | None = None
|
||||
MinioManager.__init__(self, minio_repository, logger, notification_handler, metrics_controller)
|
||||
|
||||
@activity.defn(name='load_query_with_minio_offload')
|
||||
async def load_query_with_minio_offload(self, input_data: dict[str, Any]) -> MinioDataFramePayload:
|
||||
"""
|
||||
Run the custom SQL load, then return a MinIO-aware dataframe wire dict.
|
||||
|
||||
Args (input_data):
|
||||
metadata (dict): Workflow metadata (same as load_custom_query).
|
||||
query (str): SQL query.
|
||||
datetime_columns (list[str], optional): Datetime column names.
|
||||
model_name (str): Model name for object key basename.
|
||||
key_prefix (str, optional): Directory prefix inside the bucket.
|
||||
size_threshold_bytes (int, optional): Override env offload threshold.
|
||||
|
||||
Returns:
|
||||
dict[str, Any]: Flat ``MinioDataFramePayload`` dict or ``success: False`` on failure.
|
||||
"""
|
||||
if self.minio_repository is None:
|
||||
self.minio_repository = MinioRepository(
|
||||
logger=logger,
|
||||
notification_handler=notification_handler,
|
||||
minio_endpoint_url=minio_config['endpoint_url'],
|
||||
minio_access_key=minio_config['access_key'],
|
||||
minio_secret_key=minio_config['secret_key'],
|
||||
minio_region_name=minio_config['region_name'],
|
||||
minio_default_bucket=minio_config['default_bucket'],
|
||||
metrics_controller=metrics_controller,
|
||||
raise ValueError('Minio repository not initialized')
|
||||
|
||||
metadata: dict = input_data.get('metadata', {})
|
||||
model_name = input_data['model_name']
|
||||
|
||||
rows = await self.load_custom_query(
|
||||
input_data,
|
||||
)
|
||||
if not rows:
|
||||
self.error('load_query_with_minio_offload failed: No data returned from query', metadata)
|
||||
dataframe = None
|
||||
else:
|
||||
dataframe = pd.DataFrame(rows)
|
||||
|
||||
return await MinioDataFramePayload.from_dataframe(
|
||||
dataframe,
|
||||
minio_repo=self.minio_repository,
|
||||
workflow_metadata=metadata,
|
||||
model_name=model_name,
|
||||
operation='initial',
|
||||
)
|
||||
|
||||
@activity.defn(name='export_payload_to_postgres')
|
||||
async def export_payload_to_postgres(self, input_data: dict[str, Any]) -> dict:
|
||||
"""
|
||||
Export a payload to PostgreSQL.
|
||||
"""
|
||||
metadata = input_data.get('metadata')
|
||||
payload: MinioDataFramePayload = input_data['data']
|
||||
data = await payload.retrieve(self.minio_repository, metadata)
|
||||
|
||||
return await self.export_data_to_postgres(
|
||||
{
|
||||
**input_data,
|
||||
'data': data,
|
||||
}
|
||||
)
|
||||
|
||||
@activity.defn(name='cleanup_minio_objects_expired')
|
||||
async def cleanup_minio_objects_expired(self, input_data: dict[str, Any]) -> dict[str, Any]:
|
||||
"""
|
||||
Delete objects under the given prefixes that are older than the retention window.
|
||||
|
||||
Args (input_data):
|
||||
metadata (dict): Workflow metadata for logging and metrics.
|
||||
prefixes (list[str]): Key prefixes to scan (one level or subtree per prefix).
|
||||
|
||||
Returns:
|
||||
dict[str, Any]: ``success``, ``deleted_count``, and optional ``message``.
|
||||
"""
|
||||
if self.minio_repository is None:
|
||||
raise ValueError('Minio repository not initialized')
|
||||
|
||||
metadata = input_data.get('metadata', {})
|
||||
prefix = input_data['prefix']
|
||||
base = now()
|
||||
cutoff = (base.replace(tzinfo=None) if base.tzinfo else base) - timedelta(
|
||||
hours=self.retention_hours
|
||||
)
|
||||
|
||||
report: dict[str, Any] = {
|
||||
'failed': {},
|
||||
'deleted': {},
|
||||
'failed_count': 0,
|
||||
'deleted_count': 0,
|
||||
}
|
||||
try:
|
||||
keys = await self.minio_repository.list_objects(
|
||||
prefix=prefix,
|
||||
recursive=True,
|
||||
metadata=metadata,
|
||||
)
|
||||
for key in keys:
|
||||
try:
|
||||
ts = MinioDataFramePayload.parse_object_timestamp(key)
|
||||
if ts is None:
|
||||
continue
|
||||
if ts >= cutoff:
|
||||
continue
|
||||
await self.minio_repository.delete_file(
|
||||
object_name=key,
|
||||
metadata=metadata,
|
||||
)
|
||||
except Exception as e:
|
||||
report['failed'][key] = {
|
||||
'success': False,
|
||||
'message': str(e),
|
||||
}
|
||||
report['failed_count'] += 1
|
||||
continue
|
||||
report['deleted'][key] = {
|
||||
'success': True,
|
||||
'message': 'Deleted',
|
||||
}
|
||||
report['deleted_count'] += 1
|
||||
except Exception as e:
|
||||
trace = traceback.format_exc()
|
||||
await self.send_notification_async(
|
||||
metadata=metadata,
|
||||
notification_id='ERROR_CLEANUP_MINIO_OBJECTS_EXPIRED',
|
||||
message=f'Error cleaning up MinIO objects: {e}',
|
||||
block='cleanup_minio_objects_expired',
|
||||
level=NotificationLevel.ERROR,
|
||||
attachment_content=trace,
|
||||
)
|
||||
self.error(trace, metadata)
|
||||
else:
|
||||
await self.send_notification_async(
|
||||
metadata=metadata,
|
||||
notification_id='CLEANUP_MINIO_OBJECTS_EXPIRED',
|
||||
message='MinIO objects cleaned up successfully',
|
||||
block='cleanup_minio_objects_expired',
|
||||
level=NotificationLevel.INFO,
|
||||
attachment_content=json.dumps(report),
|
||||
)
|
||||
|
||||
return report
|
||||
|
||||
|
||||
|
||||
@activity.defn(name='query_to_minio')
|
||||
async def query_to_minio(self, input_data: dict[str, Any]) -> dict[str, Any]:
|
||||
@@ -83,11 +222,18 @@ class Storage(Postgres):
|
||||
raise ValueError('Minio repository not initialized')
|
||||
|
||||
metadata = input_data.get('metadata', {})
|
||||
model_name = input_data.get('model_name') or metadata.get('model_name') or 'unknown'
|
||||
object_prefix = input_data.get('object_prefix', 'datasets/retrain')
|
||||
|
||||
timestamp = now().strftime(DATETIME_FORMAT_FILENAME)
|
||||
object_name = f'{object_prefix}_{timestamp}.parquet'
|
||||
uri = f's3://{self.minio_repository.minio_bucket}/{object_name}'
|
||||
# Keep a stable model-level layout for minimal_retrain:
|
||||
# training_datasets/<model_name>/<filename>
|
||||
# Sanitize object_prefix to avoid extra subdirectories in the relative key.
|
||||
safe_prefix = str(object_prefix).strip().strip('/').replace('/', '_')
|
||||
filename = f'{safe_prefix}_{timestamp}.parquet'
|
||||
relative_key = f'training_datasets/{model_name}/{filename}'
|
||||
bucket = getattr(self.minio_repository, 'bucket', 'streamlit-connectors')
|
||||
uri = f's3://{bucket}/{relative_key}'
|
||||
|
||||
try:
|
||||
data = await self.load_custom_query(input_data)
|
||||
@@ -98,12 +244,20 @@ class Storage(Postgres):
|
||||
# Ensure we have a DataFrame
|
||||
data = pd.DataFrame(data)
|
||||
|
||||
# Write parquet to memory and upload via persistent client
|
||||
await self.minio_repository.store_dataframe_as_parquet(
|
||||
dataframe=data, uri=uri, object_name=object_name, metadata=metadata
|
||||
# Convert DataFrame -> parquet bytes, then upload using the new MinIO interface.
|
||||
parquet_buffer = BytesIO()
|
||||
data.to_parquet(parquet_buffer, engine='pyarrow', index=True)
|
||||
file_bytes = parquet_buffer.getvalue()
|
||||
|
||||
upload_result = await self.minio_repository.upload_file(
|
||||
file_bytes=file_bytes,
|
||||
relative_key=relative_key,
|
||||
metadata=metadata,
|
||||
)
|
||||
|
||||
return {'success': True, 'object_key': object_name, 'uri': uri}
|
||||
object_key_full = upload_result.get('minio_object_name', relative_key)
|
||||
uri = f's3://{bucket}/{object_key_full}'
|
||||
return {'success': True, 'object_key': object_key_full, 'uri': uri}
|
||||
except Exception as e:
|
||||
trace = traceback.format_exc()
|
||||
await self.send_notification_async(
|
||||
@@ -121,18 +275,8 @@ class Storage(Postgres):
|
||||
|
||||
def close(self) -> None:
|
||||
"""Close Storage resources (MinIO client and Postgres engine)."""
|
||||
try:
|
||||
if hasattr(self, 'minio_repository') and self.minio_repository is not None:
|
||||
try:
|
||||
self.minio_repository.close()
|
||||
finally:
|
||||
self.minio_repository = None
|
||||
finally:
|
||||
# Ensure Postgres resources are disposed as well
|
||||
try:
|
||||
super().close()
|
||||
except Exception:
|
||||
self.logger.error('Error closing Postgres resources')
|
||||
Postgres.close(self)
|
||||
MinioManager.close(self)
|
||||
|
||||
def __del__(self):
|
||||
self.close()
|
||||
|
||||
Reference in New Issue
Block a user