Merge branch 'main' into release/SIENTIAPDE-1645
This commit is contained in:
vitor-aignosi
@@ -1,5 +1,5 @@
|
||||
"""
|
||||
Cleanup activities for removing stale files from MinIO and local filesystem.
|
||||
Cleanup activities for removing stale files from local filesystem.
|
||||
|
||||
This module provides activities for cleaning up temporary files and directories
|
||||
that are older than the configured retention period. It operates independently
|
||||
@@ -13,7 +13,7 @@ with workflow.unsafe.imports_passed_through():
|
||||
import re
|
||||
import shutil
|
||||
import traceback
|
||||
from datetime import UTC, datetime, timedelta
|
||||
from datetime import datetime, timedelta
|
||||
from typing import Any
|
||||
|
||||
from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
|
||||
@@ -27,7 +27,6 @@ with workflow.unsafe.imports_passed_through():
|
||||
|
||||
RETENTION_HOURS = int(os.getenv('CLEANUP_RETENTION_HOURS', '24'))
|
||||
DRY_RUN = os.getenv('CLEANUP_DRY_RUN', 'false').lower() == 'true'
|
||||
MAX_KEYS_CLEANUP = int(os.getenv('MAX_KEYS_CLEANUP', '1000'))
|
||||
|
||||
|
||||
class Cleanup(SientiaMonitoring):
|
||||
@@ -35,13 +34,11 @@ class Cleanup(SientiaMonitoring):
|
||||
Activity for cleaning up stale files and directories.
|
||||
|
||||
This activity extends SientiaMonitoring and handles cleanup of:
|
||||
- MinIO files with timestamp prefixes (timestamp-filename pattern)
|
||||
- Local temporary directories with timestamp suffixes
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
minio_repository: MinioRepository,
|
||||
logger: Logger,
|
||||
notification_handler: NotificationHandler,
|
||||
metrics_controller: MetricsController,
|
||||
@@ -50,145 +47,21 @@ class Cleanup(SientiaMonitoring):
|
||||
Initialize Cleanup activity.
|
||||
|
||||
Args:
|
||||
minio_repository: Repository for MinIO operations
|
||||
logger: Logger instance for observability
|
||||
notification_handler: Handler for sending notifications
|
||||
metrics_controller: Controller for metrics emission
|
||||
"""
|
||||
SientiaMonitoring.__init__(self, logger, notification_handler, metrics_controller)
|
||||
self.minio_repository = minio_repository
|
||||
|
||||
# Configuration from environment variables
|
||||
self.retention_hours = RETENTION_HOURS
|
||||
self.dry_run = DRY_RUN
|
||||
|
||||
# MinIO list operation page size
|
||||
self.max_keys_cleanup = MAX_KEYS_CLEANUP
|
||||
|
||||
# Regex patterns for timestamp extraction
|
||||
self.minio_timestamp_pattern = re.compile(r'^(\d{13})-(.+)') # timestamp-filename
|
||||
self.dir_timestamp_pattern = re.compile(
|
||||
r'^(.+)_(\d{8}_\d{6}_\d{6})$'
|
||||
) # name_YYYYMMDD_HHMMSS_microseconds
|
||||
|
||||
@activity.defn(name='cleanup_minio_files')
|
||||
async def cleanup_minio_files(self, input_data: dict[str, Any]) -> None:
|
||||
"""
|
||||
Clean up stale files from MinIO based on timestamp in filename.
|
||||
|
||||
This activity scans a single MinIO bucket for files following the pattern
|
||||
'{timestamp}-{filename}' where timestamp is milliseconds since epoch.
|
||||
Files older than the retention period are deleted.
|
||||
|
||||
Args:
|
||||
input_data: Cleanup configuration containing:
|
||||
- metadata (dict): Workflow execution metadata
|
||||
- bucket_name (str): Name of the bucket to scan
|
||||
|
||||
Returns:
|
||||
None: Results are logged and tracked via metrics
|
||||
|
||||
Raises:
|
||||
Exception: If cleanup fails (after sending notification)
|
||||
"""
|
||||
metadata = input_data.get('metadata', {})
|
||||
bucket_name = input_data.get('bucket_name')
|
||||
metrics_status = 'success'
|
||||
|
||||
if not bucket_name:
|
||||
raise ValueError('bucket_name must be provided')
|
||||
|
||||
cutoff_time = datetime.now(UTC) - timedelta(hours=self.retention_hours)
|
||||
cutoff_timestamp_ms = int(cutoff_time.timestamp() * 1000)
|
||||
|
||||
try:
|
||||
self.info(
|
||||
f'Starting MinIO cleanup - Bucket: {bucket_name}, '
|
||||
f'Retention: {self.retention_hours}h, Dry run: {self.dry_run}, '
|
||||
f'Cutoff: {cutoff_time.isoformat()}',
|
||||
metadata,
|
||||
)
|
||||
|
||||
files_scanned = 0
|
||||
files_deleted = 0
|
||||
errors = []
|
||||
|
||||
# List objects in the specified bucket. MinioRepository applies BASE_PREFIX
|
||||
# internally; we request all objects under that prefix for this bucket.
|
||||
objects = await self.minio_repository.list_objects(
|
||||
prefix='',
|
||||
bucket=bucket_name,
|
||||
recursive=True,
|
||||
metadata=metadata,
|
||||
)
|
||||
|
||||
for obj_key in objects:
|
||||
files_scanned += 1
|
||||
|
||||
# Extract timestamp from the filename portion of the object key
|
||||
filename = obj_key.split('/')[-1]
|
||||
match = self.minio_timestamp_pattern.match(filename)
|
||||
if not match:
|
||||
self.debug(f'Skipping file without timestamp pattern: {obj_key}', metadata)
|
||||
continue
|
||||
|
||||
file_timestamp_ms = int(match.group(1))
|
||||
|
||||
if file_timestamp_ms < cutoff_timestamp_ms:
|
||||
if self.dry_run:
|
||||
self.info(
|
||||
f'[DRY RUN] Would delete: {obj_key} (age: {(cutoff_time.timestamp() - file_timestamp_ms / 1000) / 3600:.1f}h)',
|
||||
metadata,
|
||||
)
|
||||
files_deleted += 1
|
||||
else:
|
||||
try:
|
||||
await self.minio_repository.delete_file(
|
||||
object_name=obj_key,
|
||||
bucket=None,
|
||||
metadata=metadata,
|
||||
)
|
||||
self.info(f'Deleted stale file: {obj_key}', metadata)
|
||||
files_deleted += 1
|
||||
except Exception as e: # noqa: BLE001
|
||||
error_msg = f'Failed to delete {obj_key}: {str(e)}'
|
||||
errors.append(error_msg)
|
||||
self.error(error_msg, metadata)
|
||||
else:
|
||||
self.debug(
|
||||
f'Keeping recent file: {obj_key} (age: {(cutoff_time.timestamp() - file_timestamp_ms / 1000) / 3600:.1f}h)',
|
||||
metadata,
|
||||
)
|
||||
|
||||
self.info(
|
||||
f'MinIO cleanup completed - Bucket: {bucket_name}, '
|
||||
f'Scanned: {files_scanned}, Deleted: {files_deleted}, Errors: {len(errors)}',
|
||||
metadata,
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
metrics_status = 'error'
|
||||
error_msg = f'Error in MinIO cleanup: {str(e)}'
|
||||
trace = traceback.format_exc()
|
||||
|
||||
self.send_notification(
|
||||
metadata=metadata,
|
||||
notification_id='CLEANUP_MINIO_ERROR',
|
||||
message=error_msg,
|
||||
block='cleanup_minio_files',
|
||||
level=NotificationLevel.ERROR,
|
||||
attachment_content=trace,
|
||||
)
|
||||
|
||||
raise
|
||||
finally:
|
||||
await self._emit_metrics(
|
||||
metadata=metadata,
|
||||
metrics_status=metrics_status,
|
||||
activity_name='cleanup_minio_files',
|
||||
emit_workflow_metric=(metrics_status == 'error'),
|
||||
)
|
||||
|
||||
@activity.defn(name='cleanup_temp_directories')
|
||||
async def cleanup_temp_directories(self, input_data: dict[str, Any]) -> None:
|
||||
"""
|
||||
|
||||
@@ -24,7 +24,6 @@ with workflow.unsafe.imports_passed_through():
|
||||
from sientia_model.wrappers.sientia_model import SientiaModel
|
||||
|
||||
from model_manager.metrics import ACTIVITY_EXECUTION_TOTAL, WORKFLOW_EXECUTION_TOTAL
|
||||
from model_manager.utils.exceptions import ModelTrainingError
|
||||
from model_manager.utils.models.train_model_params import TrainModelParams
|
||||
from model_manager.utils.repository.data_manager_repository import DataManagerRepository
|
||||
|
||||
@@ -261,11 +260,7 @@ class Training(SientiaMonitoring):
|
||||
except Exception as e: # noqa: BLE001
|
||||
metrics_status = 'error'
|
||||
|
||||
error_msg = (
|
||||
'Error training model - '
|
||||
f'model_trained={model_trained}, model_saved={model_saved}, '
|
||||
f'error: {str(e)}'
|
||||
)
|
||||
error_msg = f'Error training model - error: {str(e)}'
|
||||
|
||||
trace = traceback.format_exc()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user