mirror of
https://github.com/datahub-project/datahub.git
synced 2025-11-10 08:21:21 +00:00
36 lines
1.4 KiB
YAML
36 lines
1.4 KiB
YAML
source:
|
|
type: datahub-gc
|
|
config:
|
|
# Whether to run the recipe in dry-run mode or not
|
|
dry_run: false
|
|
# Cleanup expired tokens
|
|
cleanup_expired_tokens: true
|
|
# Whether to truncate elasticsearch indices or not which can be safely truncated
|
|
truncate_indices: true
|
|
|
|
# Cleanup DataProcess Instances
|
|
dataprocess_cleanup:
|
|
retention_days: 10
|
|
# Delete empty Data Jobs (if no DataProcessInstance associated with the DataJob)
|
|
delete_empty_data_jobs: true
|
|
# Delete empty Data Flow (if no DataJob associated with the DataFlow)
|
|
delete_empty_data_flows: true
|
|
# Whether to hard delete entities or soft delete them
|
|
hard_delete_entities: false
|
|
# Keep the last n dataprocess instances
|
|
keep_last_n: 5
|
|
soft_deleted_entities_cleanup:
|
|
# Delete soft deleted entities which were deleted 10 days ago
|
|
retention_days: 10
|
|
execution_request_cleanup:
|
|
# Minimum number of execution requests to keep, per ingestion source
|
|
keep_history_min_count: 10
|
|
# Maximum number of execution requests to keep, per ingestion source
|
|
keep_history_max_count: 1000
|
|
# Maximum number of days to keep execution requests for, per ingestion source
|
|
keep_history_max_days: 30
|
|
# Number of records per read operation
|
|
batch_read_size: 100
|
|
# Global switch for this cleanup task
|
|
enabled: true
|