# v0.3.9

---

## Release Availability Date

17-Mar-2025

## Recommended CLI/SDK

1.0.0

## Helm Chart

1.5.5 or greater

## Known Issues

- OpenAPI Async Timeseries Aspects will not automatically create the entity's key aspect.
- Writes for hard deleted entities will be dropped for 60 seconds after the hard delete is processed.
- API Tracing is considered as a beta release

## Release Changelog

---

### v0.3.9.2

- [Lineage Visualization] Fix bug where assets would not appear when hiding transformations.
- [Remote Executor] Create upgrade job to remove legacy remote executor status
- [Usage Ranking] Make usage feature reporting source more robust to non-standard data.
- [Proposals] Make action request owner source more robust to non-standard data.
- [Platform] Add error handling when deleting an aspect that does not exist.

### v0.3.9

- All changes in https://github.com/datahub-project/datahub/releases/tag/v0.15.0.1

  - Note Breaking Changes: https://docs.datahub.com/docs/how/updating-datahub/#0150
  - Also includes some, but not all, changes in the upcoming v1.0.0 release

- Breaking Changes

- Bug Fixes

  - [Compliance Forms] Fix a few inaccuracies in the Compliance Forms analytics tab - handle multiple forms per asset properly and fix a few bugs in the forms analytics ingestion source when generating this analytics data.
  - [Compliance Forms] Fix bug in nested select component when adding a Domain question to your Compliance Form when selecting child domains. Now you can properly select a parent and their children.
  - [Queries Tab] Fix column and user filters in the Query tab by showing the proper display name instead of urns.
  - [Search Results] Fix order of parent entity paths in the autocomplete dropdown for a given result.
  - [CSV Export] Fix missing display name for Groups when downloading search results.
  - [Users & Groups] Fix group membership inconsistencies on groups page. Correctly show the count of members and improve the experience to make it clearer who is a member of what group.
  - [Columns Tab] Fix bug in schema table where we were not showing metadata if a field changed in ingestion from V1 to V2 field path or vice versa.
  - [Search Filtering] Fix dropdowns for selecting platforms and other filters when creating Views that were not showing any results.
  - [Search Results] Fix lineage counts on search result cards that were incorrectly counting "ghost" (non-existent) entities.
  - [Compliance Forms] Fix bug when filling out documentation prompts on Datasets to update the correct aspect.
  - [Log Out] Fix logout bug in new navigation bar redesign when a user is logged in with SSO.
  - [Search Ranking] Improved memory usage of usage ranking job; fix bugs when usage was missing.

- Product

  - Introducing a new Stats Tab redesign for Datasets and Columns! This release gives you all the functionality you had with Dataset and Columns stats previously, but now in a much cleaner, more consumable way. We also add a few new stats and charts to render additional helpful information about your assets. Note that statistics must be enabled in ingestion to view them on the stats tab.
  - Improved support for ML Models and ML Groups as part of the expanded MLflow ingestion source. Data process instances can now appear on container pages and lineage.
  - Improve the Compliance Forms experience while filling out questions by pre-filling responses for the user with existing metadata on the asset. Now, a user will have an even easier time filling out Compliance Forms for their assets.
  - The new navigation bar experience is now the default! Quickly understand & navigate to every DataHub feature.
  - Improve the navigation bar experience by centering and expanding the search bar at the top of the page.
  - Add Compliance Forms validation to prevent duplicate question IDs across and within Compliance Forms.
  - Elevate structured properties displayed on Asset Sidebar about Status section
  - Entity versioning is now supported via ingestion, for version-native sources like MLflow.

- Platform

  - Remote Executor: Introduced new Prometheus Metrics for remote executor monitoring:
    - Ingestion: `datahub_executor_worker_ingestion_requests` and `datahub_executor_worker_ingestion_errors` to monitor ingestion jobs received from queue
    - Memory: `datahub_executor_memory_*` to monitor usage and limits by process group/host
    - CPU: `datahub_executor_cpu_*` to monitor usage and limits by process group/host
    - Disk: `datahub_executor_disk_*` to monitor total bytes and bytes used
    - Network: `datahub_executor_net_*` to monitor bytes and packets sent/received, etc.

- Ingestion
  - MLflow: Support for experiments & runs ingestion, enhanced property ingestion for models/model versions with native versioning support
    - Dataset ↔ Run lineage is coming soon.
  - Spark: Column-level lineage now runs through a Spark DataJob rather than directly between datasets.