[Serve][3/N] Add application-level autoscaling snapshot #59995
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Dongjun Na <[email protected]>
Signed-off-by: Dongjun Na <[email protected]>
Signed-off-by: Dongjun Na <[email protected]>
nadongjun
changed the title
7 tasks
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request extends autoscaling observability to the application level by introducing ApplicationSnapshot logs. The changes are well-structured, reusing existing patterns from deployment-level snapshots, and include comprehensive tests. I've identified a couple of areas for improvement to enhance code clarity and correctness. Overall, this is a solid addition to Ray Serve's observability features.
Signed-off-by: Dongjun Na <[email protected]>
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
Signed-off-by: Dongjun Na <[email protected]>
ray-gardener
bot
added
serve
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Add application-level autoscaling snapshot support for observability.
This PR extends the existing deployment-level autoscaling snapshot feature (PR #56225) to support application-level autoscaling. When an app-level autoscaling policy is configured, the controller now emits
ApplicationSnapshotlogs containing aggregated metrics across all deployments in the application.Related issues
Related to #55833
Additional information
bash % cat /tmp/ray/session_latest/logs/serve/autoscaling_snapshot_6668.log {"asctime": "2026-01-09 13:56:19,481", "levelname": "INFO", "message": "{'snapshots': [{'snapshot_type': 'application', 'timestamp_str': '2026-01-09T04:56:19Z', 'app': 'app_snap_1767934578', 'num_deployments': 2, 'total_current_replicas': 0, 'total_target_replicas': 2, 'scaling_status': 'scaling up', 'policy_name': 'ray.serve.tests.test_controller.simple_app_policy_for_test', 'errors': []}]}", "filename": "controller.py", "lineno": 511, "process": 6668, "timestamp_ns": 1767934579481838000} {"asctime": "2026-01-09 13:56:19,999", "levelname": "INFO", "message": "{'snapshots': [{'snapshot_type': 'application', 'timestamp_str': '2026-01-09T04:56:19Z', 'app': 'app_snap_1767934578', 'num_deployments': 2, 'total_current_replicas': 2, 'total_target_replicas': 2, 'scaling_status': 'stable', 'policy_name': 'ray.serve.tests.test_controller.simple_app_policy_for_test', 'errors': []}]}", "filename": "controller.py", "lineno": 511, "process": 6668, "timestamp_ns": 1767934579999085000}