[Serve] Support headers in Readiness Probe #3552
Merged
Conversation
This file contains 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
5 tasks
Michaelvll
reviewed
May 18, 2024
There was a problem hiding this comment.
Thanks for adding the support for the authorization token in the readiness probe @cblmemo! It looks mostly good to me!
sky/serve/service_spec.py
Outdated
| if self.readiness_headers is None: | ||
| headers = '' | ||
| else: | ||
| headers = f' with headers {json.dumps(self.readiness_headers)}' |
There was a problem hiding this comment.
nit: Showing the authorization token directly in the log may not be very safe. We may want to redact the value of the headers?
There was a problem hiding this comment.
Good point! Changed to with custom headers now.
Michaelvll
approved these changes
May 20, 2024
There was a problem hiding this comment.
Thanks for adding this @cblmemo! LGTM with the comment fixed.
sky/serve/replica_managers.py
Outdated
| @@ -567,7 +570,8 @@ def __init__(self, service_name: str, | |||
| self._update_mode = serve_utils.DEFAULT_UPDATE_MODE | |||
| logger.info(f'Readiness probe path: {spec.readiness_path}\n' | |||
| f'Initial delay seconds: {spec.initial_delay_seconds}\n' | |||
| f'Post data: {spec.post_data}') | |||
| f'Post data: {spec.post_data}\n' | |||
| f'Readiness headers: {spec.readiness_headers}') | |||
There was a problem hiding this comment.
Seems we are still printing out the headers? Should we use list(spec.readiness_headers.keys()) instead?
There was a problem hiding this comment.
Good catch! Fixed. Thanks!
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Closes #3549 by adding headers configuration in readiness probe.
Tested (run the relevant ones):
bash format.shllm/vllm/service-with-auth.yaml$ sky serve up llm/vllm/service-with-auth.yaml --gpus L4 Service from YAML spec: llm/vllm/service-with-auth.yaml Service Spec: Readiness probe method: GET /v1/models with headers {"Authorization": "Bearer sky-authkey-3d2105b9-a9ba-4f13"} Readiness initial delay seconds: 1200 Replica autoscaling policy: Fixed 1 replica Spot Policy: No spot policy $ curl $(sky serve status --endpoint sky-service-4233)/v1/models -H 'Authorization: Bearer sky-authkey-3d2105b9-a9ba-4f13' {"object":"list","data":[{"id":"meta-llama/Llama-2-7b-chat-hf","object":"model","created":1715746959,"owned_by":"vllm","root":"meta-llama/Llama-2-7b-chat-hf","parent":null,"permission":[{"id":"modelperm-5cf910e014484663a648f66e38b08174","object":"model_permission","created":1715746959,"allow_create_engine":false,"allow_sampling":true,"allow_logprobs":true,"allow_search_indices":false,"allow_view":true,"allow_fine_tuning":false,"organization":"*","group":null,"is_blocking":false}]}]}pytest tests/test_smoke.pypytest tests/test_smoke.py::test_fill_in_the_nameconda deactivate; bash -i tests/backward_compatibility_tests.sh