[SkyServe] Fix replica log not found when replica cluster not found #2924
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
MaoZiming
reviewed
Jan 1, 2024
| @@ -580,6 +575,11 @@ def _get_replica_status() -> serve_state.ReplicaStatus: | |||
| f'of replica {replica_id}...{colorama.Style.RESET_ALL}') | |||
|
|
|||
| backend = backends.CloudVmRayBackend() | |||
| handle = global_user_state.get_handle_from_cluster_name( | |||
There was a problem hiding this comment.
Move handle = global_user_state.get_handle_from_cluster_name(...) before # Notify user here to make sure user won't think the log is finished.?
There was a problem hiding this comment.
That makes sense! 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Outdated suggestions cannot be applied.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.
Previous SkyServe has a bug: when the replica cluster is not created yet,
sky serve logscannot correctly show the replica launch log. This PR fixes the problem. This bug is common when we retry on scarce resources, where within the inner waiting time, there is no cluster in the SkyServe controller's database.Tested (run the relevant ones):
bash format.shsky serve upa cluster w/ OnDemand A100 and runsky serve logs <service-name> 1pytest tests/test_smoke.pypytest tests/test_smoke.py::test_fill_in_the_namebash tests/backward_comaptibility_tests.sh