[Serve] Propagate replica constructor error to deployment status message and print num retries left #48531
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
Signed-off-by: akyang-anyscale <alexyang@anyscale.com>
Signed-off-by: akyang-anyscale <alexyang@anyscale.com>
Signed-off-by: akyang-anyscale <alexyang@anyscale.com>
Signed-off-by: akyang-anyscale <alexyang@anyscale.com>
zcin
reviewed
Nov 20, 2024
| @@ -1942,6 +1944,22 @@ def check_curr_status(self) -> Tuple[bool, bool]: | |||
| ) | |||
| return False, any_replicas_recovering | |||
|
|
|||
| if failed_to_start_count > self._prev_replica_constructor_retry_counter: | |||
There was a problem hiding this comment.
Why is _prev_replica_constructor_retry_counter necessary? Can we just always call update_message and change it to a no-op if the message is the same?
There was a problem hiding this comment.
yeah you're right
Signed-off-by: akyang-anyscale <alexyang@anyscale.com>
Signed-off-by: akyang-anyscale <alexyang@anyscale.com>
zcin
approved these changes
Nov 20, 2024
Comment on lines
1958
to
1959
| if message != self._curr_status_info.message: | ||
| self._curr_status_info = self._curr_status_info.update_message(message) |
There was a problem hiding this comment.
might be easier to move the check into update_message method
Signed-off-by: akyang-anyscale <alexyang@anyscale.com>
Signed-off-by: akyang-anyscale <alexyang@anyscale.com>
Signed-off-by: akyang-anyscale <alexyang@anyscale.com>
MortalHappiness
pushed a commit
to MortalHappiness/ray
that referenced
this pull request
Nov 22, 2024
…age and print num retries left (ray-project#48531) ## Why are these changes needed? This change will surface the replica constructor error as soon as the replica constructor fails for whatever reason. The exception will be populated in the deployment status so that it's viewable from the ray dashboard. Additionally, the number of replica constructor retries left will also be updated in the error message. This will help users more quickly debug a deployment that is failing to start. ## Related issue number <!-- For example: "Closes ray-project#1234" --> Closes ray-project#35604 Signed-off-by: akyang-anyscale <alexyang@anyscale.com>
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.
Why are these changes needed?
This change will surface the replica constructor error as soon as the replica constructor fails for whatever reason. The exception will be populated in the deployment status so that it's viewable from the ray dashboard. Additionally, the number of replica constructor retries left will also be updated in the error message. This will help users more quickly debug a deployment that is failing to start.
Related issue number
Closes #35604
Checks
git commit -s) in this PR.scripts/format.shto lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/under thecorresponding
.rstfile.