[ML] Check total_definition_length is consistent on start deployment #80553
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
|
Pinging @elastic/ml-core (Team:ML) |
benwtrent
approved these changes
Nov 9, 2021
|
I did some further testing of the native process streaming a model that differed in length to the reported size. In all cases the process detected the irregularity and exited after a logging a message. |
davidkyle
added a commit
to davidkyle/elasticsearch
that referenced
this pull request
Nov 10, 2021
…lastic#80553) Before a model deployment is started check the the individual model part documents have a consistent value for total_definition_length. Any inconsistency is an unrecoverable error.
💚 Backport successful
|
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Outdated suggestions cannot be applied.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.
Before a model deployment is started check the the individual model part documents have a consistent value for
total_definition_length.This is an unrecoverable error as it shows the model definition sizes are not reliable, the only solution is to delete the model and recreate it and the error message should express this to the user.