[ML] fail inference processor more consistently on certain error types #81475
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
Collaborator
|
Pinging @elastic/ml-core (Team:ML) |
davidkyle
reviewed
Dec 8, 2021
| if (unwrapped instanceof ElasticsearchStatusException) { | ||
| ElasticsearchStatusException ex = (ElasticsearchStatusException) unwrapped; | ||
| if (ex.status().equals(RestStatus.TOO_MANY_REQUESTS)) { | ||
| if (unwrapped instanceof ElasticsearchException ex) { |
| ElasticsearchStatusException ex = (ElasticsearchStatusException) unwrapped; | ||
| if (ex.status().equals(RestStatus.TOO_MANY_REQUESTS)) { | ||
| if (unwrapped instanceof ElasticsearchException ex) { | ||
| if (FAILURE_STATUSES.contains(ex.status())) { |
Member
There was a problem hiding this comment.
Looking at the changes in FillMaskProcessor it makes more sense for individual processors to decide which errors are exceptions and which are WarningInferenceResults. I think this logic and be removed as the processor and deployment manager know best what is an error
Member
Author
There was a problem hiding this comment.
@davidkyle this assumes that we catch and return a warning down at the task level. I can do that but its a larger refactor.
…ference-failure-solidification
benwtrent
added
the
auto-merge-without-approval
Collaborator
💔 Backport failed
You can use sqren/backport to manually backport by running |
benwtrent
added a commit
to benwtrent/elasticsearch
that referenced
this pull request
Dec 8, 2021
elastic#81475) This updates the following scenarios and causes NER/native inference to fail and not write a warning: - missing vocabulary values - missing model/deployment - native process failed - native process stopping - request timed out - misconfigured inference task update type
elasticsearchmachine
pushed a commit
that referenced
this pull request
Dec 8, 2021
…r types (#81475) (#81546) * [ML] fail inference processor more consistently on certain error types (#81475) This updates the following scenarios and causes NER/native inference to fail and not write a warning: - missing vocabulary values - missing model/deployment - native process failed - native process stopping - request timed out - misconfigured inference task update type * fixing for backport * fixing backport * fixing backport
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
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.
This updates the following scenarios and causes NER/native inference to fail and not write a warning: