[ML] Wait for allocation on scale up #114719
Merged
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
davidkyle
added
>enhancement
:ml
Collaborator
|
Pinging @elastic/ml-core (Team:ML) |
Collaborator
|
Hi @davidkyle, I've created a changelog YAML for you. |
jan-elastic
reviewed
Oct 14, 2024
...RestTest/java/org/elasticsearch/xpack/ml/integration/AdaptiveAllocationsScaleFromZeroIT.java
Outdated
Show resolved
Hide resolved
jan-elastic
reviewed
Oct 14, 2024
...RestTest/java/org/elasticsearch/xpack/ml/integration/AdaptiveAllocationsScaleFromZeroIT.java
Outdated
Show resolved
Hide resolved
jan-elastic
reviewed
Oct 14, 2024
...s/src/javaRestTest/java/org/elasticsearch/xpack/ml/integration/PyTorchModelRestTestCase.java
Show resolved
Hide resolved
jan-elastic
reviewed
Oct 14, 2024
...in/ml/src/main/java/org/elasticsearch/xpack/ml/action/TransportInternalInferModelAction.java
Outdated
Show resolved
Hide resolved
jan-elastic
reviewed
Oct 14, 2024
...plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/InferenceWaitForAllocation.java
Outdated
Show resolved
Hide resolved
jan-elastic
reviewed
Oct 14, 2024
...plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/InferenceWaitForAllocation.java
Outdated
Show resolved
Hide resolved
jan-elastic
reviewed
Oct 14, 2024
...plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/InferenceWaitForAllocation.java
Outdated
Show resolved
Hide resolved
jan-elastic
reviewed
Oct 14, 2024
...c/main/java/org/elasticsearch/xpack/core/ml/inference/assignment/TrainedModelAssignment.java
Outdated
Show resolved
Hide resolved
jan-elastic
reviewed
Oct 14, 2024
...plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/InferenceWaitForAllocation.java
Outdated
Show resolved
Hide resolved
jan-elastic
approved these changes
Oct 14, 2024
Contributor
jan-elastic
left a comment
jan-elastic
left a comment
There was a problem hiding this comment.
Generally LGTM. Some some minor comments.
Please have another look at the logging. It looks like there's some leftover debug logging (logged at info).
davidkyle
force-pushed
the
adaptive-allocations-from-0
branch
from
5f9dddc to
a959890
Compare
jan-elastic
reviewed
Oct 15, 2024
| CHUNKING_SETTINGS_ENABLED("es.inference_chunking_settings_feature_flag_enabled=true", Version.fromString("8.16.0"), null), | ||
| INFERENCE_DEFAULT_ELSER("es.inference_default_elser_feature_flag_enabled=true", Version.fromString("8.16.0"), null); | ||
| INFERENCE_DEFAULT_ELSER("es.inference_default_elser_feature_flag_enabled=true", Version.fromString("8.16.0"), null), | ||
| ML_SCALE_FROM_ZERO("es.ml_scale_from_zero_feature_flag_enabled=true", Version.fromString("8.16.0"), null); |
Contributor
There was a problem hiding this comment.
I'd prefix with INFERENCE instead of ML.
Very subtle naming btw: we used to have scale_to_zero_feature_flag, and now scale_from_zero_feature_flag :)
davidkyle
removed
the
auto-backport
georgewallace
pushed a commit
to georgewallace/elasticsearch
that referenced
this pull request
Oct 25, 2024
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.
Changes TransportInternalInferModelAction to queue inference requests when an model deployment is scaling up from 0 allocations. Incoming inference requests are stored in a queue then send to the model once it is deployed on a node.
Adds a setting to control the adaptive allocations scale to zero period for the purpose of running tests.