[main] Undeploy code change: add edge case for models that are marked as not found in cache #3520 #3523
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
brianf-aws
requested review from
b4sjoo,
dhrubo-os,
mingshl,
jngz-es,
model-collapse,
rbhavna,
ylwu-amzn,
zane-neo,
Zhangxunmt,
austintlee,
HenryL27 and
xinyual
as code owners
brianf-aws
had a problem deploying
to
ml-commons-cicd-env-require-approval
GitHub Actions
Failure
brianf-aws
had a problem deploying
to
ml-commons-cicd-env-require-approval
GitHub Actions
Failure
|
Can we add 2.19 backport? |
Zhangxunmt
approved these changes
Feb 11, 2025
pyek-bot
approved these changes
Feb 11, 2025
dhrubo-os
reviewed
Feb 11, 2025
| @@ -198,7 +200,19 @@ private void undeployModels( | |||
| * Having this change enables a check that this edge case occurs along with having access to the model id | |||
| * allowing us to update the stale model index correctly to `UNDEPLOYED` since no nodes service the model. | |||
| */ | |||
| if (response.getNodes().isEmpty()) { | |||
| boolean modelNotFoundInNodesCache = response.getNodes().stream().allMatch(nodeResponse -> { | |||
| Map<String, String> status = nodeResponse.getModelUndeployStatus(); | |||
There was a problem hiding this comment.
can nodeResponse be null?
There was a problem hiding this comment.
From my experience no, if the response is empty is a empty list but not null
brianf-aws
had a problem deploying
to
ml-commons-cicd-env-require-approval
GitHub Actions
Failure
There is a code change that requires to check the response of the model undeploy response object to check that the model has been marked as not found on all nodes. Signed-off-by: Brian Flores <[email protected]>
brianf-aws
force-pushed
the
undeploy-patch-fix
branch
from
a4abd20 to
0acafc2
Compare
|
Rebased with main branch |
brianf-aws
had a problem deploying
to
ml-commons-cicd-env-require-approval
GitHub Actions
Error
brianf-aws
temporarily deployed
to
ml-commons-cicd-env-require-approval
GitHub Actions
Inactive
brianf-aws
had a problem deploying
to
ml-commons-cicd-env-require-approval
GitHub Actions
Failure
brianf-aws
temporarily deployed
to
ml-commons-cicd-env-require-approval
GitHub Actions
Inactive
jngz-es
approved these changes
Feb 14, 2025
dhrubo-os
approved these changes
Feb 14, 2025
opensearch-trigger-bot bot
pushed a commit
that referenced
this pull request
Feb 14, 2025
There is a code change that requires to check the response of the model undeploy response object to check that the model has been marked as not found on all nodes. Signed-off-by: Brian Flores <[email protected]> (cherry picked from commit c5ceb48)
opensearch-trigger-bot bot
pushed a commit
that referenced
this pull request
Feb 14, 2025
There is a code change that requires to check the response of the model undeploy response object to check that the model has been marked as not found on all nodes. Signed-off-by: Brian Flores <[email protected]> (cherry picked from commit c5ceb48)
dhrubo-os
pushed a commit
that referenced
this pull request
Feb 18, 2025
… (#3552) There is a code change that requires to check the response of the model undeploy response object to check that the model has been marked as not found on all nodes. Signed-off-by: Brian Flores <[email protected]> (cherry picked from commit c5ceb48) Co-authored-by: Brian Flores <[email protected]>
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.
There is a code change that requires to check the response of the model undeploy response object to check that the model has been marked as not found on all nodes.
Previously when we received a
{}response it was assumed that no nodes are servicing the model but it turns out there was a code change that didn't update the model index but reported back that it couldn't find the modelReproduction
A. Normal case
B. Edge case (Turn off sync up job)
{}Related Issues
Resolves #[Issue number to be closed when this PR is merged]
Check List
--signoff.By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.