Set allocatable replicas for unhealthy cluster to zero when scale up.

[LivingCcj]

What type of PR is this?
/kind bug

What this PR does / why we need it:

Which issue(s) this PR fixes:

Fixes #6861

Does this PR introduce a user-facing change?:

karmada-scheduler ignore unhealthy member cluster when scale up workload.

[gemini-code-assist]

Summary of Changes

Hello @LivingCcj, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a bug in the Karmada scheduler by preventing it from scaling up workloads on unhealthy member clusters. It introduces a new helper function to determine cluster readiness and integrates this check into the dynamic scale-up algorithm. Consequently, any cluster not in a ready state will have its allocatable replicas set to zero, ensuring that workloads are only distributed to healthy and available clusters.

Highlights

• New Cluster Health Helper: Introduced a new helper function, IsClusterReady(), within pkg/apis/cluster/v1alpha1/cluster_helper.go to provide a standardized way to check if a cluster is in a ready state based on its status conditions.
• Enhanced Dynamic Scale-Up Logic: Modified the dynamicScaleUp function in pkg/scheduler/core/division_algorithm.go to incorporate the new IsClusterReady() check. This ensures that during workload scale-up, the scheduler evaluates the health of each member cluster.
• Prevent Allocation to Unhealthy Clusters: Implemented logic to set the AllocatableReplicas to zero for any member cluster identified as not ready during the scale-up process. This prevents the Karmada scheduler from attempting to allocate workloads to unhealthy clusters, improving system stability and reliability.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[Copilot]

Pull Request Overview

This PR addresses a bug where the scheduler would attempt to scale up workloads to unhealthy member clusters. The fix ensures that unhealthy clusters are skipped during scale-up operations by setting their allocatable replicas to zero.

• Adds IsClusterReady() helper method to check cluster health status
• Updates dynamicScaleUp() to skip unhealthy clusters when scaling up workloads
• Logs warnings when unhealthy clusters are encountered during scale-up

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
pkg/apis/cluster/v1alpha1/cluster_helper.go	Adds IsClusterReady() method to check if cluster status condition is ready
pkg/scheduler/core/division_algorithm.go	Implements check to set allocatable replicas to zero for unhealthy clusters during scale-up

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

Modifying the cluster variable here only affects the loop-local copy and doesn't update the original clusters slice. This means cluster.AllocatableReplicas = 0 has no effect on the value used in line 133. You should modify clusters[i].AllocatableReplicas = 0 instead to ensure the change persists.

Suggested change

	cluster.AllocatableReplicas = 0
	}
	clusterAvailableReplicas[i] = workv1alpha2.TargetCluster{
	Name: cluster.Name,
	Replicas: cluster.AllocatableReplicas,
	clusters[i].AllocatableReplicas = 0
	}
	clusterAvailableReplicas[i] = workv1alpha2.TargetCluster{
	Name: cluster.Name,
	Replicas: clusters[i].AllocatableReplicas,

[gemini-code-assist]

Code Review

This pull request correctly addresses the issue of scheduling workloads to unhealthy clusters during scale-up operations by setting their allocatable replicas to zero. The addition of the IsClusterReady helper function is a good practice for code clarity and reusability. I have one suggestion in pkg/scheduler/core/division_algorithm.go to improve code readability and prevent potential future bugs related to modifying loop variables.

[codecov-commenter]

⚠️ Please install the to ensure uploads and comments are reliably processed by Codecov.

Codecov Report

❌ Patch coverage is 60.00000% with 2 lines in your changes missing coverage. Please review.
✅ Project coverage is 46.40%. Comparing base (8dbca68) to head (060724a).
⚠️ Report is 2 commits behind head on master.

Files with missing lines	Patch %	Lines
pkg/apis/cluster/v1alpha1/cluster_helper.go	0.00%	2 Missing ⚠️
❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

@@           Coverage Diff           @@
##           master    #6863   +/-   ##
=======================================
  Coverage   46.39%   46.40%           
=======================================
  Files         698      698           
  Lines       47763    47768    +5     
=======================================
+ Hits        22160    22166    +6     
  Misses      23934    23934           
+ Partials     1669     1668    -1     

Flag	Coverage Δ
unittests	46.40% <60.00%> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[RainbowMango]

@LivingCcj Can you help look into the failing tests?

[LivingCcj]

@LivingCcj Can you help look into the failing tests?

Ok

[LivingCcj]

/retest

[karmada-bot]

@LivingCcj: Cannot trigger testing until a trusted user reviews the PR and leaves an /ok-to-test message.

In response to this:

/retest

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository.

[LivingCcj]

/retest

[karmada-bot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
Once this PR has been reviewed and has the lgtm label, please assign rainbowmango, xishanyongye-chang for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Needs approval from an approver in each of these files:

• pkg/apis/OWNERS
• pkg/scheduler/OWNERS
• test/OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment