From 0190222c7b32fbe6ec84c5e62ec7cb10eaf58044 Mon Sep 17 00:00:00 2001
From: ravisantoshgudimetla <ravisantoshgudimetla@gmail.com>
Date: Tue, 14 Jan 2025 15:17:08 -0800
Subject: [PATCH] PDB based taint tolerance

---
 keps/prod-readiness/sig-apps/4987.yaml        |   3 +
 .../4987-taint-tolerance-pdb/README.md        | 824 ++++++++++++++++++
 .../4987-taint-tolerance-pdb/kep.yaml         |  36 +
 3 files changed, 863 insertions(+)
 create mode 100644 keps/prod-readiness/sig-apps/4987.yaml
 create mode 100644 keps/sig-apps/4987-taint-tolerance-pdb/README.md
 create mode 100644 keps/sig-apps/4987-taint-tolerance-pdb/kep.yaml

diff --git a/keps/prod-readiness/sig-apps/4987.yaml b/keps/prod-readiness/sig-apps/4987.yaml
new file mode 100644
index 00000000000..799de1f4b29
--- /dev/null
+++ b/keps/prod-readiness/sig-apps/4987.yaml
@@ -0,0 +1,3 @@
+kep-number: 4987
+alpha:
+  approver: "@soltysh"
diff --git a/keps/sig-apps/4987-taint-tolerance-pdb/README.md b/keps/sig-apps/4987-taint-tolerance-pdb/README.md
new file mode 100644
index 00000000000..4fa62c37898
--- /dev/null
+++ b/keps/sig-apps/4987-taint-tolerance-pdb/README.md
@@ -0,0 +1,824 @@
+
+# KEP-4987: PDBBasedTaintTolerance
+
+<!--
+This is the title of your KEP. Keep it short, simple, and descriptive. A good
+title can help communicate what the KEP is and should be considered as part of
+any review.
+-->
+
+<!--
+A table of contents is helpful for quickly jumping to sections of a KEP and for
+highlighting any additional information provided beyond the standard KEP
+template.
+
+Ensure the TOC is wrapped with
+  <code>&lt;!-- toc --&rt;&lt;!-- /toc --&rt;</code>
+tags, and then generate with `hack/update-toc.sh`.
+-->
+
+<!-- toc -->
+- [Release Signoff Checklist](#release-signoff-checklist)
+- [Summary](#summary)
+- [Motivation](#motivation)
+  - [Goals](#goals)
+  - [Non-Goals](#non-goals)
+- [Proposal](#proposal)
+  - [User Stories (Optional)](#user-stories-optional)
+    - [Story 1](#story-1)
+    - [Story 2](#story-2)
+  - [Notes/Constraints/Caveats (Optional)](#notesconstraintscaveats-optional)
+  - [Risks and Mitigations](#risks-and-mitigations)
+- [Design Details](#design-details)
+  - [Test Plan](#test-plan)
+      - [Prerequisite testing updates](#prerequisite-testing-updates)
+      - [Unit tests](#unit-tests)
+      - [Integration tests](#integration-tests)
+      - [e2e tests](#e2e-tests)
+  - [Graduation Criteria](#graduation-criteria)
+    - [Alpha](#alpha)
+    - [Beta](#beta)
+    - [GA](#ga)
+  - [Upgrade / Downgrade Strategy](#upgrade--downgrade-strategy)
+  - [Version Skew Strategy](#version-skew-strategy)
+- [Production Readiness Review Questionnaire](#production-readiness-review-questionnaire)
+  - [Feature Enablement and Rollback](#feature-enablement-and-rollback)
+  - [Rollout, Upgrade and Rollback Planning](#rollout-upgrade-and-rollback-planning)
+  - [Monitoring Requirements](#monitoring-requirements)
+  - [Dependencies](#dependencies)
+  - [Scalability](#scalability)
+  - [Troubleshooting](#troubleshooting)
+- [Implementation History](#implementation-history)
+- [Drawbacks](#drawbacks)
+- [Alternatives](#alternatives)
+- [Infrastructure Needed (Optional)](#infrastructure-needed-optional)
+<!-- /toc -->
+
+## Release Signoff Checklist
+
+<!--
+**ACTION REQUIRED:** In order to merge code into a release, there must be an
+issue in [kubernetes/enhancements] referencing this KEP and targeting a release
+milestone **before the [Enhancement Freeze](https://git.k8s.io/sig-release/releases)
+of the targeted release**.
+
+For enhancements that make changes to code or processes/procedures in core
+Kubernetes—i.e., [kubernetes/kubernetes], we require the following Release
+Signoff checklist to be completed.
+
+Check these off as they are completed for the Release Team to track. These
+checklist items _must_ be updated for the enhancement to be released.
+-->
+
+Items marked with (R) are required *prior to targeting to a milestone / release*.
+
+- [] (R) Enhancement issue in release milestone, which links to KEP dir in [kubernetes/enhancements] (not the initial KEP PR)
+- [ ] (R) KEP approvers have approved the KEP status as `implementable`
+- [ ] (R) Design details are appropriately documented
+- [ ] (R) Test plan is in place, giving consideration to SIG Architecture and SIG Testing input (including test refactors)
+  - [ ] e2e Tests for all Beta API Operations (endpoints)
+  - [ ] (R) Ensure GA e2e tests meet requirements for [Conformance Tests](https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/conformance-tests.md) 
+  - [ ] (R) Minimum Two Week Window for GA e2e tests to prove flake free
+- [ ] (R) Graduation criteria is in place
+  - [ ] (R) [all GA Endpoints](https://github.com/kubernetes/community/pull/1806) must be hit by [Conformance Tests](https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/conformance-tests.md) 
+- [ ] (R) Production readiness review completed
+- [ ] (R) Production readiness review approved
+- [ ] "Implementation History" section is up-to-date for milestone
+- [ ] User-facing documentation has been created in [kubernetes/website], for publication to [kubernetes.io]
+- [ ] Supporting documentation—e.g., additional design documents, links to mailing list discussions/SIG meetings, relevant PRs/issues, release notes
+
+<!--
+**Note:** This checklist is iterative and should be reviewed and updated every time this enhancement is being considered for a milestone.
+-->
+
+[kubernetes.io]: https://kubernetes.io/
+[kubernetes/enhancements]: https://git.k8s.io/enhancements
+[kubernetes/kubernetes]: https://git.k8s.io/kubernetes
+[kubernetes/website]: https://git.k8s.io/website
+
+## Summary
+Currently, tolerations allow users to specify how long a pod can tolerate a taint. This proposal aims to introduce an additional dimension of toleration based on the Pod Disruption Budget.
+
+<!--
+This section is incredibly important for producing high-quality, user-focused
+documentation such as release notes or a development roadmap. It should be
+possible to collect this information before implementation begins, in order to
+avoid requiring implementors to split their attention between writing release
+notes and implementing the feature itself. KEP editors and SIG Docs
+should help to ensure that the tone and content of the `Summary` section is
+useful for a wide audience.
+
+A good summary is probably at least a paragraph in length.
+
+Both in this section and below, follow the guidelines of the [documentation
+style guide]. In particular, wrap lines to a reasonable length, to make it
+easier for reviewers to cite specific portions, and to minimize diff churn on
+updates.
+
+[documentation style guide]: https://github.com/kubernetes/community/blob/master/contributors/guide/style-guide.md
+-->
+
+## Motivation
+The current approach of using tolerationSeconds in pod specifications has two key limitations:
+- Most application developers and cluster operators lack the detailed knowledge to set tolerationSeconds accurately, leading to guesswork and potential issues. Some clusters have had to implement validating webhooks to prevent indefinite tolerations.
+- Taint-based "evictions" ultimately result in [pod deletion](https://github.com/kubernetes/kubernetes/blob/1b3d7d06c59c44de2775975a599130a2f89539fb/pkg/controller/tainteviction/taint_eviction.go#L146), but some workloads require stronger disruption handling guarantees. Cluster admins and developers have had to write custom webhooks to intercept these deletion requests.
+<!--
+This section is for explicitly listing the motivation, goals, and non-goals of
+this KEP.  Describe why the change is important and the benefits to users. The
+motivation section can optionally provide links to [experience reports] to
+demonstrate the interest in a KEP within the wider Kubernetes community.
+
+[experience reports]: https://github.com/golang/go/wiki/ExperienceReports
+-->
+
+### Goals
+- Allow users to express the intention that PDB should be honored instead of directly deleting the pod once the tolerationSeconds are up. This means that when a pod's toleration period is not specified and instead the new api is chosen, the system will first check the Pod Disruption Budget (PDB) constraints before deciding to evict the pod. If the PDB allows for the disruption, the pod can be safely evicted; otherwise, the pod will remain running to ensure application availability and stability.
+- Reduce the need for custom webhooks and other complex solutions by offering built-in support for PDB-based tolerations, simplifying cluster management and reducing operational overhead.
+- Enhance the ability to maintain high availability for critical workloads by ensuring that PDB constraints are respected during node maintenance, scaling activities, and other disruptive events.
+<!--
+List the specific goals of the KEP. What is it trying to achieve? How will we
+know that this has succeeded?
+-->
+
+### Non-Goals
+- Changes to Pod Disruption Budget APIs. This proposal does not aim to modify the existing Pod Disruption Budget (PDB) APIs or their functionality. Instead, it focuses on leveraging the current PDB mechanisms to enhance toleration strategies. The goal is to integrate PDB checks into the toleration process without altering how PDBs are defined, managed, or enforced. This ensures backward compatibility and avoids introducing additional complexity to the existing PDB framework.
+- While the proposal aims to improve the reliability and control of pod evictions, it does not specifically target performance optimization of the eviction process.
+<!--
+What is out of scope for this KEP? Listing non-goals helps to focus discussion
+and make progress.
+-->
+
+## Proposal
+Historically, the tolerations API specified [tolerationSeconds](https://github.com/kubernetes/kubernetes/blob/1b3d7d06c59c44de2775975a599130a2f89539fb/pkg/apis/core/types.go#L3242-#L3247), which defines the duration for which a pod can tolerate a taint before it is deleted.
+As part of this proposal, a new boolean field will be added to the tolerations API to indicate whether eviction API should be used of deletion.
+
+
+When this field is set, the NoExecute taint manager will use the eviction API instead of directly deleting the pod. The outcome of this change is that when a pod is running something really important and the taint, while important enough to move workloads, is not important enough to disrupt those workloads. This will be useful in cases where we want stronger guarantees around the availability of workloads.
+
+
+<!--
+This is where we get down to the specifics of what the proposal actually is.
+This should have enough detail that reviewers can understand exactly what
+you're proposing, but should not include things like API designs or
+implementation. What is the desired outcome and how do we measure success?.
+The "Design Details" section below is for the real
+nitty-gritty.
+-->
+
+### User Stories (Optional)
+
+#### Story 1
+As a cluster operator, I want to ensure that critical workloads are not disrupted during node maintenance. For example, in a deployment of Cassandra, which requires high availability and consistency, I can use the PDB-based toleration to configure my pods to respect PDB constraints. Previously, I had to disable the taint manager altogether because it used the delete API instead of the eviction API.
+
+#### Story 2
+As an application developer, I want to avoid writing custom webhooks to handle pod evictions. For example, in a deployment of Elasticsearch, which requires careful handling of node disruptions to maintain data availability and cluster health, I can use PDB-based toleration. This allows Kubernetes to manage pod evictions based on PDB constraints, simplifying my deployment process and reducing operational overhead.
+
+
+### Notes/Constraints/Caveats (Optional)
+
+<!--
+What are the caveats to the proposal?
+What are some important details that didn't come across above?
+Go in to as much detail as necessary here.
+This might be a good place to talk about core concepts and how they relate.
+-->
+
+### Risks and Mitigations
+We are proposing a new field called `UseEvictionAPI` whose default value is false. In this mode, taint manager will behave exactly like current behavior. It's possible we introduce a bug in the implementation. The bug can cause:
+- Pod not being deleted because eviction is triggered and there is a PDB associated, breaking the user expectation
+- Pod to be deleted even `UseEvictionAPI` is set to true
+
+The mitigation currently is that this field will be disabled by default in alpha phase behind a feature gate for people to try out and give feedback. In beta phase when it is enabled by default, people will only see issues or bugs when `UseEvictionAPI` is set to true. Since people would have tried this feature in beta, we would have had time to fix any issues.
+<!--
+What are the risks of this proposal, and how do we mitigate? Think broadly.
+For example, consider both security and how this will impact the larger
+Kubernetes ecosystem.
+
+How will security be reviewed, and by whom?
+
+How will UX be reviewed, and by whom?
+
+Consider including folks who also work outside the SIG or subproject.
+-->
+
+## Design Details
+```go
+// Toleration represents the toleration object that can be attached to a pod.
+// The pod this Toleration is attached to tolerates any taint that matches
+// the triple <key,value,effect> using the matching operator <operator>.
+type Toleration struct {
+	// Key is the taint key that the toleration applies to. Empty means match all taint keys.
+	// If the key is empty, operator must be Exists; this combination means to match all values and all keys.
+	// +optional
+	Key string
+	// Operator represents a key's relationship to the value.
+	// Valid operators are Exists and Equal. Defaults to Equal.
+	// Exists is equivalent to wildcard for value, so that a pod can
+	// tolerate all taints of a particular category.
+	// +optional
+	Operator TolerationOperator
+	// Value is the taint value the toleration matches to.
+	// If the operator is Exists, the value should be empty, otherwise just a regular string.
+	// +optional
+	Value string
+	// Effect indicates the taint effect to match. Empty means match all taint effects.
+	// When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute.
+	// +optional
+	Effect TaintEffect
+	// TolerationSeconds represents the period of time the toleration (which must be
+	// of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default,
+	// it is not set, which means tolerate the taint forever (do not evict). Zero and
+	// negative values will be treated as 0 (evict immediately) by the system.
+	// +optional
+	TolerationSeconds *int64
+    // UseEvictionAPI indicates that the taint manager should use the eviction API instead of directly deleting the pod.
+    // This field cannot be used in conjunction with tolerationSeconds, as the pod will continue to run until the matching
+    // Pod Disruption Budget (PDB) allows for its disruption. This ensures that critical workloads are not disrupted
+    // unnecessarily and that PDB constraints are respected.
+    //
+    // Example scenarios where UseEvictionAPI would be beneficial:
+    // 1. During node maintenance, where you want to ensure that critical pods are not evicted unless the PDB allows it.
+    // 2. When dealing with taints that are important but not critical enough to disrupt essential services immediately.
+    //
+    // +optional
+    UseEvictionAPI bool
+}
+```
+
+<!--
+This section should contain enough information that the specifics of your
+change are understandable. This may include API specs (though not always
+required) or even code snippets. If there's any ambiguity about HOW your
+proposal will be implemented, this is the place to discuss them.
+-->
+
+### Test Plan
+Unit, integration and E2E tests cover the existing taint-manager mechanics. Additionally, unit and integration tests will be added to cover the api validation, behavioral change of taint-manager with feature gate enabled and disabled.
+<!--
+**Note:** *Not required until targeted at a release.*
+The goal is to ensure that we don't accept enhancements with inadequate testing.
+
+All code is expected to have adequate tests (eventually with coverage
+expectations). Please adhere to the [Kubernetes testing guidelines][testing-guidelines]
+when drafting this test plan.
+
+[testing-guidelines]: https://git.k8s.io/community/contributors/devel/sig-testing/testing.md
+-->
+
+[x] I/we understand the owners of the involved components may require updates to
+existing tests to make this code solid enough prior to committing the changes necessary
+to implement this enhancement.
+
+##### Prerequisite testing updates
+
+<!--
+Based on reviewers feedback describe what additional tests need to be added prior
+implementing this enhancement to ensure the enhancements have also solid foundations.
+-->
+
+##### Unit tests
+
+<!--
+In principle every added code should have complete unit test coverage, so providing
+the exact set of tests will not bring additional value.
+However, if complete unit test coverage is not possible, explain the reason of it
+together with explanation why this is acceptable.
+-->
+
+<!--
+Additionally, for Alpha try to enumerate the core package you will be touching
+to implement this enhancement and provide the current unit coverage for those
+in the form of:
+- <package>: <date> - <current test coverage>
+The data can be easily read from:
+https://testgrid.k8s.io/sig-testing-canaries#ci-kubernetes-coverage-unit
+
+This can inform certain test coverage improvements that we want to do before
+extending the production code to implement this enhancement.
+-->
+
+- `<package>`: `<date>` - `<test coverage>`
+
+##### Integration tests
+
+<!--
+Integration tests are contained in k8s.io/kubernetes/test/integration.
+Integration tests allow control of the configuration parameters used to start the binaries under test.
+This is different from e2e tests which do not allow configuration of parameters.
+Doing this allows testing non-default options and multiple different and potentially conflicting command line options.
+-->
+
+<!--
+This question should be filled when targeting a release.
+For Alpha, describe what tests will be added to ensure proper quality of the enhancement.
+
+For Beta and GA, add links to added tests together with links to k8s-triage for those tests:
+https://storage.googleapis.com/k8s-triage/index.html
+-->
+
+- <test>: <link to test coverage>
+
+##### e2e tests
+
+<!--
+This question should be filled when targeting a release.
+For Alpha, describe what tests will be added to ensure proper quality of the enhancement.
+
+For Beta and GA, add links to added tests together with links to k8s-triage for those tests:
+https://storage.googleapis.com/k8s-triage/index.html
+
+We expect no non-infra related flakes in the last month as a GA graduation criteria.
+-->
+
+- <test>: <link to test coverage>
+
+### Graduation Criteria
+This will be added as a alpha field enhancement to tolerations API with a backward compatible default and we'd make sure that tolerationSeconds and this new field are mutually exclusive. After sufficient exposure this field would be promoted to beta, and then to GA in successive releases. The feature gate for this field will be `PDBBasedTaintTolerance`.
+
+#### Alpha
+- Complete feature behind a featuregate
+- Have proper unit and integration tests
+
+#### Beta
+- Gather feedback from developers and end users
+- Additional tests are in Testgrid and linked in KEP
+
+#### GA
+Gather examples from users who are benefitting from this feature
+
+<!--
+**Note:** *Not required until targeted at a release.*
+
+Define graduation milestones.
+
+These may be defined in terms of API maturity, [feature gate] graduations, or as
+something else. The KEP should keep this high-level with a focus on what
+signals will be looked at to determine graduation.
+
+Consider the following in developing the graduation criteria for this enhancement:
+- [Maturity levels (`alpha`, `beta`, `stable`)][maturity-levels]
+- [Feature gate][feature gate] lifecycle
+- [Deprecation policy][deprecation-policy]
+
+Clearly define what graduation means by either linking to the [API doc
+definition](https://kubernetes.io/docs/concepts/overview/kubernetes-api/#api-versioning)
+or by redefining what graduation means.
+
+In general we try to use the same stages (alpha, beta, GA), regardless of how the
+functionality is accessed.
+
+[feature gate]: https://git.k8s.io/community/contributors/devel/sig-architecture/feature-gates.md
+[maturity-levels]: https://git.k8s.io/community/contributors/devel/sig-architecture/api_changes.md#alpha-beta-and-stable-versions
+[deprecation-policy]: https://kubernetes.io/docs/reference/using-api/deprecation-policy/
+
+Below are some examples to consider, in addition to the aforementioned [maturity levels][maturity-levels].
+
+#### Alpha
+
+- Feature implemented behind a feature flag
+- Initial e2e tests completed and enabled
+
+#### Beta
+
+- Gather feedback from developers and surveys
+- Complete features A, B, C
+- Additional tests are in Testgrid and linked in KEP
+
+#### GA
+
+- N examples of real-world usage
+- N installs
+- More rigorous forms of testing—e.g., downgrade tests and scalability tests
+- Allowing time for feedback
+
+**Note:** Generally we also wait at least two releases between beta and
+GA/stable, because there's no opportunity for user feedback, or even bug reports,
+in back-to-back releases.
+
+**For non-optional features moving to GA, the graduation criteria must include
+[conformance tests].**
+
+[conformance tests]: https://git.k8s.io/community/contributors/devel/sig-architecture/conformance-tests.md
+
+#### Deprecation
+
+- Announce deprecation and support policy of the existing flag
+- Two versions passed since introducing the functionality that deprecates the flag (to address version skew)
+- Address feedback on usage/changed behavior, provided on GitHub issues
+- Deprecate the flag
+-->
+
+### Upgrade / Downgrade Strategy
+- Upgrades: When upgrading from a release without this feature to a release with this feature, we will set `UseEvictionAPI` to false. This would give users the same default behavior.
+- Downgrades: When downgrading from a release with this feature to a release without this feature, there are 2 cases
+    - If `UseEvictionAPI` is set to true, the taint manager wouldn't honor this field which is expected.
+    - If `UseEvictionAPI` is set to false, the user won't see any difference in behavior.
+
+We will ensure that the `UseEvictionAPI` is properly validated before persisting.
+<!--
+If applicable, how will the component be upgraded and downgraded? Make sure
+this is in the test plan.
+
+Consider the following in developing an upgrade/downgrade strategy for this
+enhancement:
+- What changes (in invocations, configurations, API use, etc.) is an existing
+  cluster required to make on upgrade, in order to maintain previous behavior?
+- What changes (in invocations, configurations, API use, etc.) is an existing
+  cluster required to make on upgrade, in order to make use of the enhancement?
+-->
+
+### Version Skew Strategy
+
+<!--
+If applicable, how will the component handle version skew with other
+components? What are the guarantees? Make sure this is in the test plan.
+
+Consider the following in developing a version skew strategy for this
+enhancement:
+- Does this enhancement involve coordinating behavior in the control plane and nodes?
+- How does an n-3 kubelet or kube-proxy without this feature available behave when this feature is used?
+- How does an n-1 kube-controller-manager or kube-scheduler without this feature available behave when this feature is used?
+- Will any other components on the node change? For example, changes to CSI,
+  CRI or CNI may require updating that component before the kubelet.
+-->
+If the feature gate is enabled, the taint controller will honor PDB instead of directly deleting the pods. If the feature gate is not enabled, the taint controller will run as usual. This feature has no node runtime or network implications.
+
+## Production Readiness Review Questionnaire
+
+<!--
+
+Production readiness reviews are intended to ensure that features merging into
+Kubernetes are observable, scalable and supportable; can be safely operated in
+production environments, and can be disabled or rolled back in the event they
+cause increased failures in production. See more in the PRR KEP at
+https://git.k8s.io/enhancements/keps/sig-architecture/1194-prod-readiness.
+
+The production readiness review questionnaire must be completed and approved
+for the KEP to move to `implementable` status and be included in the release.
+
+In some cases, the questions below should also have answers in `kep.yaml`. This
+is to enable automation to verify the presence of the review, and to reduce review
+burden and latency.
+
+The KEP must have a approver from the
+[`prod-readiness-approvers`](http://git.k8s.io/enhancements/OWNERS_ALIASES)
+team. Please reach out on the
+[#prod-readiness](https://kubernetes.slack.com/archives/CPNHUMN74) channel if
+you need any help or guidance.
+-->
+
+### Feature Enablement and Rollback
+
+<!--
+This section must be completed when targeting alpha to a release.
+-->
+
+###### How can this feature be enabled / disabled in a live cluster?
+<!--
+Pick one of these and delete the rest.
+
+Documentation is available on [feature gate lifecycle] and expectations, as
+well as the [existing list] of feature gates.
+
+[feature gate lifecycle]: https://git.k8s.io/community/contributors/devel/sig-architecture/feature-gates.md
+[existing list]: https://kubernetes.io/docs/reference/command-line-tools-reference/feature-gates/
+-->
+
+- [ ] Feature gate (also fill in values in `kep.yaml`)
+  - Feature gate name:  "PDBBasedTaintTolerance"
+  - Components depending on the feature gate:
+        - kube-controller-manager
+        - kube-apiserver
+
+###### Does enabling the feature change any default behavior?
+No, the user still needs to `UseEvictionAPI` in the tolerations spec
+<!--
+Any change of default behavior may be surprising to users or break existing
+automations, so be extremely careful here.
+-->
+
+###### Can the feature be disabled once it has been enabled (i.e. can we roll back the enablement)?
+Yes. Using the featuregate is the only way to enable/disable this feature
+<!--
+Describe the consequences on existing workloads (e.g., if this is a runtime
+feature, can it break the existing applications?).
+
+Feature gates are typically disabled by setting the flag to `false` and
+restarting the component. No other changes should be necessary to disable the
+feature.
+
+NOTE: Also set `disable-supported` to `true` or `false` in `kep.yaml`.
+-->
+
+###### What happens if we reenable the feature if it was previously rolled back?
+The taint manager starts honoring PDBs again
+###### Are there any tests for feature enablement/disablement?
+Yes, unit, integration tests for feature on, off
+<!--
+The e2e framework does not currently support enabling or disabling feature
+gates. However, unit tests in each component dealing with managing data, created
+with and without the feature, are necessary. At the very least, think about
+conversion tests if API types are being modified.
+
+Additionally, for features that are introducing a new API field, unit tests that
+are exercising the `switch` of feature gate itself (what happens if I disable a
+feature gate after having objects written with the new field) are also critical.
+You can take a look at one potential example of such test in:
+https://github.com/kubernetes/kubernetes/pull/97058/files#diff-7826f7adbc1996a05ab52e3f5f02429e94b68ce6bce0dc534d1be636154fded3R246-R282
+-->
+
+### Rollout, Upgrade and Rollback Planning
+
+<!--
+This section must be completed when targeting beta to a release.
+-->
+
+###### How can a rollout or rollback fail? Can it impact already running workloads?
+Already running workloads can be impacted if this feature is enabled. However the user needs to explicitly set the `useEvictionAPI` on the tolerations of the pod spec to use this feature.
+<!--
+Try to be as paranoid as possible - e.g., what if some components will restart
+mid-rollout?
+
+Be sure to consider highly-available clusters, where, for example,
+feature flags will be enabled on some API servers and not others during the
+rollout. Similarly, consider large clusters and how enablement/disablement
+will rollout across nodes.
+-->
+
+###### What specific metrics should inform a rollback?
+If the count of pods that are not getting is deleted increasing, we can start issuing a rollback. `kube_pod_deletion_timestamp` metric also tracks when the pod got deleted but it is experimental.
+<!--
+What signals should users be paying attention to when the feature is young
+that might indicate a serious problem?
+-->
+
+###### Were upgrade and rollback tested? Was the upgrade->downgrade->upgrade path tested?
+No
+<!--
+Describe manual testing that was done and the outcomes.
+Longer term, we may want to require automated upgrade/rollback tests, but we
+are missing a bunch of machinery and tooling and can't do that now.
+-->
+
+###### Is the rollout accompanied by any deprecations and/or removals of features, APIs, fields of API types, flags, etc.?
+None
+<!--
+Even if applying deprecation policies, they may still surprise some users.
+-->
+
+### Monitoring Requirements
+
+<!--
+This section must be completed when targeting beta to a release.
+
+For GA, this section is required: approvers should be able to confirm the
+previous answers based on experience in the field.
+-->
+
+###### How can an operator determine if the feature is in use by workloads?
+We can add 2 new metrics:
+- pdb_blocked_successful_evictions: To count the number of successful evictions
+- pdb_blocked_failed_evictions: To count the number of failed evictions by taint controller, and use these metrics to see if the feature is in use by workloads.
+
+<!--
+Ideally, this should be a metric. Operations against the Kubernetes API (e.g.,
+checking if there are objects with field X set) may be a last resort. Avoid
+logs or events for this purpose.
+-->
+
+###### How can someone using this feature know that it is working for their instance?
+
+<!--
+For instance, if this is a pod-related feature, it should be possible to determine if the feature is functioning properly
+for each individual pod.
+Pick one more of these and delete the rest.
+Please describe all items visible to end users below with sufficient detail so that they can verify correct enablement
+and operation of this feature.
+Recall that end users cannot usually observe component logs or access metrics.
+-->
+
+- [x] Events
+  - Event Reason: Pod eviction failed
+- [ ] API .status
+  - Condition name: 
+  - Other field: 
+- [ ] Other (treat as last resort)
+  - Details:
+
+###### What are the reasonable SLOs (Service Level Objectives) for the enhancement?
+
+<!--
+This is your opportunity to define what "normal" quality of service looks like
+for a feature.
+
+It's impossible to provide comprehensive guidance, but at the very
+high level (needs more precise definitions) those may be things like:
+  - per-day percentage of API calls finishing with 5XX errors <= 1%
+  - 99% percentile over day of absolute value from (job creation time minus expected
+    job creation time) for cron job <= 10%
+  - 99.9% of /health requests per day finish with 200 code
+
+These goals will help you determine what you need to measure (SLIs) in the next
+question.
+-->
+
+###### What are the SLIs (Service Level Indicators) an operator can use to determine the health of the service?
+
+<!--
+Pick one more of these and delete the rest.
+-->
+
+- [x] Metrics
+  - Metric name: `pdb_blocked_successful_evictions` and `pdb_blocked_failed_evictions`
+  - [Optional] Aggregation method:
+  - Components exposing the metric: kube-controller-manager
+- [ ] Other (treat as last resort)
+  - Details:
+
+###### Are there any missing metrics that would be useful to have to improve observability of this feature?
+None for now but this can revisited.
+<!--
+Describe the metrics themselves and the reasons why they weren't added (e.g., cost,
+implementation difficulties, etc.).
+-->
+
+### Dependencies
+
+<!--
+This section must be completed when targeting beta to a release.
+-->
+
+###### Does this feature depend on any specific services running in the cluster?
+None. It is part of taint controller in kube-controller-manager
+<!--
+Think about both cluster-level services (e.g. metrics-server) as well
+as node-level agents (e.g. specific version of CRI). Focus on external or
+optional services that are needed. For example, if this feature depends on
+a cloud provider API, or upon an external software-defined storage or network
+control plane.
+
+For each of these, fill in the following—thinking about running existing user workloads
+and creating new ones, as well as about cluster-level services (e.g. DNS):
+  - [Dependency name]
+    - Usage description:
+      - Impact of its outage on the feature:
+      - Impact of its degraded performance or high-error rates on the feature:
+-->
+
+### Scalability
+
+<!--
+For alpha, this section is encouraged: reviewers should consider these questions
+and attempt to answer them.
+
+For beta, this section is required: reviewers must answer these questions.
+
+For GA, this section is required: approvers should be able to confirm the
+previous answers based on experience in the field.
+-->
+
+###### Will enabling / using this feature result in any new API calls?
+
+<!--
+Describe them, providing:
+  - API call type (e.g. PATCH pods)
+  - estimated throughput
+  - originating component(s) (e.g. Kubelet, Feature-X-controller)
+Focusing mostly on:
+  - components listing and/or watching resources they didn't before
+  - API calls that may be triggered by changes of some Kubernetes resources
+    (e.g. update of object X triggers new updates of object Y)
+  - periodic API calls to reconcile state (e.g. periodic fetching state,
+    heartbeats, leader election, etc.)
+-->
+Instead of delete, it'll be evict API call
+###### Will enabling / using this feature result in introducing new API types?
+No
+<!--
+Describe them, providing:
+  - API type
+  - Supported number of objects per cluster
+  - Supported number of objects per namespace (for namespace-scoped objects)
+-->
+
+###### Will enabling / using this feature result in any new calls to the cloud provider?
+
+<!--
+Describe them, providing:
+  - Which API(s):
+  - Estimated increase:
+-->
+No
+###### Will enabling / using this feature result in increasing size or count of the existing API objects?
+
+<!--
+Describe them, providing:
+  - API type(s):
+  - Estimated increase in size: (e.g., new annotation of size 32B)
+  - Estimated amount of new objects: (e.g., new Object X for every existing Pod)
+-->
+Yes. API type(s): pod.Spec.tolerations
+New bool field which is 1 byte
+###### Will enabling / using this feature result in increasing time taken by any operations covered by existing SLIs/SLOs?
+No unless the operation covers both eviction and deletion instead of just deletion
+<!--
+Look at the [existing SLIs/SLOs].
+
+Think about adding additional work or introducing new steps in between
+(e.g. need to do X to start a container), etc. Please describe the details.
+
+[existing SLIs/SLOs]: https://git.k8s.io/community/sig-scalability/slos/slos.md#kubernetes-slisslos
+-->
+
+###### Will enabling / using this feature result in non-negligible increase of resource usage (CPU, RAM, disk, IO, ...) in any components?
+No
+<!--
+Things to keep in mind include: additional in-memory state, additional
+non-trivial computations, excessive access to disks (including increased log
+volume), significant amount of data sent and/or received over network, etc.
+This through this both in small and large cases, again with respect to the
+[supported limits].
+
+[supported limits]: https://git.k8s.io/community//sig-scalability/configs-and-limits/thresholds.md
+-->
+
+###### Can enabling / using this feature result in resource exhaustion of some node resources (PIDs, sockets, inodes, etc.)?
+No
+<!--
+Focus not just on happy cases, but primarily on more pathological cases
+(e.g. probes taking a minute instead of milliseconds, failed pods consuming resources, etc.).
+If any of the resources can be exhausted, how this is mitigated with the existing limits
+(e.g. pods per node) or new limits added by this KEP?
+
+Are there any tests that were run/should be run to understand performance characteristics better
+and validate the declared limits?
+-->
+
+### Troubleshooting
+
+<!--
+This section must be completed when targeting beta to a release.
+
+For GA, this section is required: approvers should be able to confirm the
+previous answers based on experience in the field.
+
+The Troubleshooting section currently serves the `Playbook` role. We may consider
+splitting it into a dedicated `Playbook` document (potentially with some monitoring
+details). For now, we leave it here.
+-->
+
+###### How does this feature react if the API server and/or etcd is unavailable?
+The controller won't be able to make progress, all currently queued resources are re-queued. This feature doesn't change current behavior of the controller in this regard.
+###### What are other known failure modes?
+  - 
+<!--
+For each of them, fill in the following information by copying the below template:
+  - [Failure mode brief description]
+    - Detection: How can it be detected via metrics? Stated another way:
+      how can an operator troubleshoot without logging into a master or worker node?
+    - Mitigations: What can be done to stop the bleeding, especially for already
+      running user workloads?
+    - Diagnostics: What are the useful log messages and their required logging
+      levels that could help debug the issue?
+      Not required until feature graduated to beta.
+    - Testing: Are there any tests for failure mode? If not, describe why.
+-->
+
+###### What steps should be taken if SLOs are not being met to determine the problem?
+- Check if the `pdb_blocked_successful_evictions` and `pdb_blocked_failed_evictions`. See if they are varying for with and without feature gate
+- Verify if kube-apiserver is healthy
+- Check if taint-manager is enabled or not
+## Implementation History
+
+<!--
+Major milestones in the lifecycle of a KEP should be tracked in this section.
+Major milestones might include:
+- the `Summary` and `Motivation` sections being merged, signaling SIG acceptance
+- the `Proposal` section being merged, signaling agreement on a proposed design
+- the date implementation started
+- the first Kubernetes release where an initial version of the KEP was available
+- the version of Kubernetes where the KEP graduated to general availability
+- when the KEP was retired or superseded
+-->
+
+## Drawbacks
+
+<!--
+Why should this KEP _not_ be implemented?
+-->
+Add more complexity to taint controller and can put strain on the PDB controller. This can also block cluster upgrades if the customer starts using this feature.
+## Alternatives
+Leave the feature as it is and allow third-party operators to implement it. This is the current situation now, however with native PDB support in taint controller, the third-party operators can focus on application-level APIs.
+<!--
+What other approaches did you consider, and why did you rule them out? These do
+not need to be as detailed as the proposal, but should include enough
+information to express the idea and why it was not acceptable.
+-->
+
+## Infrastructure Needed (Optional)
+
+<!--
+Use this section if you need things from the project/SIG. Examples include a
+new subproject, repos requested, or GitHub details. Listing these here allows a
+SIG to get the process for these resources started right away.
+-->
\ No newline at end of file
diff --git a/keps/sig-apps/4987-taint-tolerance-pdb/kep.yaml b/keps/sig-apps/4987-taint-tolerance-pdb/kep.yaml
new file mode 100644
index 00000000000..0b8d8e4f65d
--- /dev/null
+++ b/keps/sig-apps/4987-taint-tolerance-pdb/kep.yaml
@@ -0,0 +1,36 @@
+title: Taint Tolerance Tied to Pod Disruption Budget
+kep-number: 4987
+authors:
+  - "@ravisantoshgudimetla"
+owning-sig: sig-apps
+status: implementable
+creation-date: 2024-12-10
+reviewers:
+  - "@soltysh"
+  - "@atosatto"
+approvers:
+  - "@soltysh"
+# The target maturity stage in the current dev cycle for this KEP.
+stage: alpha
+
+# The most recent milestone for which work toward delivery of this KEP has been
+# done. This can be the current (upcoming) milestone, if it is being actively
+# worked on.
+latest-milestone: "v1.33"
+
+# The milestone at which this feature was, or is targeted to be, at each stage.
+milestone:
+  alpha: "v1.33"
+
+# The following PRR answers are required at alpha release
+# List the feature gate name and the components for which it must be enabled
+feature-gates:
+  - name: PDBBasedTaintTolerance
+    components:
+      - kube-apiserver
+      - kube-controller-manager
+disable-supported: true
+
+# # The following PRR answers are required at beta release
+# metrics:
+#   - my_feature_metric