From 4fdf46ac2dacc3ee2cba5de6a5ed9eed1ac6386d Mon Sep 17 00:00:00 2001
From: kerthcet <kerthcet@gmail.com>
Date: Wed, 5 Jan 2022 16:15:53 +0800
Subject: [PATCH] KEP: PodTopoplogySpread considering taints

Signed-off-by: kerthcet <kerthcet@gmail.com>
---
 keps/prod-readiness/sig-scheduling/3094.yaml  |   3 +
 .../README.md                                 | 861 ++++++++++++++++++
 .../kep.yaml                                  |  47 +
 3 files changed, 911 insertions(+)
 create mode 100644 keps/prod-readiness/sig-scheduling/3094.yaml
 create mode 100644 keps/sig-scheduling/3094-pod-topology-spread-considering-taints/README.md
 create mode 100644 keps/sig-scheduling/3094-pod-topology-spread-considering-taints/kep.yaml

diff --git a/keps/prod-readiness/sig-scheduling/3094.yaml b/keps/prod-readiness/sig-scheduling/3094.yaml
new file mode 100644
index 000000000000..2539f0331643
--- /dev/null
+++ b/keps/prod-readiness/sig-scheduling/3094.yaml
@@ -0,0 +1,3 @@
+kep-number: 3094
+alpha:
+  approver: ""
diff --git a/keps/sig-scheduling/3094-pod-topology-spread-considering-taints/README.md b/keps/sig-scheduling/3094-pod-topology-spread-considering-taints/README.md
new file mode 100644
index 000000000000..c3442e746d92
--- /dev/null
+++ b/keps/sig-scheduling/3094-pod-topology-spread-considering-taints/README.md
@@ -0,0 +1,861 @@
+<!--
+**Note:** When your KEP is complete, all of these comment blocks should be removed.
+
+To get started with this template:
+
+- [ ] **Pick a hosting SIG.**
+  Make sure that the problem space is something the SIG is interested in taking
+  up. KEPs should not be checked in without a sponsoring SIG.
+- [ ] **Create an issue in kubernetes/enhancements**
+  When filing an enhancement tracking issue, please make sure to complete all
+  fields in that template. One of the fields asks for a link to the KEP. You
+  can leave that blank until this KEP is filed, and then go back to the
+  enhancement and add the link.
+- [ ] **Make a copy of this template directory.**
+  Copy this template into the owning SIG's directory and name it
+  `NNNN-short-descriptive-title`, where `NNNN` is the issue number (with no
+  leading-zero padding) assigned to your enhancement above.
+- [ ] **Fill out as much of the kep.yaml file as you can.**
+  At minimum, you should fill in the "Title", "Authors", "Owning-sig",
+  "Status", and date-related fields.
+- [ ] **Fill out this file as best you can.**
+  At minimum, you should fill in the "Summary" and "Motivation" sections.
+  These should be easy if you've preflighted the idea of the KEP with the
+  appropriate SIG(s).
+- [ ] **Create a PR for this KEP.**
+  Assign it to people in the SIG who are sponsoring this process.
+- [ ] **Merge early and iterate.**
+  Avoid getting hung up on specific details and instead aim to get the goals of
+  the KEP clarified and merged quickly. The best way to do this is to just
+  start with the high-level sections and fill out details incrementally in
+  subsequent PRs.
+
+Just because a KEP is merged does not mean it is complete or approved. Any KEP
+marked as `provisional` is a working document and subject to change. You can
+denote sections that are under active debate as follows:
+
+```
+<<[UNRESOLVED optional short context or usernames ]>>
+Stuff that is being argued.
+<<[/UNRESOLVED]>>
+```
+
+When editing KEPS, aim for tightly-scoped, single-topic PRs to keep discussions
+focused. If you disagree with what is already in a document, open a new PR
+with suggested changes.
+
+One KEP corresponds to one "feature" or "enhancement" for its whole lifecycle.
+You do not need a new KEP to move from beta to GA, for example. If
+new details emerge that belong in the KEP, edit the KEP. Once a feature has become
+"implemented", major changes should get new KEPs.
+
+The canonical place for the latest set of instructions (and the likely source
+of this file) is [here](/keps/NNNN-kep-template/README.md).
+
+**Note:** Any PRs to move a KEP to `implementable`, or significant changes once
+it is marked `implementable`, must be approved by each of the KEP approvers.
+If none of those approvers are still appropriate, then changes to that list
+should be approved by the remaining approvers and/or the owning SIG (or
+SIG Architecture for cross-cutting KEPs).
+-->
+# KEP-3094: Take taints/tolerations into consideration when calculating PodTopologySpread skew
+
+<!--
+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)
+  - [Graduation Criteria](#graduation-criteria)
+  - [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*.
+
+- [x] (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`
+- [x] (R) Design details are appropriately documented
+- [x] (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 for 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
+- [x] (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
+- [x] "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
+
+<!--
+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
+-->
+This KEP introduces a new field as an option for end-users to honor all taints or
+only system-generated unschedulable taints when computing pod topology spread skew.
+This helps improving the scheduling efficiency by filtering out nodes don't meet the
+toleration requirements.
+
+## Motivation
+
+<!--
+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
+-->
+Currently, when we compute pod topology spread skew, we will ignore the impact of
+node taints whatever pod tolerates or not, which may lead to some unexpected results.
+E.g. node with pod untolerated taints might be the candidate node after computing,
+then the pod would be stuck in Pending state. So toleration/taints should be taken into
+consideration when computing pod topology spread skew. For backwards compatibility,
+we'd like to define this as an option for end-users to honor all taints or
+only system-generated unschedulable taints.
+
+### Goals
+
+<!--
+List the specific goals of the KEP. What is it trying to achieve? How will we
+know that this has succeeded?
+-->
+- Filtering out pod untolerated nodes when computing pod topology spread skew
+- Provide an option for end-users to specify whether to honor all taints or
+only system-generated unschedulable taints
+
+### Non-Goals
+
+<!--
+What is out of scope for this KEP? Listing non-goals helps to focus discussion
+and make progress.
+-->
+- Refactor or introduce any breaking changes to PodTopologySpread plugin
+
+## Proposal
+
+<!--
+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.
+-->
+A new field `TaintStrategy` defined in `TopologySpreadConstraint` will be available for
+end-users to specify different strategies about how to treat taints in computing skew.
+
+### User Stories (Optional)
+
+<!--
+Detail the things that people will be able to do if this KEP is implemented.
+Include as much detail as possible so that people can understand the "how" of
+the system. The goal here is to make this feel real for users without getting
+bogged down.
+-->
+
+#### Story 1
+When computing pod topology spread skew, I want to exclude nodes that don't tolerate
+all taints to prevent pods from falling into unexpected Pending state. I can simply
+configure this by specifying a taintStrategy:
+
+    apiVersion: v1
+    kind: Pod
+    metadata:
+    name: mypod
+    spec:
+      topologySpreadConstraints:
+        - maxSkew: 1
+          topologyKey: zone
+          whenUnsatisfiable: DoNotSchedule
+          labelSelector:
+            matchLabels:
+              foo: bar
+          taintStrategy: "honorAllTaints"
+
+### 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
+
+<!--
+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.
+-->
+
+- Looping all the toleration/taints to filter out unsatisfied nodes may
+lead to performance problem.
+- Some usual schedulable nodes may become unschedulable, which might be
+confusing for end-users.
+
+## Design Details
+
+<!--
+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.
+-->
+
+A new field named `TaintStrategy` will be introduced to `TopologySpreadConstraint`:
+
+    type TopologySpreadConstraint struct {
+      MaxSkew int32
+      TopologyKey string
+      WhenUnsatisfiable UnsatisfiableConstraintAction
+      LabelSelector *metav1.LabelSelector
+      TaintStrategy taintStrategy
+    }
+
+Correspondingly, the internal version for v1.TopologySpreadConstraint named
+`topologySpreadConstraint` will also add a `TaintStrategy` field:
+
+    type topologySpreadConstraint struct {
+      MaxSkew       int32
+      TopologyKey   string
+      Selector      labels.Selector
+      TaintStrategy taintStrategy
+    }
+
+`taintStrategy` is a potential type of `String`, and there are two available options
+for users.
+
+One is `honorAllTaints` which means when computing pod topology spread skew,
+all kinds of node taints should be taken into consideration, if any of these taints pod
+doesn't tolerate, the node is excluded.
+
+The other one is `honorUnschedulableTaint`, which means instead of considering all taints
+node carried, we only concern about taint `node.kubernetes.io/unschedulable:NoSchedule`.
+
+This behavior is controlled by feature gate `TaintStrategy`, if this feature gate is on
+and `TaintStrategy` doesn't set, `honorAllTaints` will take effect by default.
+
+We'd like to implement this part of logic before computing skew for code efficiency.
+
+### Test Plan
+
+<!--
+**Note:** *Not required until targeted at a release.*
+
+Consider the following in developing a test plan for this enhancement:
+- Will there be e2e and integration tests, in addition to unit tests?
+- How will it be tested in isolation vs with other components?
+
+No need to outline all of the test cases, just the general strategy. Anything
+that would count as tricky in the implementation, and anything particularly
+challenging to test, should be called out.
+
+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
+-->
+- Unit and integration tests:
+  - Defaulting and validation tests
+  - Feature gate enable/disable tests.
+  - `TaintStrategy` works as expected
+- Benchmark tests:
+  - Verify the performance of looping all toleration and taints in computing skew is acceptable
+
+### Graduation Criteria
+
+<!--
+**Note:** *Not required until targeted at a release.*
+
+Define graduation milestones.
+
+These may be defined in terms of API maturity, 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]
+- [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.
+
+[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.mdfd
+
+#### 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
+-->
+#### Alpha
+- Feature implemented behind feature gate.
+- Test cases mentioned in Test Plan
+
+#### Beta
+- Feature is enabled by default
+- Gather feedback from developers and surveys.
+- No performance problem.
+
+#### GA
+- No negative feedback.
+
+### Upgrade / Downgrade Strategy
+
+<!--
+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?
+-->
+
+- Upgrade
+  - While the feature gate is disabled, field `TaintStrategy` will be ignored.
+  - While the feature gate is enabled, `TaintStrategy` provides two optional values
+  for end-users to specify how to treat node taints.
+  - While the feature gate is enabled, and we don't set this field, `taintStrategy` of
+   `honorAllTaints` will take effect by default.
+- Downgrade
+  - Whatever we enable/disable feature gate, previously configured values will
+  be ignored.
+
+
+### Version Skew Strategy
+N/A
+
+<!--
+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
+  in the kubelet? How does an n-2 kubelet 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.
+-->
+
+## 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.
+-->
+
+- [x] Feature gate (also fill in values in `kep.yaml`)
+  - Feature gate name: TaintStrategy
+  - Components depending on the feature gate: kube-scheduler, kube-apiserver
+- [x] Other
+  - Describe the mechanism:
+
+    Specify strategy about how to treat taints.
+
+  - Will enabling / disabling the feature require downtime of the control
+    plane?
+
+    Yes.
+
+  - Will enabling / disabling the feature require downtime or reprovisioning
+    of a node? (Do not assume `Dynamic Kubelet Config` feature is enabled).
+
+    No.
+
+###### Does enabling the feature change any default behavior?
+
+<!--
+Any change of default behavior may be surprising to users or break existing
+automations, so be extremely careful here.
+-->
+Yes, some usual schedulable nodes might be unschedulable.
+
+###### Can the feature be disabled once it has been enabled (i.e. can we roll back the enablement)?
+
+<!--
+Describe the consequences on existing workloads (e.g., if this is a runtime
+feature, can it break the existing applications?).
+
+NOTE: Also set `disable-supported` to `true` or `false` in `kep.yaml`.
+-->
+Yes.
+
+###### What happens if we reenable the feature if it was previously rolled back?
+N/A.
+
+###### Are there any tests for feature enablement/disablement?
+Yes.
+
+<!--
+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.
+-->
+
+### 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?
+
+<!--
+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.
+-->
+A malformed configuration will cause the scheduler failing to start. Running workloads are not affected.
+
+###### What specific metrics should inform a rollback?
+
+<!--
+What signals should users be paying attention to when the feature is young
+that might indicate a serious problem?
+-->
+- A spike on metric schedule_attempts_total{result="error|unschedulable"} when pods using this feature are added.
+- Metric plugin_execution_duration_seconds{plugin="PodTopologySpread"} larger than 100ms on 90-percentile.
+- A spike on failure events with keyword "failed spreadConstraint" in scheduler log.
+
+###### Were upgrade and rollback tested? Was the upgrade->downgrade->upgrade path tested?
+N/A
+
+<!--
+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.?
+No
+
+<!--
+Even if applying deprecation policies, they may still surprise some users.
+-->
+
+### Monitoring Requirements
+
+<!--
+This section must be completed when targeting beta to a release.
+-->
+
+###### How can an operator determine 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.
+-->
+Operator can query `pod.spec.topologySpreadConstraints[].taintStrategy` field
+and identify if this is set.
+
+###### 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.
+-->
+
+<!-- - [ ] Events
+  - Event Reason:
+- [ ] API .status
+  - Condition name:
+  - Other field:
+- [ ] Other (treat as last resort)
+  - Details: -->
+
+N/A
+
+###### 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.
+-->
+
+- Metric plugin_execution_duration_seconds{plugin="PodTopologySpread"} <= 100ms on 90-percentile.
+- Frequency of critical error keywords <= 2 times per minute.
+- Frequency of regular scheduling failures < 10 times per minute.
+
+###### 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.
+-->
+
+<!-- - [ ] Metrics
+  - Metric name:
+  - [Optional] Aggregation method:
+  - Components exposing the metric:
+- [ ] Other (treat as last resort)
+  - Details: -->
+
+- Metric plugin_execution_duration_seconds{plugin="PodTopologySpread"} to indicate the scheduling latency for a pod using this feature.
+- Frequency of critical error keywords in scheduler log:
+  - "PreFilterPodTopologySpread"
+  - "convert to podtopologyspread.preFilterState error"
+  - "hard topology spread constraints"
+  - "internal error: get paths from key"
+- Frequency of regular scheduling failures (with keyword "failed spreadConstraint") in scheduler log.
+
+###### Are there any missing metrics that would be useful to have to improve observability of this feature?
+
+<!--
+Describe the metrics themselves and the reasons why they weren't added (e.g., cost,
+implementation difficulties, etc.).
+-->
+N/A
+
+### Dependencies
+
+<!--
+This section must be completed when targeting beta to a release.
+-->
+
+###### Does this feature depend on any specific services running in the cluster?
+
+<!--
+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:
+-->
+No
+
+### 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.
+-->
+No
+
+###### 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.)
+-->
+No
+
+###### Will enabling / using this feature result in introducing new API types?
+
+<!--
+Describe them, providing:
+  - API type
+  - Supported number of objects per cluster
+  - Supported number of objects per namespace (for namespace-scoped objects)
+-->
+No
+
+###### 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)
+-->
+No
+
+###### Will enabling / using this feature result in increasing time taken by any operations covered by existing SLIs/SLOs?
+
+<!--
+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
+-->
+No
+
+###### Will enabling / using this feature result in non-negligible increase of resource usage (CPU, RAM, disk, IO, ...) in any components?
+
+<!--
+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
+-->
+No
+
+### Troubleshooting
+
+<!--
+This section must be completed when targeting beta to a release.
+
+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?
+N/A
+
+###### 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.
+-->
+
+Configuration errors are logged to stderr.
+
+###### What steps should be taken if SLOs are not being met to determine the problem?
+N/A
+
+## 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
+-->
+
+- 2021.01.05: KEP proposed for review, including motivation, proposal, risks,
+test plan and graduation criteria.
+
+## Drawbacks
+
+<!--
+Why should this KEP _not_ be implemented?
+-->
+N/A
+
+## Alternatives
+
+<!--
+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.
+-->
+N/A
+
+## 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.
+-->
+N/A
diff --git a/keps/sig-scheduling/3094-pod-topology-spread-considering-taints/kep.yaml b/keps/sig-scheduling/3094-pod-topology-spread-considering-taints/kep.yaml
new file mode 100644
index 000000000000..00b0efd3487f
--- /dev/null
+++ b/keps/sig-scheduling/3094-pod-topology-spread-considering-taints/kep.yaml
@@ -0,0 +1,47 @@
+title: Take taints/tolerations into consideration when calculating PodTopologySpread skew
+kep-number: 3094
+authors:
+  - "@kerthcet"
+owning-sig: sig-scheduling
+participating-sigs:
+status: implementable
+creation-date: 2021-12-30
+reviewers:
+  - TBD
+approvers:
+  - TBD
+
+see-also:
+  - "/keps/sig-scheduling/895-pod-topology-spread"
+  - "/keps/sig-scheduling/1258-default-pod-topology-spread"
+
+##### WARNING !!! ######
+# prr-approvers has been moved to its own location
+# You should create your own in keps/prod-readiness
+# Please make a copy of keps/prod-readiness/template/nnnn.yaml
+# to keps/prod-readiness/sig-xxxxx/00000.yaml (replace with kep number)
+#prr-approvers:
+
+# 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: "v1.24"
+
+# The milestone at which this feature was, or is targeted to be, at each stage.
+milestone:
+  alpha: "v1.24"
+  beta: "v1.25"
+  stable: "v1.26"
+
+# 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: TaintStrategy
+    components:
+      - kube-apiserver
+      - kube-scheduler
+
+disable-supported: false