From 24a688c05fc5fef1e4609b932c2c5569f5ea6057 Mon Sep 17 00:00:00 2001
From: Yuki Iwai <yuki.iwai.tz@gmail.com>
Date: Tue, 6 Jun 2023 22:03:24 +0900
Subject: [PATCH] KEP-3998: Job success/completion policy

Signed-off-by: Yuki Iwai <yuki.iwai.tz@gmail.com>
---
 keps/prod-readiness/sig-apps/3998.yaml        |    3 +
 .../README.md                                 | 1071 +++++++++++++++++
 .../kep.yaml                                  |   42 +
 3 files changed, 1116 insertions(+)
 create mode 100644 keps/prod-readiness/sig-apps/3998.yaml
 create mode 100644 keps/sig-apps/3998-job-success-completion-policy/README.md
 create mode 100644 keps/sig-apps/3998-job-success-completion-policy/kep.yaml

diff --git a/keps/prod-readiness/sig-apps/3998.yaml b/keps/prod-readiness/sig-apps/3998.yaml
new file mode 100644
index 000000000000..07d7140592ac
--- /dev/null
+++ b/keps/prod-readiness/sig-apps/3998.yaml
@@ -0,0 +1,3 @@
+kep-number: 3998
+beta:
+  approver: "@wojtek-t"
diff --git a/keps/sig-apps/3998-job-success-completion-policy/README.md b/keps/sig-apps/3998-job-success-completion-policy/README.md
new file mode 100644
index 000000000000..6c0f29f28812
--- /dev/null
+++ b/keps/sig-apps/3998-job-success-completion-policy/README.md
@@ -0,0 +1,1071 @@
+<!--
+**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-3998: Job success/completion policy
+
+<!--
+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)
+    - [Story 3](#story-3)
+  - [Notes/Constraints/Caveats (Optional)](#notesconstraintscaveats-optional)
+  - [Risks and Mitigations](#risks-and-mitigations)
+    - [The Job object too big](#the-job-object-too-big) 
+- [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)
+  - [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
+
+<!--
+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 extends the Job API to allow setting conditions under which the Job can be declared as succeeded. 
+
+## 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
+-->
+
+There are cases where a batch workload requires an indexed job that want to care 
+only about drivers (leaders) indexes in determining the success or failure of a Job,
+for example MPI and PyTorch etc. This is currently not possible because the indexed job 
+is marked as Completed only if all indexes are succeeded.
+
+Additionally, there are cases where a batch workload requires a number
+to be specified as a percentage when determining the success of a job
+because an indexed job author might not know how many indexes the job will have in advance
+when the above batch workload has an autoscale semantic.
+
+Some third-party frameworks have implemented success policy.
+
+- [Kubeflow Training Operator](https://www.kubeflow.org/docs/components/training)
+- [Flux Operator](https://flux-framework.org/flux-operator/)
+
+### Goals
+
+<!--
+List the specific goals of the KEP. What is it trying to achieve? How will we
+know that this has succeeded?
+-->
+
+- allow to mark a job as a `Succeeded` even if some of the indexes fail.
+
+### Non-Goals
+
+<!--
+What is out of scope for this KEP? Listing non-goals helps to focus discussion
+and make progress.
+-->
+
+- Change the existing behavior of `NonIndexed` mode.
+- Change the existing behavior of `Indexed` mode without a SuccessfulPolicy.
+
+## 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.
+-->
+
+We propose new policies under which a job can be declared as succeeded.
+Those policies can be modeled in the following:
+
+1. An indexed job completes if a set of [x, y, z...] indexes are successful.
+2. An indexed job completes if x or x% of indexes are successful.
+
+### 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
+
+As a machine-learning researcher, I run a indexed job which drivers (leaders) are launched
+as index=0,1,2, and workers are launched as non index=0,1,2.
+I want to care about only the drivers when the result of job is evaluated.
+
+```yaml
+apiVersion: v1
+kind: Job
+spec:
+  parallelism: 10
+  completions: 10
+  completionMode: Indexed
+  successfulPolicy:
+    onRequiredIndexes: [0,1,2]
+  template:
+    spec:
+      restartPolicy: Never
+      containers:
+      - name: job-container
+        image: job-image
+        command: ["./sample"]
+```
+
+#### Story 2
+
+As a machine-learning researcher, I run an indexed job with an autoscale semantic
+set as a minimum number is 5 and a maximum number is 20.
+I want to mark the job as successful at least 5 indexes succeeded, even if 
+all indexes don't succeed.
+
+```yaml
+apiVersion: v1
+kind: Job
+spec:
+  parallelism: 10
+  completions: 10
+  completionMode: Indexed
+  successfulPolicy:
+    onIndexesThreshold: 5
+  template:
+    spec:
+      restartPolicy: Never
+      containers:
+      - name: job-container
+        image: job-image
+        command: ["./sample"]
+```
+
+#### Story 3
+
+As a machine-learning researcher from the [Story 2](#story-2), I want to mark the job
+as successful if 50% of all indexes succeed because I can not know how many indexes 
+will have in advance.
+
+```yaml
+apiVersion: v1
+kind: Job
+spec:
+  parallelism: 10
+  completions: 10
+  completionMode: Indexed
+  successfulPolicy:
+    onIndexesThreshold: 50%
+  template:
+    spec:
+      restartPolicy: Never
+      containers:
+        - name: job-container
+          image: job-image
+          command: ["./sample"]
+```
+
+### 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.
+-->
+
+#### Incorrect `.status.completedIndexes`
+
+If the job object's size reaches to limit of the etcd and
+the job controller can't store a correct value in `.status.completedIndexes`,
+we probably can not evaluate the SuccessfulPolicy correctly.
+
+#### The Job object too big
+
+If we allow users to set all indexes (`0~10^5`) to `.spec.successfulPolicy.requiredIndexes`
+and don't limit the number of list sizes, there are cases that the size of a job object is too big.  
+
+In the worst case, allowed all indexes (`0~10^5`) are added to requiredIndexes.
+In that case, a `requiredIndexes` size is `SUM[9*10^n*(n+1)]+2+6≈5.6656MiB`, where:
+- `n` starts from `0` and goes up to `5`.
+- `1` of `n+1` means a separator that indicates `,`.
+- `2` is the sum of the index `0` and `,`.
+- `6` is the size of indexes `10^5`.
+
+## 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.
+-->
+
+### Job API
+
+We extend the Job API to set different policies by which a Job can be declared as succeeded.
+
+```golang
+type JobSpec struct {
+	...
+	// Specifies the policy when the job can be declared as succeeded.
+	// If empty, the default behavior applies - the job is declared as succeeded
+	// only when the number of succeeded pods equals to the completions.
+	// This policy can not be specified more than one.
+	//
+	// This field is alpha-level. To use this field, you must enable the
+	// `JobSuccessPolicy` feature gate (disable by default).
+	// +option
+	SuccessfulPolicy *SuccessfulPolicy
+}
+
+// SuccessfulPolicy describes how succeeded pods influence the conditions.
+type SuccessfulPolicy struct {
+	// Specifies a set of required indexes.
+    // The job is declared as succeeded if a set of indexes are succeeded. 
+    // The list of indexes must come within 0 to `.spec.completions` and
+    // must not contain duplicates. At least one element is required. 
+    // 
+    // +option
+	OnRequiredIndexes []int
+
+    // Specifies the required number of indexes.
+    // Value can be an absolute number (ex: 5) or a percentage of total indexes
+    // when the job can be declared as succeeded (ex: 50%).
+    // The absolute number is calculated from the percentage by rounding up. 
+    // 
+    // +option
+	OnIndexesThreshold intstr.IntOrString
+}
+```
+
+Moreover, we validate the following constraints:
+- exactly one of the fields `onRequiredIndexes` and `onIndexesThreshold` is specified
+  for a requirement.
+- whether the specified indexes in the `onRequiredIndexes` and
+  the number of indexes in the `onIndexesThreshold` don't exceed the value of `completions`.
+- whether `Indexed` is specified in the `completionMode` field.
+
+### Evaluation
+We evaluate the SuccessfulPolicy after all indexes have been finished.
+And then if the job meets the SuccessfulPolicy, we add `Completed` condition
+instead of `Failed` condition to `.status.conditions` even if other indexes fail.
+
+If a set of indexes are specified in the `onRequiredIndexes` field,
+we evaluate `.status.completedIndexes` to see if a set of indexes is there.
+
+If the number of indexes is specified in the `onIndexesThreshold`, 
+we evaluate `.status.succeeded` to see if the value is `onIndexesThreshold` or more.
+
+### Test Plan
+
+<!--
+**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.
+-->
+
+- Test cases:
+  - tests for Defaulting and Validating
+  - tests for rounding up absolute numbers in `.spec.successfulPolicy.onRequiredIndexesThreshold`.
+  - verify whether a job has condition=completed if the job meets to successfulPolicy
+  and some indexes fail.
+
+- `k8s.io/kubernetes/pkg/controller/job`: `6 June 2023` - `90.5%`
+- `k8s.io/kubernetes/pkg/apis/batch/validation`: `6 June 2023` - `98.5%`
+
+##### 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 scenarios:
+  - enabling, disabling and re-enabling of the `JobSuccessfulPolicy` feature gate
+  - handling of successfulPolicy when all indexes succeeded
+  - handling of the `.spec.successfulPolicy.onRequiredIndexes` when some indexes fail
+  - handling of the `.spec.successfulPolicy.onRequiredIndexesThreshold` when some indexes fail
+
+##### 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 scenarios:
+  - handling of successfulPolicy when all indexes succeeded
+  - handling of the `.spec.successfulPolicy.onRequiredIndexes` when some indexes fail
+  - handling of the `.spec.successfulPolicy.onRequiredIndexesThreshold` when some indexes fail
+
+### Graduation Criteria
+
+<!--
+**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
+-->
+
+
+#### Alpha
+
+- Feature implemented behind the `JobSuccessfulPolicy` feature gate.
+- Unit and integration tests passed as designed in [TestPlan](#test-plan).
+
+#### Beta
+
+- E2E tests passed as designed in [TestPlan](#test-plan).
+- Added a new reasons to the existing `job_finished_total` metric in [Monitoring Requirements](#monitoring-requirements).
+- Feature is enabled by default.
+- Gather feedback from developers.
+
+#### 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
+  - If the feature gate is enabled, `JobSuccessfulPolicy` are allowed to use only.
+  - If the feature gate is enabled without `JobSuccessfulPolicy`, 
+  the default values will be applied to a job object.
+  - Even if the feature gate is enabled, the Job controller doesn't update
+  `.status.conditions` in already finished jobs.
+- Downgrade
+  - Previously configured values will be ignored, and the job will be marked
+  as completed only when all indexes succeed.
+  - the Job controller doesn't update `.status.conditions` in already finished jobs.
+
+### 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
+  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.
+-->
+
+The apiserver's version should be consistent with the kube-controller-manager version,
+or this feature will not work.
+
+## 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/
+-->
+
+- [x] Feature gate (also fill in values in `kep.yaml`)
+  - Feature gate name:
+  - Components depending on the feature gate:
+    - kube-apiserver
+    - kube-controller-manager
+
+###### 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.
+-->
+
+No.
+
+###### 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?).
+
+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`.
+-->
+
+Yes, we can disable the `JobSuccessfulPolicy` feature gate.
+
+###### What happens if we reenable the feature if it was previously rolled back?
+
+The Job controller considers the `.spec.successfulPolicy` when it updates `.status.conditions`
+only for running Jobs and don't update `.status.conditions` for already finished jobs. 
+
+###### Are there any tests for feature enablement/disablement?
+
+<!--
+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
+-->
+
+No, we'll add them during alpha.
+
+### 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.
+-->
+
+No. The Job controller considers `.spec.successfulPolicy` after all indexes (pods) are finished.
+
+###### 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?
+-->
+
+An increase in the `job_sync_duration_seconds` metrics can mean that finished jobs
+are taking longer to evaluate.   
+
+The users should check whether the completed jobs have the appropriate condition,
+specifically the reason.
+
+###### Were upgrade and rollback tested? Was the upgrade->downgrade->upgrade path tested?
+
+<!--
+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.
+-->
+
+No.
+
+###### Is the rollout accompanied by any deprecations and/or removals of features, APIs, fields of API types, flags, etc.?
+
+<!--
+Even if applying deprecation policies, they may still surprise some users.
+-->
+
+No.
+
+### 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?
+
+<!--
+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.
+-->
+
+`job_finished_total`: the new `JobSuccessfulPolicy` and `Completions` values for the `reason` label. 
+  - `JobSuccessfulPolicy` indicates a job is declared as succeeded because the job meets `.spec.successfulPolicy`.
+  - `Completions` indicates a job is declared as succeeded because the job mees `spec.completions`.
+
+###### 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] Job API .status
+  - The Job controller will add a condition with `JobSuccessfulPolicy` reason to `conditions`. 
+
+###### 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: `job_sync_duration_seconds` (existing): can be used to see how much the
+    feature enablement increases the time spent in the sync job
+  - Components exposing the metric:
+
+###### 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.).
+-->
+
+No.
+
+### 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)
+-->
+
+Yes, it will increase the size of existing API objects only when the `.spec.successfulPolicy` is set.
+
+- API type(s): Job
+- Estimated increase in size: `.spec.successPolicy.requiredIndexes` field are impacted.
+In the worst case, the size of `requiredIndexes` can be estimated about 5.6MiB (see [The Job object too big](#the-job-object-too-big)).
+
+###### 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.
+
+###### Can enabling / using this feature result in resource exhaustion of some node resources (PIDs, sockets, inodes, etc.)?
+
+<!--
+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?
+-->
+
+No.
+
+### 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?
+
+###### 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.
+-->
+
+None.
+
+###### What steps should be taken if SLOs are not being met to determine the problem?
+
+## 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
+-->
+- 2023.06.06: This KEP is ready for review.
+
+## Drawbacks
+
+<!--
+Why should this KEP _not_ be implemented?
+-->
+
+## 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.
+-->
+
+### Relax a validation for `.spec.completions`
+Currently, a job is restricted `.spec.completion!=nil`.
+By relaxing the validation, the job can be declared as succeeded when some indexes succeeded,
+similar to NonIndexed jobs.
+
+## 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.
+-->
diff --git a/keps/sig-apps/3998-job-success-completion-policy/kep.yaml b/keps/sig-apps/3998-job-success-completion-policy/kep.yaml
new file mode 100644
index 000000000000..86c628e4b044
--- /dev/null
+++ b/keps/sig-apps/3998-job-success-completion-policy/kep.yaml
@@ -0,0 +1,42 @@
+title: Job success/completion policy
+kep-number: 3998
+authors:
+  - "@tenzen-y"
+owning-sig: sig-apps
+participating-sigs:
+  - sig-apps
+status: implementable
+creation-date: 2023-06-05
+reviewers:
+  - "@mimowo"
+  - "@alculquicondor"
+approvers:
+  - "@wojtek-t"
+  - "@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: "v1.28"
+
+# The milestone at which this feature was, or is targeted to be, at each stage.
+milestone:
+  alpha: "v1.28"
+  beta: "v1.29"
+  stable: "v1.30"
+
+# 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: JobSuccessfulPolicy
+    components:
+      - kube-apiserver
+      - kube-controller-manager
+disable-supported: true
+
+# The following PRR answers are required at beta release
+metrics:
+  - jobs_finished_total