MON-4029: Add KubeStateMetricsConfig to ClusterMonitoring API#2778
Conversation
|
Pipeline controller notification For optional jobs, comment This repository is configured in: LGTM mode |
openshift-ci-robot
added
the
jira/valid-reference
|
@danielmellado: This pull request references MON-4029 which is a valid jira issue. Warning: The referenced jira issue has an invalid target version for the target branch this PR targets: expected the story to target the "4.22.0" version, but no target version was set. DetailsIn response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository. |
|
Hello @danielmellado! Some important instructions when contributing to openshift/api: |
openshift-ci
Bot
added
the
size/XXL
|
@everettraven this PR continues #2461 and rebases and adds your comments. Thanks! |
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
📝 WalkthroughWalkthroughAdded an optional 🚥 Pre-merge checks | ✅ 11 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (11 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://cdn.github.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In
`@payload-manifests/crds/0000_10_config-operator_01_clustermonitorings.crd.yaml`:
- Around line 1117-1234: The CRD currently documents invariants but doesn't
enforce them; update the schema for the PodTopologySpread-like object to:
restrict whenUnsatisfiable to an enum of allowed values (e.g.,
"DoNotSchedule","ScheduleAnyway") on the whenUnsatisfiable property, add
minimum: 1 (and disallow 0) on maxSkew (format int32) and minimum: 1 on
minDomains (or use minimum: 1 when present), and add a validation rule that
requires labelSelector when matchLabelKeys is set (make matchLabelKeys mutually
exclusive with labelSelector and/or add a x-kubernetes-requirements or OpenAPI
dependency that enforces labelSelector presence when matchLabelKeys exists).
Target the properties named whenUnsatisfiable, maxSkew, minDomains,
matchLabelKeys and labelSelector in the CRD fragment to implement these
constraints.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Organization UI (inherited)
Review profile: CHILL
Plan: Pro
Run ID: a91c322b-92fd-43a0-a96f-b2b4da86aa91
⛔ Files ignored due to path filters (3)
config/v1alpha1/zz_generated.crd-manifests/0000_10_config-operator_01_clustermonitorings.crd.yamlis excluded by!**/zz_generated.crd-manifests/*config/v1alpha1/zz_generated.featuregated-crd-manifests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yamlis excluded by!**/zz_generated.featuregated-crd-manifests/**openapi/generated_openapi/zz_generated.openapi.gois excluded by!openapi/**
📒 Files selected for processing (5)
config/v1alpha1/tests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yamlconfig/v1alpha1/types_cluster_monitoring.goconfig/v1alpha1/zz_generated.deepcopy.goconfig/v1alpha1/zz_generated.swagger_doc_generated.gopayload-manifests/crds/0000_10_config-operator_01_clustermonitorings.crd.yaml
openshift-ci
Bot
added
the
needs-rebase
02919b5 to
361dc49
Compare
openshift-ci
Bot
removed
the
needs-rebase
|
/hold until openshift/cluster-monitoring-operator#2553 merges |
openshift-ci
Bot
added
the
do-not-merge/hold
|
/cc @rexagod |
361dc49 to
d134762
Compare
|
/unhold |
openshift-ci
Bot
removed
the
do-not-merge/hold
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
payload-manifests/crds/0000_10_config-operator_01_clustermonitorings.crd.yaml (1)
1175-1292:⚠️ Potential issue | 🟠 MajorEnforce documented topology spread invariants in schema (still missing).
This block documents constraints, but schema-level enforcement is still incomplete (
whenUnsatisfiablevalues, positivemaxSkew/minDomains, andmatchLabelKeysrequiringlabelSelector). Invalid CRs can pass admission and fail later.🔧 Proposed schema validation patch
maxSkew: @@ format: int32 + minimum: 1 type: integer minDomains: @@ format: int32 + minimum: 1 type: integer @@ whenUnsatisfiable: @@ + enum: + - DoNotSchedule + - ScheduleAnyway type: string required: - maxSkew - topologyKey - whenUnsatisfiable type: object + x-kubernetes-validations: + - message: minDomains can only be set when whenUnsatisfiable is DoNotSchedule + rule: '!has(self.minDomains) || self.whenUnsatisfiable == ''DoNotSchedule''' + - message: matchLabelKeys cannot be set when labelSelector is not set + rule: '!has(self.matchLabelKeys) || has(self.labelSelector)'🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@payload-manifests/crds/0000_10_config-operator_01_clustermonitorings.crd.yaml` around lines 1175 - 1292, The CRD currently documents invariants but doesn't enforce them; update the CRD's openAPIV3Schema to (1) restrict whenUnsatisfiable to the allowed enum values (e.g., "DoNotSchedule","ScheduleAnyway"), (2) add minimum: 1 for maxSkew and minDomains (and type integer) so maxSkew cannot be 0/negative and minDomains > 0, (3) add a conditional validation that when minDomains is set then whenUnsatisfiable must equal "DoNotSchedule", and (4) add validations requiring that matchLabelKeys cannot be present unless labelSelector is set and that keys in matchLabelKeys do not overlap with labelSelector keys; implement the conditional/complex checks using CRD CEL (x-kubernetes-validations) or equivalent CRD validation mechanisms referencing the fields matchLabelKeys, labelSelector, maxSkew, minDomains, and whenUnsatisfiable so invalid CRs are rejected at admission time.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In
`@config/v1alpha1/tests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yaml`:
- Around line 2145-2158: The test "Should reject KubeStateMetricsConfig with
duplicate resource in additionalResourceLabels" uses an invalid resource value
"jobs" which triggers enum validation before duplicate detection; update the two
entries under spec.kubeStateMetricsConfig.additionalResourceLabels to use a
valid resource (for example "pods" or another accepted enum value) so the YAML
passes resource validation and the duplicate-resource check is exercised by
ClusterMonitoring validation.
---
Duplicate comments:
In
`@payload-manifests/crds/0000_10_config-operator_01_clustermonitorings.crd.yaml`:
- Around line 1175-1292: The CRD currently documents invariants but doesn't
enforce them; update the CRD's openAPIV3Schema to (1) restrict whenUnsatisfiable
to the allowed enum values (e.g., "DoNotSchedule","ScheduleAnyway"), (2) add
minimum: 1 for maxSkew and minDomains (and type integer) so maxSkew cannot be
0/negative and minDomains > 0, (3) add a conditional validation that when
minDomains is set then whenUnsatisfiable must equal "DoNotSchedule", and (4) add
validations requiring that matchLabelKeys cannot be present unless labelSelector
is set and that keys in matchLabelKeys do not overlap with labelSelector keys;
implement the conditional/complex checks using CRD CEL
(x-kubernetes-validations) or equivalent CRD validation mechanisms referencing
the fields matchLabelKeys, labelSelector, maxSkew, minDomains, and
whenUnsatisfiable so invalid CRs are rejected at admission time.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Central YAML (inherited)
Review profile: CHILL
Plan: Pro Plus
Run ID: 5847c428-e700-46b3-84f5-f167574373e9
⛔ Files ignored due to path filters (6)
config/v1alpha1/zz_generated.crd-manifests/0000_10_config-operator_01_clustermonitorings.crd.yamlis excluded by!**/zz_generated.crd-manifests/*config/v1alpha1/zz_generated.deepcopy.gois excluded by!**/zz_generated*config/v1alpha1/zz_generated.featuregated-crd-manifests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yamlis excluded by!**/zz_generated.featuregated-crd-manifests/**config/v1alpha1/zz_generated.swagger_doc_generated.gois excluded by!**/zz_generated*openapi/generated_openapi/zz_generated.openapi.gois excluded by!openapi/**,!**/zz_generated*openapi/openapi.jsonis excluded by!openapi/**
📒 Files selected for processing (3)
config/v1alpha1/tests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yamlconfig/v1alpha1/types_cluster_monitoring.gopayload-manifests/crds/0000_10_config-operator_01_clustermonitorings.crd.yaml
🚧 Files skipped from review as they are similar to previous changes (1)
- config/v1alpha1/types_cluster_monitoring.go
|
@danielmellado could you please rebase this? Thanks again for the patch! :) |
openshift-ci
Bot
added
the
needs-rebase
d134762 to
d1719c1
Compare
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (2)
config/v1alpha1/tests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yaml (1)
2231-2506: Add explicit negative tests fornodeSelectorandtolerationsinkubeStateMetricsConfig.
nodeSelectorandtolerationsare only exercised in the all-fields happy path (Line 2237 and Line 2243). Unlike sibling configs in this file, there are no reject cases for empty/oversized values, so regressions in those validations could slip through.🧪 Suggested test additions
+ - name: Should reject KubeStateMetricsConfig with empty nodeSelector + initial: | + apiVersion: config.openshift.io/v1alpha1 + kind: ClusterMonitoring + spec: + kubeStateMetricsConfig: + nodeSelector: {} + expectedError: 'spec.kubeStateMetricsConfig.nodeSelector: Invalid value: 0: spec.kubeStateMetricsConfig.nodeSelector in body should have at least 1 properties' + + - name: Should reject KubeStateMetricsConfig with more than 10 nodeSelector entries + initial: | + apiVersion: config.openshift.io/v1alpha1 + kind: ClusterMonitoring + spec: + kubeStateMetricsConfig: + nodeSelector: + key1: val1 + key2: val2 + key3: val3 + key4: val4 + key5: val5 + key6: val6 + key7: val7 + key8: val8 + key9: val9 + key10: val10 + key11: val11 + expectedError: 'spec.kubeStateMetricsConfig.nodeSelector: Too many: 11: must have at most 10 items' + + - name: Should reject KubeStateMetricsConfig with empty tolerations array + initial: | + apiVersion: config.openshift.io/v1alpha1 + kind: ClusterMonitoring + spec: + kubeStateMetricsConfig: + tolerations: [] + expectedError: 'spec.kubeStateMetricsConfig.tolerations: Invalid value: 0: spec.kubeStateMetricsConfig.tolerations in body should have at least 1 items' + + - name: Should reject KubeStateMetricsConfig with more than 10 tolerations + initial: | + apiVersion: config.openshift.io/v1alpha1 + kind: ClusterMonitoring + spec: + kubeStateMetricsConfig: + tolerations: + - key: "key1" + operator: "Exists" + - key: "key2" + operator: "Exists" + - key: "key3" + operator: "Exists" + - key: "key4" + operator: "Exists" + - key: "key5" + operator: "Exists" + - key: "key6" + operator: "Exists" + - key: "key7" + operator: "Exists" + - key: "key8" + operator: "Exists" + - key: "key9" + operator: "Exists" + - key: "key10" + operator: "Exists" + - key: "key11" + operator: "Exists" + expectedError: 'spec.kubeStateMetricsConfig.tolerations: Too many: 11: must have at most 10 items'🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@config/v1alpha1/tests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yaml` around lines 2231 - 2506, The test suite lacks negative cases for kubeStateMetricsConfig.nodeSelector and kubeStateMetricsConfig.tolerations; add reject tests that mirror existing patterns: (1) a case where kubeStateMetricsConfig.nodeSelector is {} and assert an expectedError about requiring at least one property; (2) a case where kubeStateMetricsConfig.nodeSelector has an empty key or invalid value (if schema enforces non-empty strings); (3) a case where kubeStateMetricsConfig.tolerations is [] and assert an expectedError about requiring at least one item; and (4) a case with too many tolerations (or duplicate tolerations) to assert the "Too many" or "Duplicate value" errors; reference the kubeStateMetricsConfig, nodeSelector, and tolerations keys when adding these new test entries consistent with the surrounding test format.config/v1alpha1/types_cluster_monitoring.go (1)
2502-2568: Consider extracting the shared scheduling/resources shape.This block re-declares the same
nodeSelector/resources/tolerations/topologySpreadConstraintsshape already present inOpenShiftStateMetricsConfig. Pulling the common part into a shared struct would reduce drift in docs and validation.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@config/v1alpha1/types_cluster_monitoring.go` around lines 2502 - 2568, KubeStateMetricsConfig duplicates the scheduling/resources fields from OpenShiftStateMetricsConfig; extract a shared struct (e.g., PodSchedulingAndResources) containing NodeSelector, Resources, Tolerations, and TopologySpreadConstraints and replace those fields in both KubeStateMetricsConfig and OpenShiftStateMetricsConfig with a single embedded/shared field of that new struct; update kubebuilder tags and JSON names on the new struct to preserve validation (Min/MaxItems, listType/listMapKey, optional, etc.) and adjust any references to the original fields in code/comments to use the new struct.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@config/v1alpha1/types_cluster_monitoring.go`:
- Around line 2601-2627: KubeStateMetricsLabelName currently only enforces
length; add CEL validation and tighten the max length to enforce valid
Kubernetes label keys or the wildcard "*". Update the type
KubeStateMetricsLabelName to change the MaxLength from 256 to 253 and add a
+kubebuilder:validation:XValidation CEL rule that allows either self == "*" or a
DNS1123 subdomain prefix + "/" + qualified name (or no prefix) using split('/')
and format.dns1123Subdomain.validate for the prefix and a regex for the name
(^[A-Za-z0-9]([-A-Za-z0-9_.]*[A-Za-z0-9])?$), with an appropriate message like
"must be a valid Kubernetes label key or *"; keep the existing MinLength and
ensure the new validation applies to KubeStateMetricsLabelName so Labels
[]KubeStateMetricsLabelName inherits it.
---
Nitpick comments:
In
`@config/v1alpha1/tests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yaml`:
- Around line 2231-2506: The test suite lacks negative cases for
kubeStateMetricsConfig.nodeSelector and kubeStateMetricsConfig.tolerations; add
reject tests that mirror existing patterns: (1) a case where
kubeStateMetricsConfig.nodeSelector is {} and assert an expectedError about
requiring at least one property; (2) a case where
kubeStateMetricsConfig.nodeSelector has an empty key or invalid value (if schema
enforces non-empty strings); (3) a case where kubeStateMetricsConfig.tolerations
is [] and assert an expectedError about requiring at least one item; and (4) a
case with too many tolerations (or duplicate tolerations) to assert the "Too
many" or "Duplicate value" errors; reference the kubeStateMetricsConfig,
nodeSelector, and tolerations keys when adding these new test entries consistent
with the surrounding test format.
In `@config/v1alpha1/types_cluster_monitoring.go`:
- Around line 2502-2568: KubeStateMetricsConfig duplicates the
scheduling/resources fields from OpenShiftStateMetricsConfig; extract a shared
struct (e.g., PodSchedulingAndResources) containing NodeSelector, Resources,
Tolerations, and TopologySpreadConstraints and replace those fields in both
KubeStateMetricsConfig and OpenShiftStateMetricsConfig with a single
embedded/shared field of that new struct; update kubebuilder tags and JSON names
on the new struct to preserve validation (Min/MaxItems, listType/listMapKey,
optional, etc.) and adjust any references to the original fields in
code/comments to use the new struct.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Central YAML (inherited)
Review profile: CHILL
Plan: Pro Plus
Run ID: d4a84268-dde5-4503-a8ce-f4b5c2c51857
⛔ Files ignored due to path filters (6)
config/v1alpha1/zz_generated.crd-manifests/0000_10_config-operator_01_clustermonitorings.crd.yamlis excluded by!**/zz_generated.crd-manifests/*config/v1alpha1/zz_generated.deepcopy.gois excluded by!**/zz_generated*config/v1alpha1/zz_generated.featuregated-crd-manifests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yamlis excluded by!**/zz_generated.featuregated-crd-manifests/**config/v1alpha1/zz_generated.swagger_doc_generated.gois excluded by!**/zz_generated*openapi/generated_openapi/zz_generated.openapi.gois excluded by!openapi/**,!**/zz_generated*openapi/openapi.jsonis excluded by!openapi/**
📒 Files selected for processing (3)
config/v1alpha1/tests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yamlconfig/v1alpha1/types_cluster_monitoring.gopayload-manifests/crds/0000_10_config-operator_01_clustermonitorings.crd.yaml
d1719c1 to
57a8c79
Compare
openshift-ci
Bot
removed
the
needs-rebase
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
config/v1alpha1/types_cluster_monitoring.go (1)
2623-2634:⚠️ Potential issue | 🟠 Major | ⚡ Quick winUse Kubernetes label-key validation here instead of a broad regex.
The current rule still accepts invalid label keys like
team/a/bor prefixes that are not valid DNS subdomains, so the CRD can persistadditionalResourceLabelsvalues that kube-state-metrics should reject downstream. Please validate the optional prefix and name segment separately (single/, DNS1123 prefix, qualified-name suffix) rather than allowing any mix of._/-.For Kubernetes CRD / kubebuilder validation, what CEL rule correctly validates a Kubernetes label key (optional DNS1123 prefix + "/" + qualified name) while also allowing the wildcard "*"?🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@config/v1alpha1/types_cluster_monitoring.go` around lines 2623 - 2634, Replace the broad XValidation on type KubeStateMetricsLabelName with a CEL rule that allows "*" or enforces an optional single "/" prefix validated as a DNS1123 subdomain and a name segment validated as a Kubernetes qualified name; for example use a rule like: self == '*' || (self.split('/').size() == 1 && self.matches('^[A-Za-z0-9]([A-Za-z0-9_.-]*[A-Za-z0-9])?$')) || (self.split('/').size() == 2 && self.split('/')[0].matches('^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$') && self.split('/')[1].matches('^[A-Za-z0-9]([A-Za-z0-9_.-]*[A-Za-z0-9])?$')); update the +kubebuilder:validation:XValidation line on the KubeStateMetricsLabelName type accordingly.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
`@payload-manifests/crds/0000_10_config-operator_01_clustermonitorings.crd.yaml`:
- Around line 933-949: The current x-kubernetes-validations regex for
KubeStateMetricsLabelName (used by additionalResourceLabels.labels) allows
multiple slashes and mixed-case DNS prefixes; replace it with a stricter
validation that enforces at most one optional DNS subdomain prefix + '/' and a
single name segment that matches Kubernetes label-key syntax (DNS subdomain must
be lower-case DNS-1123 subdomain, name segment max 63 chars, begins/ends with
alphanumeric, and only contains alphanumerics, -, _, . in between). Update the
validation rule on the x-kubernetes-validations entry for
KubeStateMetricsLabelName so it rejects strings like "a/b/c" or
"Example.COM/key" by requiring a single optional lowercase DNS prefix and a
single valid name segment.
---
Duplicate comments:
In `@config/v1alpha1/types_cluster_monitoring.go`:
- Around line 2623-2634: Replace the broad XValidation on type
KubeStateMetricsLabelName with a CEL rule that allows "*" or enforces an
optional single "/" prefix validated as a DNS1123 subdomain and a name segment
validated as a Kubernetes qualified name; for example use a rule like: self ==
'*' || (self.split('/').size() == 1 &&
self.matches('^[A-Za-z0-9]([A-Za-z0-9_.-]*[A-Za-z0-9])?$')) ||
(self.split('/').size() == 2 &&
self.split('/')[0].matches('^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$')
&& self.split('/')[1].matches('^[A-Za-z0-9]([A-Za-z0-9_.-]*[A-Za-z0-9])?$'));
update the +kubebuilder:validation:XValidation line on the
KubeStateMetricsLabelName type accordingly.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Central YAML (inherited)
Review profile: CHILL
Plan: Enterprise
Run ID: 498ad17f-d61b-43f6-aa2f-a3df6fb77a07
⛔ Files ignored due to path filters (6)
config/v1alpha1/zz_generated.crd-manifests/0000_10_config-operator_01_clustermonitorings.crd.yamlis excluded by!**/zz_generated.crd-manifests/*config/v1alpha1/zz_generated.deepcopy.gois excluded by!**/zz_generated*config/v1alpha1/zz_generated.featuregated-crd-manifests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yamlis excluded by!**/zz_generated.featuregated-crd-manifests/**config/v1alpha1/zz_generated.swagger_doc_generated.gois excluded by!**/zz_generated*openapi/generated_openapi/zz_generated.openapi.gois excluded by!openapi/**,!**/zz_generated*openapi/openapi.jsonis excluded by!openapi/**
📒 Files selected for processing (3)
config/v1alpha1/tests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yamlconfig/v1alpha1/types_cluster_monitoring.gopayload-manifests/crds/0000_10_config-operator_01_clustermonitorings.crd.yaml
I'm fine with @saschagrunert recommendations, it totally makes sense to follow Kubernetes conventions. |
36cf1a4 to
acf2876
Compare
|
Scheduling tests matching the |
|
/test e2e-aws-ovn-hypershift-conformance |
everettraven
left a comment
everettraven
left a comment
There was a problem hiding this comment.
Overall the structure here looks good. Just a couple questions.
| // Each entry specifies a resource name and a list of Kubernetes label names to expose. | ||
| // Use "*" in the labels list to expose all labels for a given resource. | ||
| // additionalResourceLabels is optional. | ||
| // When omitted, only the default set of resource labels is exposed. |
There was a problem hiding this comment.
What is the "default set of resource labels"?
How would I as a user know if I need to configure this?
There was a problem hiding this comment.
By "default set of resource labels", this refers to the labels kube-state-metrics exposes out of the box, which is effectively none for Jobs/CronJobs. kube-state-metrics does not expose Kubernetes object labels as metric labels by default; it only does so when explicitly configured via --metric-labels-allowlist.
I agree the wording is misleading. I'll rephrase to something like:
"When omitted, no additional Kubernetes object labels are exposed as metrics by kube-state-metrics beyond its built-in metric labels (e.g. namespace, job_name). Use this field to opt in to exposing specific Kubernetes labels as metric labels for the supported resource types."
|
Correct. kube-state-metrics always collects its built-in metrics for all resources it watches (Jobs, CronJobs, Pods, etc.) -- that part is not affected by this config. What additionalResourceLabels controls is whether Kubernetes object labels (the user-defined labels on the resource metadata, like app=frontend) are promoted into metric labels. If you don't add an entry for, say, CronJob in additionalResourceLabels, kube-state-metrics still collects CronJob metrics, but none of the CronJob's Kubernetes labels appear as metric labels. Adding an entry lets you opt in to that per resource. |
Adds a new KubeStateMetricsConfig struct to the ClusterMonitoring CRD, allowing configuration of the kube-state-metrics agent (node selectors, resources, tolerations, topology spread constraints). Includes comprehensive integration tests for validation. Signed-off-by: Daniel Mellado <dmellado@fedoraproject.org>
acf2876 to
1a302b0
Compare
|
Scheduling tests matching the |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: everettraven, saschagrunert, simonpasquier The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
openshift-ci
Bot
added
the
approved
|
/retest-required |
4 similar comments
|
/retest-required |
|
/retest-required |
|
/retest-required |
|
/retest-required |
|
/verified by tests |
openshift-ci-robot
added
the
verified
|
@danielmellado: This PR has been marked as verified by DetailsIn response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository. |
|
@danielmellado: all tests passed! Full PR test history. Your PR dashboard. DetailsInstructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here. |
7 participants
Adds a new KubeStateMetricsConfig struct to the ClusterMonitoring CRD,
allowing configuration of the kube-state-metrics agent (node selectors,
resources, tolerations, topology spread constraints). Includes
comprehensive integration tests for validation.
Signed-off-by: Daniel Mellado dmellado@redhat.com