Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add common labels into alert definitions #1622

Merged
merged 1 commit into from
Nov 27, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
88 changes: 66 additions & 22 deletions hack/prom-rule-ci/prom-rules-tests.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,9 @@ tests:
summary: "1 out-of-band CR modifications were detected in the last 10 minutes."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorCRModification"
exp_labels:
severity: "warning"
severity: "warning"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
component_name: "kubevirt/kubevirt-kubevirt-hyperconverged"

# New increases must be detected
Expand All @@ -40,7 +42,9 @@ tests:
summary: "3 out-of-band CR modifications were detected in the last 10 minutes."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorCRModification"
exp_labels:
severity: "warning"
severity: "warning"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
component_name: "kubevirt/kubevirt-kubevirt-hyperconverged"

# Old increases must be ignored.
Expand All @@ -52,7 +56,9 @@ tests:
summary: "1 out-of-band CR modifications were detected in the last 10 minutes."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorCRModification"
exp_labels:
severity: "warning"
severity: "warning"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
component_name: "kubevirt/kubevirt-kubevirt-hyperconverged"

# Should resolve after 10 minutes if there is no new change
Expand All @@ -74,7 +80,9 @@ tests:
summary: "1 out-of-band CR modifications were detected in the last 10 minutes."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorCRModification"
exp_labels:
severity: "warning"
severity: "warning"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
component_name: "kubevirt/kubevirt-kubevirt-hyperconverged"

# After restart, new increases must be detected
Expand All @@ -86,7 +94,9 @@ tests:
summary: "2 out-of-band CR modifications were detected in the last 10 minutes."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorCRModification"
exp_labels:
severity: "warning"
severity: "warning"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
component_name: "kubevirt/kubevirt-kubevirt-hyperconverged"
# Test unsafe modification counter
- interval: 1m
Expand Down Expand Up @@ -116,21 +126,27 @@ tests:
summary: "1 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "kubevirt.kubevirt.io/jsonpatch"
- exp_annotations:
description: "unsafe modification for the containerizeddataimporter.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
summary: "1 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "containerizeddataimporter.kubevirt.io/jsonpatch"
- exp_annotations:
description: "unsafe modification for the networkaddonsconfigs.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
summary: "5 unsafe modifications were detected in the HyperConverged resource."
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "networkaddonsconfigs.kubevirt.io/jsonpatch"

# New increases must be detected
Expand All @@ -142,22 +158,28 @@ tests:
summary: "3 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "kubevirt.kubevirt.io/jsonpatch"
- exp_annotations:
description: "unsafe modification for the containerizeddataimporter.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
summary: "3 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "containerizeddataimporter.kubevirt.io/jsonpatch"
# still using the 10 minutes max
- exp_annotations:
description: "unsafe modification for the networkaddonsconfigs.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
summary: "1 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "networkaddonsconfigs.kubevirt.io/jsonpatch"

# counter can be reduced
Expand All @@ -169,22 +191,28 @@ tests:
summary: "3 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "kubevirt.kubevirt.io/jsonpatch"
# Reduced
- exp_annotations:
description: "unsafe modification for the containerizeddataimporter.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
summary: "1 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "containerizeddataimporter.kubevirt.io/jsonpatch"
- exp_annotations:
description: "unsafe modification for the networkaddonsconfigs.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
summary: "1 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "networkaddonsconfigs.kubevirt.io/jsonpatch"

# no alert if the value is 0
Expand All @@ -196,14 +224,18 @@ tests:
summary: "3 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "kubevirt.kubevirt.io/jsonpatch"
- exp_annotations:
description: "unsafe modification for the containerizeddataimporter.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
summary: "3 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "containerizeddataimporter.kubevirt.io/jsonpatch"

# no alert if the value is 0 for all of the annotations
Expand All @@ -220,22 +252,28 @@ tests:
summary: "1 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "kubevirt.kubevirt.io/jsonpatch"
# Reduced
- exp_annotations:
description: "unsafe modification for the containerizeddataimporter.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
summary: "2 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "containerizeddataimporter.kubevirt.io/jsonpatch"
- exp_annotations:
description: "unsafe modification for the networkaddonsconfigs.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
summary: "3 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "networkaddonsconfigs.kubevirt.io/jsonpatch"

# no data
Expand All @@ -252,22 +290,28 @@ tests:
summary: "2 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "kubevirt.kubevirt.io/jsonpatch"
# Reduced
- exp_annotations:
description: "unsafe modification for the containerizeddataimporter.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
summary: "3 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "containerizeddataimporter.kubevirt.io/jsonpatch"
- exp_annotations:
description: "unsafe modification for the networkaddonsconfigs.kubevirt.io/jsonpatch annotation in the HyperConverged resource."
summary: "1 unsafe modifications were detected in the HyperConverged resource."
runbook_url: "https://kubevirt.io/monitoring/runbooks/KubevirtHyperconvergedClusterOperatorUSModification"
exp_labels:
severity: "info"
severity: "info"
kubernetes_operator_part_of: "kubevirt"
kubernetes_operator_component: "hyperconverged-cluster-operator"
annotation_name: "networkaddonsconfigs.kubevirt.io/jsonpatch"
# Test recording rule
- interval: 1m
Expand Down
8 changes: 6 additions & 2 deletions pkg/controller/operands/monitoring.go
Original file line number Diff line number Diff line change
Expand Up @@ -264,7 +264,9 @@ func NewPrometheusRuleSpec() *monitoringv1.PrometheusRuleSpec {
"runbook_url": outOfBandUpdateRunbookUrl,
},
Labels: map[string]string{
"severity": "warning",
"severity": "warning",
"kubernetes_operator_part_of": "kubevirt",
"kubernetes_operator_component": "hyperconverged-cluster-operator",
},
},
{
Expand All @@ -276,7 +278,9 @@ func NewPrometheusRuleSpec() *monitoringv1.PrometheusRuleSpec {
"runbook_url": unsafeModificationRunbookUrl,
},
Labels: map[string]string{
"severity": "info",
"severity": "info",
"kubernetes_operator_part_of": "kubevirt",
"kubernetes_operator_component": "hyperconverged-cluster-operator",
},
},
// Recording rules for openshift/cluster-monitoring-operator
Expand Down