Skip to content

OPRUN-4569: test: remove OLMv1 OTE exceptions; scope OLMv0 exceptions to SNO #31172

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.

Sign up for GitHub

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

Open
tmshort wants to merge 1 commit into
base: main
Choose a base branch
from
+11 −12
Open

OPRUN-4569: test: remove OLMv1 OTE exceptions; scope OLMv0 exceptions to SNO #31172

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
23 changes: 11 additions & 12 deletions pkg/monitortests/clusterversionoperator/legacycvomonitortests/operators.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -369,15 +369,6 @@ func testUpgradeOperatorStateTransitions(events monitorapi.Intervals, clientConf
(condition.Status == configv1.ConditionUnknown && condition.Reason == "UpdatingPrometheusFailed") {
return "https://issues.redhat.com/browse/OCPBUGS-23745"
}
case "olm":
if condition.Type == configv1.OperatorAvailable &&
condition.Status == configv1.ConditionFalse &&
// "OperatorcontrollerDeploymentOperatorControllerControllerManager_Deploying"
// "CatalogdDeploymentCatalogdControllerManager_Deploying"
// "CatalogdDeploymentCatalogdControllerManager_Deploying::OperatorcontrollerDeploymentOperatorControllerControllerManager_Deploying"
strings.HasSuffix(condition.Reason, "ControllerManager_Deploying") {
return "https://issues.redhat.com/browse/OCPBUGS-62517"
}
case "openshift-apiserver":
if condition.Type == configv1.OperatorAvailable && condition.Status == configv1.ConditionFalse {
if isTwoNode && condition.Reason == "APIServices_PreconditionNotReady" {
Expand Down Expand Up @@ -634,12 +625,14 @@ func testUpgradeOperatorProgressingStateTransitions(events monitorapi.Intervals,
multiUpgrades := platformidentification.UpgradeNumberDuringCollection(events, time.Time{}, time.Time{}) > 1

isTwoNode := false
isSingleNode := false
if clientConfig != nil {
topology, err := getControlPlaneTopology(clientConfig)
if err != nil {
logrus.Warnf("Error checking for ControlPlaneTopology configuration for MCO co-progressing monitor (unable to apply two-node TNF exceptions): %v", err)
logrus.Warnf("Error checking for ControlPlaneTopology configuration for MCO co-progressing monitor (unable to apply topology exceptions): %v", err)
} else {
isTwoNode = topology == configv1.HighlyAvailableArbiterMode || topology == configv1.DualReplicaTopologyMode
isSingleNode = topology == configv1.SingleReplicaTopologyMode
}
}

Expand Down Expand Up @@ -802,11 +795,17 @@ func testUpgradeOperatorProgressingStateTransitions(events monitorapi.Intervals,
case "olm":
// CatalogdDeploymentCatalogdControllerManager_Deploying
// OperatorcontrollerDeploymentOperatorControllerControllerManager_Deploying
if strings.HasSuffix(reason, "ControllerManager_Deploying") {
// On HA, cluster-olm-operator PR #202 (2 replicas + PDB) prevents this.
// On SNO there is only one replica and the node reboot restarts all pods simultaneously.
if strings.HasSuffix(reason, "ControllerManager_Deploying") && isSingleNode {
return "https://issues.redhat.com/browse/OCPBUGS-62635"
}
case "operator-lifecycle-manager-packageserver":
if reason == "" {
// On HA, isAPIServiceBackendDisrupted() in operator-framework-olm detects terminating
// pods and returns RetryableError to prevent the CSV phase from changing to Failed.
// On SNO the OS-level node reboot kills all pods simultaneously so no terminating pod
// is ever observed; the detection does not fire and Progressing=True is still set.
if reason == "" && isSingleNode {
return "https://issues.redhat.com/browse/OCPBUGS-63672"
}
case "openshift-apiserver":
Expand Down