Skip to content

[release-4.19] OCPBUGS-63126: Ensure the node passed to RunCordonOrUncordon comes from the latest updated state #5348

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
wants to merge 1 commit into
base: release-4.19
Choose a base branch
from
Open

[release-4.19] OCPBUGS-63126: Ensure the node passed to RunCordonOrUncordon comes from the latest updated state #5348

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
12 changes: 7 additions & 5 deletions pkg/controller/drain/drain_controller.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -569,11 +569,13 @@ func (ctrl *Controller) cordonOrUncordonNode(desired bool, node *corev1.Node, dr
}

var lastErr error

currentNode := node.DeepCopy()
if err := wait.ExponentialBackoff(ctrl.cfg.CordonOrUncordonBackoff, func() (bool, error) {
// Log has been added to ensure that MCO is correctly performing cordon/uncordon.
// This should help us with debugging bugs like https://bugzilla.redhat.com/show_bug.cgi?id=2022387
ctrl.logNode(node, "initiating %s (currently schedulable: %t)", verb, !node.Spec.Unschedulable)
err := drain.RunCordonOrUncordon(drainer, node, desired)
ctrl.logNode(node, "initiating %s (currently schedulable: %t)", verb, !currentNode.Spec.Unschedulable)
err := drain.RunCordonOrUncordon(drainer, currentNode, desired)
if err != nil {
lastErr = err
klog.Infof("%s failed with: %v, retrying", verb, err)
Expand All @@ -587,14 +589,14 @@ func (ctrl *Controller) cordonOrUncordonNode(desired bool, node *corev1.Node, dr
klog.Errorf("Failed to fetch node %v, retrying", err)
return false, nil
}

if updatedNode.Spec.Unschedulable != desired {
currentNode = updatedNode
if currentNode.Spec.Unschedulable != desired {
// See https://bugzilla.redhat.com/show_bug.cgi?id=2022387
ctrl.logNode(node, "RunCordonOrUncordon() succeeded but node is still not in %s state, retrying", verb)
return false, nil
}

ctrl.logNode(node, "%s succeeded (currently schedulable: %t)", verb, !updatedNode.Spec.Unschedulable)
ctrl.logNode(node, "%s succeeded (currently schedulable: %t)", verb, !currentNode.Spec.Unschedulable)
return true, nil
}); err != nil {
if wait.Interrupted(err) {
Expand Down