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.

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

Fix issue where HumioClusterReconciler is stuck pinning an empty zone #919

Merged
merged 1 commit into from
Feb 13, 2025
Merged

Fix issue where HumioClusterReconciler is stuck pinning an empty zone #919

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
15 changes: 9 additions & 6 deletions controllers/humiocluster_controller.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1957,15 +1957,18 @@ func (r *HumioClusterReconciler) ensureMismatchedPodsAreDeleted(ctx context.Cont
podListForCurrentZoneWithWrongPodRevisionAndNonEmptyNodeName := FilterPodsExcludePodsWithEmptyNodeName(podListForCurrentZoneWithWrongPodRevisionOrPodHash)
r.Log.Info(fmt.Sprintf("zone awareness enabled, len(podListForCurrentZoneWithWrongPodRevisionOrPodHash)=%d len(podListForCurrentZoneWithWrongPodRevisionAndNonEmptyNodeName)=%d", len(podListForCurrentZoneWithWrongPodRevisionOrPodHash), len(podListForCurrentZoneWithWrongPodRevisionAndNonEmptyNodeName)))

if len(podListForCurrentZoneWithWrongPodRevisionAndNonEmptyNodeName) > 0 {
newZoneUnderMaintenance, err := kubernetes.GetZoneForNodeName(ctx, r, podListForCurrentZoneWithWrongPodRevisionAndNonEmptyNodeName[0].Spec.NodeName)
// pin the zone if we can find a non-empty zone
for _, pod := range podListForCurrentZoneWithWrongPodRevisionAndNonEmptyNodeName {
newZoneUnderMaintenance, err := kubernetes.GetZoneForNodeName(ctx, r, pod.Spec.NodeName)
if err != nil {
return reconcile.Result{}, r.logErrorAndReturn(err, "unable to fetch zone")
}
r.Log.Info(fmt.Sprintf("zone awareness enabled, pinning zone for nodePool=%s in oldZoneUnderMaintenance=%s newZoneUnderMaintenance=%s",
hnp.GetNodePoolName(), hnp.GetZoneUnderMaintenance(), newZoneUnderMaintenance))
return r.updateStatus(ctx, r.Client.Status(), hc, statusOptions().
withNodePoolState(hnp.GetState(), hnp.GetNodePoolName(), hnp.GetDesiredPodRevision(), hnp.GetDesiredPodHash(), hnp.GetDesiredBootstrapTokenHash(), newZoneUnderMaintenance))
if newZoneUnderMaintenance != "" {
r.Log.Info(fmt.Sprintf("zone awareness enabled, pinning zone for nodePool=%s in oldZoneUnderMaintenance=%s newZoneUnderMaintenance=%s",
hnp.GetNodePoolName(), hnp.GetZoneUnderMaintenance(), newZoneUnderMaintenance))
return r.updateStatus(ctx, r.Client.Status(), hc, statusOptions().
withNodePoolState(hnp.GetState(), hnp.GetNodePoolName(), hnp.GetDesiredPodRevision(), hnp.GetDesiredPodHash(), hnp.GetDesiredBootstrapTokenHash(), newZoneUnderMaintenance))
}
}
} else {
// clear the zone-under-maintenance marker if no more work is left in that zone
Expand Down
Loading