Skip to content

fix(imagejob): skip nodes with insufficient resources before scheduling pods #1235

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
AruneshDwivedi wants to merge 2 commits into
base: main
Choose a base branch
from
+30 −1
Open

fix(imagejob): skip nodes with insufficient resources before scheduling pods #1235

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
efabfd9
fix(imagejob): ignore NotFound errors when looking up PodTemplate
AruneshDwivedi Aug 20, 2026
a26644e
fix(imagejob): skip nodes with insufficient resources before scheduli…
AruneshDwivedi Aug 20, 2026
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
31 changes: 30 additions & 1 deletion controllers/imagejob/imagejob_controller.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,7 +307,7 @@ func (r *Reconciler) handleNewJob(ctx context.Context, imageJob *eraserv1.ImageJ
&template,
)
if err != nil {
return err
return client.IgnoreNotFound(err)
}

imageJob.Status = eraserv1.ImageJobStatus{
Expand Down Expand Up @@ -362,6 +362,13 @@ func (r *Reconciler) handleNewJob(ctx context.Context, imageJob *eraserv1.ImageJ
podSpecTemplate := template.Template.Spec
for i := range nodeList {
log := log.WithValues("node", nodeList[i].Name)

// Skip nodes with insufficient resources
if insufficientResources(&nodeList[i], &podSpecTemplate) {
log.Info("skipping node: insufficient resources for eraser pod")
continue
}

podSpec, err := copyAndFillTemplateSpec(&podSpecTemplate, env, &nodeList[i], &eraserConfig.Manager.Runtime)
if err != nil {
return err
Expand Down Expand Up @@ -530,6 +537,28 @@ nodes:
return nodeList, skipped, nil
}

func insufficientResources(node *corev1.Node, podSpec *corev1.PodSpec) bool {
allocatable := node.Status.Allocatable
requests := podSpec.Containers[0].Resources.Requests
limits := podSpec.Containers[0].Resources.Limits

for name, req := range requests {
if available, ok := allocatable[name]; ok {
if available.Cmp(req) < 0 {
return true
}
}
}
for name, limit := range limits {
if available, ok := allocatable[name]; ok {
if available.Cmp(limit) < 0 {
return true
}
}
}
return false
}

func copyAndFillTemplateSpec(templateSpecTemplate *corev1.PodSpec, env []corev1.EnvVar, node *corev1.Node, runtimeSpec *unversioned.RuntimeSpec) (*corev1.PodSpec, error) {
nodeName := node.Name

Expand Down