Skip to content

Fix/multi device quota enforcement #2218

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

Closed
manmathbh wants to merge 1 commit into from
Closed

Fix/multi device quota enforcement #2218

Show file tree
Hide file tree
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
7 changes: 3 additions & 4 deletions pkg/scheduler/webhook.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,11 +130,10 @@ func isPrivilegedContainer(ctr *corev1.Container) bool {

func fitResourceQuota(pod *corev1.Pod) bool {
for deviceName, dev := range device.GetDevices() {
// Only supports NVIDIA
if deviceName != nvidia.NvidiaGPUDevice {
continue
memoryFactor := int32(1)
if deviceName == nvidia.NvidiaGPUDevice {
memoryFactor = nvidia.MemoryFactor
}
memoryFactor := nvidia.MemoryFactor
resourceNames := dev.GetResourceNames()
resourceName := corev1.ResourceName(resourceNames.ResourceCountName)
memResourceName := corev1.ResourceName(resourceNames.ResourceMemoryName)
Expand Down
110 changes: 105 additions & 5 deletions pkg/scheduler/webhook_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,40 @@ import (
"github.com/Project-HAMi/HAMi/pkg/scheduler/config"
)

type mockDevices struct {
resourceNames device.ResourceNames
}

func (m *mockDevices) CommonWord() string { return "mock" }
func (m *mockDevices) MutateAdmission(ctr *corev1.Container, pod *corev1.Pod) (bool, error) {
return true, nil
}
func (m *mockDevices) CheckHealth(devType string, n *corev1.Node) (bool, bool) {
return true, true
}
func (m *mockDevices) NodeCleanUp(nn string) error { return nil }
func (m *mockDevices) GetResourceNames() device.ResourceNames { return m.resourceNames }
func (m *mockDevices) GetNodeDevices(n corev1.Node) ([]*device.DeviceInfo, error) {
return []*device.DeviceInfo{}, nil
}
func (m *mockDevices) LockNode(n *corev1.Node, p *corev1.Pod) error { return nil }
func (m *mockDevices) ReleaseNodeLock(n *corev1.Node, p *corev1.Pod) error { return nil }
func (m *mockDevices) GenerateResourceRequests(ctr *corev1.Container) device.ContainerDeviceRequest {
return device.ContainerDeviceRequest{}
}
func (m *mockDevices) PatchAnnotations(pod *corev1.Pod, annoinput *map[string]string, pd device.PodDevices) map[string]string {
return map[string]string{}
}
func (m *mockDevices) ScoreNode(node *corev1.Node, podDevices device.PodSingleDevice, previous []*device.DeviceUsage, policy string) float32 {
return 1.0
}
func (m *mockDevices) AddResourceUsage(pod *corev1.Pod, n *device.DeviceUsage, ctr *device.ContainerDevice) error {
return nil
}
func (m *mockDevices) Fit(devices []*device.DeviceUsage, request device.ContainerDeviceRequest, pod *corev1.Pod, nodeInfo *device.NodeInfo, allocated *device.PodDevices) (bool, map[string]device.ContainerDevices, string) {
return true, nil, ""
}

func TestHandle(t *testing.T) {
// create a Pod object
pod := &corev1.Pod{
Expand Down Expand Up @@ -263,14 +297,27 @@ func TestFitResourceQuota(t *testing.T) {
klog.Fatalf("Failed to initialize devices with config: %v", err)
}

ascendCountName := "huawei.com/Ascend910B"
ascendMemName := "huawei.com/Ascend910B-memory"
device.DevicesMap["Ascend910B"] = &mockDevices{
resourceNames: device.ResourceNames{
ResourceCountName: ascendCountName,
ResourceMemoryName: ascendMemName,
},
}
Comment on lines +300 to +307
defer func() {
delete(device.DevicesMap, "Ascend910B")
}()

qm := device.NewQuotaManager()
ns := "default"
memName := "nvidia.com/gpumem"
coreName := "nvidia.com/gpucores"
nvidiaMemName := "nvidia.com/gpumem"
nvidiaCoreName := "nvidia.com/gpucores"

qm.Quotas[ns] = &device.DeviceQuota{
memName: &device.Quota{Used: 1000, Limit: 2000},
coreName: &device.Quota{Used: 200, Limit: 400},
nvidiaMemName: &device.Quota{Used: 1000, Limit: 2000},
nvidiaCoreName: &device.Quota{Used: 200, Limit: 400},
ascendMemName: &device.Quota{Used: 0, Limit: 1000},
Comment on lines +302 to +320

@coderabbitai coderabbitai Bot Jul 30, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🩺 Stability & Availability | 🟡 Minor | ⚡ Quick win

Restore the global test state instead of deleting it.

Line 302 can overwrite an existing Ascend910B device, but the defer always deletes it; Line 317 also leaves the singleton quota entry for default behind. Save and restore both prior values so later tests cannot become order-dependent.

Proposed fix 
+	oldAscend, hadAscend := device.DevicesMap["Ascend910B"]
+	oldQuota, hadQuota := qm.Quotas[ns]
 	device.DevicesMap["Ascend910B"] = &mockDevices{
 		resourceNames: device.ResourceNames{
 			ResourceCountName:  ascendCountName,
 			ResourceMemoryName: ascendMemName,
 		},
 	}
 	defer func() {
-		delete(device.DevicesMap, "Ascend910B")
+		if hadAscend {
+			device.DevicesMap["Ascend910B"] = oldAscend
+		} else {
+			delete(device.DevicesMap, "Ascend910B")
+		}
+		if hadQuota {
+			qm.Quotas[ns] = oldQuota
+		} else {
+			delete(qm.Quotas, ns)
+		}
 	}()
🤖 Prompt for AI Agents 
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@pkg/scheduler/webhook_test.go` around lines 302 - 320, Update the test setup
around the Ascend910B device and default quota entry to save their existing
global values before overwriting them, then restore those values in defer
cleanup; only delete each key when no prior value existed. Ensure both
device.DevicesMap and qm.Quotas retain their original state for subsequent
tests.

}

testCases := []struct {
Expand Down Expand Up @@ -387,7 +434,7 @@ func TestFitResourceQuota(t *testing.T) {
fit: true,
},
{
name: "request ascend",
name: "request ascend exceeded quota",
pod: &corev1.Pod{
ObjectMeta: metav1.ObjectMeta{
Name: "test-pod",
Expand All @@ -411,6 +458,59 @@ func TestFitResourceQuota(t *testing.T) {
},
},
},
fit: false,
},
{
name: "request ascend within quota",
pod: &corev1.Pod{
ObjectMeta: metav1.ObjectMeta{
Name: "test-pod",
Namespace: "default",
},
Spec: corev1.PodSpec{
SchedulerName: "hami-scheduler",
Containers: []corev1.Container{
{
Name: "container1",
SecurityContext: &corev1.SecurityContext{
Privileged: nil,
},
Resources: corev1.ResourceRequirements{
Limits: corev1.ResourceList{
"huawei.com/Ascend910B": resource.MustParse("1"),
"huawei.com/Ascend910B-memory": resource.MustParse("500"),
},
},
},
},
},
},
fit: true,
},
{
name: "request ascend memory only no count",
pod: &corev1.Pod{
ObjectMeta: metav1.ObjectMeta{
Name: "test-pod",
Namespace: "default",
},
Spec: corev1.PodSpec{
SchedulerName: "hami-scheduler",
Containers: []corev1.Container{
{
Name: "container1",
SecurityContext: &corev1.SecurityContext{
Privileged: nil,
},
Resources: corev1.ResourceRequirements{
Limits: corev1.ResourceList{
"huawei.com/Ascend910B-memory": resource.MustParse("2000"),
},
},
},
},
},
},
fit: true,
},
}
Expand Down
Loading