Skip to content

FIx CI, add 910B4-1 template and fix vGPUmonitor metrics error #1345

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

Merged
hami-robot merged 3 commits into from
Sep 14, 2025
Merged

FIx CI, add 910B4-1 template and fix vGPUmonitor metrics error #1345

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
257ee7b
update
archlitchi Sep 12, 2025
4a6db19
update
archlitchi Sep 12, 2025
cd05308
update
archlitchi Sep 13, 2025
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
17 changes: 17 additions & 0 deletions charts/hami/templates/scheduler/device-configmap.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,23 @@ data:
memory: 32768
aiCore: 10
aiCPU: 3
- chipName: 910B4-1
commonWord: Ascend910B4-1
resourceName: huawei.com/Ascend910B4-1
resourceMemoryName: huawei.com/Ascend910B4-1-memory
memoryAllocatable: 65536
memoryCapacity: 65536
aiCore: 20
aiCPU: 7
templates:
- name: vir05_1c_8g
memory: 8192
aiCore: 5
aiCPU: 1
- name: vir10_3c_16g
memory: 16384
aiCore: 10
aiCPU: 3
- chipName: 910B4
commonWord: Ascend910B4
resourceName: huawei.com/Ascend910B4
Expand Down
4 changes: 3 additions & 1 deletion charts/hami/values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ global:
## - myRegistryKeySecretName
## @param global.imagePullSecrets Global Docker image pull secrets
imagePullSecrets: []
imageTag: "v2.6.0"
imageTag: "v2.6.1"
gpuHookPath: /usr/local
labels: {}
annotations: {}
Expand Down Expand Up @@ -384,6 +384,8 @@ devices:
- huawei.com/Ascend910B3-memory
- huawei.com/Ascend910B4
- huawei.com/Ascend910B4-memory
- huawei.com/Ascend910B4-1
- huawei.com/Ascend910B4-1-memory
- huawei.com/Ascend310P
- huawei.com/Ascend310P-memory

2 changes: 1 addition & 1 deletion pkg/device/enflame/gcu.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,7 @@ func (dev *GCUDevices) AddResourceUsage(pod *corev1.Pod, n *device.DeviceUsage,
return nil
}

func (gcuDev *GCUDevices) Fit(devices []*device.DeviceUsage, request device.ContainerDeviceRequest, annos map[string]string, pod *corev1.Pod, nodeInfo *device.NodeInfo, allocated *device.PodDevices) (bool, map[string]device.ContainerDevices, string) {
func (gcuDev *GCUDevices) Fit(devices []*device.DeviceUsage, request device.ContainerDeviceRequest, pod *corev1.Pod, nodeInfo *device.NodeInfo, allocated *device.PodDevices) (bool, map[string]device.ContainerDevices, string) {
k := request
originReq := k.Nums
klog.InfoS("Allocating device for container request", "pod", klog.KObj(pod), "card request", k)
Expand Down
7 changes: 6 additions & 1 deletion pkg/device/enflame/gcu_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -577,7 +577,12 @@ func TestGCUDevices_Fit(t *testing.T) {
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
allocated := &device.PodDevices{}
fit, result, reason := dev.Fit(test.devices, test.request, test.annos, &corev1.Pod{}, &device.NodeInfo{}, allocated)
pod := &corev1.Pod{
ObjectMeta: metav1.ObjectMeta{
Annotations: test.annos,
},
}
fit, result, reason := dev.Fit(test.devices, test.request, pod, &device.NodeInfo{}, allocated)
if fit != test.wantFit {
t.Errorf("Fit: got %v, want %v", fit, test.wantFit)
}
Expand Down
12 changes: 6 additions & 6 deletions pkg/monitor/nvidia/v1/spec.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,47 +90,47 @@ func (s Spec) DeviceNum() int {

func (s Spec) DeviceMemoryContextSize(idx int) uint64 {
v := uint64(0)
for _, p := range s.sr.procs {
for _, p := range s.sr.procs[:int(s.sr.procnum)] {
Comment thread
archlitchi marked this conversation as resolved.
v += p.used[idx].contextSize
}
return v
}

func (s Spec) DeviceMemoryModuleSize(idx int) uint64 {
v := uint64(0)
for _, p := range s.sr.procs {
for _, p := range s.sr.procs[:int(s.sr.procnum)] {
v += p.used[idx].moduleSize
}
return v
}

func (s Spec) DeviceMemoryBufferSize(idx int) uint64 {
v := uint64(0)
for _, p := range s.sr.procs {
for _, p := range s.sr.procs[:int(s.sr.procnum)] {
v += p.used[idx].bufferSize
}
return v
}

func (s Spec) DeviceMemoryOffset(idx int) uint64 {
v := uint64(0)
for _, p := range s.sr.procs {
for _, p := range s.sr.procs[:int(s.sr.procnum)] {
v += p.used[idx].offset
}
return v
}

func (s Spec) DeviceMemoryTotal(idx int) uint64 {
v := uint64(0)
for _, p := range s.sr.procs {
for _, p := range s.sr.procs[:int(s.sr.procnum)] {
v += p.used[idx].total
}
return v
}

func (s Spec) DeviceSmUtil(idx int) uint64 {
v := uint64(0)
for _, p := range s.sr.procs {
for _, p := range s.sr.procs[:int(s.sr.procnum)] {
v += p.deviceUtil[idx].smUtil
}
return v
Expand Down
12 changes: 12 additions & 0 deletions pkg/monitor/nvidia/v1/spec_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,6 +114,7 @@ func Test_DeviceMemoryContextSize(t *testing.T) {
idx: int(0),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
used: [16]deviceMemory{
Expand Down Expand Up @@ -150,6 +151,7 @@ func Test_DeviceMemoryContextSize(t *testing.T) {
idx: int(1),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
used: [16]deviceMemory{
Expand Down Expand Up @@ -205,6 +207,7 @@ func Test_DeviceMemoryModuleSize(t *testing.T) {
idx: int(0),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
used: [16]deviceMemory{
Expand Down Expand Up @@ -241,6 +244,7 @@ func Test_DeviceMemoryModuleSize(t *testing.T) {
idx: int(1),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
used: [16]deviceMemory{
Expand Down Expand Up @@ -296,6 +300,7 @@ func Test_DeviceMemoryBufferSize(t *testing.T) {
idx: int(0),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
used: [16]deviceMemory{
Expand Down Expand Up @@ -332,6 +337,7 @@ func Test_DeviceMemoryBufferSize(t *testing.T) {
idx: int(1),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
used: [16]deviceMemory{
Expand Down Expand Up @@ -387,6 +393,7 @@ func Test_DeviceMemoryOffset(t *testing.T) {
idx: int(0),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
used: [16]deviceMemory{
Expand Down Expand Up @@ -423,6 +430,7 @@ func Test_DeviceMemoryOffset(t *testing.T) {
idx: int(1),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
used: [16]deviceMemory{
Expand Down Expand Up @@ -478,6 +486,7 @@ func Test_DeviceMemoryTotal(t *testing.T) {
idx: int(0),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
used: [16]deviceMemory{
Expand Down Expand Up @@ -514,6 +523,7 @@ func Test_DeviceMemoryTotal(t *testing.T) {
idx: int(1),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
used: [16]deviceMemory{
Expand Down Expand Up @@ -569,6 +579,7 @@ func Test_DeviceSmUtil(t *testing.T) {
idx: int(0),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
deviceUtil: [16]deviceUtilization{
Expand Down Expand Up @@ -605,6 +616,7 @@ func Test_DeviceSmUtil(t *testing.T) {
idx: int(1),
spec: &Spec{
sr: &sharedRegionT{
procnum: 2,
procs: [1024]shrregProcSlotT{
{
deviceUtil: [16]deviceUtilization{
Expand Down
Loading