Skip to content

gpu: levelzero: use correct struct for temp printing #2155

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
merged 1 commit into from
Oct 20, 2025
+7 −9
Merged

gpu: levelzero: use correct struct for temp printing #2155

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: 4 additions & 3 deletions cmd/gpu_plugin/gpu_plugin.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -396,7 +396,7 @@ func (dp *devicePlugin) healthStatusForCard(cardPath string) string {
return health
}

dt, err := dp.levelzeroService.GetDeviceTemperature(bdfAddr)
deviceTemps, err := dp.levelzeroService.GetDeviceTemperature(bdfAddr)
// In case of any errors, return the current health status
if err != nil {
klog.Warningf("Device temperature retrieval failed: %v", err)
Expand All @@ -407,9 +407,10 @@ func (dp *devicePlugin) healthStatusForCard(cardPath string) string {
limit := float64(dp.options.temperatureLimit)

// Temperatures for different areas
klog.V(4).Infof("Temperatures: Memory=%.1fC, GPU=%.1fC, Global=%.1fC", dh.MemoryTemperature, dh.GPUTemperature, dh.GlobalTemperature)
klog.V(4).Infof("Temperatures: Memory=%.1fC, GPU=%.1fC, Global=%.1fC",
deviceTemps.Memory, deviceTemps.GPU, deviceTemps.Global)

if dt.GPU > limit || dt.Global > limit || dt.Memory > limit {
if deviceTemps.GPU > limit || deviceTemps.Global > limit || deviceTemps.Memory > limit {
health = pluginapi.Unhealthy
}

Expand Down
9 changes: 3 additions & 6 deletions cmd/gpu_plugin/levelzeroservice/levelzero_service.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,12 +33,9 @@ type LevelzeroService interface {
}

type DeviceHealth struct {
Memory bool
Bus bool
SoC bool
GlobalTemperature float64
GPUTemperature float64
MemoryTemperature float64
Memory bool
Bus bool
SoC bool
}

type DeviceTemperature struct {
Expand Down