Skip to content

Add enhanced CI check and nil checks for neuron decorators #377

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
wants to merge 2 commits into
base: aws-cwa-dev
Choose a base branch
from
+39 −16
Open

Add enhanced CI check and nil checks for neuron decorators #377

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
abf485f
Add enhanced CI check and nil checks for neuron decorators
sky333999 Oct 24, 2025
77ac962
Merge branch 'aws-cwa-dev' into sky333999/neuron-fix
sky333999 Oct 27, 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
21 changes: 21 additions & 0 deletions receiver/awscontainerinsightreceiver/internal/stores/nodeinfo.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,6 +96,9 @@ func (n *nodeInfo) getNodeStats() nodeStats {
}

func (n *nodeInfo) getNodeStatusCapacityPods() (uint64, bool) {
if n.provider == nil {
return 0, false
}
capacityResources, ok := n.provider.NodeToCapacityMap()[n.nodeName]
if !ok {
return 0, false
Expand All @@ -105,6 +108,9 @@ func (n *nodeInfo) getNodeStatusCapacityPods() (uint64, bool) {
}

func (n *nodeInfo) getNodeStatusAllocatablePods() (uint64, bool) {
if n.provider == nil {
return 0, false
}
allocatableResources, ok := n.provider.NodeToAllocatableMap()[n.nodeName]
if !ok {
return 0, false
Expand All @@ -114,6 +120,9 @@ func (n *nodeInfo) getNodeStatusAllocatablePods() (uint64, bool) {
}

func (n *nodeInfo) getNodeStatusCapacityGPUs() (uint64, bool) {
if n.provider == nil {
return 0, false
}
capacityResources, ok := n.provider.NodeToCapacityMap()[n.nodeName]
if !ok {
return 0, false
Expand All @@ -123,6 +132,9 @@ func (n *nodeInfo) getNodeStatusCapacityGPUs() (uint64, bool) {
}

func (n *nodeInfo) getNodeStatusCapacityEfas() (uint64, bool) {
if n.provider == nil {
return 0, false
}
capacityResources, ok := n.provider.NodeToCapacityMap()[n.nodeName]
if !ok {
return 0, false
Expand All @@ -132,6 +144,9 @@ func (n *nodeInfo) getNodeStatusCapacityEfas() (uint64, bool) {
}

func (n *nodeInfo) getNeuronResourceCapacity(resourceKey v1.ResourceName) (uint64, bool) {
if n.provider == nil {
return 0, false
}
capacityResources, ok := n.provider.NodeToCapacityMap()[n.nodeName]
if !ok {
return 0, false
Expand Down Expand Up @@ -184,6 +199,9 @@ func (n *nodeInfo) getNodeStatusCapacityNeuronCores() (uint64, bool) {
}

func (n *nodeInfo) getNodeStatusCondition(conditionType v1.NodeConditionType) (uint64, bool) {
if n.provider == nil {
return 0, false
}
if nodeConditions, ok := n.provider.NodeToConditionsMap()[n.nodeName]; ok {
if conditionStatus, ok := nodeConditions[conditionType]; ok {
if conditionStatus == v1.ConditionTrue {
Expand All @@ -196,6 +214,9 @@ func (n *nodeInfo) getNodeStatusCondition(conditionType v1.NodeConditionType) (u
}

func (n *nodeInfo) getNodeConditionUnknown() (uint64, bool) {
if n.provider == nil {
return 0, false
}
if nodeConditions, ok := n.provider.NodeToConditionsMap()[n.nodeName]; ok {
for _, conditionStatus := range nodeConditions {
if conditionStatus == v1.ConditionUnknown {
Expand Down
34 changes: 18 additions & 16 deletions receiver/awscontainerinsightreceiver/internal/stores/podstore.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,24 +322,26 @@ func (p *PodStore) refreshInternal(now time.Time, podList []corev1.Pod) {
cpuRequest += tmpCPUReq
tmpMemReq, _ := getResourceSettingForPod(&pod, p.nodeInfo.getMemCapacity(), memoryKey, getRequestForContainer)
memRequest += tmpMemReq
if coresLimit, coresReq, hasNeuron := p.getNeuronCoresFromPod(&pod); hasNeuron {
neuroncoreRequest += coresReq
if pod.Status.Phase == corev1.PodRunning {
neuroncoreUsageTotal += coresLimit
if p.includeEnhancedMetrics && p.enableAcceleratedComputeMetrics {
if coresLimit, coresReq, hasNeuron := p.getNeuronCoresFromPod(&pod); hasNeuron {
neuroncoreRequest += coresReq
if pod.Status.Phase == corev1.PodRunning {
neuroncoreUsageTotal += coresLimit
}
}
}
if tmpGpuLimit, ok := getResourceSettingForPod(&pod, 0, gpuKey, getLimitForContainer); ok {
tmpGpuReq, _ := getResourceSettingForPod(&pod, 0, gpuKey, getRequestForContainer)
gpuRequest += tmpGpuReq
if pod.Status.Phase == corev1.PodRunning {
gpuUsageTotal += tmpGpuLimit
if tmpGpuLimit, ok := getResourceSettingForPod(&pod, 0, gpuKey, getLimitForContainer); ok {
tmpGpuReq, _ := getResourceSettingForPod(&pod, 0, gpuKey, getRequestForContainer)
gpuRequest += tmpGpuReq
if pod.Status.Phase == corev1.PodRunning {
gpuUsageTotal += tmpGpuLimit
}
}
}
if tmpEfaLimit, ok := getResourceSettingForPod(&pod, 0, efaKey, getLimitForContainer); ok {
tmpEfaReq, _ := getResourceSettingForPod(&pod, 0, efaKey, getRequestForContainer)
efaRequest += tmpEfaReq
if pod.Status.Phase == corev1.PodRunning {
efaUsageTotal += tmpEfaLimit
if tmpEfaLimit, ok := getResourceSettingForPod(&pod, 0, efaKey, getLimitForContainer); ok {
tmpEfaReq, _ := getResourceSettingForPod(&pod, 0, efaKey, getRequestForContainer)
efaRequest += tmpEfaReq
if pod.Status.Phase == corev1.PodRunning {
efaUsageTotal += tmpEfaLimit
}
}
}
}
Expand Down
Loading