Skip to content

Add UltraServer support for CloudWatch agent #1571

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 9 commits into
base: main
Choose a base branch
from
Open

Add UltraServer support for CloudWatch agent #1571

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
d57685e
Add UltraServer support for CloudWatch agent
petruanica Feb 26, 2025
166704b
Add fmt changes
petruanica Feb 26, 2025
d172274
Merge branch 'main' into feat-ultraserver-tupperware-support
petruanica Mar 3, 2025
954d78f
Merge branch 'main' into feat-ultraserver-tupperware-support
petruanica Mar 4, 2025
06053ca
Merge branch 'aws:main' into feat-ultraserver-tupperware-support
petruanica Mar 4, 2025
e8eb480
Merge branch 'main' into feat-ultraserver-tupperware-support
petruanica Mar 5, 2025
a3d5799
Merge branch 'main' into feat-ultraserver-tupperware-support
petruanica Mar 7, 2025
9836c91
Merge branch 'main' into feat-ultraserver-tupperware-support
petruanica Mar 14, 2025
06f23cc
Merge branch 'main' into feat-ultraserver-tupperware-support
petruanica Mar 19, 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
1 change: 1 addition & 0 deletions internal/containerinsightscommon/const.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@ const (
MetricType = "Type"
SourcesKey = "Sources"
GpuDeviceKey = "GpuDevice"
UltraServerKey = "UltraServer"

ClusterQueueNameKey = "ClusterQueue"
ClusterQueueStatusKey = "Status"
Expand Down
27 changes: 15 additions & 12 deletions plugins/processors/gpuattributes/internal/metricFilters/gpumetricfilters.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,10 +104,11 @@ var PodNeuronLabelFilter = map[string]map[string]interface{}{
pod_owners: nil,
containerinsightscommon.K8sLabelsKey: nil,
},
internal.Region: nil,
internal.SubnetId: nil,
internal.NeuronCore: nil,
containerinsightscommon.MetricType: nil,
internal.Region: nil,
internal.SubnetId: nil,
internal.NeuronCore: nil,
containerinsightscommon.MetricType: nil,
containerinsightscommon.UltraServerKey: nil,
}

var ContainerNeuronLabelFilter = map[string]map[string]interface{}{
Expand All @@ -130,10 +131,11 @@ var ContainerNeuronLabelFilter = map[string]map[string]interface{}{
pod_owners: nil,
containerinsightscommon.K8sLabelsKey: nil,
},
internal.Region: nil,
internal.SubnetId: nil,
internal.NeuronCore: nil,
containerinsightscommon.MetricType: nil,
internal.Region: nil,
internal.SubnetId: nil,
internal.NeuronCore: nil,
containerinsightscommon.MetricType: nil,
containerinsightscommon.UltraServerKey: nil,
}

var NodeNeuronLabelFilter = map[string]map[string]interface{}{
Expand All @@ -149,8 +151,9 @@ var NodeNeuronLabelFilter = map[string]map[string]interface{}{
containerinsightscommon.HostKey: nil,
containerinsightscommon.K8sLabelsKey: nil,
},
internal.Region: nil,
internal.SubnetId: nil,
internal.NeuronCore: nil,
containerinsightscommon.MetricType: nil,
internal.Region: nil,
internal.SubnetId: nil,
internal.NeuronCore: nil,
containerinsightscommon.MetricType: nil,
containerinsightscommon.UltraServerKey: nil,
}
6 changes: 6 additions & 0 deletions translator/tocwconfig/sampleConfig/emf_and_kubernetes_with_gpu_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -478,6 +478,8 @@ exporters:
- pod_neurondevice_hw_ecc_events_total
- dimensions:
- - ClusterName
- - ClusterName
- UltraServer
- - ClusterName
- InstanceId
- NodeName
Expand All @@ -497,6 +499,8 @@ exporters:
- node_neuroncore_memory_usage_tensors
- dimensions:
- - ClusterName
- - ClusterName
- UltraServer
- - ClusterName
- InstanceId
- NodeName
Expand All @@ -506,6 +510,8 @@ exporters:
- node_neuron_execution_latency
- dimensions:
- - ClusterName
- - ClusterName
- UltraServer
- - ClusterName
- InstanceId
- NodeName
Expand Down
6 changes: 3 additions & 3 deletions translator/translate/otel/exporter/awsemf/kubernetes.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -560,7 +560,7 @@ func getAwsNeuronMetricDeclarations(conf *confmap.Conf) []*awsemfexporter.Metric
},
},
{
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "InstanceId", "NodeName"}, {"ClusterName", "InstanceType", "InstanceId", "NodeName", "NeuronDevice", "NeuronCore"}},
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "UltraServer"}, {"ClusterName", "InstanceId", "NodeName"}, {"ClusterName", "InstanceType", "InstanceId", "NodeName", "NeuronDevice", "NeuronCore"}},
MetricNameSelectors: []string{
"node_neuroncore_utilization",
"node_neuroncore_memory_usage_total",
Expand All @@ -572,15 +572,15 @@ func getAwsNeuronMetricDeclarations(conf *confmap.Conf) []*awsemfexporter.Metric
},
},
{
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "InstanceId", "NodeName"}},
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "UltraServer"}, {"ClusterName", "InstanceId", "NodeName"}},
MetricNameSelectors: []string{
"node_neuron_execution_errors_total",
"node_neurondevice_runtime_memory_used_bytes",
"node_neuron_execution_latency",
},
},
{
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "InstanceId", "NodeName"}, {"ClusterName", "InstanceId", "NodeName", "NeuronDevice"}},
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "UltraServer"}, {"ClusterName", "InstanceId", "NodeName"}, {"ClusterName", "InstanceId", "NodeName", "NeuronDevice"}},
MetricNameSelectors: []string{
"node_neurondevice_hw_ecc_events_total",
},
Expand Down
6 changes: 3 additions & 3 deletions translator/translate/otel/exporter/awsemf/translator_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -457,7 +457,7 @@ func TestTranslator(t *testing.T) {
},
},
{
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "InstanceId", "NodeName"}, {"ClusterName", "InstanceType", "InstanceId", "NodeName", "NeuronDevice", "NeuronCore"}},
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "UltraServer"}, {"ClusterName", "InstanceId", "NodeName"}, {"ClusterName", "InstanceType", "InstanceId", "NodeName", "NeuronDevice", "NeuronCore"}},
MetricNameSelectors: []string{
"node_neuroncore_utilization",
"node_neuroncore_memory_usage_total",
Expand All @@ -469,15 +469,15 @@ func TestTranslator(t *testing.T) {
},
},
{
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "InstanceId", "NodeName"}},
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "UltraServer"}, {"ClusterName", "InstanceId", "NodeName"}},
MetricNameSelectors: []string{
"node_neuron_execution_errors_total",
"node_neurondevice_runtime_memory_used_bytes",
"node_neuron_execution_latency",
},
},
{
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "InstanceId", "NodeName"}, {"ClusterName", "InstanceId", "NodeName", "NeuronDevice"}},
Dimensions: [][]string{{"ClusterName"}, {"ClusterName", "UltraServer"}, {"ClusterName", "InstanceId", "NodeName"}, {"ClusterName", "InstanceId", "NodeName", "NeuronDevice"}},
MetricNameSelectors: []string{
"node_neurondevice_hw_ecc_events_total",
},
Expand Down