Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

Kasus penggunaan umum

{
    "ClusterName": "my-cluster",
    "InstanceGroups": [{
        "InstanceGroupName": "worker-group-1",
        "InstanceType": "ml.p4d.24xlarge",
        "InstanceCount": 4,
        "LifeCycleConfig": {
            "SourceS3Uri": "s3://my-bucket/lifecycle-config.sh",
            "OnCreate": "on-create.sh"
        },
        "ExecutionRole": "arn:aws:iam::123456789012:role/HyperPodExecutionRole",
        "ThreadsPerCore": 1,
        "KubernetesConfig": { 
            "Labels": {
                "env": "prod",
                "team": "ml-training",
                "gpu-type": "a100"
            },
            "Taints": [{
                "key": "gpu",
                "value": "true",
                "effect": "NoSchedule"
            },
            {
                "key": "dedicated",
                "value": "ml-workloads",
                "effect": "NoExecute"
            }]
        }
    }],
    "VpcConfig": {
        "SecurityGroupIds": ["sg-0123456789abcdef0"],
        "Subnets": ["subnet-0123456789abcdef0", "subnet-0123456789abcdef1"]
    },
    "Orchestrator": {
        "Eks": {
            "ClusterArn": "arn:aws:eks:us-west-2:123456789012:cluster/my-eks-cluster"
        }
    }
}

Dalam contoh ini:

{
    "ClusterName": "my-cluster",
    "InstanceGroups": [{
        "InstanceGroupName": "worker-group-1",
        "KubernetesConfig": { 
            "Labels": {
                "env": "prod",
                "team": "ml-training",
                "gpu-type": "a100",
                "cost-center": "ml-ops"
            },
            "Taints": [{
                "key": "gpu",
                "value": "true",
                "effect": "NoSchedule"
            }]
        }
    }]
}

{
    "ClusterName": "my-cluster",
    "ClusterStatus": "InService",
    "InstanceGroups": [{
        "InstanceGroupName": "worker-group-1",
        "InstanceType": "ml.p4d.24xlarge",
        "CurrentInstanceCount": 4,
        "TargetInstanceCount": 4,
        "KubernetesConfig": {
            "CurrentLabels": {
                "env": "prod",
                "team": "ml-training",
                "gpu-type": "a100"
            },
            "DesiredLabels": {
                "env": "prod",
                "team": "ml-training",
                "gpu-type": "a100"
            },
            "CurrentTaints": [{
                "key": "gpu",
                "value": "true",
                "effect": "NoSchedule"
            }],
            "DesiredTaints": [{
                "key": "gpu",
                "value": "true",
                "effect": "NoSchedule"
            }]
        }
    }]
}

{
    "NodeDetails": { 
        "InstanceId": "i-0123456789abcdef0",
        "InstanceGroupName": "worker-group-1",
        "InstanceType": "ml.p4d.24xlarge",
        "InstanceStatus": {
            "Status": "Running",
            "Message": "Node is healthy"
        },
        "LifeCycleConfig": {
            "SourceS3Uri": "s3://my-bucket/lifecycle-config.sh",
            "OnCreate": "on-create.sh"
        },
        "LaunchTime": 1699564800.0,
        "KubernetesConfig": {
            "CurrentLabels": {
                "env": "prod",
                "team": "ml-training",
                "gpu-type": "a100"
            },
            "DesiredLabels": {
                "env": "prod",
                "team": "ml-training",
                "gpu-type": "a100"
            },
            "CurrentTaints": [{
                "key": "gpu",
                "value": "true",
                "effect": "NoSchedule"
            }],
            "DesiredTaints": [{
                "key": "gpu",
                "value": "true",
                "effect": "NoSchedule"
            }]
        }
    }
}