Get a workload.

GET

http://localhost:8080/api/v1/workloads/:workloadId

GET

/api/v1/workloads/:workloadId

curl http://localhost:8080/api/v1/workloads/workloadId \
     -H "Authorization: Bearer <token>"

{
  "tenantId": 1001,
  "runningPods": 1,
  "phaseUpdatedAt": "2022-06-08T11:28:24.131Z",
  "k8sPhaseUpdatedAt": "2022-06-08T11:28:24.131Z",
  "updatedAt": "2022-06-08T11:28:24.131Z",
  "source": "CLI",
  "deletedAt": "2022-08-12T19:28:24.131Z",
  "type": "runai-job",
  "name": "very-important-job",
  "id": "string",
  "priority": 50,
  "priorityClassName": "high-priority",
  "clusterId": "71f69d83-ba66-4822-adf5-55ce55efd210",
  "projectName": "proj-1",
  "projectId": "1",
  "departmentName": "department-1",
  "departmentId": "1",
  "namespace": "runai-proj-1",
  "createdAt": "2022-01-01T03:49:52.531Z",
  "phase": "Creating",
  "conditions": [
    {
      "type": "Ready",
      "status": "False",
      "message": "Resource validation failed: ...",
      "reason": "ErrorConfig",
      "lastTransitionTime": "2022-01-01T03:49:52.531Z"
    }
  ],
  "k8sPhase": "Pending",
  "category": "Train",
  "submittedBy": "researcher@run.ai",
  "workloadRequestedResources": {
    "gpuRequestType": "portion",
    "gpu": {
      "limit": 1.5,
      "request": 1
    },
    "gpuMemory": {
      "limit": "2G",
      "request": "200M"
    },
    "cpu": {
      "limit": 1.5,
      "request": 1
    },
    "cpuMemory": {
      "limit": "2G",
      "request": "200M"
    },
    "extendedResources": [
      {
        "resource": "hardware-vendor.example/foo",
        "quantity": "2",
        "exclude": false
      }
    ]
  },
  "podsRequestedResources": {
    "gpuRequestType": "portion",
    "gpu": {
      "limit": 1.5,
      "request": 1
    },
    "gpuMemory": {
      "limit": "2G",
      "request": "200M"
    },
    "cpu": {
      "limit": 1.5,
      "request": 1
    },
    "cpuMemory": {
      "limit": "2G",
      "request": "200M"
    },
    "extendedResources": [
      {
        "resource": "hardware-vendor.example/foo",
        "quantity": "2",
        "exclude": false
      }
    ]
  },
  "allocatedResources": {
    "gpu": 1.5,
    "gpuMemory": "200Mi",
    "cpu": 0.5,
    "cpuMemory": "0B",
    "extendedResources": [
      {
        "resource": "hardware-vendor.example/foo",
        "quantity": "2",
        "exclude": false
      }
    ]
  },
  "actionsSupport": {
    "delete": true,
    "suspend": true
  },
  "phaseMessage": "Not enough resources in the requested nodepool",
  "requestedPods": {
    "number": 1,
    "min": 2,
    "max": 5,
    "parallelism": 3,
    "completions": 5
  },
  "requestedNodePools": [
    "default"
  ],
  "currentNodePools": [
    "default"
  ],
  "completedAt": "2022-01-01T03:49:52.531Z",
  "images": [
    "alpine:latest"
  ],
  "urls": [
    "string"
  ],
  "datasources": [
    {
      "name": "my-pvc-datasource-1",
      "id": "string",
      "type": "pvc"
    }
  ],
  "environments": [
    {
      "name": "pytorch",
      "id": "string",
      "connections": [
        {
          "name": "my-pytorch-env",
          "toolType": "pytorch",
          "connectionType": "ExternalUrl",
          "url": "http://wandb.com/yourproject",
          "authorizationType": "public",
          "authorizedUsers": [
            "user@company.ai",
            "another@company.ai"
          ],
          "authorizedGroups": [
            "group-a",
            "group-b"
          ],
          "containerPort": 8080
        }
      ],
      "replicaType": "Master"
    }
  ],
  "externalConnections": [
    {
      "name": "my-pytorch-env",
      "toolType": "pytorch",
      "connectionType": "ExternalUrl",
      "url": "http://wandb.com/yourproject",
      "authorizationType": "public",
      "authorizedUsers": [
        "user@company.ai",
        "another@company.ai"
      ],
      "authorizedGroups": [
        "group-a",
        "group-b"
      ],
      "containerPort": 8080
    }
  ],
  "distributedFramework": "Pytorch",
  "additionalFields": {},
  "preemptible": true,
  "preemptibility": "non-preemptible",
  "environmentVariables": {},
  "command": "sleep",
  "arguments": "1000",
  "phaseReason": "string",
  "idleAllocatedGpus": 1,
  "totalPendingTimeSeconds": 60,
  "totalRunningTimeSeconds": 60,
  "guaranteedRuntimeEndsAt": "2025-08-01T03:49:52.531Z",
  "aiApplicationId": "string",
  "aiApplicationName": "string",
  "sourceApi": "WorkloadsV2",
  "topology": {
    "name": "string",
    "preferredPlacement": "string",
    "requiredPlacement": "string",
    "actualPlacement": {
      "level": "string",
      "value": "string"
    }
  },
  "endpoints": [
    {
      "host": "string",
      "port": 1,
      "path": "string",
      "tlsEnabled": true,
      "protocol": "string",
      "url": "string"
    }
  ],
  "kubernetesRef": {
    "group": "string",
    "version": "string"
  },
  "pendingSchedulingMessages": [
    {
      "nodePool": "default",
      "phaseReason": "NonPreemptibleOverQuota",
      "reason": "Non-preemptible over quota",
      "orgType": "string",
      "userMessage": "You have reached the limit of non-preemptible resources"
    }
  ]
}

Retrieve workload data using a workloadId.

Authentication

AuthorizationBearer

Bearer authentication

Path parameters

workloadIdstringRequiredformat: "uuid"

The Universally Unique Identifier (UUID) of the workload.

Response

Executed successfully.

tenantIdinteger

The id of the tenant.

runningPodsinteger

phaseUpdatedAtdatetime

k8sPhaseUpdatedAtdatetime

updatedAtdatetime

sourceenum

Allowed values:

deletedAtdatetime or null

typestring

namestring

idstringformat: "uuid"

priorityinteger or null

priorityClassNamestring

clusterIdstringformat: "uuid"

The id of the cluster.

projectNamestring

projectIdstring

departmentNamestring

departmentIdstring

namespacestring

createdAtdatetime

phaseenum

conditionslist of objects

k8sPhasestring

categorystring

Category Description

submittedBystringOptional

workloadRequestedResourcesobjectOptional

podsRequestedResourcesobjectOptional

allocatedResourcesobjectOptional

actionsSupportobjectOptional

The actions support provided for the workload.

phaseMessagestringOptional

requestedPodsobjectOptional

requestedNodePoolslist of stringsOptional

currentNodePoolslist of stringsOptional

completedAtdatetime or nullOptional

imageslist of stringsOptional

urlslist of stringsOptional

DEPRECATED: This field is deprecated. Use Get workload endpoints to retrieve workload network endpoints instead.Requires cluster version 2.25 or above.

datasourceslist of objectsOptional

environmentslist of objectsOptional

externalConnectionslist of objectsOptional

DEPRECATED: This field is deprecated. Use Get workload endpoints to retrieve workload network endpoints instead.Requires cluster version 2.25 or above.

distributedFrameworkstringOptional

additionalFieldsmap from strings to anyOptional

preemptibleboolean or nullOptional

preemptibilitystring or nullOptional

environmentVariablesmap from strings to stringsOptional

commandstringOptional

argumentsstringOptional

phaseReasonenum or nullOptional

Allowed values:

idleAllocatedGpusdouble or nullOptional

sum of idle allocated gpus in the workload

totalPendingTimeSecondsinteger or nullOptional

The total cumulative time, in seconds, that the workload has spent in the Pending phase since submission.

totalRunningTimeSecondsinteger or nullOptional

The total cumulative time, in seconds, that the workload has spent in the Running phase since submission.

guaranteedRuntimeEndsAtdatetime or nullOptional

A timestamp indicating when the workload will reach its minimum guaranteed runtime, as defined by minGuaranteedRuntime. Until this time, the workload is considered non-preemptible and cannot be interrupted by higher-priority workloads.

aiApplicationIdstringOptional

aiApplicationNamestringOptional

sourceApienumOptional

Allowed values:

topologyobject or nullOptional

The workload’s network topology. Populated whenever the workload requested topology constraints, or runs on nodepools associated with a network topology.

endpointslist of objectsOptional

List of network endpoints through which the workload is exposed.

kubernetesRefobjectOptional

Reference to the underlying Kubernetes object's API group and version. Null when not set.

pendingSchedulingMessageslist of objects or nullOptional

Errors

401

Unauthorized Error

403

Forbidden Error

404

Not Found Error

500

Internal Server Error

503

Service Unavailable Error