Index: discovery/googleapis_beta/dataproc__v1beta1.json |
diff --git a/discovery/googleapis_beta/dataproc__v1beta1.json b/discovery/googleapis_beta/dataproc__v1beta1.json |
index 4db858738a6f9ee84eda2e9c6d2ce2880125f097..9c5bf10b0a258fac6b3d14325d4a7e784cc9284f 100644 |
--- a/discovery/googleapis_beta/dataproc__v1beta1.json |
+++ b/discovery/googleapis_beta/dataproc__v1beta1.json |
@@ -24,22 +24,16 @@ |
"ownerDomain": "google.com", |
"ownerName": "Google", |
"parameters": { |
- "pp": { |
- "default": "true", |
- "description": "Pretty-print response.", |
+ "oauth_token": { |
+ "description": "OAuth 2.0 token for the current user.", |
"location": "query", |
- "type": "boolean" |
+ "type": "string" |
}, |
"bearer_token": { |
"description": "OAuth bearer token.", |
"location": "query", |
"type": "string" |
}, |
- "oauth_token": { |
- "description": "OAuth 2.0 token for the current user.", |
- "location": "query", |
- "type": "string" |
- }, |
"upload_protocol": { |
"description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", |
"location": "query", |
@@ -61,11 +55,6 @@ |
"location": "query", |
"type": "string" |
}, |
- "callback": { |
- "description": "JSONP", |
- "location": "query", |
- "type": "string" |
- }, |
"$.xgafv": { |
"description": "V1 error format.", |
"enum": [ |
@@ -79,6 +68,11 @@ |
"location": "query", |
"type": "string" |
}, |
+ "callback": { |
+ "description": "JSONP", |
+ "location": "query", |
+ "type": "string" |
+ }, |
"alt": { |
"default": "json", |
"description": "Data format for response.", |
@@ -109,6 +103,12 @@ |
"description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.", |
"location": "query", |
"type": "string" |
+ }, |
+ "pp": { |
+ "default": "true", |
+ "description": "Pretty-print response.", |
+ "location": "query", |
+ "type": "boolean" |
} |
}, |
"protocol": "rest", |
@@ -234,200 +234,215 @@ |
}, |
"projects": { |
"resources": { |
- "clusters": { |
+ "jobs": { |
"methods": { |
- "create": { |
- "description": "Creates a cluster in a project.", |
+ "submit": { |
+ "description": "Submits a job to a cluster.", |
"httpMethod": "POST", |
- "id": "dataproc.projects.clusters.create", |
+ "id": "dataproc.projects.jobs.submit", |
"parameterOrder": [ |
"projectId" |
], |
"parameters": { |
"projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/clusters", |
+ "path": "v1beta1/projects/{projectId}/jobs:submit", |
"request": { |
- "$ref": "Cluster" |
+ "$ref": "SubmitJobRequest" |
}, |
"response": { |
- "$ref": "Operation" |
+ "$ref": "Job" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
- "patch": { |
- "description": "Updates a cluster in a project.", |
- "httpMethod": "PATCH", |
- "id": "dataproc.projects.clusters.patch", |
+ "delete": { |
+ "description": "Deletes the job from the project. If the job is active, the delete fails, and the response returns FAILED_PRECONDITION.", |
+ "httpMethod": "DELETE", |
+ "id": "dataproc.projects.jobs.delete", |
"parameterOrder": [ |
"projectId", |
- "clusterName" |
+ "jobId" |
], |
"parameters": { |
- "clusterName": { |
- "description": "Required The cluster name.", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "projectId": { |
- "description": "Required The ID of the Google Cloud Platform project the cluster belongs to.", |
+ "jobId": { |
+ "description": "Required The job ID.", |
"location": "path", |
"required": true, |
"type": "string" |
- }, |
- "updateMask": { |
- "description": "Required Specifies the path, relative to <code>Cluster</code>, of the field to update. For example, to change the number of workers in a cluster to 5, the <code>update_mask</code> parameter would be specified as <code>configuration.worker_configuration.num_instances</code>, and the PATCH request body would specify the new value, as follows:\n{\n \"configuration\":{\n \"workerConfiguration\":{\n \"numInstances\":\"5\"\n }\n }\n}\nSimilarly, to change the number of preemptible workers in a cluster to 5, the <code>update_mask</code> parameter would be <code>config.secondary_worker_config.num_instances</code>, and the PATCH request body would be set as follows:\n{\n \"config\":{\n \"secondaryWorkerConfig\":{\n \"numInstances\":\"5\"\n }\n }\n}\n<strong>Note:</strong> Currently, <code>config.worker_config.num_instances</code> and <code>config.secondary_worker_config.num_instances</code> are the only fields that can be updated.", |
- "format": "google-fieldmask", |
- "location": "query", |
- "type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/clusters/{clusterName}", |
- "request": { |
- "$ref": "Cluster" |
- }, |
+ "path": "v1beta1/projects/{projectId}/jobs/{jobId}", |
"response": { |
- "$ref": "Operation" |
+ "$ref": "Empty" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
- "get": { |
- "description": "Gets the resource representation for a cluster in a project.", |
+ "list": { |
+ "description": "Lists jobs in a project.", |
"httpMethod": "GET", |
- "id": "dataproc.projects.clusters.get", |
+ "id": "dataproc.projects.jobs.list", |
"parameterOrder": [ |
- "projectId", |
- "clusterName" |
+ "projectId" |
], |
"parameters": { |
+ "filter": { |
+ "description": "Optional A filter constraining which jobs to list. Valid filters contain job state and label terms such as: labels.key1 = val1 AND (labels.k2 = val2 OR labels.k3 = val3)", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "jobStateMatcher": { |
+ "description": "Optional Specifies enumerated categories of jobs to list.", |
+ "enum": [ |
+ "ALL", |
+ "ACTIVE", |
+ "NON_ACTIVE" |
+ ], |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "pageToken": { |
+ "description": "Optional The page token, returned by a previous call, to request the next page of results.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "pageSize": { |
+ "description": "Optional The number of results to return in each response.", |
+ "format": "int32", |
+ "location": "query", |
+ "type": "integer" |
+ }, |
"clusterName": { |
- "description": "Required The cluster name.", |
- "location": "path", |
- "required": true, |
+ "description": "Optional If set, the returned jobs list includes only jobs that were submitted to the named cluster.", |
+ "location": "query", |
"type": "string" |
}, |
"projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/clusters/{clusterName}", |
+ "path": "v1beta1/projects/{projectId}/jobs", |
"response": { |
- "$ref": "Cluster" |
+ "$ref": "ListJobsResponse" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
- "delete": { |
- "description": "Deletes a cluster in a project.", |
- "httpMethod": "DELETE", |
- "id": "dataproc.projects.clusters.delete", |
+ "cancel": { |
+ "description": "Starts a job cancellation request. To access the job resource after cancellation, call jobs.list or jobs.get.", |
+ "httpMethod": "POST", |
+ "id": "dataproc.projects.jobs.cancel", |
"parameterOrder": [ |
"projectId", |
- "clusterName" |
+ "jobId" |
], |
"parameters": { |
- "clusterName": { |
- "description": "Required The cluster name.", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "jobId": { |
+ "description": "Required The job ID.", |
"location": "path", |
"required": true, |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/clusters/{clusterName}", |
+ "path": "v1beta1/projects/{projectId}/jobs/{jobId}:cancel", |
+ "request": { |
+ "$ref": "CancelJobRequest" |
+ }, |
"response": { |
- "$ref": "Operation" |
+ "$ref": "Job" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
- "diagnose": { |
- "description": "Gets cluster diagnostic information. After the operation completes, the Operation.response field contains DiagnoseClusterOutputLocation.", |
- "httpMethod": "POST", |
- "id": "dataproc.projects.clusters.diagnose", |
+ "patch": { |
+ "description": "Updates a job in a project.", |
+ "httpMethod": "PATCH", |
+ "id": "dataproc.projects.jobs.patch", |
"parameterOrder": [ |
"projectId", |
- "clusterName" |
+ "jobId" |
], |
"parameters": { |
- "clusterName": { |
- "description": "Required The cluster name.", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "jobId": { |
+ "description": "Required The job ID.", |
"location": "path", |
"required": true, |
"type": "string" |
+ }, |
+ "updateMask": { |
+ "description": "Required Specifies the path, relative to <code>Job</code>, of the field to update. For example, to update the labels of a Job the <code>update_mask</code> parameter would be specified as <code>labels</code>, and the PATCH request body would specify the new value. <strong>Note:</strong> Currently, <code>labels</code> is the only field that can be updated.", |
+ "format": "google-fieldmask", |
+ "location": "query", |
+ "type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/clusters/{clusterName}:diagnose", |
+ "path": "v1beta1/projects/{projectId}/jobs/{jobId}", |
"request": { |
- "$ref": "DiagnoseClusterRequest" |
+ "$ref": "Job" |
}, |
"response": { |
- "$ref": "Operation" |
+ "$ref": "Job" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
- "list": { |
- "description": "Lists all clusters in a project.", |
+ "get": { |
+ "description": "Gets the resource representation for a job in a project.", |
"httpMethod": "GET", |
- "id": "dataproc.projects.clusters.list", |
+ "id": "dataproc.projects.jobs.get", |
"parameterOrder": [ |
- "projectId" |
+ "projectId", |
+ "jobId" |
], |
"parameters": { |
- "filter": { |
- "description": "Optional A filter constraining which clusters to list. Valid filters contain label terms such as: labels.key1 = val1 AND (-labels.k2 = val2 OR labels.k3 = val3)", |
- "location": "query", |
- "type": "string" |
- }, |
- "pageToken": { |
- "description": "The standard List page token.", |
- "location": "query", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
+ "location": "path", |
+ "required": true, |
"type": "string" |
}, |
- "pageSize": { |
- "description": "The standard List page size.", |
- "format": "int32", |
- "location": "query", |
- "type": "integer" |
- }, |
- "projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "jobId": { |
+ "description": "Required The job ID.", |
"location": "path", |
"required": true, |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/clusters", |
+ "path": "v1beta1/projects/{projectId}/jobs/{jobId}", |
"response": { |
- "$ref": "ListClustersResponse" |
+ "$ref": "Job" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
@@ -435,215 +450,200 @@ |
} |
} |
}, |
- "jobs": { |
+ "clusters": { |
"methods": { |
"get": { |
- "description": "Gets the resource representation for a job in a project.", |
+ "description": "Gets the resource representation for a cluster in a project.", |
"httpMethod": "GET", |
- "id": "dataproc.projects.jobs.get", |
+ "id": "dataproc.projects.clusters.get", |
"parameterOrder": [ |
"projectId", |
- "jobId" |
+ "clusterName" |
], |
"parameters": { |
- "projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
+ "clusterName": { |
+ "description": "Required The cluster name.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "jobId": { |
- "description": "Required The job ID.", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/jobs/{jobId}", |
+ "path": "v1beta1/projects/{projectId}/clusters/{clusterName}", |
"response": { |
- "$ref": "Job" |
+ "$ref": "Cluster" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
"patch": { |
- "description": "Updates a job in a project.", |
+ "description": "Updates a cluster in a project.", |
"httpMethod": "PATCH", |
- "id": "dataproc.projects.jobs.patch", |
+ "id": "dataproc.projects.clusters.patch", |
"parameterOrder": [ |
"projectId", |
- "jobId" |
+ "clusterName" |
], |
"parameters": { |
- "updateMask": { |
- "description": "Required Specifies the path, relative to <code>Job</code>, of the field to update. For example, to update the labels of a Job the <code>update_mask</code> parameter would be specified as <code>labels</code>, and the PATCH request body would specify the new value. <strong>Note:</strong> Currently, <code>labels</code> is the only field that can be updated.", |
- "format": "google-fieldmask", |
- "location": "query", |
+ "clusterName": { |
+ "description": "Required The cluster name.", |
+ "location": "path", |
+ "required": true, |
"type": "string" |
}, |
"projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
+ "description": "Required The ID of the Google Cloud Platform project the cluster belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "jobId": { |
- "description": "Required The job ID.", |
- "location": "path", |
- "required": true, |
+ "updateMask": { |
+ "description": "Required Specifies the path, relative to <code>Cluster</code>, of the field to update. For example, to change the number of workers in a cluster to 5, the <code>update_mask</code> parameter would be specified as <code>configuration.worker_configuration.num_instances</code>, and the PATCH request body would specify the new value, as follows:\n{\n \"configuration\":{\n \"workerConfiguration\":{\n \"numInstances\":\"5\"\n }\n }\n}\nSimilarly, to change the number of preemptible workers in a cluster to 5, the <code>update_mask</code> parameter would be <code>config.secondary_worker_config.num_instances</code>, and the PATCH request body would be set as follows:\n{\n \"config\":{\n \"secondaryWorkerConfig\":{\n \"numInstances\":\"5\"\n }\n }\n}\n<strong>Note:</strong> Currently, <code>config.worker_config.num_instances</code> and <code>config.secondary_worker_config.num_instances</code> are the only fields that can be updated.", |
+ "format": "google-fieldmask", |
+ "location": "query", |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/jobs/{jobId}", |
+ "path": "v1beta1/projects/{projectId}/clusters/{clusterName}", |
"request": { |
- "$ref": "Job" |
+ "$ref": "Cluster" |
}, |
"response": { |
- "$ref": "Job" |
+ "$ref": "Operation" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
- "submit": { |
- "description": "Submits a job to a cluster.", |
+ "diagnose": { |
+ "description": "Gets cluster diagnostic information. After the operation completes, the Operation.response field contains DiagnoseClusterOutputLocation.", |
"httpMethod": "POST", |
- "id": "dataproc.projects.jobs.submit", |
+ "id": "dataproc.projects.clusters.diagnose", |
"parameterOrder": [ |
- "projectId" |
+ "projectId", |
+ "clusterName" |
], |
"parameters": { |
+ "clusterName": { |
+ "description": "Required The cluster name.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
+ }, |
"projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
+ "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/jobs:submit", |
+ "path": "v1beta1/projects/{projectId}/clusters/{clusterName}:diagnose", |
"request": { |
- "$ref": "SubmitJobRequest" |
+ "$ref": "DiagnoseClusterRequest" |
}, |
"response": { |
- "$ref": "Job" |
+ "$ref": "Operation" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
"delete": { |
- "description": "Deletes the job from the project. If the job is active, the delete fails, and the response returns FAILED_PRECONDITION.", |
+ "description": "Deletes a cluster in a project.", |
"httpMethod": "DELETE", |
- "id": "dataproc.projects.jobs.delete", |
+ "id": "dataproc.projects.clusters.delete", |
"parameterOrder": [ |
"projectId", |
- "jobId" |
+ "clusterName" |
], |
"parameters": { |
- "projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
+ "clusterName": { |
+ "description": "Required The cluster name.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "jobId": { |
- "description": "Required The job ID.", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/jobs/{jobId}", |
+ "path": "v1beta1/projects/{projectId}/clusters/{clusterName}", |
"response": { |
- "$ref": "Empty" |
+ "$ref": "Operation" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
"list": { |
- "description": "Lists jobs in a project.", |
+ "description": "Lists all clusters in a project.", |
"httpMethod": "GET", |
- "id": "dataproc.projects.jobs.list", |
+ "id": "dataproc.projects.clusters.list", |
"parameterOrder": [ |
"projectId" |
], |
"parameters": { |
+ "filter": { |
+ "description": "Optional A filter constraining which clusters to list. Valid filters contain label terms such as: labels.key1 = val1 AND (-labels.k2 = val2 OR labels.k3 = val3)", |
+ "location": "query", |
+ "type": "string" |
+ }, |
"pageToken": { |
- "description": "Optional The page token, returned by a previous call, to request the next page of results.", |
+ "description": "The standard List page token.", |
"location": "query", |
"type": "string" |
}, |
"pageSize": { |
- "description": "Optional The number of results to return in each response.", |
+ "description": "The standard List page size.", |
"format": "int32", |
"location": "query", |
"type": "integer" |
}, |
- "clusterName": { |
- "description": "Optional If set, the returned jobs list includes only jobs that were submitted to the named cluster.", |
- "location": "query", |
- "type": "string" |
- }, |
"projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
+ "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
- }, |
- "filter": { |
- "description": "Optional A filter constraining which jobs to list. Valid filters contain job state and label terms such as: labels.key1 = val1 AND (labels.k2 = val2 OR labels.k3 = val3)", |
- "location": "query", |
- "type": "string" |
- }, |
- "jobStateMatcher": { |
- "description": "Optional Specifies enumerated categories of jobs to list.", |
- "enum": [ |
- "ALL", |
- "ACTIVE", |
- "NON_ACTIVE" |
- ], |
- "location": "query", |
- "type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/jobs", |
+ "path": "v1beta1/projects/{projectId}/clusters", |
"response": { |
- "$ref": "ListJobsResponse" |
+ "$ref": "ListClustersResponse" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
- "cancel": { |
- "description": "Starts a job cancellation request. To access the job resource after cancellation, call jobs.list or jobs.get.", |
+ "create": { |
+ "description": "Creates a cluster in a project.", |
"httpMethod": "POST", |
- "id": "dataproc.projects.jobs.cancel", |
+ "id": "dataproc.projects.clusters.create", |
"parameterOrder": [ |
- "projectId", |
- "jobId" |
+ "projectId" |
], |
"parameters": { |
"projectId": { |
- "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
- "location": "path", |
- "required": true, |
- "type": "string" |
- }, |
- "jobId": { |
- "description": "Required The job ID.", |
+ "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/jobs/{jobId}:cancel", |
+ "path": "v1beta1/projects/{projectId}/clusters", |
"request": { |
- "$ref": "CancelJobRequest" |
+ "$ref": "Cluster" |
}, |
"response": { |
- "$ref": "Job" |
+ "$ref": "Operation" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
@@ -654,28 +654,145 @@ |
} |
} |
}, |
- "revision": "20170207", |
+ "revision": "20170228", |
"rootUrl": "https://dataproc.googleapis.com/", |
"schemas": { |
- "GceClusterConfiguration": { |
- "description": "Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster.", |
- "id": "GceClusterConfiguration", |
+ "ClusterMetrics": { |
+ "description": "Contains cluster daemon metrics, such as HDFS and YARN stats.", |
+ "id": "ClusterMetrics", |
+ "properties": { |
+ "yarnMetrics": { |
+ "additionalProperties": { |
+ "format": "int64", |
+ "type": "string" |
+ }, |
+ "description": "The YARN metrics.", |
+ "type": "object" |
+ }, |
+ "hdfsMetrics": { |
+ "additionalProperties": { |
+ "format": "int64", |
+ "type": "string" |
+ }, |
+ "description": "The HDFS metrics.", |
+ "type": "object" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "ClusterConfiguration": { |
+ "description": "The cluster configuration.", |
+ "id": "ClusterConfiguration", |
+ "properties": { |
+ "masterConfiguration": { |
+ "$ref": "InstanceGroupConfiguration", |
+ "description": "Optional The Google Compute Engine configuration settings for the master instance in a cluster." |
+ }, |
+ "secondaryWorkerConfiguration": { |
+ "$ref": "InstanceGroupConfiguration", |
+ "description": "Optional The Google Compute Engine configuration settings for additional worker instances in a cluster." |
+ }, |
+ "initializationActions": { |
+ "description": "Optional Commands to execute on each node after configuration is completed. By default, executables are run on master and all worker nodes. You can test a node's <code>role</code> metadata to run an executable on a master or worker node, as shown below:\nROLE=$(/usr/share/google/get_metadata_value attributes/role)\nif [[ \"${ROLE}\" == 'Master' ]]; then\n ... master specific actions ...\nelse\n ... worker specific actions ...\nfi\n", |
+ "items": { |
+ "$ref": "NodeInitializationAction" |
+ }, |
+ "type": "array" |
+ }, |
+ "workerConfiguration": { |
+ "$ref": "InstanceGroupConfiguration", |
+ "description": "Optional The Google Compute Engine configuration settings for worker instances in a cluster." |
+ }, |
+ "softwareConfiguration": { |
+ "$ref": "SoftwareConfiguration", |
+ "description": "Optional The configuration settings for software inside the cluster." |
+ }, |
+ "gceClusterConfiguration": { |
+ "$ref": "GceClusterConfiguration", |
+ "description": "Required The shared Google Compute Engine configuration settings for all instances in a cluster." |
+ }, |
+ "configurationBucket": { |
+ "description": "Optional A Google Cloud Storage staging bucket used for sharing generated SSH keys and configuration. If you do not specify a staging bucket, Cloud Dataproc will determine an appropriate Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Google Compute Engine zone where your cluster is deployed, and then it will create and manage this project-level, per-location bucket for you.", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "LoggingConfiguration": { |
+ "description": "The runtime logging configuration of the job.", |
+ "id": "LoggingConfiguration", |
"properties": { |
- "tags": { |
- "description": "The Google Compute Engine tags to add to all instances.", |
- "items": { |
+ "driverLogLevels": { |
+ "additionalProperties": { |
+ "enum": [ |
+ "LEVEL_UNSPECIFIED", |
+ "ALL", |
+ "TRACE", |
+ "DEBUG", |
+ "INFO", |
+ "WARN", |
+ "ERROR", |
+ "FATAL", |
+ "OFF" |
+ ], |
"type": "string" |
}, |
- "type": "array" |
+ "description": "The per-package log levels for the driver. This may include \"root\" package name to configure rootLogger. Examples: 'com.google = FATAL', 'root = INFO', 'org.apache = DEBUG'", |
+ "type": "object" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "InstanceGroupConfiguration": { |
+ "description": "The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group.", |
+ "id": "InstanceGroupConfiguration", |
+ "properties": { |
+ "numInstances": { |
+ "description": "The number of VM instances in the instance group. For master instance groups, must be set to 1.", |
+ "format": "int32", |
+ "type": "integer" |
}, |
- "serviceAccount": { |
- "description": "Optional The service account of the instances. Defaults to the default Google Compute Engine service account. Custom service accounts need permissions equivalent to the folloing IAM roles:\nroles/logging.logWriter\nroles/storage.objectAdmin(see https://cloud.google.com/compute/docs/access/service-accounts#custom_service_accounts for more information). Example: [account_id]@[project_id].iam.gserviceaccount.com", |
+ "diskConfiguration": { |
+ "$ref": "DiskConfiguration", |
+ "description": "Disk option configuration settings." |
+ }, |
+ "isPreemptible": { |
+ "description": "Specifies that this instance group contains Preemptible Instances.", |
+ "type": "boolean" |
+ }, |
+ "imageUri": { |
+ "description": "Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version.", |
"type": "string" |
}, |
- "subnetworkUri": { |
- "description": "The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri. Example: https://www.googleapis.com/compute/v1/projects/[project_id]/regions/us-east1/sub0.", |
+ "machineTypeUri": { |
+ "description": "The Google Compute Engine machine type used for cluster instances. Example: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2.", |
"type": "string" |
}, |
+ "managedGroupConfiguration": { |
+ "$ref": "ManagedGroupConfiguration", |
+ "description": "Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups." |
+ }, |
+ "instanceNames": { |
+ "description": "The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name).", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ }, |
+ "accelerators": { |
+ "description": "Optional The Google Compute Engine accelerator configuration for these instances.", |
+ "items": { |
+ "$ref": "AcceleratorConfiguration" |
+ }, |
+ "type": "array" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "GceClusterConfiguration": { |
+ "description": "Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster.", |
+ "id": "GceClusterConfiguration", |
+ "properties": { |
"networkUri": { |
"description": "The Google Compute Engine network to be used for machine communications. Cannot be specified with subnetwork_uri. If neither network_uri nor subnetwork_uri is specified, the \"default\" network of the project is used, if it exists. Cannot be a \"Custom Subnet Network\" (see https://cloud.google.com/compute/docs/subnetworks for more information). Example: https://www.googleapis.com/compute/v1/projects/[project_id]/regions/global/default.", |
"type": "string" |
@@ -701,6 +818,21 @@ |
"type": "string" |
}, |
"type": "array" |
+ }, |
+ "tags": { |
+ "description": "The Google Compute Engine tags to add to all instances.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ }, |
+ "serviceAccount": { |
+ "description": "Optional The service account of the instances. Defaults to the default Google Compute Engine service account. Custom service accounts need permissions equivalent to the folloing IAM roles:\nroles/logging.logWriter\nroles/storage.objectAdmin(see https://cloud.google.com/compute/docs/access/service-accounts#custom_service_accounts for more information). Example: [account_id]@[project_id].iam.gserviceaccount.com", |
+ "type": "string" |
+ }, |
+ "subnetworkUri": { |
+ "description": "The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri. Example: https://www.googleapis.com/compute/v1/projects/[project_id]/regions/us-east1/sub0.", |
+ "type": "string" |
} |
}, |
"type": "object" |
@@ -712,11 +844,11 @@ |
"type": "object" |
}, |
"DiagnoseClusterOutputLocation": { |
- "description": "The location where output from diagnostic command can be found.", |
+ "description": "The location of diagnostic output.", |
"id": "DiagnoseClusterOutputLocation", |
"properties": { |
"outputUri": { |
- "description": "Output-only The Google Cloud Storage URI of the diagnostic output. This will be a plain text file with summary of collected diagnostics.", |
+ "description": "Output-only The Google Cloud Storage URI of the diagnostic output. This is a plain text file with a summary of collected diagnostics.", |
"type": "string" |
} |
}, |
@@ -726,6 +858,10 @@ |
"description": "This resource represents a long-running operation that is the result of a network API call.", |
"id": "Operation", |
"properties": { |
+ "done": { |
+ "description": "If the value is false, it means the operation is still in progress. If true, the operation is completed, and either error or response is available.", |
+ "type": "boolean" |
+ }, |
"response": { |
"additionalProperties": { |
"description": "Properties of the object. Contains field @type with type URL.", |
@@ -749,10 +885,6 @@ |
}, |
"description": "Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.", |
"type": "object" |
- }, |
- "done": { |
- "description": "If the value is false, it means the operation is still in progress. If true, the operation is completed, and either error or response is available.", |
- "type": "boolean" |
} |
}, |
"type": "object" |
@@ -761,10 +893,6 @@ |
"description": "The status of the operation.", |
"id": "OperationStatus", |
"properties": { |
- "innerState": { |
- "description": "A message containing the detailed operation state.", |
- "type": "string" |
- }, |
"stateStartTime": { |
"description": "The time this state was entered.", |
"format": "google-datetime", |
@@ -789,6 +917,10 @@ |
"details": { |
"description": "A message containing any operation metadata details.", |
"type": "string" |
+ }, |
+ "innerState": { |
+ "description": "A message containing the detailed operation state.", |
+ "type": "string" |
} |
}, |
"type": "object" |
@@ -802,7 +934,7 @@ |
"type": "string" |
}, |
"jobId": { |
- "description": "Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or hyphens (-). The maximum length is 512 characters.", |
+ "description": "Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or hyphens (-). The maximum length is 100 characters.", |
"type": "string" |
} |
}, |
@@ -823,11 +955,6 @@ |
"description": "The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC (https://github.com/grpc). The error model is designed to be:\nSimple to use and understand for most users\nFlexible enough to meet unexpected needsOverviewThe Status message contains three pieces of data: error code, error message, and error details. The error code should be an enum value of google.rpc.Code, but it may accept additional error codes if needed. The error message should be a developer-facing English message that helps developers understand and resolve the error. If a localized user-facing error message is needed, put the localized message in the error details or localize it in the client. The optional error details may contain arbitrary information about the error. There is a predefined set of error detail types in the package google.rpc which can be used for common error conditions.Language mappingThe Status message is the logical representation of the error model, but it is not necessarily the actual wire format. When the Status message is exposed in different client libraries and different wire protocols, it can be mapped differently. For example, it will likely be mapped to some exceptions in Java, but more likely mapped to some error codes in C.Other usesThe error model and the Status message can be used in a variety of environments, either with or without APIs, to provide a consistent developer experience across different environments.Example uses of this error model include:\nPartial errors. If a service needs to return partial errors to the client, it may embed the Status in the normal response to indicate the partial errors.\nWorkflow errors. A typical workflow has multiple steps. Each step may have a Status message for error reporting purpose.\nBatch operations. If a client uses batch request and batch response, the Status message should be used directly inside batch response, one for each error sub-response.\nAsynchronous operations. If an API call embeds asynchronous operation results in its response, the status of those operations should be represented directly using the Status message.\nLogging. If some API errors are stored in logs, the message Status could be used directly after any stripping needed for security/privacy reasons.", |
"id": "Status", |
"properties": { |
- "code": { |
- "description": "The status code, which should be an enum value of google.rpc.Code.", |
- "format": "int32", |
- "type": "integer" |
- }, |
"message": { |
"description": "A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.", |
"type": "string" |
@@ -842,6 +969,11 @@ |
"type": "object" |
}, |
"type": "array" |
+ }, |
+ "code": { |
+ "description": "The status code, which should be an enum value of google.rpc.Code.", |
+ "format": "int32", |
+ "type": "integer" |
} |
}, |
"type": "object" |
@@ -862,14 +994,14 @@ |
"description": "Specifies an executable to run on a fully configured node and a timeout period for executable completion.", |
"id": "NodeInitializationAction", |
"properties": { |
- "executableFile": { |
- "description": "Required Google Cloud Storage URI of executable file.", |
- "type": "string" |
- }, |
"executionTimeout": { |
"description": "Optional Amount of time executable has to complete. Default is 10 minutes. Cluster creation fails with an explanatory error message (the name of the executable that caused the error and the exceeded timeout period) if the executable is not completed at end of the timeout period.", |
"format": "google-duration", |
"type": "string" |
+ }, |
+ "executableFile": { |
+ "description": "Required Google Cloud Storage URI of executable file.", |
+ "type": "string" |
} |
}, |
"type": "object" |
@@ -878,16 +1010,16 @@ |
"description": "A list of jobs in a project.", |
"id": "ListJobsResponse", |
"properties": { |
- "nextPageToken": { |
- "description": "Optional This token is included in the response if there are more results to fetch. To fetch additional results, provide this value as the page_token in a subsequent <code>ListJobsRequest</code>.", |
- "type": "string" |
- }, |
"jobs": { |
"description": "Output-only Jobs list.", |
"items": { |
"$ref": "Job" |
}, |
"type": "array" |
+ }, |
+ "nextPageToken": { |
+ "description": "Optional This token is included in the response if there are more results to fetch. To fetch additional results, provide this value as the page_token in a subsequent <code>ListJobsRequest</code>.", |
+ "type": "string" |
} |
}, |
"type": "object" |
@@ -902,14 +1034,14 @@ |
"description": "A Cloud Dataproc job for running Spark SQL queries.", |
"id": "SparkSqlJob", |
"properties": { |
- "queryList": { |
- "$ref": "QueryList", |
- "description": "A list of queries." |
- }, |
"queryFileUri": { |
"description": "The HCFS URI of the script that contains SQL queries.", |
"type": "string" |
}, |
+ "queryList": { |
+ "$ref": "QueryList", |
+ "description": "A list of queries." |
+ }, |
"scriptVariables": { |
"additionalProperties": { |
"type": "string" |
@@ -1013,52 +1145,6 @@ |
"description": "Output-only Short description of operation.", |
"type": "string" |
}, |
- "status": { |
- "$ref": "OperationStatus", |
- "description": "Output-only Current operation status." |
- }, |
- "state": { |
- "description": "A message containing the operation state.", |
- "enum": [ |
- "UNKNOWN", |
- "PENDING", |
- "RUNNING", |
- "DONE" |
- ], |
- "enumDescriptions": [ |
- "Unused.", |
- "The operation has been created.", |
- "The operation is currently running.", |
- "The operation is done, either cancelled or completed." |
- ], |
- "type": "string" |
- }, |
- "details": { |
- "description": "A message containing any operation metadata details.", |
- "type": "string" |
- }, |
- "clusterName": { |
- "description": "Name of the cluster for the operation.", |
- "type": "string" |
- }, |
- "clusterUuid": { |
- "description": "Cluster UUId for the operation.", |
- "type": "string" |
- }, |
- "innerState": { |
- "description": "A message containing the detailed operation state.", |
- "type": "string" |
- }, |
- "endTime": { |
- "description": "The time that the operation completed.", |
- "format": "google-datetime", |
- "type": "string" |
- }, |
- "startTime": { |
- "description": "The time that the operation was started by the server.", |
- "format": "google-datetime", |
- "type": "string" |
- }, |
"warnings": { |
"description": "Output-only Errors encountered during operation execution.", |
"items": { |
@@ -1066,10 +1152,9 @@ |
}, |
"type": "array" |
}, |
- "insertTime": { |
- "description": "The time that the operation was requested.", |
- "format": "google-datetime", |
- "type": "string" |
+ "status": { |
+ "$ref": "OperationStatus", |
+ "description": "Output-only Current operation status." |
}, |
"statusHistory": { |
"description": "Output-only Previous operation status.", |
@@ -1077,6 +1162,14 @@ |
"$ref": "OperationStatus" |
}, |
"type": "array" |
+ }, |
+ "clusterName": { |
+ "description": "Name of the cluster for the operation.", |
+ "type": "string" |
+ }, |
+ "clusterUuid": { |
+ "description": "Cluster UUId for the operation.", |
+ "type": "string" |
} |
}, |
"type": "object" |
@@ -1100,15 +1193,6 @@ |
"description": "The status of a cluster and its instances.", |
"id": "ClusterStatus", |
"properties": { |
- "stateStartTime": { |
- "description": "Time when this state was entered.", |
- "format": "google-datetime", |
- "type": "string" |
- }, |
- "detail": { |
- "description": "Optional details of cluster's state.", |
- "type": "string" |
- }, |
"state": { |
"description": "The cluster's state.", |
"enum": [ |
@@ -1128,6 +1212,15 @@ |
"The cluster is being updated. It continues to accept and process jobs." |
], |
"type": "string" |
+ }, |
+ "stateStartTime": { |
+ "description": "Time when this state was entered.", |
+ "format": "google-datetime", |
+ "type": "string" |
+ }, |
+ "detail": { |
+ "description": "Optional details of cluster's state.", |
+ "type": "string" |
} |
}, |
"type": "object" |
@@ -1140,20 +1233,13 @@ |
"description": "Optional Whether to continue executing queries if a query fails. The default value is false. Setting to true can be useful when executing independent parallel queries.", |
"type": "boolean" |
}, |
- "queryList": { |
- "$ref": "QueryList", |
- "description": "A list of queries." |
- }, |
"queryFileUri": { |
"description": "The HCFS URI of the script that contains the Pig queries.", |
"type": "string" |
}, |
- "jarFileUris": { |
- "description": "Optional HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
+ "queryList": { |
+ "$ref": "QueryList", |
+ "description": "A list of queries." |
}, |
"scriptVariables": { |
"additionalProperties": { |
@@ -1162,6 +1248,13 @@ |
"description": "Optional Mapping of query variable names to values (equivalent to the Pig command: name=[value]).", |
"type": "object" |
}, |
+ "jarFileUris": { |
+ "description": "Optional HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ }, |
"loggingConfiguration": { |
"$ref": "LoggingConfiguration", |
"description": "Optional The runtime log configuration for job execution." |
@@ -1176,17 +1269,18 @@ |
}, |
"type": "object" |
}, |
- "ManagedGroupConfiguration": { |
- "description": "Specifies the resources used to actively manage an instance group.", |
- "id": "ManagedGroupConfiguration", |
+ "AcceleratorConfiguration": { |
+ "description": "Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine).", |
+ "id": "AcceleratorConfiguration", |
"properties": { |
- "instanceGroupManagerName": { |
- "description": "Output-only The name of the Instance Group Manager for this group.", |
+ "acceleratorTypeUri": { |
+ "description": "Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes)", |
"type": "string" |
}, |
- "instanceTemplateName": { |
- "description": "Output-only The name of the Instance Template used for the Managed Instance Group.", |
- "type": "string" |
+ "acceleratorCount": { |
+ "description": "The number of the accelerator cards of this type exposed to this instance.", |
+ "format": "int32", |
+ "type": "integer" |
} |
}, |
"type": "object" |
@@ -1209,30 +1303,37 @@ |
}, |
"type": "object" |
}, |
+ "ManagedGroupConfiguration": { |
+ "description": "Specifies the resources used to actively manage an instance group.", |
+ "id": "ManagedGroupConfiguration", |
+ "properties": { |
+ "instanceGroupManagerName": { |
+ "description": "Output-only The name of the Instance Group Manager for this group.", |
+ "type": "string" |
+ }, |
+ "instanceTemplateName": { |
+ "description": "Output-only The name of the Instance Template used for the Managed Instance Group.", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"Job": { |
"description": "A Cloud Dataproc job resource.", |
"id": "Job", |
"properties": { |
- "interactive": { |
- "description": "Optional If set to true, the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.", |
- "type": "boolean" |
- }, |
- "driverInputResourceUri": { |
- "description": "Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.", |
- "type": "string" |
- }, |
"hadoopJob": { |
"$ref": "HadoopJob", |
"description": "Job is a Hadoop job." |
}, |
- "status": { |
- "$ref": "JobStatus", |
- "description": "Output-only The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields." |
- }, |
"placement": { |
"$ref": "JobPlacement", |
"description": "Required Job information, including how, when, and where to run the job." |
}, |
+ "status": { |
+ "$ref": "JobStatus", |
+ "description": "Output-only The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields." |
+ }, |
"driverControlFilesUri": { |
"description": "Output-only If present, the location of miscellaneous control files which may be used as part of job setup and handling. If not present, control files may be placed in the same location as driver_output_uri.", |
"type": "string" |
@@ -1268,6 +1369,10 @@ |
"$ref": "SparkSqlJob", |
"description": "Job is a SparkSql job." |
}, |
+ "sparkJob": { |
+ "$ref": "SparkJob", |
+ "description": "Job is a Spark job." |
+ }, |
"statusHistory": { |
"description": "Output-only The previous job status.", |
"items": { |
@@ -1275,10 +1380,6 @@ |
}, |
"type": "array" |
}, |
- "sparkJob": { |
- "$ref": "SparkJob", |
- "description": "Job is a Spark job." |
- }, |
"yarnApplications": { |
"description": "Output-only The collection of YARN applications spun up by this job.", |
"items": { |
@@ -1293,6 +1394,14 @@ |
"reference": { |
"$ref": "JobReference", |
"description": "Optional The fully qualified reference to the job, which can be used to obtain the equivalent REST path of the job resource. If this property is not specified when a job is created, the server generates a <code>job_id</code>." |
+ }, |
+ "interactive": { |
+ "description": "Optional If set to true, the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.", |
+ "type": "boolean" |
+ }, |
+ "driverInputResourceUri": { |
+ "description": "Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.", |
+ "type": "string" |
} |
}, |
"type": "object" |
@@ -1301,6 +1410,21 @@ |
"description": "A Cloud Dataproc job for running Spark applications on YARN.", |
"id": "SparkJob", |
"properties": { |
+ "mainClass": { |
+ "description": "The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris.", |
+ "type": "string" |
+ }, |
+ "archiveUris": { |
+ "description": "Optional HCFS URIs of archives to be extracted in the working directory of Spark drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ }, |
+ "mainJarFileUri": { |
+ "description": "The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.", |
+ "type": "string" |
+ }, |
"jarFileUris": { |
"description": "Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.", |
"items": { |
@@ -1332,21 +1456,6 @@ |
"type": "string" |
}, |
"type": "array" |
- }, |
- "mainClass": { |
- "description": "The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris.", |
- "type": "string" |
- }, |
- "archiveUris": { |
- "description": "Optional HCFS URIs of archives to be extracted in the working directory of Spark drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
- }, |
- "mainJarFileUri": { |
- "description": "The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.", |
- "type": "string" |
} |
}, |
"type": "object" |
@@ -1520,11 +1629,6 @@ |
"description": "A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.", |
"id": "YarnApplication", |
"properties": { |
- "progress": { |
- "description": "Required The numerical progress of the application, from 1 to 100.", |
- "format": "float", |
- "type": "number" |
- }, |
"state": { |
"description": "Required The application state.", |
"enum": [ |
@@ -1558,6 +1662,11 @@ |
"trackingUrl": { |
"description": "Optional The HTTP URL of the ApplicationMaster, HistoryServer, or TimelineServer that provides application-specific information. The URL uses the internal hostname, and requires a proxy server for resolution and, possibly, access.", |
"type": "string" |
+ }, |
+ "progress": { |
+ "description": "Required The numerical progress of the application, from 1 to 100.", |
+ "format": "float", |
+ "type": "number" |
} |
}, |
"type": "object" |
@@ -1616,34 +1725,28 @@ |
}, |
"type": "object" |
}, |
- "Empty": { |
- "description": "A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance:\nservice Foo {\n rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);\n}\nThe JSON representation for Empty is empty JSON object {}.", |
- "id": "Empty", |
- "properties": {}, |
- "type": "object" |
- }, |
"HiveJob": { |
"description": "A Cloud Dataproc job for running Hive queries on YARN.", |
"id": "HiveJob", |
"properties": { |
- "properties": { |
- "additionalProperties": { |
- "type": "string" |
- }, |
- "description": "Optional A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.", |
- "type": "object" |
- }, |
"continueOnFailure": { |
"description": "Optional Whether to continue executing queries if a query fails. The default value is false. Setting to true can be useful when executing independent parallel queries.", |
"type": "boolean" |
}, |
+ "queryList": { |
+ "$ref": "QueryList", |
+ "description": "A list of queries." |
+ }, |
"queryFileUri": { |
"description": "The HCFS URI of the script that contains Hive queries.", |
"type": "string" |
}, |
- "queryList": { |
- "$ref": "QueryList", |
- "description": "A list of queries." |
+ "scriptVariables": { |
+ "additionalProperties": { |
+ "type": "string" |
+ }, |
+ "description": "Optional Mapping of query variable names to values (equivalent to the Hive command: SET name=\"value\";).", |
+ "type": "object" |
}, |
"jarFileUris": { |
"description": "Optional HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.", |
@@ -1652,16 +1755,22 @@ |
}, |
"type": "array" |
}, |
- "scriptVariables": { |
+ "properties": { |
"additionalProperties": { |
"type": "string" |
}, |
- "description": "Optional Mapping of query variable names to values (equivalent to the Hive command: SET name=\"value\";).", |
+ "description": "Optional A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.", |
"type": "object" |
} |
}, |
"type": "object" |
}, |
+ "Empty": { |
+ "description": "A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance:\nservice Foo {\n rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);\n}\nThe JSON representation for Empty is empty JSON object {}.", |
+ "id": "Empty", |
+ "properties": {}, |
+ "type": "object" |
+ }, |
"DiagnoseClusterResults": { |
"description": "The location of diagnostic output.", |
"id": "DiagnoseClusterResults", |
@@ -1695,31 +1804,6 @@ |
"description": "A Cloud Dataproc job for running PySpark applications on YARN.", |
"id": "PySparkJob", |
"properties": { |
- "fileUris": { |
- "description": "Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
- }, |
- "pythonFileUris": { |
- "description": "Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
- }, |
- "mainPythonFileUri": { |
- "description": "Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.", |
- "type": "string" |
- }, |
- "archiveUris": { |
- "description": "Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
- }, |
"jarFileUris": { |
"description": "Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.", |
"items": { |
@@ -1744,131 +1828,31 @@ |
"type": "string" |
}, |
"type": "array" |
- } |
- }, |
- "type": "object" |
- }, |
- "ClusterMetrics": { |
- "description": "Contains cluster daemon metrics, such as HDFS and YARN stats.", |
- "id": "ClusterMetrics", |
- "properties": { |
- "hdfsMetrics": { |
- "additionalProperties": { |
- "format": "int64", |
- "type": "string" |
- }, |
- "description": "The HDFS metrics.", |
- "type": "object" |
- }, |
- "yarnMetrics": { |
- "additionalProperties": { |
- "format": "int64", |
- "type": "string" |
- }, |
- "description": "The YARN metrics.", |
- "type": "object" |
- } |
- }, |
- "type": "object" |
- }, |
- "ClusterConfiguration": { |
- "description": "The cluster configuration.", |
- "id": "ClusterConfiguration", |
- "properties": { |
- "secondaryWorkerConfiguration": { |
- "$ref": "InstanceGroupConfiguration", |
- "description": "Optional The Google Compute Engine configuration settings for additional worker instances in a cluster." |
}, |
- "initializationActions": { |
- "description": "Optional Commands to execute on each node after configuration is completed. By default, executables are run on master and all worker nodes. You can test a node's <code>role</code> metadata to run an executable on a master or worker node, as shown below:\nROLE=$(/usr/share/google/get_metadata_value attributes/role)\nif [[ \"${ROLE}\" == 'Master' ]]; then\n ... master specific actions ...\nelse\n ... worker specific actions ...\nfi\n", |
+ "fileUris": { |
+ "description": "Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.", |
"items": { |
- "$ref": "NodeInitializationAction" |
+ "type": "string" |
}, |
"type": "array" |
}, |
- "workerConfiguration": { |
- "$ref": "InstanceGroupConfiguration", |
- "description": "Optional The Google Compute Engine configuration settings for worker instances in a cluster." |
- }, |
- "softwareConfiguration": { |
- "$ref": "SoftwareConfiguration", |
- "description": "Optional The configuration settings for software inside the cluster." |
- }, |
- "gceClusterConfiguration": { |
- "$ref": "GceClusterConfiguration", |
- "description": "Required The shared Google Compute Engine configuration settings for all instances in a cluster." |
- }, |
- "configurationBucket": { |
- "description": "Optional A Google Cloud Storage staging bucket used for sharing generated SSH keys and configuration. If you do not specify a staging bucket, Cloud Dataproc will determine an appropriate Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Google Compute Engine zone where your cluster is deployed, and then it will create and manage this project-level, per-location bucket for you.", |
- "type": "string" |
- }, |
- "masterConfiguration": { |
- "$ref": "InstanceGroupConfiguration", |
- "description": "Optional The Google Compute Engine configuration settings for the master instance in a cluster." |
- } |
- }, |
- "type": "object" |
- }, |
- "LoggingConfiguration": { |
- "description": "The runtime logging configuration of the job.", |
- "id": "LoggingConfiguration", |
- "properties": { |
- "driverLogLevels": { |
- "additionalProperties": { |
- "enum": [ |
- "LEVEL_UNSPECIFIED", |
- "ALL", |
- "TRACE", |
- "DEBUG", |
- "INFO", |
- "WARN", |
- "ERROR", |
- "FATAL", |
- "OFF" |
- ], |
+ "pythonFileUris": { |
+ "description": "Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.", |
+ "items": { |
"type": "string" |
}, |
- "description": "The per-package log levels for the driver. This may include \"root\" package name to configure rootLogger. Examples: 'com.google = FATAL', 'root = INFO', 'org.apache = DEBUG'", |
- "type": "object" |
- } |
- }, |
- "type": "object" |
- }, |
- "InstanceGroupConfiguration": { |
- "description": "The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group.", |
- "id": "InstanceGroupConfiguration", |
- "properties": { |
- "diskConfiguration": { |
- "$ref": "DiskConfiguration", |
- "description": "Disk option configuration settings." |
- }, |
- "isPreemptible": { |
- "description": "Specifies that this instance group contains Preemptible Instances.", |
- "type": "boolean" |
- }, |
- "imageUri": { |
- "description": "Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version.", |
- "type": "string" |
+ "type": "array" |
}, |
- "machineTypeUri": { |
- "description": "The Google Compute Engine machine type used for cluster instances. Example: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2.", |
+ "mainPythonFileUri": { |
+ "description": "Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.", |
"type": "string" |
}, |
- "managedGroupConfiguration": { |
- "$ref": "ManagedGroupConfiguration", |
- "description": "Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups." |
- }, |
- "instanceNames": { |
- "description": "The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name).", |
+ "archiveUris": { |
+ "description": "Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.", |
"items": { |
"type": "string" |
}, |
"type": "array" |
- }, |
- "numInstances": { |
- "description": "The number of VM instances in the instance group. For master instance groups, must be set to 1.", |
- "format": "int32", |
- "type": "integer" |
} |
}, |
"type": "object" |