Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(453)

Unified Diff: discovery/googleapis/dataproc__v1beta2.json

Issue 2973303002: Api-Roll 51: 2017-07-10 (Closed)
Patch Set: Created 3 years, 5 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « discovery/googleapis/dataproc__v1.json ('k') | discovery/googleapis/datastore__v1.json » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: discovery/googleapis/dataproc__v1beta2.json
diff --git a/discovery/googleapis/dataproc__v1.json b/discovery/googleapis/dataproc__v1beta2.json
similarity index 95%
copy from discovery/googleapis/dataproc__v1.json
copy to discovery/googleapis/dataproc__v1beta2.json
index 9da68d7d22173b565cfc0832e6b0f24520680aa3..64b5af945bdeac1888319c9515836a1a0212b208 100644
--- a/discovery/googleapis/dataproc__v1.json
+++ b/discovery/googleapis/dataproc__v1beta2.json
@@ -18,25 +18,14 @@
"x16": "http://www.google.com/images/icons/product/search-16.gif",
"x32": "http://www.google.com/images/icons/product/search-32.gif"
},
- "id": "dataproc:v1",
+ "id": "dataproc:v1beta2",
"kind": "discovery#restDescription",
"name": "dataproc",
"ownerDomain": "google.com",
"ownerName": "Google",
"parameters": {
- "alt": {
- "default": "json",
- "description": "Data format for response.",
- "enum": [
- "json",
- "media",
- "proto"
- ],
- "enumDescriptions": [
- "Responses with Content-Type of application/json",
- "Media download with context-dependent Content-Type",
- "Responses with Content-Type of application/x-protobuf"
- ],
+ "access_token": {
+ "description": "OAuth access token.",
"location": "query",
"type": "string"
},
@@ -45,11 +34,6 @@
"location": "query",
"type": "string"
},
- "access_token": {
- "description": "OAuth access token.",
- "location": "query",
- "type": "string"
- },
"quotaUser": {
"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",
@@ -109,6 +93,22 @@
"description": "JSONP",
"location": "query",
"type": "string"
+ },
+ "alt": {
+ "default": "json",
+ "description": "Data format for response.",
+ "enum": [
+ "json",
+ "media",
+ "proto"
+ ],
+ "enumDescriptions": [
+ "Responses with Content-Type of application/json",
+ "Media download with context-dependent Content-Type",
+ "Responses with Content-Type of application/x-protobuf"
+ ],
+ "location": "query",
+ "type": "string"
}
},
"protocol": "rest",
@@ -117,147 +117,61 @@
"resources": {
"regions": {
"resources": {
- "jobs": {
+ "clusters": {
"methods": {
- "submit": {
- "description": "Submits a job to a cluster.",
- "httpMethod": "POST",
- "id": "dataproc.projects.regions.jobs.submit",
- "parameterOrder": [
- "projectId",
- "region"
- ],
- "parameters": {
- "projectId": {
- "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "region": {
- "description": "Required. The Cloud Dataproc region in which to handle the request.",
- "location": "path",
- "required": true,
- "type": "string"
- }
- },
- "path": "v1/projects/{projectId}/regions/{region}/jobs:submit",
- "request": {
- "$ref": "SubmitJobRequest"
- },
- "response": {
- "$ref": "Job"
- },
- "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.",
- "httpMethod": "DELETE",
- "id": "dataproc.projects.regions.jobs.delete",
- "parameterOrder": [
- "projectId",
- "region",
- "jobId"
- ],
- "parameters": {
- "jobId": {
- "description": "Required. The job ID.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "projectId": {
- "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "region": {
- "description": "Required. The Cloud Dataproc region in which to handle the request.",
- "location": "path",
- "required": true,
- "type": "string"
- }
- },
- "path": "v1/projects/{projectId}/regions/{region}/jobs/{jobId}",
- "response": {
- "$ref": "Empty"
- },
- "scopes": [
- "https://www.googleapis.com/auth/cloud-platform"
- ]
- },
"list": {
- "description": "Lists regions/{region}/jobs in a project.",
+ "description": "Lists all regions/{region}/clusters in a project.",
"httpMethod": "GET",
- "id": "dataproc.projects.regions.jobs.list",
+ "id": "dataproc.projects.regions.clusters.list",
"parameterOrder": [
"projectId",
"region"
],
"parameters": {
"filter": {
- "description": "Optional. A filter constraining the jobs to list. Filters are case-sensitive and have the following syntax:field = value AND field = value ...where field is status.state or labels.[KEY], and [KEY] is a label key. value can be * to match all values. status.state can be either ACTIVE or INACTIVE. Only the logical AND operator is supported; space-separated items are treated as having an implicit AND operator.Example filter:status.state = ACTIVE AND labels.env = staging AND labels.starred = *",
+ "description": "Optional. A filter constraining the clusters to list. Filters are case-sensitive and have the following syntax:field = value AND field = value ...where field is one of status.state, clusterName, or labels.[KEY], and [KEY] is a label key. value can be * to match all values. status.state can be one of the following: ACTIVE, INACTIVE, CREATING, RUNNING, ERROR, DELETING, or UPDATING. ACTIVE contains the CREATING, UPDATING, and RUNNING states. INACTIVE contains the DELETING and ERROR states. clusterName is the name of the cluster provided at creation time. Only the logical AND operator is supported; space-separated items are treated as having an implicit AND operator.Example filter:status.state = ACTIVE AND clusterName = mycluster AND labels.env = staging AND labels.starred = *",
"location": "query",
"type": "string"
},
- "jobStateMatcher": {
- "description": "Optional. Specifies enumerated categories of jobs to list (default = match ALL jobs).",
- "enum": [
- "ALL",
- "ACTIVE",
- "NON_ACTIVE"
- ],
- "location": "query",
+ "region": {
+ "description": "Required. The Cloud Dataproc region in which to handle the request.",
+ "location": "path",
+ "required": true,
"type": "string"
},
"pageToken": {
- "description": "Optional. The page token, returned by a previous call, to request the next page of results.",
+ "description": "Optional. The standard List page token.",
"location": "query",
"type": "string"
},
"pageSize": {
- "description": "Optional. The number of results to return in each response.",
+ "description": "Optional. The standard List page size.",
"format": "int32",
"location": "query",
"type": "integer"
},
- "region": {
- "description": "Required. The Cloud Dataproc region in which to handle the request.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "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"
}
},
- "path": "v1/projects/{projectId}/regions/{region}/jobs",
+ "path": "v1beta2/projects/{projectId}/regions/{region}/clusters",
"response": {
- "$ref": "ListJobsResponse"
+ "$ref": "ListClustersResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
- "cancel": {
- "description": "Starts a job cancellation request. To access the job resource after cancellation, call regions/{region}/jobs.list or regions/{region}/jobs.get.",
+ "create": {
+ "description": "Creates a cluster in a project.",
"httpMethod": "POST",
- "id": "dataproc.projects.regions.jobs.cancel",
+ "id": "dataproc.projects.regions.clusters.create",
"parameterOrder": [
"projectId",
- "region",
- "jobId"
+ "region"
],
"parameters": {
"region": {
@@ -266,42 +180,36 @@
"required": true,
"type": "string"
},
- "jobId": {
- "description": "Required. The job ID.",
- "location": "path",
- "required": true,
- "type": "string"
- },
"projectId": {
- "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
+ "description": "Required. The ID of the Google Cloud Platform project that the cluster belongs to.",
"location": "path",
"required": true,
"type": "string"
}
},
- "path": "v1/projects/{projectId}/regions/{region}/jobs/{jobId}:cancel",
+ "path": "v1beta2/projects/{projectId}/regions/{region}/clusters",
"request": {
- "$ref": "CancelJobRequest"
+ "$ref": "Cluster"
},
"response": {
- "$ref": "Job"
+ "$ref": "Operation"
},
"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.regions.jobs.patch",
+ "id": "dataproc.projects.regions.clusters.patch",
"parameterOrder": [
"projectId",
"region",
- "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.",
+ "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>config.worker_config.num_instances</code>, and the PATCH request body would specify the new value, as follows:\n{\n \"config\":{\n \"workerConfig\":{\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 only some fields can be updated: |Mask|Purpose| |labels|Updates labels| |config.worker_config.num_instances|Resize primary worker group| |config.secondary_worker_config.num_instances|Resize secondary worker group|",
"format": "google-fieldmask",
"location": "query",
"type": "string"
@@ -312,104 +220,97 @@
"required": true,
"type": "string"
},
- "jobId": {
- "description": "Required. The job ID.",
+ "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"
}
},
- "path": "v1/projects/{projectId}/regions/{region}/jobs/{jobId}",
+ "path": "v1beta2/projects/{projectId}/regions/{region}/clusters/{clusterName}",
"request": {
- "$ref": "Job"
+ "$ref": "Cluster"
},
"response": {
- "$ref": "Job"
+ "$ref": "Operation"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"get": {
- "description": "Gets the resource representation for a job in a project.",
+ "description": "Gets the resource representation for a cluster in a project.",
"httpMethod": "GET",
- "id": "dataproc.projects.regions.jobs.get",
+ "id": "dataproc.projects.regions.clusters.get",
"parameterOrder": [
"projectId",
"region",
- "jobId"
+ "clusterName"
],
"parameters": {
- "jobId": {
- "description": "Required. The job ID.",
+ "region": {
+ "description": "Required. The Cloud Dataproc region in which to handle the request.",
"location": "path",
"required": true,
"type": "string"
},
- "projectId": {
- "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
+ "clusterName": {
+ "description": "Required. The cluster name.",
"location": "path",
"required": true,
"type": "string"
},
- "region": {
- "description": "Required. The Cloud Dataproc region in which to handle the request.",
+ "projectId": {
+ "description": "Required. The ID of the Google Cloud Platform project that the cluster belongs to.",
"location": "path",
"required": true,
"type": "string"
}
},
- "path": "v1/projects/{projectId}/regions/{region}/jobs/{jobId}",
+ "path": "v1beta2/projects/{projectId}/regions/{region}/clusters/{clusterName}",
"response": {
- "$ref": "Job"
+ "$ref": "Cluster"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
- }
- }
- },
- "clusters": {
- "methods": {
- "diagnose": {
- "description": "Gets cluster diagnostic information. After the operation completes, the Operation.response field contains DiagnoseClusterOutputLocation.",
- "httpMethod": "POST",
- "id": "dataproc.projects.regions.clusters.diagnose",
+ },
+ "delete": {
+ "description": "Deletes a cluster in a project.",
+ "httpMethod": "DELETE",
+ "id": "dataproc.projects.regions.clusters.delete",
"parameterOrder": [
"projectId",
"region",
"clusterName"
],
"parameters": {
- "clusterName": {
- "description": "Required. The cluster name.",
+ "region": {
+ "description": "Required. The Cloud Dataproc region in which to handle the request.",
"location": "path",
"required": true,
"type": "string"
},
- "projectId": {
- "description": "Required. The ID of the Google Cloud Platform project that the cluster belongs to.",
+ "clusterName": {
+ "description": "Required. The cluster name.",
"location": "path",
"required": true,
"type": "string"
},
- "region": {
- "description": "Required. The Cloud Dataproc region in which to handle the request.",
+ "projectId": {
+ "description": "Required. The ID of the Google Cloud Platform project that the cluster belongs to.",
"location": "path",
"required": true,
"type": "string"
}
},
- "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}:diagnose",
- "request": {
- "$ref": "DiagnoseClusterRequest"
- },
+ "path": "v1beta2/projects/{projectId}/regions/{region}/clusters/{clusterName}",
"response": {
"$ref": "Operation"
},
@@ -417,22 +318,16 @@
"https://www.googleapis.com/auth/cloud-platform"
]
},
- "delete": {
- "description": "Deletes a cluster in a project.",
- "httpMethod": "DELETE",
- "id": "dataproc.projects.regions.clusters.delete",
+ "diagnose": {
+ "description": "Gets cluster diagnostic information. After the operation completes, the Operation.response field contains DiagnoseClusterOutputLocation.",
+ "httpMethod": "POST",
+ "id": "dataproc.projects.regions.clusters.diagnose",
"parameterOrder": [
"projectId",
"region",
"clusterName"
],
"parameters": {
- "clusterName": {
- "description": "Required. The cluster name.",
- "location": "path",
- "required": true,
- "type": "string"
- },
"projectId": {
"description": "Required. The ID of the Google Cloud Platform project that the cluster belongs to.",
"location": "path",
@@ -444,134 +339,94 @@
"location": "path",
"required": true,
"type": "string"
+ },
+ "clusterName": {
+ "description": "Required. The cluster name.",
+ "location": "path",
+ "required": true,
+ "type": "string"
}
},
- "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}",
+ "path": "v1beta2/projects/{projectId}/regions/{region}/clusters/{clusterName}:diagnose",
+ "request": {
+ "$ref": "DiagnoseClusterRequest"
+ },
"response": {
"$ref": "Operation"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
- },
- "list": {
- "description": "Lists all regions/{region}/clusters in a project.",
- "httpMethod": "GET",
- "id": "dataproc.projects.regions.clusters.list",
+ }
+ }
+ },
+ "operations": {
+ "methods": {
+ "cancel": {
+ "description": "Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of 1, corresponding to Code.CANCELLED.",
+ "httpMethod": "POST",
+ "id": "dataproc.projects.regions.operations.cancel",
"parameterOrder": [
- "projectId",
- "region"
+ "name"
],
"parameters": {
- "filter": {
- "description": "Optional. A filter constraining the clusters to list. Filters are case-sensitive and have the following syntax:field = value AND field = value ...where field is one of status.state, clusterName, or labels.[KEY], and [KEY] is a label key. value can be * to match all values. status.state can be one of the following: ACTIVE, INACTIVE, CREATING, RUNNING, ERROR, DELETING, or UPDATING. ACTIVE contains the CREATING, UPDATING, and RUNNING states. INACTIVE contains the DELETING and ERROR states. clusterName is the name of the cluster provided at creation time. Only the logical AND operator is supported; space-separated items are treated as having an implicit AND operator.Example filter:status.state = ACTIVE AND clusterName = mycluster AND labels.env = staging AND labels.starred = *",
- "location": "query",
- "type": "string"
- },
- "region": {
- "description": "Required. The Cloud Dataproc region in which to handle the request.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "pageToken": {
- "description": "Optional. The standard List page token.",
- "location": "query",
- "type": "string"
- },
- "pageSize": {
- "description": "Optional. 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.",
+ "name": {
+ "description": "The name of the operation resource to be cancelled.",
"location": "path",
+ "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
- "path": "v1/projects/{projectId}/regions/{region}/clusters",
+ "path": "v1beta2/{+name}:cancel",
"response": {
- "$ref": "ListClustersResponse"
+ "$ref": "Empty"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
- "create": {
- "description": "Creates a cluster in a project.",
- "httpMethod": "POST",
- "id": "dataproc.projects.regions.clusters.create",
+ "delete": {
+ "description": "Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED.",
+ "httpMethod": "DELETE",
+ "id": "dataproc.projects.regions.operations.delete",
"parameterOrder": [
- "projectId",
- "region"
+ "name"
],
"parameters": {
- "projectId": {
- "description": "Required. The ID of the Google Cloud Platform project that the cluster belongs to.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "region": {
- "description": "Required. The Cloud Dataproc region in which to handle the request.",
+ "name": {
+ "description": "The name of the operation resource to be deleted.",
"location": "path",
+ "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
- "path": "v1/projects/{projectId}/regions/{region}/clusters",
- "request": {
- "$ref": "Cluster"
- },
+ "path": "v1beta2/{+name}",
"response": {
- "$ref": "Operation"
+ "$ref": "Empty"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
- "patch": {
- "description": "Updates a cluster in a project.",
- "httpMethod": "PATCH",
- "id": "dataproc.projects.regions.clusters.patch",
+ "get": {
+ "description": "Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.",
+ "httpMethod": "GET",
+ "id": "dataproc.projects.regions.operations.get",
"parameterOrder": [
- "projectId",
- "region",
- "clusterName"
+ "name"
],
"parameters": {
- "updateMask": {
- "description": "Required. Specifies the path, relative to Cluster, of the field to update. For example, to change the number of workers in a cluster to 5, the update_mask parameter would be specified as config.worker_config.num_instances, and the PATCH request body would specify the new value, as follows:\n{\n \"config\":{\n \"workerConfig\":{\n \"numInstances\":\"5\"\n }\n }\n}\nSimilarly, to change the number of preemptible workers in a cluster to 5, the update_mask parameter would be config.secondary_worker_config.num_instances, 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, only the following fields can be updated:<table> <tbody> <tr> <td><strong>Mask</strong></td> <td><strong>Purpose</strong></td> </tr> <tr> <td><strong><em>labels</em></strong></td> <td>Update labels</td> </tr> <tr> <td><strong><em>config.worker_config.num_instances</em></strong></td> <td>Resize primary worker group</td> </tr> <tr> <td><strong><em>config.secondary_worker_config.num_instances</em></strong></td> <td>Resize secondary worker group</td> </tr> </tbody> </table>",
- "format": "google-fieldmask",
- "location": "query",
- "type": "string"
- },
- "region": {
- "description": "Required. The Cloud Dataproc region in which to handle the request.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "clusterName": {
- "description": "Required. The cluster name.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "projectId": {
- "description": "Required. The ID of the Google Cloud Platform project the cluster belongs to.",
+ "name": {
+ "description": "The name of the operation resource.",
"location": "path",
+ "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
- "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}",
- "request": {
- "$ref": "Cluster"
- },
+ "path": "v1beta2/{+name}",
"response": {
"$ref": "Operation"
},
@@ -579,38 +434,41 @@
"https://www.googleapis.com/auth/cloud-platform"
]
},
- "get": {
- "description": "Gets the resource representation for a cluster in a project.",
+ "list": {
+ "description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED.NOTE: the name binding allows API services to override the binding to use different resource name schemes, such as users/*/operations. To override the binding, API services can add a binding such as \"/v1/{name=users/*}/operations\" to their service configuration. For backwards compatibility, the default name includes the operations collection id, however overriding users must ensure the name binding is the parent resource, without the operations collection id.",
"httpMethod": "GET",
- "id": "dataproc.projects.regions.clusters.get",
+ "id": "dataproc.projects.regions.operations.list",
"parameterOrder": [
- "projectId",
- "region",
- "clusterName"
+ "name"
],
"parameters": {
- "region": {
- "description": "Required. The Cloud Dataproc region in which to handle the request.",
- "location": "path",
- "required": true,
+ "pageSize": {
+ "description": "The standard list page size.",
+ "format": "int32",
+ "location": "query",
+ "type": "integer"
+ },
+ "filter": {
+ "description": "The standard list filter.",
+ "location": "query",
"type": "string"
},
- "clusterName": {
- "description": "Required. The cluster name.",
- "location": "path",
- "required": true,
+ "pageToken": {
+ "description": "The standard list page token.",
+ "location": "query",
"type": "string"
},
- "projectId": {
- "description": "Required. The ID of the Google Cloud Platform project that the cluster belongs to.",
+ "name": {
+ "description": "The name of the operation's parent resource.",
"location": "path",
+ "pattern": "^projects/[^/]+/regions/[^/]+/operations$",
"required": true,
"type": "string"
}
},
- "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}",
+ "path": "v1beta2/{+name}",
"response": {
- "$ref": "Cluster"
+ "$ref": "ListOperationsResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
@@ -618,115 +476,257 @@
}
}
},
- "operations": {
+ "jobs": {
"methods": {
- "cancel": {
- "description": "Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of 1, corresponding to Code.CANCELLED.",
+ "submit": {
+ "description": "Submits a job to a cluster.",
"httpMethod": "POST",
- "id": "dataproc.projects.regions.operations.cancel",
+ "id": "dataproc.projects.regions.jobs.submit",
"parameterOrder": [
- "name"
+ "projectId",
+ "region"
],
"parameters": {
- "name": {
- "description": "The name of the operation resource to be cancelled.",
+ "region": {
+ "description": "Required. The Cloud Dataproc region in which to handle the request.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "projectId": {
+ "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
"location": "path",
- "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
- "path": "v1/{+name}:cancel",
+ "path": "v1beta2/projects/{projectId}/regions/{region}/jobs:submit",
+ "request": {
+ "$ref": "SubmitJobRequest"
+ },
"response": {
- "$ref": "Empty"
+ "$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"delete": {
- "description": "Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED.",
+ "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.regions.operations.delete",
+ "id": "dataproc.projects.regions.jobs.delete",
"parameterOrder": [
- "name"
+ "projectId",
+ "region",
+ "jobId"
],
"parameters": {
- "name": {
- "description": "The name of the operation resource to be deleted.",
+ "region": {
+ "description": "Required. The Cloud Dataproc region in which to handle the request.",
"location": "path",
- "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
- }
- },
- "path": "v1/{+name}",
- "response": {
- "$ref": "Empty"
- },
- "scopes": [
- "https://www.googleapis.com/auth/cloud-platform"
- ]
- },
- "get": {
- "description": "Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.",
- "httpMethod": "GET",
- "id": "dataproc.projects.regions.operations.get",
- "parameterOrder": [
- "name"
- ],
- "parameters": {
- "name": {
- "description": "The name of the operation resource.",
+ },
+ "jobId": {
+ "description": "Required. The job ID.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "projectId": {
+ "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
"location": "path",
- "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
- "path": "v1/{+name}",
+ "path": "v1beta2/projects/{projectId}/regions/{region}/jobs/{jobId}",
"response": {
- "$ref": "Operation"
+ "$ref": "Empty"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"list": {
- "description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED.NOTE: the name binding allows API services to override the binding to use different resource name schemes, such as users/*/operations. To override the binding, API services can add a binding such as \"/v1/{name=users/*}/operations\" to their service configuration. For backwards compatibility, the default name includes the operations collection id, however overriding users must ensure the name binding is the parent resource, without the operations collection id.",
+ "description": "Lists regions/{region}/jobs in a project.",
"httpMethod": "GET",
- "id": "dataproc.projects.regions.operations.list",
+ "id": "dataproc.projects.regions.jobs.list",
"parameterOrder": [
- "name"
+ "projectId",
+ "region"
],
"parameters": {
- "pageToken": {
- "description": "The standard list page token.",
+ "projectId": {
+ "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "filter": {
+ "description": "Optional. A filter constraining the jobs to list. Filters are case-sensitive and have the following syntax:field = value AND field = value ...where field is status.state or labels.[KEY], and [KEY] is a label key. value can be * to match all values. status.state can be either ACTIVE or INACTIVE. Only the logical AND operator is supported; space-separated items are treated as having an implicit AND operator.Example filter:status.state = ACTIVE AND labels.env = staging AND labels.starred = *",
"location": "query",
"type": "string"
},
- "name": {
- "description": "The name of the operation's parent resource.",
- "location": "path",
- "pattern": "^projects/[^/]+/regions/[^/]+/operations$",
- "required": true,
+ "jobStateMatcher": {
+ "description": "Optional. Specifies enumerated categories of jobs to list (default = match ALL jobs).",
+ "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": "The standard list page size.",
+ "description": "Optional. The number of results to return in each response.",
"format": "int32",
"location": "query",
"type": "integer"
},
- "filter": {
- "description": "The standard list filter.",
- "location": "query",
- "type": "string"
+ "region": {
+ "description": "Required. The Cloud Dataproc region in which to handle the request.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "clusterName": {
+ "description": "Optional. If set, the returned jobs list includes only jobs that were submitted to the named cluster.",
+ "location": "query",
+ "type": "string"
}
},
- "path": "v1/{+name}",
+ "path": "v1beta2/projects/{projectId}/regions/{region}/jobs",
"response": {
- "$ref": "ListOperationsResponse"
+ "$ref": "ListJobsResponse"
+ },
+ "scopes": [
+ "https://www.googleapis.com/auth/cloud-platform"
+ ]
+ },
+ "cancel": {
+ "description": "Starts a job cancellation request. To access the job resource after cancellation, call regions/{region}/jobs.list or regions/{region}/jobs.get.",
+ "httpMethod": "POST",
+ "id": "dataproc.projects.regions.jobs.cancel",
+ "parameterOrder": [
+ "projectId",
+ "region",
+ "jobId"
+ ],
+ "parameters": {
+ "region": {
+ "description": "Required. The Cloud Dataproc region in which to handle the request.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "jobId": {
+ "description": "Required. The job ID.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "projectId": {
+ "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ }
+ },
+ "path": "v1beta2/projects/{projectId}/regions/{region}/jobs/{jobId}:cancel",
+ "request": {
+ "$ref": "CancelJobRequest"
+ },
+ "response": {
+ "$ref": "Job"
+ },
+ "scopes": [
+ "https://www.googleapis.com/auth/cloud-platform"
+ ]
+ },
+ "get": {
+ "description": "Gets the resource representation for a job in a project.",
+ "httpMethod": "GET",
+ "id": "dataproc.projects.regions.jobs.get",
+ "parameterOrder": [
+ "projectId",
+ "region",
+ "jobId"
+ ],
+ "parameters": {
+ "jobId": {
+ "description": "Required. The job ID.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "projectId": {
+ "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "region": {
+ "description": "Required. The Cloud Dataproc region in which to handle the request.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ }
+ },
+ "path": "v1beta2/projects/{projectId}/regions/{region}/jobs/{jobId}",
+ "response": {
+ "$ref": "Job"
+ },
+ "scopes": [
+ "https://www.googleapis.com/auth/cloud-platform"
+ ]
+ },
+ "patch": {
+ "description": "Updates a job in a project.",
+ "httpMethod": "PATCH",
+ "id": "dataproc.projects.regions.jobs.patch",
+ "parameterOrder": [
+ "projectId",
+ "region",
+ "jobId"
+ ],
+ "parameters": {
+ "updateMask": {
+ "description": "Required. Specifies the path, relative to <code>Job</code>, of the field to update. For example, to update the labels of a Job the <code>update_mask</code> parameter would be specified as <code>labels</code>, and the PATCH request body would specify the new value. <strong>Note:</strong> Currently, <code>labels</code> is the only field that can be updated.",
+ "format": "google-fieldmask",
+ "location": "query",
+ "type": "string"
+ },
+ "region": {
+ "description": "Required. The Cloud Dataproc region in which to handle the request.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "jobId": {
+ "description": "Required. The job ID.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "projectId": {
+ "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ }
+ },
+ "path": "v1beta2/projects/{projectId}/regions/{region}/jobs/{jobId}",
+ "request": {
+ "$ref": "Job"
+ },
+ "response": {
+ "$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
@@ -739,220 +739,575 @@
}
}
},
- "revision": "20170606",
+ "revision": "20170707",
"rootUrl": "https://dataproc.googleapis.com/",
"schemas": {
- "ListClustersResponse": {
- "description": "The list of all clusters in a project.",
- "id": "ListClustersResponse",
+ "Status": {
+ "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 that 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.\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": {
- "nextPageToken": {
- "description": "Output-only. 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 ListClustersRequest.",
+ "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"
},
- "clusters": {
- "description": "Output-only. The clusters in the project.",
+ "details": {
+ "description": "A list of messages that carry the error details. There will be a common set of message types for APIs to use.",
"items": {
- "$ref": "Cluster"
+ "additionalProperties": {
+ "description": "Properties of the object. Contains field @type with type URL.",
+ "type": "any"
+ },
+ "type": "object"
},
"type": "array"
}
},
"type": "object"
},
- "SparkJob": {
- "description": "A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN.",
- "id": "SparkJob",
+ "JobScheduling": {
+ "description": "Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release.",
+ "id": "JobScheduling",
"properties": {
- "mainJarFileUri": {
- "description": "The HCFS URI of the jar file that contains the main class.",
+ "maxFailuresPerHour": {
+ "description": "Optional. Maximum number of times per hour a driver may be restarted as a result of driver terminating with non-zero code before job is reported failed.A job may be reported as thrashing if driver exits with non-zero code 4 times within 10 minute window.Maximum value is 10.",
+ "format": "int32",
+ "type": "integer"
+ }
+ },
+ "type": "object"
+ },
+ "InstanceGroupConfig": {
+ "description": "Optional. The config settings for Google Compute Engine resources in an instance group, such as a master or worker group.",
+ "id": "InstanceGroupConfig",
+ "properties": {
+ "diskConfig": {
+ "$ref": "DiskConfig",
+ "description": "Optional. Disk option config settings."
+ },
+ "machineTypeUri": {
+ "description": "Optional. The Google Compute Engine machine type used for cluster instances.A full URL, partial URI, or short name are valid. Examples:\nhttps://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2\nprojects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2\nn1-standard-2",
"type": "string"
},
- "jarFileUris": {
- "description": "Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.",
- "items": {
- "type": "string"
- },
- "type": "array"
+ "imageUri": {
+ "description": "Output-only. The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfig.image_version.",
+ "type": "string"
},
- "loggingConfig": {
- "$ref": "LoggingConfig",
- "description": "Optional. The runtime log config for job execution."
+ "managedGroupConfig": {
+ "$ref": "ManagedGroupConfig",
+ "description": "Output-only. The config for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups."
},
- "properties": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "Optional. A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.",
- "type": "object"
+ "isPreemptible": {
+ "description": "Optional. Specifies that this instance group contains preemptible instances.",
+ "type": "boolean"
},
- "args": {
- "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
+ "instanceNames": {
+ "description": "Optional. The list of instance names. Cloud Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Cloud Dataproc derive the name).",
"items": {
"type": "string"
},
"type": "array"
},
- "fileUris": {
- "description": "Optional. HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.",
+ "accelerators": {
+ "description": "Optional. The Google Compute Engine accelerator configuration for these instances.Beta Feature: This feature is still under development. It may be changed before final release.",
"items": {
- "type": "string"
+ "$ref": "AcceleratorConfig"
},
"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.",
+ "numInstances": {
+ "description": "Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.",
+ "format": "int32",
+ "type": "integer"
+ }
+ },
+ "type": "object"
+ },
+ "NodeInitializationAction": {
+ "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"
},
- "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.",
+ "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"
+ }
+ },
+ "type": "object"
+ },
+ "ListJobsResponse": {
+ "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": {
- "type": "string"
+ "$ref": "Job"
},
"type": "array"
}
},
"type": "object"
},
- "Job": {
- "description": "A Cloud Dataproc job resource.",
- "id": "Job",
- "properties": {
- "hiveJob": {
- "$ref": "HiveJob",
- "description": "Job is a Hive job."
+ "CancelJobRequest": {
+ "description": "A request to cancel a job.",
+ "id": "CancelJobRequest",
+ "properties": {},
+ "type": "object"
+ },
+ "SparkSqlJob": {
+ "description": "A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries.",
+ "id": "SparkSqlJob",
+ "properties": {
+ "scriptVariables": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name=\"value\";).",
+ "type": "object"
},
- "labels": {
+ "jarFileUris": {
+ "description": "Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "loggingConfig": {
+ "$ref": "LoggingConfig",
+ "description": "Optional. The runtime log config for job execution."
+ },
+ "properties": {
"additionalProperties": {
"type": "string"
},
- "description": "Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.",
+ "description": "Optional. A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.",
"type": "object"
},
- "driverOutputResourceUri": {
- "description": "Output-only. A URI pointing to the location of the stdout of the job's driver program.",
+ "queryFileUri": {
+ "description": "The HCFS URI of the script that contains SQL queries.",
"type": "string"
},
- "sparkSqlJob": {
- "$ref": "SparkSqlJob",
- "description": "Job is a SparkSql job."
+ "queryList": {
+ "$ref": "QueryList",
+ "description": "A list of queries."
+ }
+ },
+ "type": "object"
+ },
+ "Cluster": {
+ "description": "Describes the identifying information, config, and status of a cluster of Google Compute Engine instances.",
+ "id": "Cluster",
+ "properties": {
+ "labels": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Optional. The labels to associate with this cluster. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a cluster.",
+ "type": "object"
},
- "sparkJob": {
- "$ref": "SparkJob",
- "description": "Job is a Spark job."
+ "metrics": {
+ "$ref": "ClusterMetrics",
+ "description": "Contains cluster daemon metrics such as HDFS and YARN stats.Beta Feature: This report is available for testing purposes only. It may be changed before final release."
+ },
+ "status": {
+ "$ref": "ClusterStatus",
+ "description": "Output-only. Cluster status."
},
"statusHistory": {
- "description": "Output-only. The previous job status.",
+ "description": "Output-only. The previous cluster status.",
"items": {
- "$ref": "JobStatus"
+ "$ref": "ClusterStatus"
},
"type": "array"
},
- "yarnApplications": {
- "description": "Output-only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release.",
+ "config": {
+ "$ref": "ClusterConfig",
+ "description": "Required. The cluster config. Note that Cloud Dataproc may set default values, and values may change when clusters are updated."
+ },
+ "clusterUuid": {
+ "description": "Output-only. A cluster UUID (Unique Universal Identifier). Cloud Dataproc generates this value when it creates the cluster.",
+ "type": "string"
+ },
+ "clusterName": {
+ "description": "Required. The cluster name. Cluster names within a project must be unique. Names of deleted clusters can be reused.",
+ "type": "string"
+ },
+ "projectId": {
+ "description": "Required. The Google Cloud Platform project ID that the cluster belongs to.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "ListOperationsResponse": {
+ "description": "The response message for Operations.ListOperations.",
+ "id": "ListOperationsResponse",
+ "properties": {
+ "nextPageToken": {
+ "description": "The standard List next-page token.",
+ "type": "string"
+ },
+ "operations": {
+ "description": "A list of operations that matches the specified filter in the request.",
"items": {
- "$ref": "YarnApplication"
+ "$ref": "Operation"
},
"type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "SoftwareConfig": {
+ "description": "Specifies the selection and config of software inside the cluster.",
+ "id": "SoftwareConfig",
+ "properties": {
+ "imageVersion": {
+ "description": "Optional. The version of software inside the cluster. It must match the regular expression [0-9]+\\.[0-9]+. If unspecified, it defaults to the latest version (see Cloud Dataproc Versioning).",
+ "type": "string"
},
- "pysparkJob": {
- "$ref": "PySparkJob",
- "description": "Job is a Pyspark job."
+ "properties": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Optional. The properties to set on daemon config files.Property keys are specified in prefix:property format, such as core:fs.defaultFS. The following are supported prefixes and their mappings:\ncapacity-scheduler: capacity-scheduler.xml\ncore: core-site.xml\ndistcp: distcp-default.xml\nhdfs: hdfs-site.xml\nhive: hive-site.xml\nmapred: mapred-site.xml\npig: pig.properties\nspark: spark-defaults.conf\nyarn: yarn-site.xml",
+ "type": "object"
+ }
+ },
+ "type": "object"
+ },
+ "JobPlacement": {
+ "description": "Cloud Dataproc job config.",
+ "id": "JobPlacement",
+ "properties": {
+ "clusterUuid": {
+ "description": "Output-only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.",
+ "type": "string"
},
- "reference": {
- "$ref": "JobReference",
- "description": "Optional. The fully qualified reference to the job, which can be used to obtain the equivalent REST path of the job resource. If this property is not specified when a job is created, the server generates a <code>job_id</code>."
+ "clusterName": {
+ "description": "Required. The name of the cluster where the job will be submitted.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "PigJob": {
+ "description": "A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN.",
+ "id": "PigJob",
+ "properties": {
+ "jarFileUris": {
+ "description": "Optional. HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
},
- "hadoopJob": {
- "$ref": "HadoopJob",
- "description": "Job is a Hadoop job."
+ "scriptVariables": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value]).",
+ "type": "object"
},
- "placement": {
- "$ref": "JobPlacement",
- "description": "Required. Job information, including how, when, and where to run the job."
+ "loggingConfig": {
+ "$ref": "LoggingConfig",
+ "description": "Optional. The runtime log config for job execution."
},
- "status": {
- "$ref": "JobStatus",
- "description": "Output-only. The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields."
+ "properties": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Optional. A mapping of property names to values, used to configure Pig. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/pig/conf/pig.properties, and classes in user code.",
+ "type": "object"
},
- "driverControlFilesUri": {
- "description": "Output-only. If present, the location of miscellaneous control files which may be used as part of job setup and handling. If not present, control files may be placed in the same location as driver_output_uri.",
- "type": "string"
+ "continueOnFailure": {
+ "description": "Optional. Whether to continue executing queries if a query fails. The default value is false. Setting to true can be useful when executing independent parallel queries.",
+ "type": "boolean"
},
- "scheduling": {
- "$ref": "JobScheduling",
- "description": "Optional. Job scheduling configuration."
+ "queryList": {
+ "$ref": "QueryList",
+ "description": "A list of queries."
},
- "pigJob": {
- "$ref": "PigJob",
- "description": "Job is a Pig job."
+ "queryFileUri": {
+ "description": "The HCFS URI of the script that contains the Pig queries.",
+ "type": "string"
}
},
"type": "object"
},
- "JobStatus": {
- "description": "Cloud Dataproc job status.",
- "id": "JobStatus",
+ "ClusterStatus": {
+ "description": "The status of a cluster and its instances.",
+ "id": "ClusterStatus",
"properties": {
- "details": {
- "description": "Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.",
+ "detail": {
+ "description": "Output-only. Optional details of cluster's state.",
"type": "string"
},
"state": {
- "description": "Output-only. A state message specifying the overall job state.",
+ "description": "Output-only. The cluster's state.",
"enum": [
- "STATE_UNSPECIFIED",
- "PENDING",
- "SETUP_DONE",
+ "UNKNOWN",
+ "CREATING",
"RUNNING",
- "CANCEL_PENDING",
- "CANCEL_STARTED",
- "CANCELLED",
- "DONE",
"ERROR",
- "ATTEMPT_FAILURE"
+ "DELETING",
+ "UPDATING"
],
"enumDescriptions": [
- "The job state is unknown.",
- "The job is pending; it has been submitted, but is not yet running.",
- "Job has been received by the service and completed initial setup; it will soon be submitted to the cluster.",
- "The job is running on the cluster.",
- "A CancelJob request has been received, but is pending.",
- "Transient in-flight resources have been canceled, and the request to cancel the running job has been issued to the cluster.",
- "The job cancellation was successful.",
- "The job has completed successfully.",
- "The job has completed, but encountered an error.",
- "Job attempt has failed. The detail field contains failure details for this attempt.Applies to restartable jobs only."
+ "The cluster state is unknown.",
+ "The cluster is being created and set up. It is not ready for use.",
+ "The cluster is currently running and healthy. It is ready for use.",
+ "The cluster encountered an error. It is not ready for use.",
+ "The cluster is being deleted. It cannot be used.",
+ "The cluster is being updated. It continues to accept and process jobs."
],
"type": "string"
},
"substate": {
- "description": "Output-only. Additional state information, which includes status reported by the agent.",
+ "description": "Output-only. Additional state information that includes status reported by the agent.",
"enum": [
"UNSPECIFIED",
- "SUBMITTED",
- "QUEUED",
+ "UNHEALTHY",
"STALE_STATUS"
],
"enumDescriptions": [
"",
- "The Job is submitted to the agent.Applies to RUNNING state.",
- "The Job has been received and is awaiting execution (it may be waiting for a condition to be met). See the \"details\" field for the reason for the delay.Applies to RUNNING state.",
- "The agent-reported status is out of date, which may be caused by a loss of communication between the agent and Cloud Dataproc. If the agent does not send a timely update, the job will fail.Applies to RUNNING state."
+ "The cluster is known to be in an unhealthy state (for example, critical daemons are not running or HDFS capacity is exhausted).Applies to RUNNING state.",
+ "The agent-reported status is out of date (may occur if Cloud Dataproc loses communication with Agent).Applies to RUNNING state."
],
"type": "string"
},
"stateStartTime": {
- "description": "Output-only. The time when this state was entered.",
+ "description": "Output-only. Time when this state was entered.",
"format": "google-datetime",
"type": "string"
}
},
"type": "object"
},
- "ManagedGroupConfig": {
- "description": "Specifies the resources used to actively manage an instance group.",
- "id": "ManagedGroupConfig",
+ "ListClustersResponse": {
+ "description": "The list of all clusters in a project.",
+ "id": "ListClustersResponse",
+ "properties": {
+ "nextPageToken": {
+ "description": "Output-only. 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>ListClustersRequest</code>.",
+ "type": "string"
+ },
+ "clusters": {
+ "description": "Output-only. The clusters in the project.",
+ "items": {
+ "$ref": "Cluster"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "Job": {
+ "description": "A Cloud Dataproc job resource.",
+ "id": "Job",
+ "properties": {
+ "yarnApplications": {
+ "description": "Output-only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release.",
+ "items": {
+ "$ref": "YarnApplication"
+ },
+ "type": "array"
+ },
+ "pysparkJob": {
+ "$ref": "PySparkJob",
+ "description": "Job is a Pyspark job."
+ },
+ "reference": {
+ "$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>."
+ },
+ "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": {
+ "$ref": "JobPlacement",
+ "description": "Required. Job information, including how, when, and where to run the job."
+ },
+ "driverControlFilesUri": {
+ "description": "Output-only. If present, the location of miscellaneous control files which may be used as part of job setup and handling. If not present, control files may be placed in the same location as driver_output_uri.",
+ "type": "string"
+ },
+ "scheduling": {
+ "$ref": "JobScheduling",
+ "description": "Optional. Job scheduling configuration."
+ },
+ "pigJob": {
+ "$ref": "PigJob",
+ "description": "Job is a Pig job."
+ },
+ "hiveJob": {
+ "$ref": "HiveJob",
+ "description": "Job is a Hive job."
+ },
+ "labels": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.",
+ "type": "object"
+ },
+ "driverOutputResourceUri": {
+ "description": "Output-only. A URI pointing to the location of the stdout of the job's driver program.",
+ "type": "string"
+ },
+ "statusHistory": {
+ "description": "Output-only. The previous job status.",
+ "items": {
+ "$ref": "JobStatus"
+ },
+ "type": "array"
+ },
+ "sparkSqlJob": {
+ "$ref": "SparkSqlJob",
+ "description": "Job is a SparkSql job."
+ },
+ "sparkJob": {
+ "$ref": "SparkJob",
+ "description": "Job is a Spark job."
+ }
+ },
+ "type": "object"
+ },
+ "SparkJob": {
+ "description": "A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN.",
+ "id": "SparkJob",
+ "properties": {
+ "mainClass": {
+ "description": "The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris.",
+ "type": "string"
+ },
+ "archiveUris": {
+ "description": "Optional. HCFS URIs of archives to be extracted in the working directory of Spark drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "mainJarFileUri": {
+ "description": "The HCFS URI of the jar file that contains the main class.",
+ "type": "string"
+ },
+ "jarFileUris": {
+ "description": "Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "loggingConfig": {
+ "$ref": "LoggingConfig",
+ "description": "Optional. The runtime log config for job execution."
+ },
+ "properties": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Optional. A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.",
+ "type": "object"
+ },
+ "args": {
+ "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "fileUris": {
+ "description": "Optional. HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "JobStatus": {
+ "description": "Cloud Dataproc job status.",
+ "id": "JobStatus",
+ "properties": {
+ "details": {
+ "description": "Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.",
+ "type": "string"
+ },
+ "state": {
+ "description": "Output-only. A state message specifying the overall job state.",
+ "enum": [
+ "STATE_UNSPECIFIED",
+ "PENDING",
+ "SETUP_DONE",
+ "RUNNING",
+ "CANCEL_PENDING",
+ "CANCEL_STARTED",
+ "CANCELLED",
+ "DONE",
+ "ERROR",
+ "ATTEMPT_FAILURE"
+ ],
+ "enumDescriptions": [
+ "The job state is unknown.",
+ "The job is pending; it has been submitted, but is not yet running.",
+ "Job has been received by the service and completed initial setup; it will soon be submitted to the cluster.",
+ "The job is running on the cluster.",
+ "A CancelJob request has been received, but is pending.",
+ "Transient in-flight resources have been canceled, and the request to cancel the running job has been issued to the cluster.",
+ "The job cancellation was successful.",
+ "The job has completed successfully.",
+ "The job has completed, but encountered an error.",
+ "Job attempt has failed. The detail field contains failure details for this attempt.Applies to restartable jobs only."
+ ],
+ "type": "string"
+ },
+ "substate": {
+ "description": "Output-only. Additional state information, which includes status reported by the agent.",
+ "enum": [
+ "UNSPECIFIED",
+ "SUBMITTED",
+ "QUEUED",
+ "STALE_STATUS"
+ ],
+ "enumDescriptions": [
+ "",
+ "The Job is submitted to the agent.Applies to RUNNING state.",
+ "The Job has been received and is awaiting execution (it may be waiting for a condition to be met). See the \"details\" field for the reason for the delay.Applies to RUNNING state.",
+ "The agent-reported status is out of date, which may be caused by a loss of communication between the agent and Cloud Dataproc. If the agent does not send a timely update, the job will fail.Applies to RUNNING state."
+ ],
+ "type": "string"
+ },
+ "stateStartTime": {
+ "description": "Output-only. The time when this state was entered.",
+ "format": "google-datetime",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "ManagedGroupConfig": {
+ "description": "Specifies the resources used to actively manage an instance group.",
+ "id": "ManagedGroupConfig",
"properties": {
"instanceGroupManagerName": {
"description": "Output-only. The name of the Instance Group Manager for this group.",
@@ -969,11 +1324,6 @@
"description": "The status of the operation.",
"id": "ClusterOperationStatus",
"properties": {
- "stateStartTime": {
- "description": "Output-only. The time this state was entered.",
- "format": "google-datetime",
- "type": "string"
- },
"details": {
"description": "Output-only.A message containing any operation metadata details.",
"type": "string"
@@ -997,20 +1347,11 @@
"innerState": {
"description": "Output-only. A message containing the detailed operation state.",
"type": "string"
- }
- },
- "type": "object"
- },
- "QueryList": {
- "description": "A list of queries to run on a cluster.",
- "id": "QueryList",
- "properties": {
- "queries": {
- "description": "Required. The queries to execute. You do not need to terminate a query with a semicolon. Multiple queries can be specified in one string by separating each with a semicolon. Here is an example of an Cloud Dataproc API snippet that uses a QueryList to specify a HiveJob:\n\"hiveJob\": {\n \"queryList\": {\n \"queries\": [\n \"query1\",\n \"query2\",\n \"query3;query4\",\n ]\n }\n}\n",
- "items": {
- "type": "string"
- },
- "type": "array"
+ },
+ "stateStartTime": {
+ "description": "Output-only. The time this state was entered.",
+ "format": "google-datetime",
+ "type": "string"
}
},
"type": "object"
@@ -1019,6 +1360,15 @@
"description": "A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.Beta Feature: This report is available for testing purposes only. It may be changed before final release.",
"id": "YarnApplication",
"properties": {
+ "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"
+ },
"state": {
"description": "Required. The application state.",
"enum": [
@@ -1048,263 +1398,30 @@
"name": {
"description": "Required. The application name.",
"type": "string"
- },
- "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"
},
- "HadoopJob": {
- "description": "A Cloud Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html).",
- "id": "HadoopJob",
+ "QueryList": {
+ "description": "A list of queries to run on a cluster.",
+ "id": "QueryList",
"properties": {
- "mainJarFileUri": {
- "description": "The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'",
- "type": "string"
- },
- "jarFileUris": {
- "description": "Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.",
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- "loggingConfig": {
- "$ref": "LoggingConfig",
- "description": "Optional. The runtime log config for job execution."
- },
- "properties": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "Optional. A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.",
- "type": "object"
- },
- "args": {
- "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as -libjars or -Dfoo=bar, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- "fileUris": {
- "description": "Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.",
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- "mainClass": {
- "description": "The name of the driver's main class. The jar file containing 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 Hadoop drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, or .zip.",
- "items": {
- "type": "string"
- },
- "type": "array"
- }
- },
- "type": "object"
- },
- "DiagnoseClusterRequest": {
- "description": "A request to collect cluster diagnostic information.",
- "id": "DiagnoseClusterRequest",
- "properties": {},
- "type": "object"
- },
- "DiskConfig": {
- "description": "Specifies the config of disk options for a group of VM instances.",
- "id": "DiskConfig",
- "properties": {
- "bootDiskSizeGb": {
- "description": "Optional. Size in GB of the boot disk (default is 500GB).",
- "format": "int32",
- "type": "integer"
- },
- "numLocalSsds": {
- "description": "Optional. Number of attached SSDs, from 0 to 4 (default is 0). If SSDs are not attached, the boot disk is used to store runtime logs and HDFS (https://hadoop.apache.org/docs/r1.2.1/hdfs_user_guide.html) data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic config and installed binaries.",
- "format": "int32",
- "type": "integer"
- }
- },
- "type": "object"
- },
- "ClusterOperationMetadata": {
- "description": "Metadata describing the operation.",
- "id": "ClusterOperationMetadata",
- "properties": {
- "operationType": {
- "description": "Output-only. The operation type.",
- "type": "string"
- },
- "description": {
- "description": "Output-only. Short description of operation.",
- "type": "string"
- },
- "warnings": {
- "description": "Output-only. Errors encountered during operation execution.",
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- "labels": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "Output-only. Labels associated with the operation",
- "type": "object"
- },
- "status": {
- "$ref": "ClusterOperationStatus",
- "description": "Output-only. Current operation status."
- },
- "statusHistory": {
- "description": "Output-only. The previous operation status.",
- "items": {
- "$ref": "ClusterOperationStatus"
- },
- "type": "array"
- },
- "clusterName": {
- "description": "Output-only. Name of the cluster for the operation.",
- "type": "string"
- },
- "clusterUuid": {
- "description": "Output-only. Cluster UUID for the operation.",
- "type": "string"
- }
- },
- "type": "object"
- },
- "HiveJob": {
- "description": "A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN.",
- "id": "HiveJob",
- "properties": {
- "properties": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "Optional. A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.",
- "type": "object"
- },
- "continueOnFailure": {
- "description": "Optional. Whether to continue executing queries if a query fails. The default value is false. Setting to true can be useful when executing independent parallel queries.",
- "type": "boolean"
- },
- "queryList": {
- "$ref": "QueryList",
- "description": "A list of queries."
- },
- "queryFileUri": {
- "description": "The HCFS URI of the script that contains Hive queries.",
- "type": "string"
- },
- "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.",
+ "queries": {
+ "description": "Required. The queries to execute. You do not need to terminate a query with a semicolon. Multiple queries can be specified in one string by separating each with a semicolon. Here is an example of an Cloud Dataproc API snippet that uses a QueryList to specify a HiveJob:\n\"hiveJob\": {\n \"queryList\": {\n \"queries\": [\n \"query1\",\n \"query2\",\n \"query3;query4\",\n ]\n }\n}\n",
"items": {
"type": "string"
},
"type": "array"
- },
- "scriptVariables": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name=\"value\";).",
- "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",
- "properties": {
- "outputUri": {
- "description": "Output-only. The Google Cloud Storage URI of the diagnostic output. The output report is a plain text file with a summary of collected diagnostics.",
- "type": "string"
- }
- },
- "type": "object"
- },
- "ClusterConfig": {
- "description": "The cluster config.",
- "id": "ClusterConfig",
- "properties": {
- "initializationActions": {
- "description": "Optional. Commands to execute on each node after config is completed. By default, executables are run on master and all worker nodes. You can test a node's role metadata to run an executable on a master or worker node, as shown below using curl (you can also use wget):\nROLE=$(curl -H Metadata-Flavor:Google http://metadata/computeMetadata/v1/instance/attributes/dataproc-role)\nif [[ \"${ROLE}\" == 'Master' ]]; then\n ... master specific actions ...\nelse\n ... worker specific actions ...\nfi\n",
- "items": {
- "$ref": "NodeInitializationAction"
- },
- "type": "array"
- },
- "configBucket": {
- "description": "Optional. A Google Cloud Storage staging bucket used for sharing generated SSH keys and config. If you do not specify a staging bucket, Cloud Dataproc will determine an appropriate Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Google Compute Engine zone where your cluster is deployed, and then it will create and manage this project-level, per-location bucket for you.",
- "type": "string"
- },
- "workerConfig": {
- "$ref": "InstanceGroupConfig",
- "description": "Optional. The Google Compute Engine config settings for worker instances in a cluster."
- },
- "gceClusterConfig": {
- "$ref": "GceClusterConfig",
- "description": "Required. The shared Google Compute Engine config settings for all instances in a cluster."
- },
- "softwareConfig": {
- "$ref": "SoftwareConfig",
- "description": "Optional. The config settings for software inside the cluster."
- },
- "masterConfig": {
- "$ref": "InstanceGroupConfig",
- "description": "Optional. The Google Compute Engine config settings for the master instance in a cluster."
- },
- "secondaryWorkerConfig": {
- "$ref": "InstanceGroupConfig",
- "description": "Optional. The Google Compute Engine config settings for additional worker instances in a cluster."
}
},
"type": "object"
},
- "PySparkJob": {
- "description": "A Cloud Dataproc job for running Apache PySpark (https://spark.apache.org/docs/0.9.0/python-programming-guide.html) applications on YARN.",
- "id": "PySparkJob",
+ "HadoopJob": {
+ "description": "A Cloud Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html).",
+ "id": "HadoopJob",
"properties": {
- "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 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.",
+ "description": "Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.",
"items": {
"type": "string"
},
@@ -1318,556 +1435,428 @@
"additionalProperties": {
"type": "string"
},
- "description": "Optional. A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.",
+ "description": "Optional. A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.",
"type": "object"
},
"args": {
- "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
+ "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as -libjars or -Dfoo=bar, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
"items": {
"type": "string"
},
"type": "array"
},
"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"
- }
- },
- "type": "object"
- },
- "GceClusterConfig": {
- "description": "Common config settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster.",
- "id": "GceClusterConfig",
- "properties": {
- "subnetworkUri": {
- "description": "Optional. 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"
- },
- "networkUri": {
- "description": "Optional. 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 Using Subnetworks for more information). Example: https://www.googleapis.com/compute/v1/projects/[project_id]/regions/global/default.",
- "type": "string"
- },
- "zoneUri": {
- "description": "Required. The zone where the Google Compute Engine cluster will be located. Example: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone].",
- "type": "string"
- },
- "internalIpOnly": {
- "description": "Optional. If true, all instances in the cluster will only have internal IP addresses. By default, clusters are not restricted to internal IP addresses, and will have ephemeral external IP addresses assigned to each instance. This internal_ip_only restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses.",
- "type": "boolean"
- },
- "metadata": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "The Google Compute Engine metadata entries to add to all instances (see Project and instance metadata (https://cloud.google.com/compute/docs/storing-retrieving-metadata#project_and_instance_metadata)).",
- "type": "object"
- },
- "serviceAccountScopes": {
- "description": "Optional. The URIs of service account scopes to be included in Google Compute Engine instances. The following base set of scopes is always included:\nhttps://www.googleapis.com/auth/cloud.useraccounts.readonly\nhttps://www.googleapis.com/auth/devstorage.read_write\nhttps://www.googleapis.com/auth/logging.writeIf no scopes are specified, the following defaults are also provided:\nhttps://www.googleapis.com/auth/bigquery\nhttps://www.googleapis.com/auth/bigtable.admin.table\nhttps://www.googleapis.com/auth/bigtable.data\nhttps://www.googleapis.com/auth/devstorage.full_control",
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- "tags": {
- "description": "The Google Compute Engine tags to add to all instances (see Tagging instances).",
+ "description": "Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.",
"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"
- }
- },
- "type": "object"
- },
- "AcceleratorConfig": {
- "description": "Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine).",
- "id": "AcceleratorConfig",
- "properties": {
- "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"
- },
- "acceleratorCount": {
- "description": "The number of the accelerator cards of this type exposed to this instance.",
- "format": "int32",
- "type": "integer"
- }
- },
- "type": "object"
- },
- "ClusterMetrics": {
- "description": "Contains cluster daemon metrics, such as HDFS and YARN stats.Beta Feature: This report is available for testing purposes only. It may be changed before final release.",
- "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"
- },
- "LoggingConfig": {
- "description": "The runtime logging config of the job.",
- "id": "LoggingConfig",
- "properties": {
- "driverLogLevels": {
- "additionalProperties": {
- "enum": [
- "LEVEL_UNSPECIFIED",
- "ALL",
- "TRACE",
- "DEBUG",
- "INFO",
- "WARN",
- "ERROR",
- "FATAL",
- "OFF"
- ],
- "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"
- },
- "Operation": {
- "description": "This resource represents a long-running operation that is the result of a network API call.",
- "id": "Operation",
- "properties": {
- "response": {
- "additionalProperties": {
- "description": "Properties of the object. Contains field @type with type URL.",
- "type": "any"
- },
- "description": "The normal response of the operation in case of success. If the original method returns no data on success, such as Delete, the response is google.protobuf.Empty. If the original method is standard Get/Create/Update, the response should be the resource. For other methods, the response should have the type XxxResponse, where Xxx is the original method name. For example, if the original method name is TakeSnapshot(), the inferred response type is TakeSnapshotResponse.",
- "type": "object"
- },
- "name": {
- "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the name should have the format of operations/some/unique/name.",
+ "mainClass": {
+ "description": "The name of the driver's main class. The jar file containing the class must be in the default CLASSPATH or specified in jar_file_uris.",
"type": "string"
},
- "error": {
- "$ref": "Status",
- "description": "The error result of the operation in case of failure or cancellation."
- },
- "metadata": {
- "additionalProperties": {
- "description": "Properties of the object. Contains field @type with type URL.",
- "type": "any"
+ "archiveUris": {
+ "description": "Optional. HCFS URIs of archives to be extracted in the working directory of Hadoop drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, or .zip.",
+ "items": {
+ "type": "string"
},
- "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"
+ "type": "array"
},
- "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"
+ "mainJarFileUri": {
+ "description": "The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'",
+ "type": "string"
}
},
"type": "object"
},
- "JobReference": {
- "description": "Encapsulates the full scoping used to reference a job.",
- "id": "JobReference",
- "properties": {
- "jobId": {
- "description": "Optional. 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"
- },
- "projectId": {
- "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
- "type": "string"
- }
- },
+ "DiagnoseClusterRequest": {
+ "description": "A request to collect cluster diagnostic information.",
+ "id": "DiagnoseClusterRequest",
+ "properties": {},
"type": "object"
},
- "SubmitJobRequest": {
- "description": "A request to submit a job.",
- "id": "SubmitJobRequest",
+ "DiskConfig": {
+ "description": "Specifies the config of disk options for a group of VM instances.",
+ "id": "DiskConfig",
"properties": {
- "job": {
- "$ref": "Job",
- "description": "Required. The job resource."
+ "numLocalSsds": {
+ "description": "Optional. Number of attached SSDs, from 0 to 4 (default is 0). If SSDs are not attached, the boot disk is used to store runtime logs and HDFS (https://hadoop.apache.org/docs/r1.2.1/hdfs_user_guide.html) data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic config and installed binaries.",
+ "format": "int32",
+ "type": "integer"
+ },
+ "bootDiskSizeGb": {
+ "description": "Optional. Size in GB of the boot disk (default is 500GB).",
+ "format": "int32",
+ "type": "integer"
}
},
"type": "object"
},
- "Status": {
- "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 that 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.\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",
+ "ClusterOperationMetadata": {
+ "description": "Metadata describing the operation.",
+ "id": "ClusterOperationMetadata",
"properties": {
- "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.",
+ "description": {
+ "description": "Output-only. Short description of operation.",
"type": "string"
},
- "details": {
- "description": "A list of messages that carry the error details. There will be a common set of message types for APIs to use.",
+ "warnings": {
+ "description": "Output-only. Errors encountered during operation execution.",
"items": {
- "additionalProperties": {
- "description": "Properties of the object. Contains field @type with type URL.",
- "type": "any"
- },
- "type": "object"
+ "type": "string"
},
"type": "array"
},
- "code": {
- "description": "The status code, which should be an enum value of google.rpc.Code.",
- "format": "int32",
- "type": "integer"
- }
- },
- "type": "object"
- },
- "InstanceGroupConfig": {
- "description": "Optional. The config settings for Google Compute Engine resources in an instance group, such as a master or worker group.",
- "id": "InstanceGroupConfig",
- "properties": {
- "numInstances": {
- "description": "Required. The number of VM instances in the instance group. For master instance groups, must be set to 1.",
- "format": "int32",
- "type": "integer"
+ "labels": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Output-only. Labels associated with the operation",
+ "type": "object"
},
- "diskConfig": {
- "$ref": "DiskConfig",
- "description": "Optional. Disk option config settings."
+ "status": {
+ "$ref": "ClusterOperationStatus",
+ "description": "Output-only. Current operation status."
},
- "managedGroupConfig": {
- "$ref": "ManagedGroupConfig",
- "description": "Output-only. The config for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups."
+ "statusHistory": {
+ "description": "Output-only. The previous operation status.",
+ "items": {
+ "$ref": "ClusterOperationStatus"
+ },
+ "type": "array"
},
- "machineTypeUri": {
- "description": "Required. 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.",
+ "clusterName": {
+ "description": "Output-only. Name of the cluster for the operation.",
"type": "string"
},
- "imageUri": {
- "description": "Output-only. The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfig.image_version.",
+ "clusterUuid": {
+ "description": "Output-only. Cluster UUID for the operation.",
"type": "string"
},
- "isPreemptible": {
- "description": "Optional. Specifies that this instance group contains preemptible instances.",
+ "operationType": {
+ "description": "Output-only. The operation type.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "HiveJob": {
+ "description": "A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN.",
+ "id": "HiveJob",
+ "properties": {
+ "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"
},
- "instanceNames": {
- "description": "Optional. The list of instance names. Cloud Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Cloud Dataproc derive the name).",
+ "queryList": {
+ "$ref": "QueryList",
+ "description": "A list of queries."
+ },
+ "queryFileUri": {
+ "description": "The HCFS URI of the script that contains Hive queries.",
+ "type": "string"
+ },
+ "jarFileUris": {
+ "description": "Optional. HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.",
"items": {
"type": "string"
},
"type": "array"
},
- "accelerators": {
- "description": "Optional. The Google Compute Engine accelerator configuration for these instances.Beta Feature: This feature is still under development. It may be changed before final release.",
- "items": {
- "$ref": "AcceleratorConfig"
+ "scriptVariables": {
+ "additionalProperties": {
+ "type": "string"
},
- "type": "array"
+ "description": "Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name=\"value\";).",
+ "type": "object"
+ },
+ "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"
}
},
"type": "object"
},
- "JobScheduling": {
- "description": "Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release.",
- "id": "JobScheduling",
- "properties": {
- "maxFailuresPerHour": {
- "description": "Optional. Maximum number of times per hour a driver may be restarted as a result of driver terminating with non-zero code before job is reported failed.A job may be reported as thrashing if driver exits with non-zero code 4 times within 10 minute window.Maximum value is 10.",
- "format": "int32",
- "type": "integer"
- }
- },
+ "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"
},
- "ListJobsResponse": {
- "description": "A list of jobs in a project.",
- "id": "ListJobsResponse",
+ "ClusterConfig": {
+ "description": "The cluster config.",
+ "id": "ClusterConfig",
"properties": {
- "jobs": {
- "description": "Output-only. Jobs list.",
+ "gceClusterConfig": {
+ "$ref": "GceClusterConfig",
+ "description": "Required. The shared Google Compute Engine config settings for all instances in a cluster."
+ },
+ "softwareConfig": {
+ "$ref": "SoftwareConfig",
+ "description": "Optional. The config settings for software inside the cluster."
+ },
+ "masterConfig": {
+ "$ref": "InstanceGroupConfig",
+ "description": "Optional. The Google Compute Engine config settings for the master instance in a cluster."
+ },
+ "secondaryWorkerConfig": {
+ "$ref": "InstanceGroupConfig",
+ "description": "Optional. The Google Compute Engine config settings for additional worker instances in a cluster."
+ },
+ "initializationActions": {
+ "description": "Optional. Commands to execute on each node after config 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 using curl (you can also use wget):\nROLE=$(curl -H Metadata-Flavor:Google http://metadata/computeMetadata/v1beta2/instance/attributes/dataproc-role)\nif [[ \"${ROLE}\" == 'Master' ]]; then\n ... master specific actions ...\nelse\n ... worker specific actions ...\nfi\n",
"items": {
- "$ref": "Job"
+ "$ref": "NodeInitializationAction"
},
"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"
- },
- "NodeInitializationAction": {
- "description": "Specifies an executable to run on a fully configured node and a timeout period for executable completion.",
- "id": "NodeInitializationAction",
- "properties": {
- "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",
+ "configBucket": {
+ "description": "Optional. A Google Cloud Storage staging bucket used for sharing generated SSH keys and config. 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"
},
- "executableFile": {
- "description": "Required. Google Cloud Storage URI of executable file.",
- "type": "string"
+ "workerConfig": {
+ "$ref": "InstanceGroupConfig",
+ "description": "Optional. The Google Compute Engine config settings for worker instances in a cluster."
}
},
"type": "object"
},
- "CancelJobRequest": {
- "description": "A request to cancel a job.",
- "id": "CancelJobRequest",
- "properties": {},
- "type": "object"
- },
- "SparkSqlJob": {
- "description": "A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries.",
- "id": "SparkSqlJob",
+ "PySparkJob": {
+ "description": "A Cloud Dataproc job for running Apache PySpark (https://spark.apache.org/docs/0.9.0/python-programming-guide.html) applications on YARN.",
+ "id": "PySparkJob",
"properties": {
+ "jarFileUris": {
+ "description": "Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "loggingConfig": {
+ "$ref": "LoggingConfig",
+ "description": "Optional. The runtime log config for job execution."
+ },
"properties": {
"additionalProperties": {
"type": "string"
},
- "description": "Optional. A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.",
+ "description": "Optional. A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.",
"type": "object"
},
- "queryList": {
- "$ref": "QueryList",
- "description": "A list of queries."
- },
- "queryFileUri": {
- "description": "The HCFS URI of the script that contains SQL queries.",
- "type": "string"
+ "args": {
+ "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
},
- "scriptVariables": {
- "additionalProperties": {
+ "fileUris": {
+ "description": "Optional. HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.",
+ "items": {
"type": "string"
},
- "description": "Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name=\"value\";).",
- "type": "object"
+ "type": "array"
},
- "jarFileUris": {
- "description": "Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.",
+ "pythonFileUris": {
+ "description": "Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.",
"items": {
"type": "string"
},
"type": "array"
},
- "loggingConfig": {
- "$ref": "LoggingConfig",
- "description": "Optional. The runtime log config for job execution."
+ "mainPythonFileUri": {
+ "description": "Required. The 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"
}
},
"type": "object"
},
- "Cluster": {
- "description": "Describes the identifying information, config, and status of a cluster of Google Compute Engine instances.",
- "id": "Cluster",
+ "GceClusterConfig": {
+ "description": "Common config settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster.",
+ "id": "GceClusterConfig",
"properties": {
- "labels": {
+ "metadata": {
"additionalProperties": {
"type": "string"
},
- "description": "Optional. The labels to associate with this cluster. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a cluster.",
+ "description": "The Google Compute Engine metadata entries to add to all instances (see Project and instance metadata (https://cloud.google.com/compute/docs/storing-retrieving-metadata#project_and_instance_metadata)).",
"type": "object"
},
- "metrics": {
- "$ref": "ClusterMetrics",
- "description": "Contains cluster daemon metrics such as HDFS and YARN stats.Beta Feature: This report is available for testing purposes only. It may be changed before final release."
+ "internalIpOnly": {
+ "description": "Optional. If true, all instances in the cluster will only have internal IP addresses. By default, clusters are not restricted to internal IP addresses, and will have ephemeral external IP addresses assigned to each instance. This internal_ip_only restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses.",
+ "type": "boolean"
},
- "status": {
- "$ref": "ClusterStatus",
- "description": "Output-only. Cluster status."
+ "serviceAccountScopes": {
+ "description": "Optional. The URIs of service account scopes to be included in Google Compute Engine instances. The following base set of scopes is always included:\nhttps://www.googleapis.com/auth/cloud.useraccounts.readonly\nhttps://www.googleapis.com/auth/devstorage.read_write\nhttps://www.googleapis.com/auth/logging.writeIf no scopes are specified, the following defaults are also provided:\nhttps://www.googleapis.com/auth/bigquery\nhttps://www.googleapis.com/auth/bigtable.admin.table\nhttps://www.googleapis.com/auth/bigtable.data\nhttps://www.googleapis.com/auth/devstorage.full_control",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
},
- "statusHistory": {
- "description": "Output-only. The previous cluster status.",
+ "tags": {
+ "description": "The Google Compute Engine tags to add to all instances (see Tagging instances).",
"items": {
- "$ref": "ClusterStatus"
+ "type": "string"
},
"type": "array"
},
- "config": {
- "$ref": "ClusterConfig",
- "description": "Required. The cluster config. Note that Cloud Dataproc may set default values, and values may change when clusters are updated."
+ "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"
},
- "clusterUuid": {
- "description": "Output-only. A cluster UUID (Unique Universal Identifier). Cloud Dataproc generates this value when it creates the cluster.",
+ "subnetworkUri": {
+ "description": "Optional. The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri.A full URL, partial URI, or short name are valid. Examples:\nhttps://www.googleapis.com/compute/v1/projects/[project_id]/regions/us-east1/sub0\nprojects/[project_id]/regions/us-east1/sub0\nsub0",
"type": "string"
},
- "clusterName": {
- "description": "Required. The cluster name. Cluster names within a project must be unique. Names of deleted clusters can be reused.",
+ "networkUri": {
+ "description": "Optional. 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 Using Subnetworks for more information).A full URL, partial URI, or short name are valid. Examples:\nhttps://www.googleapis.com/compute/v1/projects/[project_id]/regions/global/default\nprojects/[project_id]/regions/global/default\ndefault",
"type": "string"
},
- "projectId": {
- "description": "Required. The Google Cloud Platform project ID that the cluster belongs to.",
+ "zoneUri": {
+ "description": "Optional. The zone where the Google Compute Engine cluster will be located. On a create request, it is required in the \"global\" region. If omitted in a non-global Cloud Dataproc region, the service will pick a zone in the corresponding GCE region. On a get request, zone will always be present.A full URL, partial URI, or short name are valid. Examples:\nhttps://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]\nprojects/[project_id]/zones/[zone]\nus-central1-f",
"type": "string"
}
},
"type": "object"
},
- "ListOperationsResponse": {
- "description": "The response message for Operations.ListOperations.",
- "id": "ListOperationsResponse",
+ "ClusterMetrics": {
+ "description": "Contains cluster daemon metrics, such as HDFS and YARN stats.Beta Feature: This report is available for testing purposes only. It may be changed before final release.",
+ "id": "ClusterMetrics",
"properties": {
- "nextPageToken": {
- "description": "The standard List next-page token.",
- "type": "string"
- },
- "operations": {
- "description": "A list of operations that matches the specified filter in the request.",
- "items": {
- "$ref": "Operation"
+ "hdfsMetrics": {
+ "additionalProperties": {
+ "format": "int64",
+ "type": "string"
},
- "type": "array"
- }
- },
- "type": "object"
- },
- "SoftwareConfig": {
- "description": "Specifies the selection and config of software inside the cluster.",
- "id": "SoftwareConfig",
- "properties": {
- "imageVersion": {
- "description": "Optional. The version of software inside the cluster. It must match the regular expression [0-9]+\\.[0-9]+. If unspecified, it defaults to the latest version (see Cloud Dataproc Versioning).",
- "type": "string"
+ "description": "The HDFS metrics.",
+ "type": "object"
},
- "properties": {
+ "yarnMetrics": {
"additionalProperties": {
+ "format": "int64",
"type": "string"
},
- "description": "Optional. The properties to set on daemon config files.Property keys are specified in prefix:property format, such as core:fs.defaultFS. The following are supported prefixes and their mappings:\ncapacity-scheduler: capacity-scheduler.xml\ncore: core-site.xml\ndistcp: distcp-default.xml\nhdfs: hdfs-site.xml\nhive: hive-site.xml\nmapred: mapred-site.xml\npig: pig.properties\nspark: spark-defaults.conf\nyarn: yarn-site.xml",
+ "description": "The YARN metrics.",
"type": "object"
}
},
"type": "object"
},
- "JobPlacement": {
- "description": "Cloud Dataproc job config.",
- "id": "JobPlacement",
+ "AcceleratorConfig": {
+ "description": "Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine).",
+ "id": "AcceleratorConfig",
"properties": {
- "clusterUuid": {
- "description": "Output-only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.",
- "type": "string"
+ "acceleratorCount": {
+ "description": "The number of the accelerator cards of this type exposed to this instance.",
+ "format": "int32",
+ "type": "integer"
},
- "clusterName": {
- "description": "Required. The name of the cluster where the job will be submitted.",
+ "acceleratorTypeUri": {
+ "description": "Full URL, partial URI, or short name of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes)Examples * https://www.googleapis.com/compute/beta/projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80 * projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80 * nvidia-tesla-k80",
"type": "string"
}
},
"type": "object"
},
- "PigJob": {
- "description": "A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN.",
- "id": "PigJob",
+ "LoggingConfig": {
+ "description": "The runtime logging config of the job.",
+ "id": "LoggingConfig",
"properties": {
- "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"
- },
- "scriptVariables": {
+ "driverLogLevels": {
"additionalProperties": {
+ "enum": [
+ "LEVEL_UNSPECIFIED",
+ "ALL",
+ "TRACE",
+ "DEBUG",
+ "INFO",
+ "WARN",
+ "ERROR",
+ "FATAL",
+ "OFF"
+ ],
"type": "string"
},
- "description": "Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value]).",
+ "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"
+ },
+ "Operation": {
+ "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"
},
- "loggingConfig": {
- "$ref": "LoggingConfig",
- "description": "Optional. The runtime log config for job execution."
- },
- "properties": {
+ "response": {
"additionalProperties": {
- "type": "string"
+ "description": "Properties of the object. Contains field @type with type URL.",
+ "type": "any"
},
- "description": "Optional. A mapping of property names to values, used to configure Pig. 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/pig/conf/pig.properties, and classes in user code.",
+ "description": "The normal response of the operation in case of success. If the original method returns no data on success, such as Delete, the response is google.protobuf.Empty. If the original method is standard Get/Create/Update, the response should be the resource. For other methods, the response should have the type XxxResponse, where Xxx is the original method name. For example, if the original method name is TakeSnapshot(), the inferred response type is TakeSnapshotResponse.",
"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"
+ "name": {
+ "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the name should have the format of operations/some/unique/name.",
+ "type": "string"
},
- "queryList": {
- "$ref": "QueryList",
- "description": "A list of queries."
+ "error": {
+ "$ref": "Status",
+ "description": "The error result of the operation in case of failure or cancellation."
},
- "queryFileUri": {
- "description": "The HCFS URI of the script that contains the Pig queries.",
- "type": "string"
+ "metadata": {
+ "additionalProperties": {
+ "description": "Properties of the object. Contains field @type with type URL.",
+ "type": "any"
+ },
+ "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"
}
},
"type": "object"
},
- "ClusterStatus": {
- "description": "The status of a cluster and its instances.",
- "id": "ClusterStatus",
+ "JobReference": {
+ "description": "Encapsulates the full scoping used to reference a job.",
+ "id": "JobReference",
"properties": {
- "substate": {
- "description": "Output-only. Additional state information that includes status reported by the agent.",
- "enum": [
- "UNSPECIFIED",
- "UNHEALTHY",
- "STALE_STATUS"
- ],
- "enumDescriptions": [
- "",
- "The cluster is known to be in an unhealthy state (for example, critical daemons are not running or HDFS capacity is exhausted).Applies to RUNNING state.",
- "The agent-reported status is out of date (may occur if Cloud Dataproc loses communication with Agent).Applies to RUNNING state."
- ],
- "type": "string"
- },
- "stateStartTime": {
- "description": "Output-only. Time when this state was entered.",
- "format": "google-datetime",
- "type": "string"
- },
- "detail": {
- "description": "Output-only. Optional details of cluster's state.",
+ "jobId": {
+ "description": "Optional. 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"
},
- "state": {
- "description": "Output-only. The cluster's state.",
- "enum": [
- "UNKNOWN",
- "CREATING",
- "RUNNING",
- "ERROR",
- "DELETING",
- "UPDATING"
- ],
- "enumDescriptions": [
- "The cluster state is unknown.",
- "The cluster is being created and set up. It is not ready for use.",
- "The cluster is currently running and healthy. It is ready for use.",
- "The cluster encountered an error. It is not ready for use.",
- "The cluster is being deleted. It cannot be used.",
- "The cluster is being updated. It continues to accept and process jobs."
- ],
+ "projectId": {
+ "description": "Required. The ID of the Google Cloud Platform project that the job belongs to.",
"type": "string"
}
},
"type": "object"
+ },
+ "SubmitJobRequest": {
+ "description": "A request to submit a job.",
+ "id": "SubmitJobRequest",
+ "properties": {
+ "job": {
+ "$ref": "Job",
+ "description": "Required. The job resource."
+ }
+ },
+ "type": "object"
}
},
"servicePath": "",
"title": "Google Cloud Dataproc API",
- "version": "v1"
+ "version": "v1beta2"
}
« no previous file with comments | « discovery/googleapis/dataproc__v1.json ('k') | discovery/googleapis/datastore__v1.json » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698