{ "parameters": { "callback": { "type": "string", "description": "JSONP", "location": "query" }, "prettyPrint": { "default": "true", "description": "Returns response with indentations and line breaks.", "location": "query", "type": "boolean" }, "quotaUser": { "type": "string", "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" }, "access_token": { "type": "string", "description": "OAuth access token.", "location": "query" }, "upload_protocol": { "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", "type": "string", "location": "query" }, "key": { "location": "query", "type": "string", "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token." }, "alt": { "default": "json", "type": "string", "location": "query", "description": "Data format for response.", "enumDescriptions": [ "Responses with Content-Type of application/json", "Media download with context-dependent Content-Type", "Responses with Content-Type of application/x-protobuf" ], "enum": [ "json", "media", "proto" ] }, "uploadType": { "location": "query", "type": "string", "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\")." }, "oauth_token": { "type": "string", "location": "query", "description": "OAuth 2.0 token for the current user." }, "$.xgafv": { "description": "V1 error format.", "location": "query", "enum": [ "1", "2" ], "enumDescriptions": [ "v1 error format", "v2 error format" ], "type": "string" }, "fields": { "location": "query", "description": "Selector specifying which fields to include in a partial response.", "type": "string" } }, "title": "Cloud Dataproc API", "description": "Manages Hadoop-based clusters and jobs on Cloud de Confiance Platform.", "resources": { "projects": { "resources": { "regions": { "resources": { "clusters": { "resources": { "nodeGroups": { "methods": { "resize": { "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/clusters/{clustersId}/nodeGroups/{nodeGroupsId}:resize", "parameterOrder": [ "name" ], "request": { "$ref": "ResizeNodeGroupRequest" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "path": "v1/{+name}:resize", "id": "dataproc.projects.regions.clusters.nodeGroups.resize", "httpMethod": "POST", "response": { "$ref": "Operation" }, "description": "Resizes a node group in a cluster. The returned Operation.metadata is [NodeGroupOperationMetadata](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#nodegroupoperationmetadata).", "parameters": { "name": { "description": "Required. The name of the node group to resize. Format: `projects/{project}/regions/{region}/clusters/{cluster}/nodeGroups/{nodeGroup}`", "type": "string", "required": true, "location": "path", "pattern": "^projects/[^/]+/regions/[^/]+/clusters/[^/]+/nodeGroups/[^/]+$" } } }, "get": { "description": "Gets the resource representation for a node group in a cluster.", "response": { "$ref": "NodeGroup" }, "id": "dataproc.projects.regions.clusters.nodeGroups.get", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc", "https://www.googleapis.com/auth/dataproc.read-only" ], "parameters": { "name": { "pattern": "^projects/[^/]+/regions/[^/]+/clusters/[^/]+/nodeGroups/[^/]+$", "location": "path", "description": "Required. The name of the node group to retrieve. Format: `projects/{project}/regions/{region}/clusters/{cluster}/nodeGroups/{nodeGroup}`", "type": "string", "required": true } }, "parameterOrder": [ "name" ], "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/clusters/{clustersId}/nodeGroups/{nodeGroupsId}", "httpMethod": "GET", "path": "v1/{+name}" } } } }, "methods": { "testIamPermissions": { "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/clusters/{clustersId}:testIamPermissions", "parameters": { "resource": { "pattern": "^projects/[^/]+/regions/[^/]+/clusters/[^/]+$", "required": true, "description": "REQUIRED: The resource for which the policy detail is being requested. See [Resource names](https://documentation.s3ns.fr/apis/design/resource_names) for the appropriate value for this field.", "type": "string", "location": "path" } }, "parameterOrder": [ "resource" ], "request": { "$ref": "TestIamPermissionsRequest" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "id": "dataproc.projects.regions.clusters.testIamPermissions", "httpMethod": "POST", "path": "v1/{+resource}:testIamPermissions", "description": "The google.iam.v1.IAMPolicy.TestIamPermissions method is not available in this (s3nsapis.fr) universe.", "response": { "$ref": "TestIamPermissionsResponse" } }, "diagnose": { "description": "Gets cluster diagnostic information. The returned Operation.metadata will be [ClusterOperationMetadata](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata). After the operation completes, Operation.response contains [DiagnoseClusterResults](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#diagnoseclusterresults).", "flatPath": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}:diagnose", "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}:diagnose", "parameterOrder": [ "projectId", "region", "clusterName" ], "id": "dataproc.projects.regions.clusters.diagnose", "httpMethod": "POST", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "request": { "$ref": "DiagnoseClusterRequest" }, "parameters": { "region": { "location": "path", "description": "Required. The region in which to handle the request.", "required": true, "type": "string" }, "projectId": { "location": "path", "description": "Required. The ID of the Cloud de Confiance Platform project that the cluster belongs to.", "required": true, "type": "string" }, "clusterName": { "type": "string", "location": "path", "description": "Required. The cluster name.", "required": true } }, "response": { "$ref": "Operation" } }, "list": { "parameters": { "pageToken": { "description": "Optional. A page token received from a previous `ListClusters` call. Provide this token to retrieve the subsequent page.", "type": "string", "location": "query" }, "region": { "description": "Required. The region in which to handle the request.", "required": true, "type": "string", "location": "path" }, "pageSize": { "description": "Optional. The maximum number of clusters to return in each response. The service may return fewer than this value. If unspecified, the default value is 200. The maximum value is 1000.", "location": "query", "format": "int32", "type": "integer" }, "filter": { "location": "query", "type": "string", "description": "Optional. A filter constraining the clusters to list. Filters are case-sensitive and have the following syntax: field = value [AND [field = value]] ... where **field** is one of `status.state`, `clusterName`, or `labels.[KEY]`, and `[KEY]` is a label key. **value** can be `\"*\"` to match all values. `status.state` can be one of the following: `ACTIVE`, `INACTIVE`, `CREATING`, `RUNNING`, `ERROR`, `DELETING`, `UPDATING`, `STOPPING`, or `STOPPED`. `ACTIVE` contains the `CREATING`, `UPDATING`, and `RUNNING` states. `INACTIVE` contains the `DELETING`, `ERROR`, `STOPPING`, and `STOPPED` states. `clusterName` is the name of the cluster provided at creation time. Only the logical `AND` operator is supported; space-separated items are treated as having an implicit `AND` operator. Example filter: status.state = ACTIVE AND clusterName = mycluster AND labels.env = staging AND labels.starred = *" }, "projectId": { "required": true, "type": "string", "description": "Required. The ID of the Cloud de Confiance Platform project that the cluster belongs to.", "location": "path" } }, "response": { "$ref": "ListClustersResponse" }, "httpMethod": "GET", "flatPath": "v1/projects/{projectId}/regions/{region}/clusters", "parameterOrder": [ "projectId", "region" ], "id": "dataproc.projects.regions.clusters.list", "path": "v1/projects/{projectId}/regions/{region}/clusters", "description": "Lists all regions/{region}/clusters in a project alphabetically.", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc", "https://www.googleapis.com/auth/dataproc.read-only" ] }, "patch": { "parameterOrder": [ "projectId", "region", "clusterName" ], "parameters": { "region": { "description": "Required. The region in which to handle the request.", "type": "string", "required": true, "location": "path" }, "projectId": { "required": true, "type": "string", "description": "Required. The ID of the Cloud de Confiance Platform project the cluster belongs to.", "location": "path" }, "updateMask": { "location": "query", "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: { \"config\":{ \"workerConfig\":{ \"numInstances\":\"5\" } } } Similarly, 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: { \"config\":{ \"secondaryWorkerConfig\":{ \"numInstances\":\"5\" } } } *Note:* Currently, only the following fields can be updated: *Mask* *Purpose* *labels* Update labels *config.worker_config.num_instances* Resize primary worker group *config.secondary_worker_config.num_instances* Resize secondary worker group config.autoscaling_config.policy_uri Use, stop using, or change autoscaling policies ", "format": "google-fieldmask", "type": "string" }, "requestId": { "location": "query", "description": "Optional. A unique ID used to identify the request. If the server receives two [UpdateClusterRequest](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.UpdateClusterRequest)s with the same id, then the second request will be ignored and the first google.longrunning.Operation created and stored in the backend is returned. It is recommended to always set this value to a [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier). The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). The maximum length is 40 characters.", "type": "string" }, "clusterName": { "location": "path", "type": "string", "required": true, "description": "Required. The cluster name." }, "gracefulDecommissionTimeout": { "format": "google-duration", "description": "Optional. Timeout for graceful YARN decommissioning. Graceful decommissioning allows removing nodes from the cluster without interrupting jobs in progress. Timeout specifies how long to wait for jobs in progress to finish before forcefully removing nodes (and potentially interrupting jobs). Default timeout is 0 (for forceful decommission), and the maximum allowed timeout is 1 day. (see JSON representation of [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)). Supported in image versions 1.2 and higher.", "type": "string", "location": "query" } }, "flatPath": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}", "description": "Updates a cluster in a project. The returned Operation.metadata will be [ClusterOperationMetadata](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata). The cluster must be in a `RUNNING` state or an error is returned.", "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}", "httpMethod": "PATCH", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "id": "dataproc.projects.regions.clusters.patch", "request": { "$ref": "Cluster" }, "response": { "$ref": "Operation" } }, "getIamPolicy": { "httpMethod": "POST", "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/clusters/{clustersId}:getIamPolicy", "id": "dataproc.projects.regions.clusters.getIamPolicy", "parameterOrder": [ "resource" ], "parameters": { "resource": { "pattern": "^projects/[^/]+/regions/[^/]+/clusters/[^/]+$", "required": true, "description": "REQUIRED: The resource for which the policy is being requested. See [Resource names](https://documentation.s3ns.fr/apis/design/resource_names) for the appropriate value for this field.", "location": "path", "type": "string" } }, "description": "The google.iam.v1.IAMPolicy.GetIamPolicy method is not available in this (s3nsapis.fr) universe.", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "request": { "$ref": "GetIamPolicyRequest" }, "response": { "$ref": "Policy" }, "path": "v1/{+resource}:getIamPolicy" }, "get": { "description": "Gets the resource representation for a cluster in a project.", "parameterOrder": [ "projectId", "region", "clusterName" ], "flatPath": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}", "response": { "$ref": "Cluster" }, "httpMethod": "GET", "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc", "https://www.googleapis.com/auth/dataproc.read-only" ], "parameters": { "projectId": { "location": "path", "description": "Required. The ID of the Cloud de Confiance Platform project that the cluster belongs to.", "type": "string", "required": true }, "region": { "type": "string", "description": "Required. The region in which to handle the request.", "required": true, "location": "path" }, "clusterName": { "required": true, "description": "Required. The cluster name.", "type": "string", "location": "path" } }, "id": "dataproc.projects.regions.clusters.get" }, "start": { "description": "Starts a cluster in a project.", "response": { "$ref": "Operation" }, "httpMethod": "POST", "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}:start", "id": "dataproc.projects.regions.clusters.start", "parameters": { "projectId": { "location": "path", "description": "Required. The ID of the Cloud de Confiance Platform project the cluster belongs to.", "required": true, "type": "string" }, "clusterName": { "type": "string", "description": "Required. The cluster name.", "location": "path", "required": true }, "region": { "required": true, "description": "Required. The region in which to handle the request.", "type": "string", "location": "path" } }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "request": { "$ref": "StartClusterRequest" }, "parameterOrder": [ "projectId", "region", "clusterName" ], "flatPath": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}:start" }, "setIamPolicy": { "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/clusters/{clustersId}:setIamPolicy", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "id": "dataproc.projects.regions.clusters.setIamPolicy", "parameterOrder": [ "resource" ], "request": { "$ref": "SetIamPolicyRequest" }, "parameters": { "resource": { "pattern": "^projects/[^/]+/regions/[^/]+/clusters/[^/]+$", "location": "path", "description": "REQUIRED: The resource for which the policy is being specified. See [Resource names](https://documentation.s3ns.fr/apis/design/resource_names) for the appropriate value for this field.", "type": "string", "required": true } }, "httpMethod": "POST", "path": "v1/{+resource}:setIamPolicy", "response": { "$ref": "Policy" }, "description": "The google.iam.v1.IAMPolicy.SetIamPolicy method is not available in this (s3nsapis.fr) universe." }, "create": { "path": "v1/projects/{projectId}/regions/{region}/clusters", "response": { "$ref": "Operation" }, "parameterOrder": [ "projectId", "region" ], "request": { "$ref": "Cluster" }, "flatPath": "v1/projects/{projectId}/regions/{region}/clusters", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "parameters": { "requestId": { "type": "string", "location": "query", "description": "Optional. A unique ID used to identify the request. If the server receives two [CreateClusterRequest](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.CreateClusterRequest)s with the same id, then the second request will be ignored and the first google.longrunning.Operation created and stored in the backend is returned. It is recommended to always set this value to a [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier). The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). The maximum length is 40 characters." }, "region": { "required": true, "type": "string", "description": "Required. The region in which to handle the request.", "location": "path" }, "projectId": { "description": "Required. The ID of the Cloud de Confiance Platform project that the cluster belongs to.", "required": true, "location": "path", "type": "string" }, "actionOnFailedPrimaryWorkers": { "enum": [ "FAILURE_ACTION_UNSPECIFIED", "NO_ACTION", "DELETE" ], "description": "Optional. Failure action when primary worker creation fails.", "enumDescriptions": [ "When FailureAction is unspecified, failure action defaults to NO_ACTION.", "Take no action on failure to create a cluster resource. NO_ACTION is the default.", "Delete the failed cluster resource." ], "location": "query", "type": "string" } }, "description": "Creates a cluster in a project. The returned Operation.metadata will be [ClusterOperationMetadata](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata).", "id": "dataproc.projects.regions.clusters.create", "httpMethod": "POST" }, "delete": { "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}", "description": "Deletes a cluster in a project. The returned Operation.metadata will be [ClusterOperationMetadata](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata).", "flatPath": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}", "id": "dataproc.projects.regions.clusters.delete", "response": { "$ref": "Operation" }, "parameters": { "requestId": { "type": "string", "description": "Optional. A unique ID used to identify the request. If the server receives two [DeleteClusterRequest](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.DeleteClusterRequest)s with the same id, then the second request will be ignored and the first google.longrunning.Operation created and stored in the backend is returned. It is recommended to always set this value to a [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier). The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). The maximum length is 40 characters.", "location": "query" }, "clusterName": { "location": "path", "description": "Required. The cluster name.", "type": "string", "required": true }, "gracefulTerminationTimeout": { "description": "Optional. The graceful termination timeout for the deletion of the cluster. Indicate the time the request will wait to complete the running jobs on the cluster before its forceful deletion. Default value is 0 indicating that the user has not enabled the graceful termination. Value can be between 60 second and 6 Hours, in case the graceful termination is enabled. (There is no separate flag to check the enabling or disabling of graceful termination, it can be checked by the values in the field).", "location": "query", "format": "google-duration", "type": "string" }, "region": { "description": "Required. The region in which to handle the request.", "type": "string", "location": "path", "required": true }, "projectId": { "location": "path", "description": "Required. The ID of the Cloud de Confiance Platform project that the cluster belongs to.", "type": "string", "required": true }, "clusterUuid": { "type": "string", "description": "Optional. Specifying the `cluster_uuid` means the RPC should fail (with error NOT_FOUND) if cluster with specified UUID does not exist.", "location": "query" } }, "parameterOrder": [ "projectId", "region", "clusterName" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "httpMethod": "DELETE" }, "stop": { "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "description": "Stops a cluster in a project.", "request": { "$ref": "StopClusterRequest" }, "flatPath": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}:stop", "parameterOrder": [ "projectId", "region", "clusterName" ], "parameters": { "region": { "required": true, "description": "Required. The region in which to handle the request.", "location": "path", "type": "string" }, "projectId": { "location": "path", "type": "string", "required": true, "description": "Required. The ID of the Cloud de Confiance Platform project the cluster belongs to." }, "clusterName": { "required": true, "description": "Required. The cluster name.", "location": "path", "type": "string" } }, "httpMethod": "POST", "id": "dataproc.projects.regions.clusters.stop", "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}:stop", "response": { "$ref": "Operation" } }, "repair": { "parameterOrder": [ "projectId", "region", "clusterName" ], "parameters": { "clusterName": { "required": true, "description": "Required. The cluster name.", "location": "path", "type": "string" }, "region": { "description": "Required. The region in which to handle the request.", "location": "path", "required": true, "type": "string" }, "projectId": { "type": "string", "required": true, "description": "Required. The ID of the Cloud de Confiance Platform project the cluster belongs to.", "location": "path" } }, "response": { "$ref": "Operation" }, "request": { "$ref": "RepairClusterRequest" }, "httpMethod": "POST", "id": "dataproc.projects.regions.clusters.repair", "path": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}:repair", "flatPath": "v1/projects/{projectId}/regions/{region}/clusters/{clusterName}:repair", "description": "Repairs a cluster.", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ] } } }, "operations": { "methods": { "delete": { "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "parameters": { "name": { "description": "The name of the operation resource to be deleted.", "type": "string", "location": "path", "required": true, "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$" } }, "response": { "$ref": "Empty" }, "parameterOrder": [ "name" ], "httpMethod": "DELETE", "path": "v1/{+name}", "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/operations/{operationsId}", "id": "dataproc.projects.regions.operations.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`." }, "getIamPolicy": { "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/operations/{operationsId}:getIamPolicy", "parameters": { "resource": { "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$", "location": "path", "type": "string", "required": true, "description": "REQUIRED: The resource for which the policy is being requested. See [Resource names](https://documentation.s3ns.fr/apis/design/resource_names) for the appropriate value for this field." } }, "request": { "$ref": "GetIamPolicyRequest" }, "description": "The google.iam.v1.IAMPolicy.GetIamPolicy method is not available in this (s3nsapis.fr) universe.", "httpMethod": "POST", "path": "v1/{+resource}:getIamPolicy", "id": "dataproc.projects.regions.operations.getIamPolicy", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "response": { "$ref": "Policy" }, "parameterOrder": [ "resource" ] }, "testIamPermissions": { "parameterOrder": [ "resource" ], "path": "v1/{+resource}:testIamPermissions", "id": "dataproc.projects.regions.operations.testIamPermissions", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/operations/{operationsId}:testIamPermissions", "request": { "$ref": "TestIamPermissionsRequest" }, "response": { "$ref": "TestIamPermissionsResponse" }, "httpMethod": "POST", "description": "The google.iam.v1.IAMPolicy.TestIamPermissions method is not available in this (s3nsapis.fr) universe.", "parameters": { "resource": { "required": true, "description": "REQUIRED: The resource for which the policy detail is being requested. See [Resource names](https://documentation.s3ns.fr/apis/design/resource_names) for the appropriate value for this field.", "type": "string", "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$", "location": "path" } } }, "get": { "path": "v1/{+name}", "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/operations/{operationsId}", "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.", "parameterOrder": [ "name" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc", "https://www.googleapis.com/auth/dataproc.read-only" ], "parameters": { "name": { "type": "string", "location": "path", "description": "The name of the operation resource.", "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$", "required": true } }, "id": "dataproc.projects.regions.operations.get", "httpMethod": "GET", "response": { "$ref": "Operation" } }, "cancel": { "id": "dataproc.projects.regions.operations.cancel", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "response": { "$ref": "Empty" }, "description": "Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of `1`, corresponding to `Code.CANCELLED`.", "parameterOrder": [ "name" ], "httpMethod": "POST", "path": "v1/{+name}:cancel", "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/operations/{operationsId}:cancel", "parameters": { "name": { "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$", "required": true, "location": "path", "type": "string", "description": "The name of the operation resource to be cancelled." } } }, "list": { "parameters": { "name": { "description": "The name of the operation's parent resource.", "required": true, "location": "path", "pattern": "^projects/[^/]+/regions/[^/]+/operations$", "type": "string" }, "filter": { "description": "The standard list filter.", "type": "string", "location": "query" }, "returnPartialSuccess": { "description": "When set to `true`, operations that are reachable are returned as normal, and those that are unreachable are returned in the ListOperationsResponse.unreachable field. This can only be `true` when reading across collections. For example, when `parent` is set to `\"projects/example/locations/-\"`. This field is not supported by default and will result in an `UNIMPLEMENTED` error if set unless explicitly documented otherwise in service or product specific documentation.", "location": "query", "type": "boolean" }, "pageSize": { "type": "integer", "location": "query", "format": "int32", "description": "The standard list page size." }, "pageToken": { "location": "query", "description": "The standard list page token.", "type": "string" } }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc", "https://www.googleapis.com/auth/dataproc.read-only" ], "path": "v1/{+name}", "description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`.", "httpMethod": "GET", "parameterOrder": [ "name" ], "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/operations", "id": "dataproc.projects.regions.operations.list", "response": { "$ref": "ListOperationsResponse" } }, "setIamPolicy": { "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/operations/{operationsId}:setIamPolicy", "description": "The google.iam.v1.IAMPolicy.SetIamPolicy method is not available in this (s3nsapis.fr) universe.", "path": "v1/{+resource}:setIamPolicy", "request": { "$ref": "SetIamPolicyRequest" }, "parameterOrder": [ "resource" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "parameters": { "resource": { "type": "string", "description": "REQUIRED: The resource for which the policy is being specified. See [Resource names](https://documentation.s3ns.fr/apis/design/resource_names) for the appropriate value for this field.", "required": true, "location": "path", "pattern": "^projects/[^/]+/regions/[^/]+/operations/[^/]+$" } }, "httpMethod": "POST", "response": { "$ref": "Policy" }, "id": "dataproc.projects.regions.operations.setIamPolicy" } } }, "jobs": { "methods": { "get": { "response": { "$ref": "Job" }, "parameterOrder": [ "projectId", "region", "jobId" ], "id": "dataproc.projects.regions.jobs.get", "httpMethod": "GET", "description": "Gets the resource representation for a job in a project.", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc", "https://www.googleapis.com/auth/dataproc.read-only" ], "parameters": { "region": { "type": "string", "required": true, "description": "Required. The Dataproc region in which to handle the request.", "location": "path" }, "projectId": { "location": "path", "description": "Required. The ID of the Cloud de Confiance Platform project that the job belongs to.", "type": "string", "required": true }, "jobId": { "location": "path", "required": true, "type": "string", "description": "Required. The job ID." } }, "flatPath": "v1/projects/{projectId}/regions/{region}/jobs/{jobId}", "path": "v1/projects/{projectId}/regions/{region}/jobs/{jobId}" }, "setIamPolicy": { "parameters": { "resource": { "description": "REQUIRED: The resource for which the policy is being specified. See [Resource names](https://documentation.s3ns.fr/apis/design/resource_names) for the appropriate value for this field.", "pattern": "^projects/[^/]+/regions/[^/]+/jobs/[^/]+$", "location": "path", "required": true, "type": "string" } }, "path": "v1/{+resource}:setIamPolicy", "id": "dataproc.projects.regions.jobs.setIamPolicy", "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/jobs/{jobsId}:setIamPolicy", "httpMethod": "POST", "description": "The google.iam.v1.IAMPolicy.SetIamPolicy method is not available in this (s3nsapis.fr) universe.", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "request": { "$ref": "SetIamPolicyRequest" }, "parameterOrder": [ "resource" ], "response": { "$ref": "Policy" } }, "delete": { "response": { "$ref": "Empty" }, "httpMethod": "DELETE", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "description": "Deletes the job from the project. If the job is active, the delete fails, and the response returns `FAILED_PRECONDITION`.", "parameters": { "region": { "type": "string", "location": "path", "description": "Required. The Dataproc region in which to handle the request.", "required": true }, "jobId": { "location": "path", "required": true, "type": "string", "description": "Required. The job ID." }, "projectId": { "required": true, "description": "Required. The ID of the Cloud de Confiance Platform project that the job belongs to.", "location": "path", "type": "string" } }, "path": "v1/projects/{projectId}/regions/{region}/jobs/{jobId}", "id": "dataproc.projects.regions.jobs.delete", "parameterOrder": [ "projectId", "region", "jobId" ], "flatPath": "v1/projects/{projectId}/regions/{region}/jobs/{jobId}" }, "testIamPermissions": { "request": { "$ref": "TestIamPermissionsRequest" }, "description": "The google.iam.v1.IAMPolicy.TestIamPermissions method is not available in this (s3nsapis.fr) universe.", "id": "dataproc.projects.regions.jobs.testIamPermissions", "response": { "$ref": "TestIamPermissionsResponse" }, "parameters": { "resource": { "type": "string", "pattern": "^projects/[^/]+/regions/[^/]+/jobs/[^/]+$", "location": "path", "required": true, "description": "REQUIRED: The resource for which the policy detail is being requested. See [Resource names](https://documentation.s3ns.fr/apis/design/resource_names) for the appropriate value for this field." } }, "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/jobs/{jobsId}:testIamPermissions", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "httpMethod": "POST", "parameterOrder": [ "resource" ], "path": "v1/{+resource}:testIamPermissions" }, "list": { "httpMethod": "GET", "parameters": { "clusterName": { "description": "Optional. If set, the returned jobs list includes only jobs that were submitted to the named cluster.", "type": "string", "location": "query" }, "projectId": { "type": "string", "location": "path", "description": "Required. The ID of the Cloud de Confiance Platform project that the job belongs to.", "required": true }, "pageSize": { "type": "integer", "description": "Optional. The number of results to return in each response.", "location": "query", "format": "int32" }, "region": { "type": "string", "location": "path", "required": true, "description": "Required. The Dataproc region in which to handle the request." }, "jobStateMatcher": { "enum": [ "ALL", "ACTIVE", "NON_ACTIVE" ], "enumDescriptions": [ "Match all jobs, regardless of state.", "Only match jobs in non-terminal states: PENDING, RUNNING, or CANCEL_PENDING.", "Only match jobs in terminal states: CANCELLED, DONE, or ERROR." ], "type": "string", "location": "query", "description": "Optional. Specifies enumerated categories of jobs to list. (default = match ALL jobs). If `filter` is provided, `jobStateMatcher` will be ignored." }, "pageToken": { "location": "query", "description": "Optional. The page token, returned by a previous call, to request the next page of results.", "type": "string" }, "filter": { "location": "query", "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 `insertTime`, or `labels.[KEY]`, and `[KEY]` is a label key. **value** can be `*` to match all values. `status.state` can be either `ACTIVE` or `NON_ACTIVE`. Allows `insertTime` to be a timestamp in RFC 3339 format in double quotes, such as `2025-01-01T00:00:00Z`. 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 = * AND insertTime \u003c= \"2025-01-01T00:00:00Z\"", "type": "string" } }, "id": "dataproc.projects.regions.jobs.list", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc", "https://www.googleapis.com/auth/dataproc.read-only" ], "response": { "$ref": "ListJobsResponse" }, "flatPath": "v1/projects/{projectId}/regions/{region}/jobs", "parameterOrder": [ "projectId", "region" ], "path": "v1/projects/{projectId}/regions/{region}/jobs", "description": "Lists regions/{region}/jobs in a project." }, "submitAsOperation": { "id": "dataproc.projects.regions.jobs.submitAsOperation", "path": "v1/projects/{projectId}/regions/{region}/jobs:submitAsOperation", "description": "Submits job to a cluster.", "response": { "$ref": "Operation" }, "parameterOrder": [ "projectId", "region" ], "parameters": { "region": { "required": true, "description": "Required. The Dataproc region in which to handle the request.", "type": "string", "location": "path" }, "projectId": { "description": "Required. The ID of the Cloud de Confiance Platform project that the job belongs to.", "required": true, "location": "path", "type": "string" } }, "flatPath": "v1/projects/{projectId}/regions/{region}/jobs:submitAsOperation", "httpMethod": "POST", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "request": { "$ref": "SubmitJobRequest" } }, "submit": { "flatPath": "v1/projects/{projectId}/regions/{region}/jobs:submit", "id": "dataproc.projects.regions.jobs.submit", "request": { "$ref": "SubmitJobRequest" }, "description": "Submits a job to a cluster.", "httpMethod": "POST", "parameterOrder": [ "projectId", "region" ], "parameters": { "region": { "required": true, "type": "string", "location": "path", "description": "Required. The Dataproc region in which to handle the request." }, "projectId": { "location": "path", "type": "string", "description": "Required. The ID of the Cloud de Confiance Platform project that the job belongs to.", "required": true } }, "response": { "$ref": "Job" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "path": "v1/projects/{projectId}/regions/{region}/jobs:submit" }, "getIamPolicy": { "flatPath": "v1/projects/{projectsId}/regions/{regionsId}/jobs/{jobsId}:getIamPolicy", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "description": "The google.iam.v1.IAMPolicy.GetIamPolicy method is not available in this (s3nsapis.fr) universe.", "request": { "$ref": "GetIamPolicyRequest" }, "path": "v1/{+resource}:getIamPolicy", "parameterOrder": [ "resource" ], "parameters": { "resource": { "type": "string", "required": true, "location": "path", "pattern": "^projects/[^/]+/regions/[^/]+/jobs/[^/]+$", "description": "REQUIRED: The resource for which the policy is being requested. See [Resource names](https://documentation.s3ns.fr/apis/design/resource_names) for the appropriate value for this field." } }, "id": "dataproc.projects.regions.jobs.getIamPolicy", "response": { "$ref": "Policy" }, "httpMethod": "POST" }, "cancel": { "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "request": { "$ref": "CancelJobRequest" }, "description": "Starts a job cancellation request. To access the job resource after cancellation, call [regions/{region}/jobs.list](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/projects.regions.jobs/list) or [regions/{region}/jobs.get](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/projects.regions.jobs/get).", "path": "v1/projects/{projectId}/regions/{region}/jobs/{jobId}:cancel", "response": { "$ref": "Job" }, "parameterOrder": [ "projectId", "region", "jobId" ], "id": "dataproc.projects.regions.jobs.cancel", "flatPath": "v1/projects/{projectId}/regions/{region}/jobs/{jobId}:cancel", "httpMethod": "POST", "parameters": { "region": { "location": "path", "type": "string", "required": true, "description": "Required. The Dataproc region in which to handle the request." }, "projectId": { "required": true, "type": "string", "location": "path", "description": "Required. The ID of the Cloud de Confiance Platform project that the job belongs to." }, "jobId": { "required": true, "type": "string", "description": "Required. The job ID.", "location": "path" } } } } } } }, "locations": { "resources": { "operations": { "methods": { "delete": { "parameterOrder": [ "name" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "path": "v1/{+name}", "response": { "$ref": "Empty" }, "httpMethod": "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`.", "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}", "id": "dataproc.projects.locations.operations.delete", "parameters": { "name": { "required": true, "location": "path", "pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$", "type": "string", "description": "The name of the operation resource to be deleted." } } }, "cancel": { "parameterOrder": [ "name" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc" ], "path": "v1/{+name}:cancel", "response": { "$ref": "Empty" }, "httpMethod": "POST", "id": "dataproc.projects.locations.operations.cancel", "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}: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`.", "parameters": { "name": { "required": true, "location": "path", "type": "string", "description": "The name of the operation resource to be cancelled.", "pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$" } } }, "get": { "parameterOrder": [ "name" ], "parameters": { "name": { "pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$", "location": "path", "required": true, "type": "string", "description": "The name of the operation resource." } }, "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.", "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}", "httpMethod": "GET", "id": "dataproc.projects.locations.operations.get", "path": "v1/{+name}", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc", "https://www.googleapis.com/auth/dataproc.read-only" ], "response": { "$ref": "Operation" } }, "list": { "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/dataproc", "https://www.googleapis.com/auth/dataproc.read-only" ], "id": "dataproc.projects.locations.operations.list", "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/operations", "path": "v1/{+name}", "parameters": { "pageToken": { "type": "string", "location": "query", "description": "The standard list page token." }, "filter": { "type": "string", "description": "The standard list filter.", "location": "query" }, "returnPartialSuccess": { "type": "boolean", "location": "query", "description": "When set to `true`, operations that are reachable are returned as normal, and those that are unreachable are returned in the ListOperationsResponse.unreachable field. This can only be `true` when reading across collections. For example, when `parent` is set to `\"projects/example/locations/-\"`. This field is not supported by default and will result in an `UNIMPLEMENTED` error if set unless explicitly documented otherwise in service or product specific documentation." }, "pageSize": { "format": "int32", "type": "integer", "description": "The standard list page size.", "location": "query" }, "name": { "location": "path", "description": "The name of the operation's parent resource.", "type": "string", "pattern": "^projects/[^/]+/locations/[^/]+/operations$", "required": true } }, "parameterOrder": [ "name" ], "description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`.", "httpMethod": "GET", "response": { "$ref": "ListOperationsResponse" } } } } } } } } }, "basePath": "", "canonicalName": "Dataproc", "rootUrl": "https://dataproc.s3nsapis.fr/", "batchPath": "batch", "kind": "discovery#restDescription", "name": "dataproc", "revision": "20261002", "protocol": "rest", "servicePath": "", "ownerDomain": "google.com", "baseUrl": "https://dataproc.s3nsapis.fr/", "icons": { "x16": "", "x32": "" }, "documentationLink": "https://documentation.s3ns.fr/dataproc", "fullyEncodeReservedExpansion": true, "id": "dataproc:v1", "auth": { "oauth2": { "scopes": { "https://www.googleapis.com/auth/dataproc": { "description": "See, edit, configure, and delete your Google Cloud Dataproc data and see the email address for your Google Account" }, "https://www.googleapis.com/auth/dataproc.read-only": { "description": "See your Google Cloud Dataproc data and the email address of your Google Account" }, "https://www.googleapis.com/auth/cloud-platform": { "description": "See, edit, configure, and delete your Google Cloud data and see the email address for your Google Account." } } } }, "discoveryVersion": "v1", "schemas": { "TestIamPermissionsRequest": { "properties": { "permissions": { "type": "array", "items": { "type": "string" }, "description": "The set of permissions to check for the `resource`. Permissions with wildcards (such as `*` or `storage.*`) are not allowed. For more information see [IAM Overview](https://documentation.s3ns.fr/iam/docs/overview#permissions)." } }, "type": "object", "id": "TestIamPermissionsRequest", "description": "Request message for `TestIamPermissions` method." }, "StopClusterRequest": { "id": "StopClusterRequest", "properties": { "requestId": { "type": "string", "description": "Optional. A unique ID used to identify the request. If the server receives two [StopClusterRequest](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.StopClusterRequest)s with the same id, then the second request will be ignored and the first google.longrunning.Operation created and stored in the backend is returned. Recommendation: Set this value to a [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier). The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). The maximum length is 40 characters." }, "clusterUuid": { "description": "Optional. Specifying the `cluster_uuid` means the RPC will fail (with error NOT_FOUND) if a cluster with the specified UUID does not exist.", "type": "string" } }, "type": "object", "description": "A request to stop a cluster." }, "JobPlacement": { "description": "Dataproc job config.", "properties": { "clusterLabels": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Optional. Cluster labels to identify a cluster where the job will be submitted." }, "clusterName": { "description": "Required. The name of the cluster where the job will be submitted.", "type": "string" }, "clusterUuid": { "description": "Output only. A cluster UUID generated by the Dataproc service when the job is submitted.", "readOnly": true, "type": "string" } }, "id": "JobPlacement", "type": "object" }, "SecurityConfig": { "description": "Security related configuration, including encryption, Kerberos, etc.", "properties": { "kerberosConfig": { "description": "Optional. Kerberos related configuration.", "$ref": "KerberosConfig" }, "identityConfig": { "$ref": "IdentityConfig", "description": "Optional. Identity related configuration, including service account based secure multi-tenancy user mappings." } }, "type": "object", "id": "SecurityConfig" }, "Status": { "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.", "type": "string" }, "code": { "description": "The status code, which should be an enum value of google.rpc.Code.", "type": "integer", "format": "int32" }, "details": { "items": { "type": "object", "additionalProperties": { "description": "Properties of the object. Contains field @type with type URL.", "type": "any" } }, "description": "A list of messages that carry the error details. There is a common set of message types for APIs to use.", "type": "array" } }, "type": "object", "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). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://documentation.s3ns.fr/apis/design/errors).", "id": "Status" }, "Operation": { "type": "object", "properties": { "metadata": { "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", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } }, "name": { "type": "string", "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 be a resource name ending with `operations/{unique_id}`." }, "done": { "type": "boolean", "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." }, "response": { "type": "object", "description": "The normal, successful response of the operation. 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`.", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } }, "error": { "$ref": "Status", "description": "The error result of the operation in case of failure or cancellation." } }, "description": "This resource represents a long-running operation that is the result of a network API call.", "id": "Operation" }, "InstanceGroupConfig": { "type": "object", "description": "The config settings for Compute Engine resources in an instance group, such as a master or worker group.", "properties": { "startupConfig": { "description": "Optional. Configuration to handle the startup of instances during cluster create and update process.", "$ref": "StartupConfig" }, "imageUri": { "type": "string", "description": "Optional. The Compute Engine image resource used for cluster instances. The URI can represent an image or image family. Image examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/global/images/[image-id]` * `projects/[project_id]/global/images/[image-id]` * `image-id` Image family examples. The service will use the most recent image from the family: * `https://www.googleapis.com/compute/v1/projects/[project_id]/global/images/family/[custom-image-family-name]` * `projects/[project_id]/global/images/family/[custom-image-family-name]` If the URI is unspecified, it will be inferred from `SoftwareConfig.image_version` or the system default." }, "preemptibility": { "description": "Optional. Specifies the preemptibility of the instance group. The default value for master and worker groups is `NON_PREEMPTIBLE`. This default cannot be changed. The default value for secondary instances is `PREEMPTIBLE`.", "enumDescriptions": [ "Preemptibility is unspecified, the system will choose the appropriate setting for each instance group.", "Instances are non-preemptible. This option is allowed for all instance groups and is the only valid value for Master and Worker instance groups.", "Instances are [preemptible] (https://documentation.s3ns.fr/compute/docs/instances/preemptible). This option is allowed only for [secondary worker] (https://documentation.s3ns.fr/dataproc/docs/concepts/compute/secondary-vms) groups.", "Instances are [Spot VMs] (https://documentation.s3ns.fr/compute/docs/instances/spot). This option is allowed only for [secondary worker] (https://documentation.s3ns.fr/dataproc/docs/concepts/compute/secondary-vms) groups. Spot VMs are the latest version of [preemptible VMs] (https://documentation.s3ns.fr/compute/docs/instances/preemptible), and provide additional features." ], "type": "string", "enum": [ "PREEMPTIBILITY_UNSPECIFIED", "NON_PREEMPTIBLE", "PREEMPTIBLE", "SPOT" ] }, "numInstances": { "type": "integer", "format": "int32", "description": "Optional. The number of VM instances in the instance group. For [HA cluster](/dataproc/docs/concepts/configuring-clusters/high-availability) [master_config](#FIELDS.master_config) groups, **must be set to 3**. For standard cluster [master_config](#FIELDS.master_config) groups, **must be set to 1**." }, "diskConfig": { "description": "Optional. Disk option config settings.", "$ref": "DiskConfig" }, "minCpuPlatform": { "description": "Optional. Specifies the minimum cpu platform for the Instance Group. See [Dataproc -\u003e Minimum CPU Platform](https://documentation.s3ns.fr/dataproc/docs/concepts/compute/dataproc-min-cpu).", "type": "string" }, "instanceFlexibilityPolicy": { "description": "Optional. Instance flexibility Policy allowing a mixture of VM shapes and provisioning models.", "$ref": "InstanceFlexibilityPolicy" }, "instanceNames": { "type": "array", "readOnly": true, "description": "Output only. The list of instance names, derived from `cluster_name`, `num_instances`, and the instance group.", "items": { "type": "string" } }, "instanceReferences": { "readOnly": true, "items": { "$ref": "InstanceReference" }, "type": "array", "description": "Output only. List of references to Compute Engine instances." }, "machineTypeUri": { "description": "Optional. The Compute Engine machine type used for cluster instances. A full URL, partial URI, or short name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]/machineTypes/n1-standard-2` * `projects/[project_id]/zones/[zone]/machineTypes/n1-standard-2` * `n1-standard-2` **Auto Zone Exception**: If you are using the Dataproc [Auto Zone Placement](https://documentation.s3ns.fr/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) feature, you must use the short name of the machine type resource, for example, `n1-standard-2`.", "type": "string" }, "managedGroupConfig": { "readOnly": true, "$ref": "ManagedGroupConfig", "description": "Output only. The config for Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups." }, "isPreemptible": { "readOnly": true, "description": "Output only. Specifies that this instance group contains preemptible instances.", "type": "boolean" }, "accelerators": { "items": { "$ref": "AcceleratorConfig" }, "description": "Optional. The Compute Engine accelerator configuration for these instances.", "type": "array" }, "minNumInstances": { "format": "int32", "type": "integer", "description": "Optional. The minimum number of primary worker instances to create. If `min_num_instances` is set, cluster creation will succeed if the number of primary workers created is at least equal to the `min_num_instances` number. Example: Cluster creation request with `num_instances` = `5` and `min_num_instances` = `3`: * If 4 VMs are created and 1 instance fails, the failed VM is deleted. The cluster is resized to 4 instances and placed in a `RUNNING` state. * If 2 instances are created and 3 instances fail, the cluster in placed in an `ERROR` state. The failed VMs are not deleted." } }, "id": "InstanceGroupConfig" }, "ClusterToRepair": { "id": "ClusterToRepair", "properties": { "clusterRepairAction": { "enumDescriptions": [ "No action will be taken by default.", "Repair cluster in ERROR_DUE_TO_UPDATE states." ], "type": "string", "enum": [ "CLUSTER_REPAIR_ACTION_UNSPECIFIED", "REPAIR_ERROR_DUE_TO_UPDATE_CLUSTER" ], "description": "Required. Repair action to take on the cluster resource." } }, "type": "object", "description": "Cluster to be repaired" }, "QueryList": { "id": "QueryList", "description": "A list of queries to run on a cluster.", "type": "object", "properties": { "queries": { "items": { "type": "string" }, "description": "Required. The queries to execute. You do not need to end a query expression with a semicolon. Multiple queries can be specified in one string by separating each with a semicolon. Here is an example of a Dataproc API snippet that uses a QueryList to specify a HiveJob: \"hiveJob\": { \"queryList\": { \"queries\": [ \"query1\", \"query2\", \"query3;query4\", ] } }", "type": "array" } } }, "NodeGroupOperationMetadata": { "type": "object", "properties": { "operationType": { "enumDescriptions": [ "Node group operation type is unknown.", "Create node group operation type.", "Update node group operation type.", "Delete node group operation type.", "Resize node group operation type.", "Repair node group operation type.", "Update node group label operation type.", "Start node group operation type.", "Stop node group operation type.", "This operation type is used to update the metadata config of a node group. We update the metadata of the VMs in the node group and await for intended config change to be completed at the node group level. Currently, only the identity config update is supported." ], "type": "string", "enum": [ "NODE_GROUP_OPERATION_TYPE_UNSPECIFIED", "CREATE", "UPDATE", "DELETE", "RESIZE", "REPAIR", "UPDATE_LABELS", "START", "STOP", "UPDATE_METADATA_CONFIG" ], "description": "The operation type." }, "labels": { "description": "Output only. Labels associated with the operation.", "additionalProperties": { "type": "string" }, "readOnly": true, "type": "object" }, "clusterUuid": { "readOnly": true, "type": "string", "description": "Output only. Cluster UUID associated with the node group operation." }, "description": { "description": "Output only. Short description of operation.", "type": "string", "readOnly": true }, "status": { "readOnly": true, "description": "Output only. Current operation status.", "$ref": "ClusterOperationStatus" }, "nodeGroupId": { "type": "string", "description": "Output only. Node group ID for the operation.", "readOnly": true }, "statusHistory": { "items": { "$ref": "ClusterOperationStatus" }, "readOnly": true, "type": "array", "description": "Output only. The previous operation status." }, "warnings": { "readOnly": true, "type": "array", "description": "Output only. Errors encountered during operation execution.", "items": { "type": "string" } } }, "description": "Metadata describing the node group operation.", "id": "NodeGroupOperationMetadata" }, "ManagedGroupConfig": { "type": "object", "id": "ManagedGroupConfig", "description": "Specifies the resources used to actively manage an instance group.", "properties": { "instanceGroupManagerName": { "readOnly": true, "type": "string", "description": "Output only. The name of the Instance Group Manager for this group." }, "instanceTemplateName": { "description": "Output only. The name of the Instance Template used for the Managed Instance Group.", "readOnly": true, "type": "string" }, "instanceGroupManagerUri": { "readOnly": true, "description": "Output only. The partial URI to the instance group manager for this group. E.g. projects/my-project/regions/us-central1/instanceGroupManagers/my-igm.", "type": "string" } } }, "InstanceReference": { "id": "InstanceReference", "properties": { "publicKey": { "type": "string", "description": "The public RSA key used for sharing data with this instance." }, "instanceId": { "description": "The unique identifier of the Compute Engine instance.", "type": "string" }, "publicEciesKey": { "type": "string", "description": "The public ECIES key used for sharing data with this instance." }, "instanceName": { "description": "The user-friendly name of the Compute Engine instance.", "type": "string" } }, "type": "object", "description": "A reference to a Compute Engine instance." }, "GkeNodePoolConfig": { "type": "object", "id": "GkeNodePoolConfig", "properties": { "config": { "description": "Optional. The node pool configuration.", "$ref": "GkeNodeConfig" }, "locations": { "description": "Optional. The list of Compute Engine [zones](https://documentation.s3ns.fr/compute/docs/zones#available) where node pool nodes associated with a Dataproc on GKE virtual cluster will be located. **Note:** All node pools associated with a virtual cluster must be located in the same region as the virtual cluster, and they must be located in the same zone within that region. If a location is not specified during node pool creation, Dataproc on GKE will choose the zone.", "type": "array", "items": { "type": "string" } }, "autoscaling": { "description": "Optional. The autoscaler configuration for this node pool. The autoscaler is enabled only when a valid configuration is present.", "$ref": "GkeNodePoolAutoscalingConfig" } }, "description": "The configuration of a GKE node pool used by a [Dataproc-on-GKE cluster](https://documentation.s3ns.fr/dataproc/docs/concepts/jobs/dataproc-gke#create-a-dataproc-on-gke-cluster)." }, "GkeClusterConfig": { "id": "GkeClusterConfig", "description": "The cluster's GKE config.", "type": "object", "properties": { "gkeClusterTarget": { "type": "string", "description": "Optional. A target GKE cluster to deploy to. It must be in the same project and region as the Dataproc cluster (the GKE cluster can be zonal or regional). Format: 'projects/{project}/locations/{location}/clusters/{cluster_id}'" }, "namespacedGkeDeploymentTarget": { "description": "Optional. Deprecated. Use gkeClusterTarget. Used only for the deprecated beta. A target for the deployment.", "$ref": "NamespacedGkeDeploymentTarget", "deprecated": true }, "nodePoolTarget": { "items": { "$ref": "GkeNodePoolTarget" }, "description": "Optional. GKE node pools where workloads will be scheduled. At least one node pool must be assigned the `DEFAULT` GkeNodePoolTarget.Role. If a `GkeNodePoolTarget` is not specified, Dataproc constructs a `DEFAULT` `GkeNodePoolTarget`. Each role can be given to only one `GkeNodePoolTarget`. All node pools must have the same location settings.", "type": "array" } } }, "ConfidentialInstanceConfig": { "description": "Confidential Instance Config for clusters using [Confidential VMs](https://documentation.s3ns.fr/compute/confidential-vm/docs)", "type": "object", "id": "ConfidentialInstanceConfig", "properties": { "enableConfidentialCompute": { "type": "boolean", "description": "Optional. Deprecated: Use 'confidential_instance_type' instead. Defines whether the instance should have confidential compute enabled.", "deprecated": true } } }, "AcceleratorConfig": { "properties": { "acceleratorTypeUri": { "type": "string", "description": "Full URL, partial URI, or short name of the accelerator type resource to expose to this instance. See [Compute Engine AcceleratorTypes](https://documentation.s3ns.fr/compute/docs/reference/v1/acceleratorTypes). Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]/acceleratorTypes/nvidia-tesla-t4` * `projects/[project_id]/zones/[zone]/acceleratorTypes/nvidia-tesla-t4` * `nvidia-tesla-t4` **Auto Zone Exception**: If you are using the Dataproc [Auto Zone Placement](https://documentation.s3ns.fr/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) feature, you must use the short name of the accelerator type resource, for example, `nvidia-tesla-t4`." }, "acceleratorCount": { "description": "The number of the accelerator cards of this type exposed to this instance.", "format": "int32", "type": "integer" } }, "description": "Specifies the type and number of accelerator cards attached to the instances of an instance. See [GPUs on Compute Engine](https://documentation.s3ns.fr/compute/docs/gpus/).", "type": "object", "id": "AcceleratorConfig" }, "BatchOperationMetadata": { "description": "Metadata describing the Batch operation.", "properties": { "labels": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Labels associated with the operation." }, "createTime": { "description": "The time when the operation was created.", "type": "string", "format": "google-datetime" }, "batch": { "type": "string", "description": "Name of the batch for the operation." }, "batchUuid": { "description": "Batch UUID for the operation.", "type": "string" }, "operationType": { "description": "The operation type.", "type": "string", "enum": [ "BATCH_OPERATION_TYPE_UNSPECIFIED", "BATCH" ], "enumDescriptions": [ "Batch operation type is unknown.", "Batch operation type." ] }, "description": { "type": "string", "description": "Short description of the operation." }, "doneTime": { "description": "The time when the operation finished.", "type": "string", "format": "google-datetime" }, "warnings": { "type": "array", "description": "Warnings encountered during operation execution.", "items": { "type": "string" } } }, "id": "BatchOperationMetadata", "type": "object" }, "SoftwareConfig": { "description": "Specifies the selection and config of software inside the cluster.", "properties": { "imageVersion": { "description": "Optional. The version of software inside the cluster. It must be one of the supported [Dataproc Versions](https://documentation.s3ns.fr/dataproc/docs/concepts/versioning/dataproc-versions#supported-dataproc-image-versions), such as \"1.2\" (including a subminor version, such as \"1.2.29\"), or the [\"preview\" version](https://documentation.s3ns.fr/dataproc/docs/concepts/versioning/dataproc-versions#other_versions). If unspecified, it defaults to the latest Debian version.", "type": "string" }, "properties": { "additionalProperties": { "type": "string" }, "type": "object", "description": "Optional. The properties to set on daemon config files. Property keys are specified in `prefix:property` format, for example `core:hadoop.tmp.dir`. The following are supported prefixes and their mappings: * capacity-scheduler: `capacity-scheduler.xml` * core: `core-site.xml` * distcp: `distcp-default.xml` * hdfs: `hdfs-site.xml` * hive: `hive-site.xml` * mapred: `mapred-site.xml` * pig: `pig.properties` * spark: `spark-defaults.conf` * yarn: `yarn-site.xml` For more information, see [Cluster properties](https://documentation.s3ns.fr/dataproc/docs/concepts/cluster-properties)." } }, "id": "SoftwareConfig", "type": "object" }, "AnalyzeOperationMetadata": { "description": "Metadata describing the Analyze operation.", "properties": { "analyzedWorkloadUuid": { "readOnly": true, "description": "Output only. unique identifier of the workload typically generated by control plane. E.g. batch uuid.", "type": "string" }, "analyzedWorkloadName": { "readOnly": true, "type": "string", "description": "Output only. name of the workload being analyzed." }, "analyzedWorkloadType": { "description": "Output only. Type of the workload being analyzed.", "enumDescriptions": [ "Undefined option", "Serverless batch job" ], "readOnly": true, "enum": [ "WORKLOAD_TYPE_UNSPECIFIED", "BATCH" ], "type": "string" }, "labels": { "description": "Output only. Labels associated with the operation.", "readOnly": true, "additionalProperties": { "type": "string" }, "type": "object" }, "warnings": { "items": { "type": "string" }, "type": "array", "readOnly": true, "description": "Output only. Warnings encountered during operation execution." }, "description": { "description": "Output only. Short description of the operation.", "readOnly": true, "type": "string" }, "createTime": { "readOnly": true, "format": "google-datetime", "type": "string", "description": "Output only. The time when the operation was created." }, "doneTime": { "description": "Output only. The time when the operation finished.", "format": "google-datetime", "readOnly": true, "type": "string" } }, "id": "AnalyzeOperationMetadata", "type": "object" }, "GetPolicyOptions": { "properties": { "requestedPolicyVersion": { "type": "integer", "description": "Optional. The maximum policy version that will be used to format the policy. Valid values are 0, 1, and 3. Requests specifying an invalid value will be rejected. Requests for policies with any conditional role bindings must specify version 3. Policies with no conditional role bindings may specify any valid value or leave the field unset. The policy in the response might use the policy version that you specified, or it might use a lower policy version. For example, if you specify version 3, but the policy has no conditional role bindings, the response uses version 1. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://documentation.s3ns.fr/iam/help/conditions/resource-policies).", "format": "int32" } }, "id": "GetPolicyOptions", "type": "object", "description": "Encapsulates settings provided to GetIamPolicy." }, "GkeNodePoolAcceleratorConfig": { "type": "object", "description": "A GkeNodeConfigAcceleratorConfig represents a Hardware Accelerator request for a node pool.", "id": "GkeNodePoolAcceleratorConfig", "properties": { "acceleratorCount": { "type": "string", "format": "int64", "description": "The number of accelerator cards exposed to an instance." }, "gpuPartitionSize": { "type": "string", "description": "Size of partitions to create on the GPU. Valid values are described in the NVIDIA [mig user guide](https://docs.nvidia.com/datacenter/tesla/mig-user-guide/#partitioning)." }, "acceleratorType": { "type": "string", "description": "The accelerator type resource namename (see GPUs on Compute Engine)." } } }, "NodeGroupAffinity": { "properties": { "nodeGroupUri": { "description": "Required. The URI of a sole-tenant [node group resource](https://documentation.s3ns.fr/compute/docs/reference/rest/v1/nodeGroups) that the cluster will be created on. A full URL, partial URI, or node group name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]/nodeGroups/node-group-1` * `projects/[project_id]/zones/[zone]/nodeGroups/node-group-1` * `node-group-1`", "type": "string" } }, "id": "NodeGroupAffinity", "description": "Node Group Affinity for clusters using sole-tenant node groups. **The `NodeGroupAffinity` resource is not related to the NodeGroup resource.**", "type": "object" }, "Metric": { "description": "A custom metric.", "id": "Metric", "properties": { "metricSource": { "description": "Required. A standard set of metrics is collected unless `metricOverrides` are specified for the metric source (see [Custom metrics] (https://documentation.s3ns.fr/dataproc/docs/guides/dataproc-metrics#custom_metrics) for more information).", "enumDescriptions": [ "Required unspecified metric source.", "Monitoring agent metrics. If this source is enabled, the service enables the monitoring agent in Compute Engine, and collects monitoring agent metrics, which are published with an `agent.googleapis.com` prefix.", "HDFS metric source.", "Spark metric source.", "YARN metric source.", "Spark History Server metric source.", "Hiveserver2 metric source.", "hivemetastore metric source", "flink metric source" ], "type": "string", "enum": [ "METRIC_SOURCE_UNSPECIFIED", "MONITORING_AGENT_DEFAULTS", "HDFS", "SPARK", "YARN", "SPARK_HISTORY_SERVER", "HIVESERVER2", "HIVEMETASTORE", "FLINK" ] }, "metricOverrides": { "type": "array", "description": "Optional. Specify one or more [Custom metrics] (https://documentation.s3ns.fr/dataproc/docs/guides/dataproc-metrics#custom_metrics) to collect for the metric course (for the `SPARK` metric source (any [Spark metric] (https://spark.apache.org/docs/latest/monitoring.html#metrics) can be specified). Provide metrics in the following format: METRIC_SOURCE: INSTANCE:GROUP:METRIC Use camelcase as appropriate. Examples: ``` yarn:ResourceManager:QueueMetrics:AppsCompleted spark:driver:DAGScheduler:job.allJobs sparkHistoryServer:JVM:Memory:NonHeapMemoryUsage.committed hiveserver2:JVM:Memory:NonHeapMemoryUsage.used ``` Notes: * Only the specified overridden metrics are collected for the metric source. For example, if one or more `spark:executive` metrics are listed as metric overrides, other `SPARK` metrics are not collected. The collection of the metrics for other enabled custom metric sources is unaffected. For example, if both `SPARK` and `YARN` metric sources are enabled, and overrides are provided for Spark metrics only, all YARN metrics are collected.", "items": { "type": "string" } } }, "type": "object" }, "ProvisioningModelMix": { "type": "object", "id": "ProvisioningModelMix", "description": "Defines how to create VMs with a mixture of provisioning models.", "properties": { "standardCapacityPercentAboveBase": { "type": "integer", "format": "int32", "description": "Optional. The percentage of target capacity that should use Standard VM. The remaining percentage will use Spot VMs. The percentage applies only to the capacity above standard_capacity_base. eg. If 15 instances are requested and standard_capacity_base is 5 and standard_capacity_percent_above_base is 30, the service will create 5 standard VMs and then start mixing spot and standard VMs for remaining 10 instances. The mix will be 30% standard and 70% spot." }, "standardCapacityBase": { "type": "integer", "format": "int32", "description": "Optional. The base capacity that will always use Standard VMs to avoid risk of more preemption than the minimum capacity you need. The service will create only standard VMs until it reaches standard_capacity_base, then it will start using standard_capacity_percent_above_base to mix Spot with Standard VMs. eg. If 15 instances are requested and standard_capacity_base is 5, the service will create 5 standard VMs and thenstart mixing spot and standard VMs for remaining 10 instances." } } }, "Job": { "type": "object", "id": "Job", "description": "A Dataproc job resource.", "properties": { "sparkRJob": { "description": "Optional. Job is a SparkR job.", "$ref": "SparkRJob" }, "driverControlFilesUri": { "description": "Output only. If present, the location of miscellaneous control files which can be used as part of job setup and handling. If not present, control files might be placed in the same location as `driver_output_uri`.", "readOnly": true, "type": "string" }, "driverSchedulingConfig": { "description": "Optional. Driver scheduling configuration.", "$ref": "DriverSchedulingConfig" }, "driverOutputResourceUri": { "readOnly": true, "description": "Output only. A URI pointing to the location of the stdout of the job's driver program.", "type": "string" }, "hadoopJob": { "$ref": "HadoopJob", "description": "Optional. Job is a Hadoop job." }, "sparkSqlJob": { "description": "Optional. Job is a SparkSql job.", "$ref": "SparkSqlJob" }, "labels": { "type": "object", "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** can 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." }, "statusHistory": { "type": "array", "description": "Output only. The previous job status.", "items": { "$ref": "JobStatus" }, "readOnly": true }, "pigJob": { "description": "Optional. Job is a Pig job.", "$ref": "PigJob" }, "scheduling": { "$ref": "JobScheduling", "description": "Optional. Job scheduling configuration." }, "sparkJob": { "$ref": "SparkJob", "description": "Optional. Job is a Spark job." }, "done": { "readOnly": true, "description": "Output only. Indicates whether the job is completed. If the value is `false`, the job is still in progress. If `true`, the job is completed, and `status.state` field will indicate if it was successful, failed, or cancelled.", "type": "boolean" }, "placement": { "description": "Required. Job information, including how, when, and where to run the job.", "$ref": "JobPlacement" }, "reference": { "$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 job_id." }, "status": { "description": "Output only. The job status. Additional application-specific status information might be contained in the type_job and yarn_applications fields.", "$ref": "JobStatus", "readOnly": true }, "yarnApplications": { "items": { "$ref": "YarnApplication" }, "description": "Output only. The collection of YARN applications spun up by this job. **Beta** Feature: This report is available for testing purposes only. It might be changed before final release.", "readOnly": true, "type": "array" }, "pysparkJob": { "description": "Optional. Job is a PySpark job.", "$ref": "PySparkJob" }, "hiveJob": { "description": "Optional. Job is a Hive job.", "$ref": "HiveJob" }, "jobUuid": { "type": "string", "description": "Output only. A UUID that uniquely identifies a job within the project over time. This is in contrast to a user-settable reference.job_id that might be reused over time.", "readOnly": true } } }, "DriverSchedulingConfig": { "type": "object", "id": "DriverSchedulingConfig", "description": "Driver scheduling configuration.", "properties": { "memoryMb": { "format": "int32", "description": "Required. The amount of memory in MB the driver is requesting.", "type": "integer" }, "vcores": { "format": "int32", "description": "Required. The number of vCPUs the driver is requesting.", "type": "integer" } } }, "AuxiliaryNodeGroup": { "id": "AuxiliaryNodeGroup", "type": "object", "description": "Node group identification and configuration information.", "properties": { "nodeGroup": { "$ref": "NodeGroup", "description": "Required. Node group configuration." }, "nodeGroupId": { "type": "string", "description": "Optional. A node group ID. Generated if not specified. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). Cannot begin or end with underscore or hyphen. Must consist of from 3 to 33 characters." } } }, "PySparkJob": { "description": "A Dataproc job for running [Apache PySpark] (https://spark.apache.org/docs/latest/api/python/index.html#pyspark-overview) applications on YARN.", "id": "PySparkJob", "properties": { "pythonFileUris": { "type": "array", "items": { "type": "string" }, "description": "Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip." }, "args": { "type": "array", "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as `--conf`, that can be set as job properties, since a collision may occur that causes an incorrect job submission.", "items": { "type": "string" } }, "fileUris": { "type": "array", "items": { "type": "string" }, "description": "Optional. HCFS URIs of files to be placed in the working directory of each executor. Useful for naively parallel tasks." }, "properties": { "type": "object", "description": "Optional. A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.", "additionalProperties": { "type": "string" } }, "mainPythonFileUri": { "description": "Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.", "type": "string" }, "jarFileUris": { "description": "Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.", "items": { "type": "string" }, "type": "array" }, "loggingConfig": { "$ref": "LoggingConfig", "description": "Optional. The runtime log config for job execution." }, "archiveUris": { "items": { "type": "string" }, "description": "Optional. HCFS URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip. Note: Spark applications must be deployed in [cluster mode](https://spark.apache.org/docs/latest/cluster-overview.html) for correct environment propagation.", "type": "array" } }, "type": "object" }, "ShieldedInstanceConfig": { "id": "ShieldedInstanceConfig", "properties": { "enableIntegrityMonitoring": { "type": "boolean", "description": "Optional. Defines whether instances have integrity monitoring enabled." }, "enableVtpm": { "description": "Optional. Defines whether instances have the vTPM enabled.", "type": "boolean" }, "enableSecureBoot": { "description": "Optional. Defines whether instances have Secure Boot enabled.", "type": "boolean" } }, "description": "Shielded Instance Config for clusters using [Compute Engine Shielded VMs](https://documentation.s3ns.fr/security/shielded-cloud/shielded-vm).", "type": "object" }, "GkeNodePoolTarget": { "id": "GkeNodePoolTarget", "description": "GKE node pools that Dataproc workloads run on.", "properties": { "roles": { "items": { "enumDescriptions": [ "Role is unspecified.", "At least one node pool must have the `DEFAULT` role. Work assigned to a role that is not associated with a node pool is assigned to the node pool with the `DEFAULT` role. For example, work assigned to the `CONTROLLER` role will be assigned to the node pool with the `DEFAULT` role if no node pool has the `CONTROLLER` role.", "Run work associated with the Dataproc control plane (for example, controllers and webhooks). Very low resource requirements.", "Run work associated with a Spark driver of a job.", "Run work associated with a Spark executor of a job." ], "type": "string", "enum": [ "ROLE_UNSPECIFIED", "DEFAULT", "CONTROLLER", "SPARK_DRIVER", "SPARK_EXECUTOR" ] }, "description": "Required. The roles associated with the GKE node pool.", "type": "array" }, "nodePoolConfig": { "$ref": "GkeNodePoolConfig", "description": "Input only. The configuration for the GKE node pool. If specified, Dataproc attempts to create a node pool with the specified shape. If one with the same name already exists, it is verified against all specified fields. If a field differs, the virtual cluster creation will fail. If omitted, any node pool with the specified name is used. If a node pool with the specified name does not exist, Dataproc create a node pool with default values. This is an input only field. It will not be returned by the API." }, "nodePool": { "description": "Required. The target GKE node pool. Format: 'projects/{project}/locations/{location}/clusters/{cluster}/nodePools/{node_pool}'", "type": "string" } }, "type": "object" }, "Interval": { "id": "Interval", "properties": { "startTime": { "description": "Optional. Inclusive start of the interval. If specified, a Timestamp matching this interval will have to be the same or after the start.", "type": "string", "format": "google-datetime" }, "endTime": { "description": "Optional. Exclusive end of the interval. If specified, a Timestamp matching this interval will have to be before the end.", "format": "google-datetime", "type": "string" } }, "description": "Represents a time interval, encoded as a Timestamp start (inclusive) and a Timestamp end (exclusive). The start must be less than or equal to the end. When the start equals the end, the interval is empty (matches no time). When both start and end are unspecified, the interval matches any time.", "type": "object" }, "ClusterStatus": { "description": "The status of a cluster and its instances.", "properties": { "substate": { "description": "Output only. Additional state information that includes status reported by the agent.", "readOnly": true, "type": "string", "enumDescriptions": [ "The cluster substate is unknown.", "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 the service loses communication with the Agent). Applies to RUNNING state." ], "enum": [ "UNSPECIFIED", "UNHEALTHY", "STALE_STATUS" ] }, "state": { "enum": [ "UNKNOWN", "CREATING", "RUNNING", "ERROR", "ERROR_DUE_TO_UPDATE", "DELETING", "UPDATING", "STOPPING", "STOPPED", "STARTING", "REPAIRING", "SCHEDULED" ], "readOnly": true, "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. **Note:** The cluster state changes from \"creating\" to \"running\" status after the master node(s), first two primary worker nodes (and the last primary worker node if primary workers \u003e 2) are running.", "The cluster encountered an error. It is not ready for use.", "The cluster has encountered an error while being updated. Jobs can be submitted to the cluster, but the cluster cannot be updated.", "The cluster is being deleted. It cannot be used.", "The cluster is being updated. It continues to accept and process jobs.", "The cluster is being stopped. It cannot be used.", "The cluster is currently stopped. It is not ready for use.", "The cluster is being started. It is not ready for use.", "The cluster is being repaired. It is not ready for use.", "Cluster creation is currently waiting for resources to be available. Once all resources are available, it will transition to CREATING and then RUNNING." ], "description": "Output only. The cluster's state.", "type": "string" }, "detail": { "description": "Optional. Details of cluster's state.", "type": "string" }, "stateStartTime": { "type": "string", "description": "Output only. Time when this state was entered (see JSON representation of [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)).", "format": "google-datetime", "readOnly": true } }, "id": "ClusterStatus", "type": "object" }, "JobScheduling": { "description": "Job scheduling options.", "properties": { "maxFailuresPerHour": { "description": "Optional. Maximum number of times per hour a driver can be restarted as a result of driver exiting with non-zero code before job is reported failed. A job might be reported as thrashing if the driver exits with a non-zero code four times within a 10-minute window. Maximum value is 10. **Note:** This restartable job option is not supported in Dataproc [workflow templates] (https://documentation.s3ns.fr/dataproc/docs/concepts/workflows/using-workflows#adding_jobs_to_a_template).", "type": "integer", "format": "int32" }, "maxFailuresTotal": { "type": "integer", "description": "Optional. Maximum total number of times a driver can be restarted as a result of the driver exiting with a non-zero code. After the maximum number is reached, the job will be reported as failed. Maximum value is 240. **Note:** Currently, this restartable job option is not supported in Dataproc [workflow templates](https://documentation.s3ns.fr/dataproc/docs/concepts/workflows/using-workflows#adding_jobs_to_a_template).", "format": "int32" } }, "id": "JobScheduling", "type": "object" }, "ClusterOperationMetadata": { "type": "object", "id": "ClusterOperationMetadata", "properties": { "warnings": { "readOnly": true, "items": { "type": "string" }, "description": "Output only. Errors encountered during operation execution.", "type": "array" }, "clusterName": { "readOnly": true, "description": "Output only. Name of the cluster for the operation.", "type": "string" }, "childOperationIds": { "readOnly": true, "items": { "type": "string" }, "description": "Output only. Child operation ids", "type": "array" }, "clusterUuid": { "readOnly": true, "type": "string", "description": "Output only. Cluster UUID for the operation." }, "description": { "type": "string", "description": "Output only. Short description of operation.", "readOnly": true }, "statusHistory": { "items": { "$ref": "ClusterOperationStatus" }, "type": "array", "description": "Output only. The previous operation status.", "readOnly": true }, "labels": { "readOnly": true, "type": "object", "additionalProperties": { "type": "string" }, "description": "Output only. Labels associated with the operation" }, "status": { "readOnly": true, "description": "Output only. Current operation status.", "$ref": "ClusterOperationStatus" }, "operationType": { "description": "Output only. The operation type.", "type": "string", "readOnly": true } }, "description": "Metadata describing the operation." }, "StartClusterRequest": { "id": "StartClusterRequest", "properties": { "requestId": { "description": "Optional. A unique ID used to identify the request. If the server receives two [StartClusterRequest](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.StartClusterRequest)s with the same id, then the second request will be ignored and the first google.longrunning.Operation created and stored in the backend is returned. Recommendation: Set this value to a [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier). The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). The maximum length is 40 characters.", "type": "string" }, "clusterUuid": { "description": "Optional. Specifying the `cluster_uuid` means the RPC will fail (with error NOT_FOUND) if a cluster with the specified UUID does not exist.", "type": "string" } }, "description": "A request to start a cluster.", "type": "object" }, "EncryptionConfig": { "id": "EncryptionConfig", "type": "object", "properties": { "kmsKey": { "description": "Optional. The Cloud KMS key resource name to use for cluster persistent disk and job argument encryption. See [Use CMEK with cluster data] (https://documentation.s3ns.fr//dataproc/docs/concepts/configuring-clusters/customer-managed-encryption#use_cmek_with_cluster_data) for more information. When this key resource name is provided, the following job arguments of the following job types submitted to the cluster are encrypted using CMEK: * [FlinkJob args](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/FlinkJob) * [HadoopJob args](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/HadoopJob) * [SparkJob args](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/SparkJob) * [SparkRJob args](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/SparkRJob) * [PySparkJob args](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/PySparkJob) * [SparkSqlJob](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/SparkSqlJob) scriptVariables and queryList.queries * [HiveJob](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/HiveJob) scriptVariables and queryList.queries * [PigJob](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/PigJob) scriptVariables and queryList.queries * [PrestoJob](https://documentation.s3ns.fr/dataproc/docs/reference/rest/v1/PrestoJob) scriptVariables and queryList.queries", "type": "string" }, "gcePdKmsKeyName": { "description": "Optional. The Cloud KMS key resource name to use for persistent disk encryption for all instances in the cluster. See [Use CMEK with cluster data] (https://documentation.s3ns.fr//dataproc/docs/concepts/configuring-clusters/customer-managed-encryption#use_cmek_with_cluster_data) for more information.", "type": "string" } }, "description": "Encryption settings for the cluster." }, "InstanceSelectionResult": { "description": "Defines a mapping from machine types to the number of VMs that are created with each machine type.", "id": "InstanceSelectionResult", "type": "object", "properties": { "vmCount": { "format": "int32", "type": "integer", "readOnly": true, "description": "Output only. Number of VM provisioned with the machine_type." }, "machineType": { "readOnly": true, "description": "Output only. Full machine-type names, e.g. \"n1-standard-16\".", "type": "string" } } }, "ClusterOperationStatus": { "description": "The status of the operation.", "id": "ClusterOperationStatus", "properties": { "stateStartTime": { "type": "string", "readOnly": true, "format": "google-datetime", "description": "Output only. The time this state was entered." }, "state": { "type": "string", "description": "Output only. A message containing the operation state.", "enum": [ "UNKNOWN", "PENDING", "RUNNING", "DONE" ], "enumDescriptions": [ "Unused.", "The operation has been created.", "The operation is running.", "The operation is done; either cancelled or completed." ], "readOnly": true }, "details": { "type": "string", "description": "Output only. A message containing any operation metadata details.", "readOnly": true }, "innerState": { "description": "Output only. A message containing the detailed operation state.", "type": "string", "readOnly": true } }, "type": "object" }, "Policy": { "properties": { "version": { "description": "Specifies the format of the policy. Valid values are `0`, `1`, and `3`. Requests that specify an invalid value are rejected. Any operation that affects conditional role bindings must specify version `3`. This requirement applies to the following operations: * Getting a policy that includes a conditional role binding * Adding a conditional role binding to a policy * Changing a conditional role binding in a policy * Removing any role binding, with or without a condition, from a policy that includes conditions **Important:** If you use IAM Conditions, you must include the `etag` field whenever you call `setIamPolicy`. If you omit this field, then IAM allows you to overwrite a version `3` policy with a version `1` policy, and all of the conditions in the version `3` policy are lost. If a policy does not include any conditions, operations on that policy may specify any valid version or leave the field unset. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://documentation.s3ns.fr/iam/help/conditions/resource-policies).", "format": "int32", "type": "integer" }, "etag": { "format": "byte", "type": "string", "description": "`etag` is used for optimistic concurrency control as a way to help prevent simultaneous updates of a policy from overwriting each other. It is strongly suggested that systems make use of the `etag` in the read-modify-write cycle to perform policy updates in order to avoid race conditions: An `etag` is returned in the response to `getIamPolicy`, and systems are expected to put that etag in the request to `setIamPolicy` to ensure that their change will be applied to the same version of the policy. **Important:** If you use IAM Conditions, you must include the `etag` field whenever you call `setIamPolicy`. If you omit this field, then IAM allows you to overwrite a version `3` policy with a version `1` policy, and all of the conditions in the version `3` policy are lost." }, "bindings": { "type": "array", "items": { "$ref": "Binding" }, "description": "Associates a list of `members`, or principals, with a `role`. Optionally, may specify a `condition` that determines how and when the `bindings` are applied. Each of the `bindings` must contain at least one principal. The `bindings` in a `Policy` can refer to up to 1,500 principals; up to 250 of these principals can be groups. Each occurrence of a principal counts towards these limits. For example, if the `bindings` grant 50 different roles to `user:alice@example.com`, and not to any other principal, then you can add another 1,450 principals to the `bindings` in the `Policy`." } }, "id": "Policy", "type": "object", "description": "An Identity and Access Management (IAM) policy, which specifies access controls for Cloud de Confiance resources. A `Policy` is a collection of `bindings`. A `binding` binds one or more `members`, or principals, to a single `role`. Principals can be user accounts, service accounts, groups, and domains (such as G Suite). A `role` is a named list of permissions; each `role` can be an IAM predefined role or a user-created custom role. For some types of Cloud de Confiance resources, a `binding` can also specify a `condition`, which is a logical expression that allows access to a resource only if the expression evaluates to `true`. A condition can add constraints based on attributes of the request, the resource, or both. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://documentation.s3ns.fr/iam/help/conditions/resource-policies). **JSON example:** ``` { \"bindings\": [ { \"role\": \"roles/resourcemanager.organizationAdmin\", \"members\": [ \"user:mike@example.com\", \"group:admins@example.com\", \"domain:s3nsapis.fr\", \"serviceAccount:my-project-id@appspot.gserviceaccount.com\" ] }, { \"role\": \"roles/resourcemanager.organizationViewer\", \"members\": [ \"user:eve@example.com\" ], \"condition\": { \"title\": \"expirable access\", \"description\": \"Does not grant access after Sep 2020\", \"expression\": \"request.time \u003c timestamp('2020-10-01T00:00:00.000Z')\", } } ], \"etag\": \"BwWWja0YfJA=\", \"version\": 3 } ``` **YAML example:** ``` bindings: - members: - user:mike@example.com - group:admins@example.com - domain:s3nsapis.fr - serviceAccount:my-project-id@appspot.gserviceaccount.com role: roles/resourcemanager.organizationAdmin - members: - user:eve@example.com role: roles/resourcemanager.organizationViewer condition: title: expirable access description: Does not grant access after Sep 2020 expression: request.time \u003c timestamp('2020-10-01T00:00:00.000Z') etag: BwWWja0YfJA= version: 3 ``` For a description of IAM and its features, see the [IAM documentation](https://documentation.s3ns.fr/iam/docs/)." }, "NodeGroup": { "description": "Node Group. **The `NodeGroup` resource is not related to the NodeGroupAffinity resource.**", "id": "NodeGroup", "properties": { "nodeGroupConfig": { "description": "Optional. The node group instance group configuration.", "$ref": "InstanceGroupConfig" }, "name": { "description": "The Node group [resource name](https://aip.dev/122).", "type": "string" }, "labels": { "type": "object", "description": "Optional. Node group labels. * Label **keys** must consist of from 1 to 63 characters and conform to [RFC 1035](https://www.ietf.org/rfc/rfc1035.txt). * Label **values** can be empty. If specified, they must consist of from 1 to 63 characters and conform to [RFC 1035] (https://www.ietf.org/rfc/rfc1035.txt). * The node group must have no more than 32 labels.", "additionalProperties": { "type": "string" } }, "roles": { "type": "array", "items": { "enumDescriptions": [ "Required unspecified role.", "Job drivers run on the node pool." ], "type": "string", "enum": [ "ROLE_UNSPECIFIED", "DRIVER" ] }, "description": "Required. Node group roles." } }, "type": "object" }, "TestIamPermissionsResponse": { "id": "TestIamPermissionsResponse", "description": "Response message for `TestIamPermissions` method.", "type": "object", "properties": { "permissions": { "type": "array", "description": "A subset of `TestPermissionsRequest.permissions` that the caller is allowed.", "items": { "type": "string" } } } }, "SessionOperationMetadata": { "type": "object", "description": "Metadata describing the Session operation.", "properties": { "sessionUuid": { "description": "Session UUID for the operation.", "type": "string" }, "description": { "type": "string", "description": "Short description of the operation." }, "operationType": { "type": "string", "enum": [ "SESSION_OPERATION_TYPE_UNSPECIFIED", "CREATE", "TERMINATE", "DELETE" ], "description": "The operation type.", "enumDescriptions": [ "Session operation type is unknown.", "Create Session operation type.", "Terminate Session operation type.", "Delete Session operation type." ] }, "labels": { "type": "object", "description": "Labels associated with the operation.", "additionalProperties": { "type": "string" } }, "warnings": { "items": { "type": "string" }, "description": "Warnings encountered during operation execution.", "type": "array" }, "session": { "description": "Name of the session for the operation.", "type": "string" }, "createTime": { "format": "google-datetime", "type": "string", "description": "The time when the operation was created." }, "doneTime": { "type": "string", "description": "The time when the operation was finished.", "format": "google-datetime" } }, "id": "SessionOperationMetadata" }, "Empty": { "id": "Empty", "properties": {}, "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: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }", "type": "object" }, "Binding": { "description": "Associates `members`, or principals, with a `role`.", "id": "Binding", "properties": { "condition": { "$ref": "Expr", "description": "The condition that is associated with this binding. If the condition evaluates to `true`, then this binding applies to the current request. If the condition evaluates to `false`, then this binding does not apply to the current request. However, a different role binding might grant the same role to one or more of the principals in this binding. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://documentation.s3ns.fr/iam/help/conditions/resource-policies)." }, "role": { "type": "string", "description": "Role that is assigned to the list of `members`, or principals. For example, `roles/viewer`, `roles/editor`, or `roles/owner`. For an overview of the IAM roles and permissions, see the [IAM documentation](https://documentation.s3ns.fr/iam/docs/roles-overview). For a list of the available pre-defined roles, see [here](https://documentation.s3ns.fr/iam/docs/understanding-roles)." }, "members": { "type": "array", "items": { "type": "string" }, "description": "Specifies the principals requesting access for a Cloud de Confiance resource. `members` can have the following values: * `allUsers`: A special identifier that represents anyone who is on the internet; with or without a account. * `allAuthenticatedUsers`: A special identifier that represents anyone who is authenticated with a account or a service account. Does not include identities that come from external identity providers (IdPs) through identity federation. * `user:{emailid}`: An email address that represents a specific account. For example, `alice@example.com` . * `serviceAccount:{emailid}`: An email address that represents a service account. For example, `my-other-app@appspot.gserviceaccount.com`. * `serviceAccount:{projectid}.svc.id.goog[{namespace}/{kubernetes-sa}]`: An identifier for a [Kubernetes service account](https://documentation.s3ns.fr/kubernetes-engine/docs/how-to/kubernetes-service-accounts). For example, `my-project.svc.id.goog[my-namespace/my-kubernetes-sa]`. * `group:{emailid}`: An email address that represents a group. For example, `admins@example.com`. * `domain:{domain}`: The G Suite domain (primary) that represents all the users of that domain. For example, `s3nsapis.fr` or `example.com`. * `principal://iam.googleapis.com/locations/global/workforcePools/{pool_id}/subject/{subject_attribute_value}`: A single identity in a workforce identity pool. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/group/{group_id}`: All workforce identities in a group. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/attribute.{attribute_name}/{attribute_value}`: All workforce identities with a specific attribute value. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/*`: All identities in a workforce identity pool. * `principal://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/subject/{subject_attribute_value}`: A single identity in a workload identity pool. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/group/{group_id}`: A workload identity pool group. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/attribute.{attribute_name}/{attribute_value}`: All identities in a workload identity pool with a certain attribute. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/*`: All identities in a workload identity pool. * `deleted:user:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a user that has been recently deleted. For example, `alice@example.com?uid=123456789012345678901`. If the user is recovered, this value reverts to `user:{emailid}` and the recovered user retains the role in the binding. * `deleted:serviceAccount:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a service account that has been recently deleted. For example, `my-other-app@appspot.gserviceaccount.com?uid=123456789012345678901`. If the service account is undeleted, this value reverts to `serviceAccount:{emailid}` and the undeleted service account retains the role in the binding. * `deleted:group:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a group that has been recently deleted. For example, `admins@example.com?uid=123456789012345678901`. If the group is recovered, this value reverts to `group:{emailid}` and the recovered group retains the role in the binding. * `deleted:principal://iam.googleapis.com/locations/global/workforcePools/{pool_id}/subject/{subject_attribute_value}`: Deleted single identity in a workforce identity pool. For example, `deleted:principal://iam.googleapis.com/locations/global/workforcePools/my-pool-id/subject/my-subject-attribute-value`." } }, "type": "object" }, "LifecycleConfig": { "description": "Specifies the cluster auto-delete schedule configuration.", "type": "object", "properties": { "idleStopTtl": { "format": "google-duration", "description": "Optional. The duration to keep the cluster started while idling (when no jobs are running). Passing this threshold will cause the cluster to be stopped. Minimum value is 5 minutes; maximum value is 14 days (see JSON representation of [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)).", "type": "string" }, "autoStopTtl": { "format": "google-duration", "type": "string", "description": "Optional. The lifetime duration of the cluster. The cluster will be auto-stopped at the end of this period, calculated from the time of submission of the create or update cluster request. Minimum value is 10 minutes; maximum value is 14 days (see JSON representation of [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json))." }, "autoDeleteTime": { "type": "string", "format": "google-datetime", "description": "Optional. The time when cluster will be auto-deleted (see JSON representation of [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json))." }, "autoStopTime": { "type": "string", "format": "google-datetime", "description": "Optional. The time when cluster will be auto-stopped (see JSON representation of [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json))." }, "idleDeleteTtl": { "description": "Optional. The duration to keep the cluster alive while idling (when no jobs are running). Passing this threshold will cause the cluster to be deleted. Minimum value is 5 minutes; maximum value is 14 days (see JSON representation of [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)).", "type": "string", "format": "google-duration" }, "autoDeleteTtl": { "format": "google-duration", "description": "Optional. The lifetime duration of cluster. The cluster will be auto-deleted at the end of this period. Minimum value is 10 minutes; maximum value is 14 days (see JSON representation of [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)).", "type": "string" }, "idleStartTime": { "description": "Output only. The time when cluster became idle (most recent job finished) and became eligible for deletion due to idleness (see JSON representation of [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)).", "format": "google-datetime", "readOnly": true, "type": "string" } }, "id": "LifecycleConfig" }, "SparkRJob": { "id": "SparkRJob", "description": "A Dataproc job for running [Apache SparkR](https://spark.apache.org/docs/latest/sparkr.html) applications on YARN.", "properties": { "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" }, "properties": { "type": "object", "description": "Optional. A mapping of property names to values, used to configure SparkR. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.", "additionalProperties": { "type": "string" } }, "mainRFileUri": { "type": "string", "description": "Required. The HCFS URI of the main R file to use as the driver. Must be a .R file." }, "archiveUris": { "description": "Optional. HCFS URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.", "type": "array", "items": { "type": "string" } }, "fileUris": { "description": "Optional. HCFS URIs of files to be placed in the working directory of each executor. Useful for naively parallel tasks.", "type": "array", "items": { "type": "string" } }, "loggingConfig": { "$ref": "LoggingConfig", "description": "Optional. The runtime log config for job execution." } }, "type": "object" }, "InstanceFlexibilityPolicy": { "description": "Instance flexibility Policy allowing a mixture of VM shapes and provisioning models.", "properties": { "instanceSelectionResults": { "readOnly": true, "type": "array", "items": { "$ref": "InstanceSelectionResult" }, "description": "Output only. A list of instance selection results in the group." }, "provisioningModelMix": { "description": "Optional. Defines how the Group selects the provisioning model to ensure required reliability.", "$ref": "ProvisioningModelMix" }, "instanceMachineTypes": { "additionalProperties": { "type": "string" }, "type": "object", "readOnly": true, "description": "Output only. A map of instance short name to machine type. The key is the short name of the Compute Engine instance, and the value is the full machine-type name (e.g., 'n1-standard-16'). See Machine types for more information on valid machine type strings." }, "instanceSelectionList": { "description": "Optional. List of instance selection options that the group will use when creating new VMs.", "type": "array", "items": { "$ref": "InstanceSelection" } } }, "type": "object", "id": "InstanceFlexibilityPolicy" }, "SparkJob": { "properties": { "mainClass": { "type": "string", "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 SparkJob.jar_file_uris." }, "mainJarFileUri": { "type": "string", "description": "The HCFS URI of the jar file that contains the main class." }, "fileUris": { "type": "array", "items": { "type": "string" }, "description": "Optional. HCFS URIs of files to be placed in the working directory of each executor. Useful for naively parallel tasks." }, "jarFileUris": { "description": "Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.", "items": { "type": "string" }, "type": "array" }, "archiveUris": { "type": "array", "items": { "type": "string" }, "description": "Optional. HCFS URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip." }, "loggingConfig": { "description": "Optional. The runtime log config for job execution.", "$ref": "LoggingConfig" }, "args": { "type": "array", "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as `--conf`, that can be set as job properties, since a collision may occur that causes an incorrect job submission.", "items": { "type": "string" } }, "properties": { "description": "Optional. A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.", "type": "object", "additionalProperties": { "type": "string" } } }, "id": "SparkJob", "description": "A Dataproc job for running [Apache Spark](https://spark.apache.org/) applications on YARN.", "type": "object" }, "StartupConfig": { "properties": { "requiredRegistrationFraction": { "type": "number", "description": "Optional. The config setting to enable cluster creation/ updation to be successful only after required_registration_fraction of instances are up and running. This configuration is applicable to only secondary workers for now. The cluster will fail if required_registration_fraction of instances are not available. This will include instance creation, agent registration, and service registration (if enabled).", "format": "double" } }, "description": "Configuration to handle the startup of instances during cluster create and update process.", "type": "object", "id": "StartupConfig" }, "GetIamPolicyRequest": { "properties": { "options": { "description": "OPTIONAL: A `GetPolicyOptions` object for specifying options to `GetIamPolicy`.", "$ref": "GetPolicyOptions" } }, "description": "Request message for `GetIamPolicy` method.", "type": "object", "id": "GetIamPolicyRequest" }, "GceClusterConfig": { "properties": { "shieldedInstanceConfig": { "description": "Optional. Shielded Instance Config for clusters using [Compute Engine Shielded VMs](https://documentation.s3ns.fr/security/shielded-cloud/shielded-vm).", "$ref": "ShieldedInstanceConfig" }, "metadata": { "description": "Optional. The Compute Engine metadata entries to add to all instances (see [Project and instance metadata](https://documentation.s3ns.fr/compute/docs/storing-retrieving-metadata#project_and_instance_metadata)).", "type": "object", "additionalProperties": { "type": "string" } }, "zoneUri": { "description": "Optional. The Compute Engine zone where the cluster will be located. If omitted, the service will pick a zone in the cluster's Compute Engine region. On a get request, zone will always be present. A full URL, partial URI, or short name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]` * `projects/[project_id]/zones/[zone]` * `[zone]`", "type": "string" }, "privateIpv6GoogleAccess": { "description": "Optional. The type of IPv6 access for a cluster.", "enumDescriptions": [ "If unspecified, Compute Engine default behavior will apply, which is the same as INHERIT_FROM_SUBNETWORK.", "Private access to and from Cloud de Confiance Services configuration inherited from the subnetwork configuration. This is the default Compute Engine behavior.", "Enables outbound private IPv6 access to Cloud de Confiance Services from the Dataproc cluster.", "Enables bidirectional private IPv6 access between Cloud de Confiance Services and the Dataproc cluster." ], "type": "string", "enum": [ "PRIVATE_IPV6_GOOGLE_ACCESS_UNSPECIFIED", "INHERIT_FROM_SUBNETWORK", "OUTBOUND", "BIDIRECTIONAL" ] }, "tags": { "items": { "type": "string" }, "description": "The Compute Engine network tags to add to all instances (see [Tagging instances](https://documentation.s3ns.fr/vpc/docs/add-remove-network-tags)).", "type": "array" }, "subnetworkUri": { "type": "string", "description": "Optional. The 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: * `https://www.googleapis.com/compute/v1/projects/[project_id]/regions/[region]/subnetworks/sub0` * `projects/[project_id]/regions/[region]/subnetworks/sub0` * `sub0`" }, "confidentialInstanceConfig": { "$ref": "ConfidentialInstanceConfig", "description": "Optional. Confidential Instance Config for clusters using [Confidential VMs](https://documentation.s3ns.fr/compute/confidential-vm/docs)." }, "internalIpOnly": { "type": "boolean", "description": "Optional. This setting applies to subnetwork-enabled networks. It is set to `true` by default in clusters created with image versions 2.2.x. When set to `true`: * All cluster VMs have internal IP addresses. * [Cloud de Confiance Private Access] (https://documentation.s3ns.fr/vpc/docs/private-google-access) must be enabled to access Dataproc and other Cloud de Confiance APIs. * Off-cluster dependencies must be configured to be accessible without external IP addresses. When set to `false`: * Cluster VMs are not restricted to internal IP addresses. * Ephemeral external IP addresses are assigned to each cluster VM." }, "serviceAccount": { "description": "Optional. The [Dataproc service account](https://documentation.s3ns.fr/dataproc/docs/concepts/configuring-clusters/service-accounts#service_accounts_in_dataproc) (also see [VM Data Plane identity](https://documentation.s3ns.fr/dataproc/docs/concepts/iam/dataproc-principals#vm_service_account_data_plane_identity)) used by Dataproc cluster VM instances to access Cloud de Confiance Platform services. If not specified, the [Compute Engine default service account](https://documentation.s3ns.fr/compute/docs/access/service-accounts#default_service_account) is used.", "type": "string" }, "serviceAccountScopes": { "description": "Optional. The URIs of service account scopes to be included in Compute Engine instances. The following base set of scopes is always included: * https://www.googleapis.com/auth/cloud.useraccounts.readonly * https://www.googleapis.com/auth/devstorage.read_write * https://www.googleapis.com/auth/logging.write If no scopes are specified, the following defaults are also provided: * https://www.googleapis.com/auth/bigquery * https://www.googleapis.com/auth/bigtable.admin.table * https://www.googleapis.com/auth/bigtable.data * https://www.googleapis.com/auth/devstorage.full_control", "items": { "type": "string" }, "type": "array" }, "resourceManagerTags": { "additionalProperties": { "type": "string" }, "description": "Optional. [Resource manager tags] (https://documentation.s3ns.fr/resource-manager/docs/tags/tags-creating-and-managing) to add to all instances (see [Use secure tags in Dataproc] (https://documentation.s3ns.fr/dataproc/docs/guides/use-secure-tags)).", "type": "object" }, "networkUri": { "type": "string", "description": "Optional. The 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](https://documentation.s3ns.fr/compute/docs/subnetworks) for more information). A full URL, partial URI, or short name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/global/networks/default` * `projects/[project_id]/global/networks/default` * `default`" }, "autoZoneExcludeZoneUris": { "description": "Optional. An optional list of Compute Engine zones where the cluster will not be located when Auto Zone is enabled. Only one of `zone_uri` or `auto_zone_exclude_zone_uris` can be set. If both are omitted, the service will pick a zone in the cluster Compute Engine region. If `auto_zone_exclude_zone_uris` is set and there is more than one non-excluded zone, the service will pick one of the non-excluded zones. Otherwise, cluster creation will fail with `INVALID_ARGUMENT` error. A full URL, partial URI, or short name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]` * `projects/[project_id]/zones/[zone]` * `[zone]`", "type": "array", "items": { "type": "string" } }, "multiZoneConfig": { "$ref": "MultiZoneConfig", "description": "Optional. Controls how instances within this Cluster are allowed to exist in multiple Zones within the Region. Only one of `zone_uri` or `multi_zone_config` must be set." }, "reservationAffinity": { "$ref": "ReservationAffinity", "description": "Optional. Reservation Affinity for consuming Zonal reservation." }, "nodeGroupAffinity": { "description": "Optional. Node Group Affinity for sole-tenant clusters.", "$ref": "NodeGroupAffinity" } }, "description": "Common config settings for resources of Compute Engine cluster instances, applicable to all instances in the cluster.", "id": "GceClusterConfig", "type": "object" }, "CancelJobRequest": { "id": "CancelJobRequest", "type": "object", "description": "A request to cancel a job.", "properties": {} }, "HiveJob": { "type": "object", "description": "A Dataproc job for running [Apache Hive](https://hive.apache.org/) queries on YARN.", "properties": { "queryFileUri": { "description": "The HCFS URI of the script that contains Hive queries.", "type": "string" }, "jarFileUris": { "description": "Optional. HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.", "items": { "type": "string" }, "type": "array" }, "queryList": { "$ref": "QueryList", "description": "A list of queries." }, "properties": { "description": "Optional. A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Dataproc API might 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", "additionalProperties": { "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" }, "scriptVariables": { "description": "Optional. Mapping of query variable names to values (equivalent to the Hive command: `SET name=\"value\";`).", "additionalProperties": { "type": "string" }, "type": "object" } }, "id": "HiveJob" }, "IdentityConfig": { "description": "Identity related configuration, including service account based secure multi-tenancy user mappings.", "type": "object", "properties": { "userServiceAccountMapping": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Required. Map of user to service account." }, "enableSsh": { "description": "Optional. Whether to enable SSH access for the cluster. The default is `true` for image versions prior to `3.1` and `false` for image versions `3.1` and later. The default behavior can be changed when creating clusters using image versions `2.3.30` and later.", "type": "boolean" } }, "id": "IdentityConfig" }, "LoggingConfig": { "properties": { "driverLogLevels": { "type": "object", "additionalProperties": { "type": "string", "enum": [ "LEVEL_UNSPECIFIED", "ALL", "TRACE", "DEBUG", "INFO", "WARN", "ERROR", "FATAL", "OFF" ], "enumDescriptions": [ "Level is unspecified. Use default level for log4j.", "Use ALL level for log4j.", "Use TRACE level for log4j.", "Use DEBUG level for log4j.", "Use INFO level for log4j.", "Use WARN level for log4j.", "Use ERROR level for log4j.", "Use FATAL level for log4j.", "Turn off log4j." ] }, "description": "The per-package log levels for the driver. This can include \"root\" package name to configure rootLogger. Examples: - 'com.google = FATAL' - 'root = INFO' - 'org.apache = DEBUG'" } }, "type": "object", "description": "The runtime logging config of the job.", "id": "LoggingConfig" }, "WorkflowMetadata": { "properties": { "state": { "readOnly": true, "type": "string", "description": "Output only. The workflow state.", "enumDescriptions": [ "Unused.", "The operation has been created.", "The operation is running.", "The operation is done; either cancelled or completed." ], "enum": [ "UNKNOWN", "PENDING", "RUNNING", "DONE" ] }, "version": { "type": "integer", "format": "int32", "description": "Output only. The version of template at the time of workflow instantiation.", "readOnly": true }, "deleteCluster": { "readOnly": true, "$ref": "ClusterOperation", "description": "Output only. The delete cluster operation metadata." }, "createCluster": { "$ref": "ClusterOperation", "readOnly": true, "description": "Output only. The create cluster operation metadata." }, "startTime": { "readOnly": true, "format": "google-datetime", "description": "Output only. Workflow start time.", "type": "string" }, "dagTimeout": { "format": "google-duration", "type": "string", "readOnly": true, "description": "Output only. The timeout duration for the DAG of jobs, expressed in seconds (see [JSON representation of duration](https://developers.google.com/protocol-buffers/docs/proto3#json))." }, "parameters": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Map from parameter names to values that were used for those parameters." }, "dagEndTime": { "format": "google-datetime", "type": "string", "description": "Output only. DAG end time, only set for workflows with dag_timeout when DAG ends.", "readOnly": true }, "endTime": { "description": "Output only. Workflow end time.", "type": "string", "format": "google-datetime", "readOnly": true }, "clusterUuid": { "description": "Output only. The UUID of target cluster.", "type": "string", "readOnly": true }, "dagStartTime": { "format": "google-datetime", "type": "string", "readOnly": true, "description": "Output only. DAG start time, only set for workflows with dag_timeout when DAG begins." }, "clusterName": { "readOnly": true, "type": "string", "description": "Output only. The name of the target cluster." }, "graph": { "description": "Output only. The workflow graph.", "readOnly": true, "$ref": "WorkflowGraph" }, "template": { "description": "Output only. The resource name of the workflow template as described in https://documentation.s3ns.fr/apis/design/resource_names. * For `projects.regions.workflowTemplates`, the resource name of the template has the following format: `projects/{project_id}/regions/{region}/workflowTemplates/{template_id}` * For `projects.locations.workflowTemplates`, the resource name of the template has the following format: `projects/{project_id}/locations/{location}/workflowTemplates/{template_id}`", "type": "string", "readOnly": true } }, "type": "object", "description": "A Dataproc workflow template resource.", "id": "WorkflowMetadata" }, "ClusterConfig": { "type": "object", "description": "The cluster config.", "id": "ClusterConfig", "properties": { "workerConfig": { "$ref": "InstanceGroupConfig", "description": "Optional. The Compute Engine config settings for the cluster's worker instances." }, "engine": { "enumDescriptions": [ "The engine is not specified. Works the same as ENGINE_DEFAULT.", "The cluster is a default engine cluster.", "The cluster is a [Lightning Engine](https://documentation.s3ns.fr/dataproc/docs/guides/lightning-engine) cluster." ], "type": "string", "enum": [ "ENGINE_UNSPECIFIED", "DEFAULT", "LIGHTNING" ], "description": "Optional. The cluster engine." }, "clusterType": { "description": "Optional. The type of the cluster.", "type": "string", "enum": [ "CLUSTER_TYPE_UNSPECIFIED", "STANDARD", "SINGLE_NODE", "ZERO_SCALE" ], "enumDescriptions": [ "Not set.", "Standard dataproc cluster with a minimum of two primary workers.", "https://documentation.s3ns.fr/dataproc/docs/concepts/configuring-clusters/single-node-clusters", "Clusters that can use only secondary workers and be scaled down to zero secondary worker nodes." ] }, "dataprocMetricConfig": { "$ref": "DataprocMetricConfig", "description": "Optional. The config for metrics." }, "auxiliaryNodeGroups": { "description": "Optional. The node group settings.", "items": { "$ref": "AuxiliaryNodeGroup" }, "type": "array" }, "securityConfig": { "description": "Optional. Security settings for the cluster.", "$ref": "SecurityConfig" }, "configBucket": { "description": "Optional. A Cloud Storage bucket used to stage job dependencies, config files, and job driver console output. If you do not specify a staging bucket, Cloud Dataproc will determine a Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Compute Engine zone where your cluster is deployed, and then create and manage this project-level, per-location bucket (see [Dataproc staging and temp buckets](https://documentation.s3ns.fr/dataproc/docs/concepts/configuring-clusters/staging-bucket)). **This field requires a Cloud Storage bucket name, not a `gs://...` URI to a Cloud Storage bucket.**", "type": "string" }, "clusterTier": { "enumDescriptions": [ "Uses standard tier if unspecified.", "Standard cluster tier.", "Premium cluster tier." ], "description": "Optional. The cluster tier.", "type": "string", "enum": [ "CLUSTER_TIER_UNSPECIFIED", "CLUSTER_TIER_STANDARD", "CLUSTER_TIER_PREMIUM" ] }, "initializationActions": { "type": "array", "description": "Optional. Commands to execute on each node after config is completed. By default, executables are run on master and all worker nodes. You can test a node's `role` metadata to run an executable on a master or worker node, as shown below using `curl` (you can also use `wget`): ROLE=$(curl -H Metadata-Flavor:Google http://metadata/computeMetadata/v1/instance/attributes/dataproc-role) if [[ \"${ROLE}\" == 'Master' ]]; then ... master specific actions ... else ... worker specific actions ... fi", "items": { "$ref": "NodeInitializationAction" } }, "encryptionConfig": { "description": "Optional. Encryption settings for the cluster.", "$ref": "EncryptionConfig" }, "softwareConfig": { "description": "Optional. The config settings for cluster software.", "$ref": "SoftwareConfig" }, "metastoreConfig": { "description": "Optional. Metastore configuration.", "$ref": "MetastoreConfig" }, "lifecycleConfig": { "description": "Optional. Lifecycle setting for the cluster.", "$ref": "LifecycleConfig" }, "diagnosticBucket": { "description": "Optional. A Cloud Storage bucket used to collect [checkpoint diagnostic data] (https://documentation.s3ns.fr/dataproc/docs/support/diagnose-clusters#checkpoint_diagnostic_data). If you do not specify a diagnostic bucket, Cloud Dataproc will use the Dataproc temp bucket to collect the checkpoint diagnostic data. **This field requires a Cloud Storage bucket name, not a `gs://...` URI to a Cloud Storage bucket.**", "type": "string" }, "secondaryWorkerConfig": { "$ref": "InstanceGroupConfig", "description": "Optional. The Compute Engine config settings for a cluster's secondary worker instances" }, "gkeClusterConfig": { "description": "Optional. BETA. The Kubernetes Engine config for clusters deployed to Kubernetes. These config settings are mutually exclusive with Compute Engine-based options, such as gce_cluster_config, master_config, worker_config, secondary_worker_config, and autoscaling_config.", "deprecated": true, "$ref": "GkeClusterConfig" }, "tempBucket": { "description": "Optional. A Cloud Storage bucket used to store ephemeral cluster and jobs data, such as Spark and MapReduce history files. If you do not specify a temp bucket, Dataproc will determine a Cloud Storage location (US, ASIA, or EU) for your cluster's temp bucket according to the Compute Engine zone where your cluster is deployed, and then create and manage this project-level, per-location bucket. The default bucket has a TTL of 90 days, but you can use any TTL (or none) if you specify a bucket (see [Dataproc staging and temp buckets](https://documentation.s3ns.fr/dataproc/docs/concepts/configuring-clusters/staging-bucket)). **This field requires a Cloud Storage bucket name, not a `gs://...` URI to a Cloud Storage bucket.**", "type": "string" }, "masterConfig": { "$ref": "InstanceGroupConfig", "description": "Optional. The Compute Engine config settings for the cluster's master instance." }, "gceClusterConfig": { "description": "Optional. The shared Compute Engine config settings for all instances in a cluster.", "$ref": "GceClusterConfig" } } }, "WorkflowGraph": { "type": "object", "id": "WorkflowGraph", "description": "The workflow graph.", "properties": { "nodes": { "readOnly": true, "items": { "$ref": "WorkflowNode" }, "description": "Output only. The workflow nodes.", "type": "array" } } }, "ListClustersResponse": { "description": "The list of all clusters in a project.", "properties": { "clusters": { "items": { "$ref": "Cluster" }, "readOnly": true, "type": "array", "description": "Output only. The clusters in the project." }, "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`.", "readOnly": true, "type": "string" } }, "type": "object", "id": "ListClustersResponse" }, "GkeNodeConfig": { "description": "Parameters that describe cluster nodes.", "properties": { "preemptible": { "description": "Optional. Whether the nodes are created as legacy [preemptible VM instances] (https://documentation.s3ns.fr/compute/docs/instances/preemptible). Also see Spot VMs, preemptible VM instances without a maximum lifetime. Legacy and Spot preemptible nodes cannot be used in a node pool with the `CONTROLLER` [role] (/dataproc/docs/reference/rest/v1/projects.regions.clusters#role) or in the DEFAULT node pool if the CONTROLLER role is not assigned (the DEFAULT node pool will assume the CONTROLLER role).", "type": "boolean" }, "machineType": { "description": "Optional. The name of a Compute Engine [machine type](https://documentation.s3ns.fr/compute/docs/machine-types).", "type": "string" }, "serviceAccount": { "description": "Optional. Specifies the service account to be used by the node pools. Specify the email address of the service account or its full resource name. Format: `projects/{project}/serviceAccounts/{service_account_email}` or `{service_account_email}`.", "type": "string" }, "accelerators": { "items": { "$ref": "GkeNodePoolAcceleratorConfig" }, "type": "array", "description": "Optional. A list of [hardware accelerators](https://documentation.s3ns.fr/compute/docs/gpus) to attach to each node." }, "minCpuPlatform": { "type": "string", "description": "Optional. [Minimum CPU platform](https://documentation.s3ns.fr/compute/docs/instances/specify-min-cpu-platform) to be used by this instance. The instance may be scheduled on the specified or a newer CPU platform. Specify the friendly names of CPU platforms, such as \"Intel Haswell\"` or Intel Sandy Bridge\"." }, "bootDiskKmsKey": { "type": "string", "description": "Optional. The [Customer Managed Encryption Key (CMEK)] (https://documentation.s3ns.fr/kubernetes-engine/docs/how-to/using-cmek) used to encrypt the boot disk attached to each node in the node pool. Specify the key using the following format: `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`" }, "localSsdCount": { "format": "int32", "description": "Optional. The number of local SSD disks to attach to the node, which is limited by the maximum number of disks allowable per zone (see [Adding Local SSDs](https://documentation.s3ns.fr/compute/docs/disks/local-ssd)).", "type": "integer" }, "spot": { "description": "Optional. Whether the nodes are created as [Spot VM instances] (https://documentation.s3ns.fr/compute/docs/instances/spot). Spot VMs are the latest update to legacy preemptible VMs. Spot VMs do not have a maximum lifetime. Legacy and Spot preemptible nodes cannot be used in a node pool with the `CONTROLLER` [role](/dataproc/docs/reference/rest/v1/projects.regions.clusters#role) or in the DEFAULT node pool if the CONTROLLER role is not assigned (the DEFAULT node pool will assume the CONTROLLER role).", "type": "boolean" } }, "type": "object", "id": "GkeNodeConfig" }, "JobReference": { "id": "JobReference", "type": "object", "properties": { "jobId": { "description": "Optional. The job ID, which must be unique within the project. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or hyphens (-). The maximum length is 100 characters. If not specified by the caller, the job ID will be provided by the server.", "type": "string" }, "projectId": { "type": "string", "description": "Optional. The ID of the Cloud de Confiance Platform project that the job belongs to. If specified, must match the request project ID." } }, "description": "Encapsulates the full scoping used to reference a job." }, "SetIamPolicyRequest": { "properties": { "policy": { "description": "REQUIRED: The complete policy to be applied to the `resource`. The size of the policy is limited to a few 10s of KB. An empty policy is a valid policy but certain Cloud de Confiance services (such as Projects) might reject them.", "$ref": "Policy" } }, "type": "object", "id": "SetIamPolicyRequest", "description": "Request message for `SetIamPolicy` method." }, "ResizeNodeGroupRequest": { "properties": { "size": { "description": "Required. The number of running instances for the node group to maintain. The group adds or removes instances to maintain the number of instances specified by this parameter.", "type": "integer", "format": "int32" }, "parentOperationId": { "type": "string", "description": "Optional. operation id of the parent operation sending the resize request" }, "requestId": { "type": "string", "description": "Optional. A unique ID used to identify the request. If the server receives two [ResizeNodeGroupRequest](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.ResizeNodeGroupRequests) with the same ID, the second request is ignored and the first google.longrunning.Operation created and stored in the backend is returned. Recommendation: Set this value to a [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier). The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). The maximum length is 40 characters." }, "gracefulDecommissionTimeout": { "format": "google-duration", "description": "Optional. Timeout for graceful YARN decommissioning. [Graceful decommissioning] (https://documentation.s3ns.fr/dataproc/docs/concepts/configuring-clusters/scaling-clusters#graceful_decommissioning) allows the removal of nodes from the Compute Engine node group without interrupting jobs in progress. This timeout specifies how long to wait for jobs in progress to finish before forcefully removing nodes (and potentially interrupting jobs). Default timeout is 0 (for forceful decommission), and the maximum allowed timeout is 1 day. (see JSON representation of [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)). Only supported on Dataproc image versions 1.2 and higher.", "type": "string" } }, "description": "A request to resize a node group.", "id": "ResizeNodeGroupRequest", "type": "object" }, "NodeInitializationAction": { "type": "object", "id": "NodeInitializationAction", "properties": { "executionTimeout": { "type": "string", "format": "google-duration", "description": "Optional. Amount of time executable has to complete. Default is 10 minutes (see JSON representation of [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)). 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." }, "executableFile": { "type": "string", "description": "Required. Cloud Storage URI of executable file." } }, "description": "Specifies an executable to run on a fully configured node and a timeout period for executable completion." }, "SparkSqlJob": { "type": "object", "id": "SparkSqlJob", "description": "A Dataproc job for running [Apache Spark SQL](https://spark.apache.org/sql/) queries.", "properties": { "queryFileUri": { "description": "The HCFS URI of the script that contains SQL queries.", "type": "string" }, "jarFileUris": { "type": "array", "description": "Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.", "items": { "type": "string" } }, "properties": { "type": "object", "description": "Optional. A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Dataproc API might be overwritten.", "additionalProperties": { "type": "string" } }, "scriptVariables": { "description": "Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET `name=\"value\";`).", "additionalProperties": { "type": "string" }, "type": "object" }, "loggingConfig": { "$ref": "LoggingConfig", "description": "Optional. The runtime log config for job execution." }, "queryList": { "description": "A list of queries.", "$ref": "QueryList" } } }, "NamespacedGkeDeploymentTarget": { "type": "object", "deprecated": true, "properties": { "targetGkeCluster": { "description": "Optional. The target GKE cluster to deploy to. Format: 'projects/{project}/locations/{location}/clusters/{cluster_id}'", "type": "string" }, "clusterNamespace": { "description": "Optional. A namespace within the GKE cluster to deploy into.", "type": "string" } }, "description": "Deprecated. Used only for the deprecated beta. A full, namespace-isolated deployment target for an existing GKE cluster.", "id": "NamespacedGkeDeploymentTarget" }, "PigJob": { "id": "PigJob", "properties": { "properties": { "description": "Optional. A mapping of property names to values, used to configure Pig. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in `/etc/hadoop/conf/*-site.xml`, /etc/pig/conf/pig.properties, and classes in user code.", "type": "object", "additionalProperties": { "type": "string" } }, "scriptVariables": { "additionalProperties": { "type": "string" }, "description": "Optional. Mapping of query variable names to values (equivalent to the Pig command: `name=[value]`).", "type": "object" }, "queryList": { "description": "A list of queries.", "$ref": "QueryList" }, "continueOnFailure": { "description": "Optional. Whether to continue executing queries if a query fails. The default value is `false`. Setting to `true` can be useful when executing independent parallel queries.", "type": "boolean" }, "loggingConfig": { "$ref": "LoggingConfig", "description": "Optional. The runtime log config for job execution." }, "queryFileUri": { "type": "string", "description": "The HCFS URI of the script that contains the Pig queries." }, "jarFileUris": { "type": "array", "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": "object", "description": "A Dataproc job for running [Apache Pig](https://pig.apache.org/) queries on YARN." }, "ClusterMetrics": { "type": "object", "id": "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.", "properties": { "yarnMetrics": { "additionalProperties": { "type": "string", "format": "int64" }, "type": "object", "description": "YARN metrics." }, "hdfsMetrics": { "additionalProperties": { "type": "string", "format": "int64" }, "type": "object", "description": "The HDFS metrics." } } }, "RepairClusterRequest": { "description": "A request to repair a cluster.", "type": "object", "properties": { "gracefulDecommissionTimeout": { "description": "Optional. Timeout for graceful YARN decommissioning. Graceful decommissioning facilitates the removal of cluster nodes without interrupting jobs in progress. The timeout specifies the amount of time to wait for jobs finish before forcefully removing nodes. The default timeout is 0 for forceful decommissioning, and the maximum timeout period is 1 day. (see [JSON Mapping—Duration] (https://developers.google.com/protocol-buffers/docs/proto3#json)). `graceful_decommission_timeout` is supported in image versions 1.2+.", "format": "google-duration", "type": "string" }, "parentOperationId": { "description": "Optional. operation id of the parent operation sending the repair request", "type": "string" }, "requestId": { "type": "string", "description": "Optional. A unique ID used to identify the request. If the server receives two RepairClusterRequests with the same ID, the second request is ignored, and the first google.longrunning.Operation created and stored in the backend is returned. Recommendation: Set this value to a [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier). The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). The maximum length is 40 characters." }, "dataprocSuperUser": { "description": "Optional. Whether the request is submitted by a super user. If true, IAM will check 'dataproc.clusters.repair' permission instead of 'dataproc.clusters.update' permission. This is to give Dataproc superuser the ability to repair clusters without granting the overly broad update permission.", "type": "boolean" }, "cluster": { "description": "Optional. Cluster to be repaired", "$ref": "ClusterToRepair" }, "nodePools": { "type": "array", "description": "Optional. Node pools and corresponding repair action to be taken. All node pools should be unique in this request. i.e. Multiple entries for the same node pool id are not allowed.", "items": { "$ref": "NodePool" } }, "clusterUuid": { "type": "string", "description": "Optional. Specifying the `cluster_uuid` means the RPC will fail (with error NOT_FOUND) if a cluster with the specified UUID does not exist." } }, "id": "RepairClusterRequest" }, "SubmitJobRequest": { "type": "object", "description": "A request to submit a job.", "id": "SubmitJobRequest", "properties": { "requestId": { "description": "Optional. A unique id used to identify the request. If the server receives two [SubmitJobRequest](https://documentation.s3ns.fr/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.SubmitJobRequest)s with the same id, then the second request will be ignored and the first Job created and stored in the backend is returned. It is recommended to always set this value to a [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier). The id must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). The maximum length is 40 characters.", "type": "string" }, "job": { "$ref": "Job", "description": "Required. The job resource." } } }, "ListOperationsResponse": { "type": "object", "description": "The response message for Operations.ListOperations.", "id": "ListOperationsResponse", "properties": { "unreachable": { "type": "array", "items": { "type": "string" }, "description": "Unordered list. Unreachable resources. Populated when the request sets `ListOperationsRequest.return_partial_success` and reads across collections. For example, when attempting to list all resources across all supported locations." }, "operations": { "items": { "$ref": "Operation" }, "description": "A list of operations that matches the specified filter in the request.", "type": "array" }, "nextPageToken": { "type": "string", "description": "The standard List next-page token." } } }, "MetastoreConfig": { "description": "Specifies a Metastore configuration.", "properties": { "dataprocMetastoreService": { "type": "string", "description": "Required. Resource name of an existing Metastore service. Example: * `projects/[project_id]/locations/[dataproc_region]/services/[service-name]`" } }, "id": "MetastoreConfig", "type": "object" }, "KerberosConfig": { "type": "object", "id": "KerberosConfig", "properties": { "truststoreUri": { "type": "string", "description": "Optional. The Cloud Storage URI of the truststore file used for SSL encryption. If not provided, the service will provide a self-signed certificate." }, "kmsKeyUri": { "type": "string", "description": "Optional. The URI of the KMS key used to encrypt sensitive files." }, "keyPasswordUri": { "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the password to the user provided key. For the self-signed certificate, this password is generated by the service.", "type": "string" }, "kdcDbKeyUri": { "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the master key of the KDC database.", "type": "string" }, "keystorePasswordUri": { "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the password to the user provided keystore. For the self-signed certificate, this password is generated by the service.", "type": "string" }, "rootPrincipalPasswordUri": { "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the root principal password.", "type": "string" }, "crossRealmTrustKdc": { "description": "Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.", "type": "string" }, "realm": { "type": "string", "description": "Optional. The name of the on-cluster Kerberos realm. If not specified, the uppercased domain of hostnames will be the realm." }, "crossRealmTrustAdminServer": { "description": "Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.", "type": "string" }, "enableKerberos": { "description": "Optional. Flag to indicate whether to Kerberize the cluster (default: false). Set this field to true to enable Kerberos on a cluster.", "type": "boolean" }, "keystoreUri": { "description": "Optional. The Cloud Storage URI of the keystore file used for SSL encryption. If not provided, the service will provide a self-signed certificate.", "type": "string" }, "crossRealmTrustRealm": { "description": "Optional. The remote realm the on-cluster KDC will trust, should the user enable cross realm trust.", "type": "string" }, "truststorePasswordUri": { "type": "string", "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the password to the user provided truststore. For the self-signed certificate, this password is generated by the service." }, "crossRealmTrustSharedPasswordUri": { "type": "string", "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the shared password between the on-cluster Kerberos realm and the remote trusted realm, in a cross realm trust relationship." }, "tgtLifetimeHours": { "type": "integer", "format": "int32", "description": "Optional. The lifetime of the ticket granting ticket, in hours. If not specified, or user specifies 0, then default value 10 will be used." } }, "description": "Specifies Kerberos related configuration." }, "YarnApplication": { "id": "YarnApplication", "type": "object", "description": "A YARN application created by a job. Application information is a subset of org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto. **Beta Feature**: This report is available for testing purposes only. It may be changed before final release.", "properties": { "state": { "enumDescriptions": [ "Status is unspecified.", "Status is NEW.", "Status is NEW_SAVING.", "Status is SUBMITTED.", "Status is ACCEPTED.", "Status is RUNNING.", "Status is FINISHED.", "Status is FAILED.", "Status is KILLED." ], "type": "string", "enum": [ "STATE_UNSPECIFIED", "NEW", "NEW_SAVING", "SUBMITTED", "ACCEPTED", "RUNNING", "FINISHED", "FAILED", "KILLED" ], "description": "Required. The application state." }, "progress": { "format": "float", "description": "Required. The numerical progress of the application, from 1 to 100.", "type": "number" }, "vcoreSeconds": { "format": "int64", "type": "string", "description": "Optional. The cumulative CPU time consumed by the application for a job, measured in vcore-seconds." }, "trackingUrl": { "type": "string", "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." }, "memoryMbSeconds": { "type": "string", "description": "Optional. The cumulative memory usage of the application for a job, measured in mb-seconds.", "format": "int64" }, "name": { "description": "Required. The application name.", "type": "string" } } }, "NodePool": { "description": "indicating a list of workers of same type", "properties": { "id": { "description": "Required. A unique id of the node pool. Primary and Secondary workers can be specified using special reserved ids PRIMARY_WORKER_POOL and SECONDARY_WORKER_POOL respectively. Aux node pools can be referenced using corresponding pool id.", "type": "string" }, "instanceNames": { "description": "Name of instances to be repaired. These instances must belong to specified node pool.", "items": { "type": "string" }, "type": "array" }, "repairAction": { "enumDescriptions": [ "No action will be taken by default.", "delete the specified list of nodes." ], "type": "string", "enum": [ "REPAIR_ACTION_UNSPECIFIED", "DELETE" ], "description": "Required. Repair action to take on specified resources of the node pool." } }, "type": "object", "id": "NodePool" }, "Cluster": { "id": "Cluster", "type": "object", "properties": { "clusterUuid": { "type": "string", "description": "Output only. A cluster UUID (Unique Universal Identifier). The service generates this value when it creates the cluster.", "readOnly": true }, "labels": { "type": "object", "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." }, "clusterName": { "description": "Required. The cluster name, which must be unique within a project. The name must start with a lowercase letter, and can contain up to 51 lowercase letters, numbers, and hyphens. It cannot end with a hyphen. The name of a deleted cluster can be reused.", "type": "string" }, "projectId": { "description": "Required. The Cloud de Confiance Platform project ID that the cluster belongs to.", "type": "string" }, "status": { "readOnly": true, "description": "Output only. Cluster status.", "$ref": "ClusterStatus" }, "metrics": { "$ref": "ClusterMetrics", "readOnly": true, "description": "Output only. 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." }, "statusHistory": { "type": "array", "description": "Output only. The previous cluster status.", "items": { "$ref": "ClusterStatus" }, "readOnly": true }, "config": { "$ref": "ClusterConfig", "description": "Optional. The cluster config for a cluster of Compute Engine Instances. Note that the service may set default values, and values may change when clusters are updated. Exactly one of ClusterConfig or VirtualClusterConfig must be specified." } }, "description": "Describes the identifying information, config, and status of a cluster" }, "GkeNodePoolAutoscalingConfig": { "description": "GkeNodePoolAutoscaling contains information the cluster autoscaler needs to adjust the size of the node pool to the current cluster usage.", "properties": { "minNodeCount": { "description": "The minimum number of nodes in the node pool. Must be \u003e= 0 and \u003c= max_node_count.", "type": "integer", "format": "int32" }, "maxNodeCount": { "type": "integer", "description": "The maximum number of nodes in the node pool. Must be \u003e= min_node_count, and must be \u003e 0. **Note:** Quota must be sufficient to scale up the cluster.", "format": "int32" } }, "type": "object", "id": "GkeNodePoolAutoscalingConfig" }, "DataprocMetricConfig": { "type": "object", "properties": { "metrics": { "type": "array", "items": { "$ref": "Metric" }, "description": "Required. Metrics sources to enable." } }, "description": "Metric config.", "id": "DataprocMetricConfig" }, "ReservationAffinity": { "type": "object", "properties": { "key": { "type": "string", "description": "Optional. Corresponds to the label key of reservation resource." }, "values": { "description": "Optional. Corresponds to the label values of reservation resource.", "items": { "type": "string" }, "type": "array" }, "consumeReservationType": { "enumDescriptions": [ "", "Do not consume from any allocated capacity.", "Consume any reservation available.", "Must consume from a specific reservation. Must specify key value fields for specifying the reservations." ], "description": "Optional. Type of reservation to consume", "type": "string", "enum": [ "TYPE_UNSPECIFIED", "NO_RESERVATION", "ANY_RESERVATION", "SPECIFIC_RESERVATION" ] } }, "description": "Reservation Affinity for consuming Zonal reservation.", "id": "ReservationAffinity" }, "InstanceSelection": { "id": "InstanceSelection", "type": "object", "properties": { "diskConfig": { "$ref": "DiskConfig", "description": "Optional. Disk configuration to apply to the instances in this instance selection. If specified on any entry in instanceSelectionList, then it must be specified on every entry in instanceSelectionList and the instanceGroupConfig must not specify any diskConfig." }, "machineTypes": { "description": "Optional. Full machine-type names, e.g. \"n1-standard-16\".", "items": { "type": "string" }, "type": "array" }, "rank": { "type": "integer", "description": "Optional. Preference of this instance selection. Lower number means higher preference. The service will first try to create a VM based on the machine-type with priority rank and fallback to next rank based on availability. Machine types and instance selections with the same priority have the same preference.", "format": "int32" } }, "description": "Defines machines types and a rank to which the machines types belong." }, "HadoopJob": { "id": "HadoopJob", "type": "object", "properties": { "jarFileUris": { "items": { "type": "string" }, "description": "Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.", "type": "array" }, "archiveUris": { "items": { "type": "string" }, "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.", "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 Dataproc API might 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 might occur that causes an incorrect job submission.", "items": { "type": "string" }, "type": "array" }, "mainJarFileUri": { "type": "string", "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'" }, "fileUris": { "type": "array", "items": { "type": "string" }, "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." }, "mainClass": { "type": "string", "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`." } }, "description": "A 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)." }, "JobStatus": { "id": "JobStatus", "description": "Dataproc job status.", "type": "object", "properties": { "details": { "description": "Optional. Job state details, such as an error description if the state is `ERROR`.", "type": "string" }, "stateStartTime": { "type": "string", "description": "Output only. The time when this state was entered.", "format": "google-datetime", "readOnly": true }, "substate": { "readOnly": true, "type": "string", "enumDescriptions": [ "The job substate is unknown.", "The Job is submitted to the agent. Applies to RUNNING state.", "The Job has been received and is awaiting execution (it might 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 can be caused by a loss of communication between the agent and Dataproc. If the agent does not send a timely update, the job will fail. Applies to RUNNING state." ], "description": "Output only. Additional state information, which includes status reported by the agent.", "enum": [ "UNSPECIFIED", "SUBMITTED", "QUEUED", "STALE_STATUS" ] }, "state": { "description": "Output only. A state message specifying the overall job state.", "readOnly": true, "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" } } }, "Expr": { "id": "Expr", "description": "Represents a textual expression in the Common Expression Language (CEL) syntax. CEL is a C-like expression language. The syntax and semantics of CEL are documented at https://github.com/google/cel-spec. Example (Comparison): title: \"Summary size limit\" description: \"Determines if a summary is less than 100 chars\" expression: \"document.summary.size() \u003c 100\" Example (Equality): title: \"Requestor is owner\" description: \"Determines if requestor is the document owner\" expression: \"document.owner == request.auth.claims.email\" Example (Logic): title: \"Public documents\" description: \"Determine whether the document should be publicly visible\" expression: \"document.type != 'private' && document.type != 'internal'\" Example (Data Manipulation): title: \"Notification string\" description: \"Create a notification string with a timestamp.\" expression: \"'New message received at ' + string(document.create_time)\" The exact variables and functions that may be referenced within an expression are determined by the service that evaluates it. See the service documentation for additional information.", "properties": { "expression": { "type": "string", "description": "Textual representation of an expression in Common Expression Language syntax." }, "title": { "description": "Optional. Title for the expression, i.e. a short string describing its purpose. This can be used e.g. in UIs which allow to enter the expression.", "type": "string" }, "description": { "description": "Optional. Description of the expression. This is a longer text which describes the expression, e.g. when hovered over it in a UI.", "type": "string" }, "location": { "description": "Optional. String indicating the location of the expression for error reporting, e.g. a file name and a position in the file.", "type": "string" } }, "type": "object" }, "MultiZoneConfig": { "description": "Configuration for multi-zonal clusters that can create instances across multiple Zones within the Region.", "properties": { "targetShape": { "type": "string", "enum": [ "TARGET_SHAPE_UNSPECIFIED", "ANY" ], "enumDescriptions": [ "Target shape is unspecified. Setting this will cause error.", "Instances may exist in any Zones within the Region." ], "description": "Optional. The distribution shape of the nodes in the multi-zonal cluster." } }, "type": "object", "id": "MultiZoneConfig" }, "DiagnoseClusterRequest": { "type": "object", "properties": { "tarballAccess": { "type": "string", "enum": [ "TARBALL_ACCESS_UNSPECIFIED", "GOOGLE_CLOUD_SUPPORT", "GOOGLE_DATAPROC_DIAGNOSE" ], "description": "Optional. (Optional) The access type to the diagnostic tarball. If not specified, falls back to default access of the bucket", "enumDescriptions": [ "Tarball Access unspecified. Falls back to default access of the bucket", "Cloud de Confiance Support group has read access to the diagnostic tarball", "Cloud de Confiance Dataproc Diagnose service account has read access to the diagnostic tarball" ] }, "diagnosisInterval": { "description": "Optional. Time interval in which diagnosis should be carried out on the cluster.", "$ref": "Interval" }, "job": { "description": "Optional. [DEPRECATED] Specifies the job on which diagnosis is to be performed. Format: projects/{project}/regions/{region}/jobs/{job}", "type": "string", "deprecated": true }, "yarnApplicationId": { "description": "Optional. [DEPRECATED] Specifies the yarn application on which diagnosis is to be performed.", "type": "string", "deprecated": true }, "yarnApplicationIds": { "items": { "type": "string" }, "description": "Optional. Specifies a list of yarn applications on which diagnosis is to be performed.", "type": "array" }, "tarballGcsDir": { "description": "Optional. (Optional) The output Cloud Storage directory for the diagnostic tarball. If not specified, a task-specific directory in the cluster's staging bucket will be used.", "type": "string" }, "jobs": { "items": { "type": "string" }, "description": "Optional. Specifies a list of jobs on which diagnosis is to be performed. Format: projects/{project}/regions/{region}/jobs/{job}", "type": "array" } }, "description": "A request to collect cluster diagnostic information.", "id": "DiagnoseClusterRequest" }, "ClusterOperation": { "id": "ClusterOperation", "type": "object", "description": "The cluster operation triggered by a workflow.", "properties": { "done": { "type": "boolean", "readOnly": true, "description": "Output only. Indicates the operation is done." }, "error": { "type": "string", "readOnly": true, "description": "Output only. Error, if operation failed." }, "operationId": { "description": "Output only. The id of the cluster operation.", "type": "string", "readOnly": true } } }, "AttachedDiskConfig": { "description": "Specifies the config of attached disk options for single VM instance.", "type": "object", "id": "AttachedDiskConfig", "properties": { "diskType": { "description": "Optional. Deprecated: Use `type` instead.", "enum": [ "DISK_TYPE_UNSPECIFIED", "HYPERDISK_BALANCED", "HYPERDISK_EXTREME", "HYPERDISK_ML", "HYPERDISK_THROUGHPUT" ], "deprecated": true, "enumDescriptions": [ "Disk type is not specified.", "Hyperdisk Balanced.", "Hyperdisk Extreme.", "Hyperdisk ML.", "Hyperdisk Throughput." ], "type": "string" }, "type": { "type": "string", "description": "Optional. Attached disk type. Currently only supports Hyperdisks. Hyperdisk Balanced High Availability is not supported. See https://documentation.s3ns.fr/compute/docs/disks/hyperdisks. Allowed values are: * `hyperdisk-balanced` * `hyperdisk-extreme` * `hyperdisk-ml` * `hyperdisk-throughput`" }, "provisionedIops": { "format": "int64", "description": "Optional. Indicates how many IOPS to provision for the attached disk. This sets the number of I/O operations per second that the disk can handle. See https://documentation.s3ns.fr/compute/docs/disks/hyperdisks#hyperdisk-features", "type": "string" }, "diskSizeGb": { "description": "Optional. Disk size in GB.", "type": "integer", "format": "int32" }, "provisionedThroughput": { "description": "Optional. Indicates how much throughput to provision for the attached disk. This sets the number of throughput mb per second that the disk can handle. See https://documentation.s3ns.fr/compute/docs/disks/hyperdisks#hyperdisk-features", "type": "string", "format": "int64" } } }, "ListJobsResponse": { "description": "A list of jobs in a project.", "properties": { "jobs": { "items": { "$ref": "Job" }, "description": "Output only. Jobs list.", "readOnly": true, "type": "array" }, "nextPageToken": { "type": "string", "description": "Optional. This token is included in the response if there are more results to fetch. To fetch additional results, provide this value as the `page_token` in a subsequent ListJobsRequest." }, "unreachable": { "type": "array", "items": { "type": "string" }, "description": "Output only. List of jobs with kms_key-encrypted parameters that could not be decrypted. A response to a `jobs.get` request may indicate the reason for the decryption failure for a specific job.", "readOnly": true } }, "id": "ListJobsResponse", "type": "object" }, "DiagnoseClusterResults": { "type": "object", "properties": { "outputUri": { "description": "Output only. The Cloud Storage URI of the diagnostic output. The output report is a plain text file with a summary of collected diagnostics.", "readOnly": true, "type": "string" } }, "id": "DiagnoseClusterResults", "description": "The location of diagnostic output." }, "JobMetadata": { "type": "object", "properties": { "jobId": { "description": "Output only. The job id.", "readOnly": true, "type": "string" }, "operationType": { "type": "string", "readOnly": true, "description": "Output only. Operation type." }, "status": { "readOnly": true, "$ref": "JobStatus", "description": "Output only. Most recent job status." }, "startTime": { "readOnly": true, "type": "string", "description": "Output only. Job submission time.", "format": "google-datetime" } }, "description": "Job Operation metadata.", "id": "JobMetadata" }, "DiskConfig": { "id": "DiskConfig", "properties": { "bootDiskSizeGb": { "description": "Optional. Size in GB of the boot disk (default is 500GB).", "type": "integer", "format": "int32" }, "bootDiskType": { "type": "string", "description": "Optional. Type of the boot disk (default is \"pd-standard\"). Valid values: \"pd-balanced\" (Persistent Disk Balanced Solid State Drive), \"pd-ssd\" (Persistent Disk Solid State Drive), or \"pd-standard\" (Persistent Disk Hard Disk Drive). See [Disk types](https://documentation.s3ns.fr/compute/docs/disks#disk-types)." }, "bootDiskProvisionedThroughput": { "format": "int64", "type": "string", "description": "Optional. Indicates how much throughput to provision for the disk. This sets the number of throughput mb per second that the disk can handle. Values must be greater than or equal to 1. **This field is supported only if boot_disk_type is `hyperdisk-balanced`.**" }, "localSsdInterface": { "description": "Optional. Interface type of local SSDs (default is \"scsi\"). Valid values: \"scsi\" (Small Computer System Interface), \"nvme\" (Non-Volatile Memory Express). See [local SSD performance](https://documentation.s3ns.fr/compute/docs/disks/local-ssd#performance).", "type": "string" }, "bootDiskProvisionedIops": { "type": "string", "format": "int64", "description": "Optional. Indicates how many IOPS to provision for the disk. This sets the number of I/O operations per second that the disk can handle. **This field is supported only if boot_disk_type is `hyperdisk-balanced`.**" }, "attachedDiskConfigs": { "type": "array", "description": "Optional. A list of attached disk configs for a group of VM instances.", "items": { "$ref": "AttachedDiskConfig" } }, "numLocalSsds": { "type": "integer", "format": "int32", "description": "Optional. Number of attached SSDs, from 0 to 8 (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. Note: Local SSD options may vary by machine type and number of vCPUs selected." } }, "description": "Specifies the config of boot disk and attached disk options for a group of VM instances.", "type": "object" }, "WorkflowNode": { "properties": { "state": { "enum": [ "NODE_STATE_UNSPECIFIED", "BLOCKED", "RUNNABLE", "RUNNING", "COMPLETED", "FAILED" ], "readOnly": true, "enumDescriptions": [ "State is unspecified.", "The node is awaiting prerequisite node to finish.", "The node is runnable but not running.", "The node is running.", "The node completed successfully.", "The node failed. A node can be marked FAILED because its ancestor or peer failed." ], "type": "string", "description": "Output only. The node state." }, "jobId": { "readOnly": true, "type": "string", "description": "Output only. The job id; populated after the node enters RUNNING state." }, "error": { "type": "string", "description": "Output only. The error detail.", "readOnly": true }, "prerequisiteStepIds": { "readOnly": true, "items": { "type": "string" }, "description": "Output only. Node's prerequisite nodes.", "type": "array" }, "stepId": { "readOnly": true, "type": "string", "description": "Output only. The name of the node." } }, "type": "object", "id": "WorkflowNode", "description": "The workflow node." } }, "ownerName": "Google", "version": "v1" }