"description":"Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED.NOTE: the name binding allows API services to override the binding to use different resource name schemes, such as users/*/operations. To override the binding, API services can add a binding such as \"/v1/{name=users/*}/operations\" to their service configuration. For backwards compatibility, the default name includes the operations collection id, however overriding users must ensure the name binding is the parent resource, without the operations collection id."
"description":"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."
},
"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.",
"response":{
"$ref":"Empty"
},
"parameterOrder":[
"name"
],
"httpMethod":"POST",
"parameters":{
"name":{
"location":"path",
"description":"The name of the operation resource to be cancelled.",
"description":"Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED.",
"description":"Optional. A filter constraining the jobs to list. Filters are case-sensitive and have the following syntax:field = value AND field = value ...where field is status.state or labels.[KEY], and [KEY] is a label key. value can be * to match all values. status.state can be either ACTIVE or NON_ACTIVE. Only the logical AND operator is supported; space-separated items are treated as having an implicit AND operator.Example filter:status.state = ACTIVE AND labels.env = staging AND labels.starred = *"
"description":"Optional. Specifies enumerated categories of jobs to list. (default = match ALL jobs).If filter is provided, jobStateMatcher will be ignored.",
"description":"Starts a job cancellation request. To access the job resource after cancellation, call regions/{region}/jobs.list or regions/{region}/jobs.get.",
"description":"Required. Specifies the path, relative to \u003ccode\u003eJob\u003c/code\u003e, of the field to update. For example, to update the labels of a Job the \u003ccode\u003eupdate_mask\u003c/code\u003e parameter would be specified as \u003ccode\u003elabels\u003c/code\u003e, and the PATCH request body would specify the new value. \u003cstrong\u003eNote:\u003c/strong\u003e Currently, \u003ccode\u003elabels\u003c/code\u003e is the only field that can be updated.",
"description":"Gets cluster diagnostic information. After the operation completes, the Operation.response field contains DiagnoseClusterOutputLocation.",
"description":"Optional. A filter constraining the clusters to list. Filters are case-sensitive and have the following syntax:field = value AND field = value ...where field is one of status.state, clusterName, or labels.[KEY], and [KEY] is a label key. value can be * to match all values. status.state can be one of the following: ACTIVE, INACTIVE, CREATING, RUNNING, ERROR, DELETING, or UPDATING. ACTIVE contains the CREATING, UPDATING, and RUNNING states. INACTIVE contains the DELETING and ERROR states. clusterName is the name of the cluster provided at creation time. Only the logical AND operator is supported; space-separated items are treated as having an implicit AND operator.Example filter:status.state = ACTIVE AND clusterName = mycluster AND labels.env = staging AND labels.starred = *",
"description":"Required. Specifies the path, relative to Cluster, of the field to update. For example, to change the number of workers in a cluster to 5, the update_mask parameter would be specified as config.worker_config.num_instances, and the PATCH request body would specify the new value, as follows:\n{\n \"config\":{\n \"workerConfig\":{\n \"numInstances\":\"5\"\n }\n }\n}\nSimilarly, to change the number of preemptible workers in a cluster to 5, the update_mask parameter would be config.secondary_worker_config.num_instances, and the PATCH request body would be set as follows:\n{\n \"config\":{\n \"secondaryWorkerConfig\":{\n \"numInstances\":\"5\"\n }\n }\n}\n\u003cstrong\u003eNote:\u003c/strong\u003e Currently, only the following fields can be updated:\u003ctable\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003e\u003cstrong\u003eMask\u003c/strong\u003e\u003c/td\u003e \u003ctd\u003e\u003cstrong\u003ePurpose\u003c/strong\u003e\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd\u003e\u003cstrong\u003e\u003cem\u003elabels\u003c/em\u003e\u003c/strong\u003e\u003c/td\u003e \u003ctd\u003eUpdate labels\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd\u003e\u003cstrong\u003e\u003cem\u003econfig.worker_config.num_instances\u003c/em\u003e\u003c/strong\u003e\u003c/td\u003e \u003ctd\u003eResize primary worker group\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd\u003e\u003cstrong\u003e\u003cem\u003econfig.secondary_worker_config.num_instances\u003c/em\u003e\u003c/strong\u003e\u003c/td\u003e \u003ctd\u003eResize secondary worker group\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/table\u003e",
"description":"Optional. Timeout for graceful YARN decomissioning. 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.Only supported on Dataproc image versions 1.2 and higher.",
"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."
"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."
"description":"Optional. A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.",
"description":"Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
"description":"Optional. HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks."
"description":"The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris."
"description":"Optional. HCFS URIs of archives to be extracted in the working directory of Spark drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.",
"description":"Output only. The job status. Additional application-specific status information may be contained in the \u003ccode\u003etype_job\u003c/code\u003e and \u003ccode\u003eyarn_applications\u003c/code\u003e fields."
"description":"Output only. If present, the location of miscellaneous control files which may be used as part of job setup and handling. If not present, control files may be placed in the same location as driver_output_uri."
"description":"Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.",
"description":"Output only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release."
"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 \u003ccode\u003ejob_id\u003c/code\u003e."
"The Job is submitted to the agent.Applies to RUNNING state.",
"The Job has been received and is awaiting execution (it may be waiting for a condition to be met). See the \"details\" field for the reason for the delay.Applies to RUNNING state.",
"The agent-reported status is out of date, which may be caused by a loss of communication between the agent and Cloud Dataproc. If the agent does not send a timely update, the job will fail.Applies to RUNNING state."
"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.",
"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'"
"description":"Optional. A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.",
"description":"Optional. The arguments to pass to the driver. Do not include arguments, such as -libjars or -Dfoo=bar, that can be set as job properties, since a collision may occur that causes an incorrect job submission."
"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.",
"description":"Required. The queries to execute. You do not need to terminate a query with a semicolon. Multiple queries can be specified in one string by separating each with a semicolon. Here is an example of an Cloud Dataproc API snippet that uses a QueryList to specify a HiveJob:\n\"hiveJob\": {\n \"queryList\": {\n \"queries\": [\n \"query1\",\n \"query2\",\n \"query3;query4\",\n ]\n }\n}\n",
"type":"array",
"items":{
"type":"string"
}
}
},
"id":"QueryList"
},
"YarnApplication":{
"description":"A YARN application created by a job. Application information is a subset of \u003ccode\u003eorg.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto\u003c/code\u003e.Beta Feature: This report is available for testing purposes only. It may be changed before final release.",
"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.",
"description":"Optional. Number of attached SSDs, from 0 to 4 (default is 0). If SSDs are not attached, the boot disk is used to store runtime logs and HDFS (https://hadoop.apache.org/docs/r1.2.1/hdfs_user_guide.html) data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic config and installed binaries.",
"description":"Metadata describing the operation."
},
"Empty":{
"type":"object",
"properties":{},
"id":"Empty",
"description":"A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance:\nservice Foo {\n rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);\n}\nThe JSON representation for Empty is empty JSON object {}."
"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."
},
"scriptVariables":{
"type":"object",
"additionalProperties":{
"type":"string"
},
"description":"Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name=\"value\";)."
"description":"Optional. A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.",
"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."
"description":"Output only. The Google Cloud Storage URI of the diagnostic output. The output report is a plain text file with a summary of collected diagnostics."
"description":"Optional. Commands to execute on each node after config is completed. By default, executables are run on master and all worker nodes. You can test a node's role metadata to run an executable on a master or worker node, as shown below using curl (you can also use wget):\nROLE=$(curl -H Metadata-Flavor:Google http://metadata/computeMetadata/v1/instance/attributes/dataproc-role)\nif [[ \"${ROLE}\" == 'Master' ]]; then\n ... master specific actions ...\nelse\n ... worker specific actions ...\nfi\n",
"description":"Optional. A Google Cloud Storage staging bucket used for sharing generated SSH keys and config. If you do not specify a staging bucket, Cloud Dataproc will determine an appropriate Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Google Compute Engine zone where your cluster is deployed, and then it will create and manage this project-level, per-location bucket for you."
"description":"Optional. A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code."
"description":"Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission."
"description":"Optional. HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.",
"description":"Optional. The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri.A full URL, partial URI, or short name are valid. Examples:\nhttps://www.googleapis.com/compute/v1/projects/[project_id]/regions/us-east1/sub0\nprojects/[project_id]/regions/us-east1/sub0\nsub0"
},
"networkUri":{
"type":"string",
"description":"Optional. The Google Compute Engine network to be used for machine communications. Cannot be specified with subnetwork_uri. If neither network_uri nor subnetwork_uri is specified, the \"default\" network of the project is used, if it exists. Cannot be a \"Custom Subnet Network\" (see Using Subnetworks for more information).A full URL, partial URI, or short name are valid. Examples:\nhttps://www.googleapis.com/compute/v1/projects/[project_id]/regions/global/default\nprojects/[project_id]/regions/global/default\ndefault"
},
"zoneUri":{
"type":"string",
"description":"Optional. The zone where the Google Compute Engine cluster will be located. On a create request, it is required in the \"global\" region. If omitted in a non-global Cloud Dataproc region, the service will pick a zone in the corresponding Compute Engine region. On a get request, zone will always be present.A full URL, partial URI, or short name are valid. Examples:\nhttps://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]\nprojects/[project_id]/zones/[zone]\nus-central1-f"
"description":"The Google Compute Engine metadata entries to add to all instances (see Project and instance metadata (https://cloud.google.com/compute/docs/storing-retrieving-metadata#project_and_instance_metadata))."
"description":"Optional. If true, all instances in the cluster will only have internal IP addresses. By default, clusters are not restricted to internal IP addresses, and will have ephemeral external IP addresses assigned to each instance. This internal_ip_only restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses.",
"type":"boolean"
},
"serviceAccountScopes":{
"description":"Optional. The URIs of service account scopes to be included in Google Compute Engine instances. The following base set of scopes is always included:\nhttps://www.googleapis.com/auth/cloud.useraccounts.readonly\nhttps://www.googleapis.com/auth/devstorage.read_write\nhttps://www.googleapis.com/auth/logging.writeIf no scopes are specified, the following defaults are also provided:\nhttps://www.googleapis.com/auth/bigquery\nhttps://www.googleapis.com/auth/bigtable.admin.table\nhttps://www.googleapis.com/auth/bigtable.data\nhttps://www.googleapis.com/auth/devstorage.full_control",
"description":"Optional. The service account of the instances. Defaults to the default Google Compute Engine service account. Custom service accounts need permissions equivalent to the folloing IAM roles:\nroles/logging.logWriter\nroles/storage.objectAdmin(see https://cloud.google.com/compute/docs/access/service-accounts#custom_service_accounts for more information). Example: [account_id]@[project_id].iam.gserviceaccount.com",
"description":"Full URL, partial URI, or short name of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes)Examples * https://www.googleapis.com/compute/beta/projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80 * projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80 * nvidia-tesla-k80"
"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.",
"description":"The per-package log levels for the driver. This may include \"root\" package name to configure rootLogger. Examples: 'com.google = FATAL', 'root = INFO', 'org.apache = DEBUG'",
"description":"Properties of the object. Contains field @type with type URL.",
"type":"any"
},
"description":"Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any."
"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.",
"description":"The normal response of the operation in case of success. If the original method returns no data on success, such as Delete, the response is google.protobuf.Empty. If the original method is standard Get/Create/Update, the response should be the resource. For other methods, the response should have the type XxxResponse, where Xxx is the original method name. For example, if the original method name is TakeSnapshot(), the inferred response type is TakeSnapshotResponse."
"description":"The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the name should have the format of operations/some/unique/name."
"description":"Optional. The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or hyphens (-). The maximum length is 100 characters.",
"description":"The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC (https://github.com/grpc). The error model is designed to be:\nSimple to use and understand for most users\nFlexible enough to meet unexpected needsOverviewThe Status message contains three pieces of data: error code, error message, and error details. The error code should be an enum value of google.rpc.Code, but it may accept additional error codes if needed. The error message should be a developer-facing English message that helps developers understand and resolve the error. If a localized user-facing error message is needed, put the localized message in the error details or localize it in the client. The optional error details may contain arbitrary information about the error. There is a predefined set of error detail types in the package google.rpc that can be used for common error conditions.Language mappingThe Status message is the logical representation of the error model, but it is not necessarily the actual wire format. When the Status message is exposed in different client libraries and different wire protocols, it can be mapped differently. For example, it will likely be mapped to some exceptions in Java, but more likely mapped to some error codes in C.Other usesThe error model and the Status message can be used in a variety of environments, either with or without APIs, to provide a consistent developer experience across different environments.Example uses of this error model include:\nPartial errors. If a service needs to return partial errors to the client, it may embed the Status in the normal response to indicate the partial errors.\nWorkflow errors. A typical workflow has multiple steps. Each step may have a Status message for error reporting.\nBatch operations. If a client uses batch request and batch response, the Status message should be used directly inside batch response, one for each error sub-response.\nAsynchronous operations. If an API call embeds asynchronous operation results in its response, the status of those operations should be represented directly using the Status message.\nLogging. If some API errors are stored in logs, the message Status could be used directly after any stripping needed for security/privacy reasons.",
"description":"A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.",
"description":"Output only. The config for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups."
"description":"Optional. The Google Compute Engine machine type used for cluster instances.A full URL, partial URI, or short name are valid. Examples:\nhttps://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2\nprojects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2\nn1-standard-2",
"description":"Optional. The list of instance names. Cloud Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Cloud Dataproc derive the name)."
"description":"Optional. The Google Compute Engine accelerator configuration for these instances.Beta Feature: This feature is still under development. It may be changed before final release.",
"description":"Optional. Maximum number of times per hour a driver may be restarted as a result of driver terminating with non-zero code before job is reported failed.A job may be reported as thrashing if driver exits with non-zero code 4 times within 10 minute window.Maximum value is 10.",
"description":"Optional. Amount of time executable has to complete. Default is 10 minutes. Cluster creation fails with an explanatory error message (the name of the executable that caused the error and the exceeded timeout period) if the executable is not completed at end of the timeout period.",
"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 \u003ccode\u003eListJobsRequest\u003c/code\u003e."
"description":"Optional. The runtime log config for job execution."
},
"properties":{
"additionalProperties":{
"type":"string"
},
"description":"Optional. A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.",
"type":"object"
},
"queryList":{
"$ref":"QueryList",
"description":"A list of queries."
},
"queryFileUri":{
"type":"string",
"description":"The HCFS URI of the script that contains SQL queries."
},
"scriptVariables":{
"additionalProperties":{
"type":"string"
},
"description":"Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name=\"value\";).",
"type":"object"
},
"jarFileUris":{
"type":"array",
"items":{
"type":"string"
},
"description":"Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH."
}
},
"id":"SparkSqlJob"
},
"Cluster":{
"description":"Describes the identifying information, config, and status of a cluster of Google Compute Engine instances.",
"type":"object",
"properties":{
"projectId":{
"description":"Required. The Google Cloud Platform project ID that the cluster belongs to.",
"type":"string"
},
"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."
},
"metrics":{
"$ref":"ClusterMetrics",
"description":"Contains cluster daemon metrics such as HDFS and YARN stats.Beta Feature: This report is available for testing purposes only. It may be changed before final release."
},
"status":{
"$ref":"ClusterStatus",
"description":"Output only. Cluster status."
},
"config":{
"$ref":"ClusterConfig",
"description":"Required. The cluster config. Note that Cloud Dataproc may set default values, and values may change when clusters are updated."
},
"statusHistory":{
"description":"Output only. The previous cluster status.",
"type":"array",
"items":{
"$ref":"ClusterStatus"
}
},
"clusterName":{
"description":"Required. The cluster name. Cluster names within a project must be unique. Names of deleted clusters can be reused.",
"type":"string"
},
"clusterUuid":{
"type":"string",
"description":"Output only. A cluster UUID (Unique Universal Identifier). Cloud Dataproc generates this value when it creates the cluster."
}
},
"id":"Cluster"
},
"ListOperationsResponse":{
"description":"The response message for Operations.ListOperations.",
"type":"object",
"properties":{
"nextPageToken":{
"type":"string",
"description":"The standard List next-page token."
},
"operations":{
"description":"A list of operations that matches the specified filter in the request.",
"type":"array",
"items":{
"$ref":"Operation"
}
}
},
"id":"ListOperationsResponse"
},
"SoftwareConfig":{
"type":"object",
"properties":{
"imageVersion":{
"type":"string",
"description":"Optional. The version of software inside the cluster. It must match the regular expression [0-9]+\\.[0-9]+. If unspecified, it defaults to the latest version (see Cloud Dataproc Versioning)."
},
"properties":{
"additionalProperties":{
"type":"string"
},
"description":"Optional. The properties to set on daemon config files.Property keys are specified in prefix:property format, such as core:fs.defaultFS. The following are supported prefixes and their mappings:\ncapacity-scheduler: capacity-scheduler.xml\ncore: core-site.xml\ndistcp: distcp-default.xml\nhdfs: hdfs-site.xml\nhive: hive-site.xml\nmapred: mapred-site.xml\npig: pig.properties\nspark: spark-defaults.conf\nyarn: yarn-site.xmlFor more information, see Cluster properties.",
"type":"object"
}
},
"id":"SoftwareConfig",
"description":"Specifies the selection and config of software inside the cluster."
},
"JobPlacement":{
"description":"Cloud Dataproc job config.",
"type":"object",
"properties":{
"clusterName":{
"type":"string",
"description":"Required. The name of the cluster where the job will be submitted."
},
"clusterUuid":{
"description":"Output only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.",
"type":"string"
}
},
"id":"JobPlacement"
},
"PigJob":{
"description":"A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN.",
"type":"object",
"properties":{
"continueOnFailure":{
"description":"Optional. Whether to continue executing queries if a query fails. The default value is false. Setting to true can be useful when executing independent parallel queries.",
"type":"boolean"
},
"queryList":{
"$ref":"QueryList",
"description":"A list of queries."
},
"queryFileUri":{
"type":"string",
"description":"The HCFS URI of the script that contains the Pig queries."
},
"jarFileUris":{
"description":"Optional. HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.",
"type":"array",
"items":{
"type":"string"
}
},
"scriptVariables":{
"type":"object",
"additionalProperties":{
"type":"string"
},
"description":"Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value])."
},
"loggingConfig":{
"$ref":"LoggingConfig",
"description":"Optional. The runtime log config for job execution."
},
"properties":{
"type":"object",
"additionalProperties":{
"type":"string"
},
"description":"Optional. A mapping of property names to values, used to configure Pig. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/pig/conf/pig.properties, and classes in user code."
}
},
"id":"PigJob"
},
"ClusterStatus":{
"type":"object",
"properties":{
"detail":{
"description":"Output only. Optional details of cluster's state.",
"type":"string"
},
"state":{
"enum":[
"UNKNOWN",
"CREATING",
"RUNNING",
"ERROR",
"DELETING",
"UPDATING"
],
"description":"Output only. The cluster's state.",
"type":"string",
"enumDescriptions":[
"The cluster state is unknown.",
"The cluster is being created and set up. It is not ready for use.",
"The cluster is currently running and healthy. It is ready for use.",
"The cluster encountered an error. It is not ready for use.",
"The cluster is being deleted. It cannot be used.",
"The cluster is being updated. It continues to accept and process jobs."
]
},
"stateStartTime":{
"description":"Output only. Time when this state was entered.",
"format":"google-datetime",
"type":"string"
},
"substate":{
"enum":[
"UNSPECIFIED",
"UNHEALTHY",
"STALE_STATUS"
],
"description":"Output only. Additional state information that includes status reported by the agent.",
"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 Cloud Dataproc loses communication with Agent).Applies to RUNNING state."
]
}
},
"id":"ClusterStatus",
"description":"The status of a cluster and its instances."
},
"ListClustersResponse":{
"description":"The list of all clusters in a project.",
"type":"object",
"properties":{
"clusters":{
"description":"Output only. The clusters in the project.",
"type":"array",
"items":{
"$ref":"Cluster"
}
},
"nextPageToken":{
"type":"string",
"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."
