// Copyright 2024 Google LLC // // Licensed under the Apache License, Version 2.0 (the "License"); // you may not use this file except in compliance with the License. // You may obtain a copy of the License at // // http://www.apache.org/licenses/LICENSE-2.0 // // Unless required by applicable law or agreed to in writing, software // distributed under the License is distributed on an "AS IS" BASIS, // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. // See the License for the specific language governing permissions and // limitations under the License. syntax = "proto3"; package google.cloud.dataproc.v1; import "google/api/annotations.proto"; import "google/api/client.proto"; import "google/api/field_behavior.proto"; import "google/api/resource.proto"; import "google/cloud/dataproc/v1/shared.proto"; import "google/longrunning/operations.proto"; import "google/protobuf/empty.proto"; import "google/protobuf/timestamp.proto"; option go_package = "cloud.google.com/go/dataproc/v2/apiv1/dataprocpb;dataprocpb"; option java_multiple_files = true; option java_outer_classname = "BatchesProto"; option java_package = "com.google.cloud.dataproc.v1"; // The BatchController provides methods to manage batch workloads. service BatchController { option (google.api.default_host) = "dataproc.googleapis.com"; option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform"; // Creates a batch workload that executes asynchronously. rpc CreateBatch(CreateBatchRequest) returns (google.longrunning.Operation) { option (google.api.http) = { post: "/v1/{parent=projects/*/locations/*}/batches" body: "batch" }; option (google.api.method_signature) = "parent,batch,batch_id"; option (google.longrunning.operation_info) = { response_type: "Batch" metadata_type: "google.cloud.dataproc.v1.BatchOperationMetadata" }; } // Gets the batch workload resource representation. rpc GetBatch(GetBatchRequest) returns (Batch) { option (google.api.http) = { get: "/v1/{name=projects/*/locations/*/batches/*}" }; option (google.api.method_signature) = "name"; } // Lists batch workloads. rpc ListBatches(ListBatchesRequest) returns (ListBatchesResponse) { option (google.api.http) = { get: "/v1/{parent=projects/*/locations/*}/batches" }; option (google.api.method_signature) = "parent"; } // Deletes the batch workload resource. If the batch is not in terminal state, // the delete fails and the response returns `FAILED_PRECONDITION`. rpc DeleteBatch(DeleteBatchRequest) returns (google.protobuf.Empty) { option (google.api.http) = { delete: "/v1/{name=projects/*/locations/*/batches/*}" }; option (google.api.method_signature) = "name"; } } // A request to create a batch workload. message CreateBatchRequest { // Required. The parent resource where this batch will be created. string parent = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { child_type: "dataproc.googleapis.com/Batch" } ]; // Required. The batch to create. Batch batch = 2 [(google.api.field_behavior) = REQUIRED]; // Optional. The ID to use for the batch, which will become the final // component of the batch's resource name. // // This value must be 4-63 characters. Valid characters are `/[a-z][0-9]-/`. string batch_id = 3 [(google.api.field_behavior) = OPTIONAL]; // Optional. A unique ID used to identify the request. If the service // receives two // [CreateBatchRequest](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.CreateBatchRequest)s // with the same request_id, the second request is ignored and the // Operation that corresponds to the first Batch created and stored // in the backend is returned. // // Recommendation: Set this value to a // [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier). // // The value must contain only letters (a-z, A-Z), numbers (0-9), // underscores (_), and hyphens (-). The maximum length is 40 characters. string request_id = 4 [(google.api.field_behavior) = OPTIONAL]; } // A request to get the resource representation for a batch workload. message GetBatchRequest { // Required. The fully qualified name of the batch to retrieve // in the format // "projects/PROJECT_ID/locations/DATAPROC_REGION/batches/BATCH_ID" string name = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { type: "dataproc.googleapis.com/Batch" } ]; } // A request to list batch workloads in a project. message ListBatchesRequest { // Required. The parent, which owns this collection of batches. string parent = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { child_type: "dataproc.googleapis.com/Batch" } ]; // Optional. The maximum number of batches to return in each response. // The service may return fewer than this value. // The default page size is 20; the maximum page size is 1000. int32 page_size = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. A page token received from a previous `ListBatches` call. // Provide this token to retrieve the subsequent page. string page_token = 3 [(google.api.field_behavior) = OPTIONAL]; // Optional. A filter for the batches to return in the response. // // A filter is a logical expression constraining the values of various fields // in each batch resource. Filters are case sensitive, and may contain // multiple clauses combined with logical operators (AND/OR). // Supported fields are `batch_id`, `batch_uuid`, `state`, and `create_time`. // // e.g. `state = RUNNING and create_time < "2023-01-01T00:00:00Z"` // filters for batches in state RUNNING that were created before 2023-01-01 // // See https://google.aip.dev/assets/misc/ebnf-filtering.txt for a detailed // description of the filter syntax and a list of supported comparisons. string filter = 4 [(google.api.field_behavior) = OPTIONAL]; // Optional. Field(s) on which to sort the list of batches. // // Currently the only supported sort orders are unspecified (empty) and // `create_time desc` to sort by most recently created batches first. // // See https://google.aip.dev/132#ordering for more details. string order_by = 5 [(google.api.field_behavior) = OPTIONAL]; } // A list of batch workloads. message ListBatchesResponse { // The batches from the specified collection. repeated Batch batches = 1; // A token, which can be sent as `page_token` to retrieve the next page. // If this field is omitted, there are no subsequent pages. string next_page_token = 2; // Output only. List of Batches that could not be included in the response. // Attempting to get one of these resources may indicate why it was not // included in the list response. repeated string unreachable = 3 [(google.api.field_behavior) = OUTPUT_ONLY]; } // A request to delete a batch workload. message DeleteBatchRequest { // Required. The fully qualified name of the batch to retrieve // in the format // "projects/PROJECT_ID/locations/DATAPROC_REGION/batches/BATCH_ID" string name = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { type: "dataproc.googleapis.com/Batch" } ]; } // A representation of a batch workload in the service. message Batch { option (google.api.resource) = { type: "dataproc.googleapis.com/Batch" pattern: "projects/{project}/locations/{location}/batches/{batch}" }; // The batch state. enum State { // The batch state is unknown. STATE_UNSPECIFIED = 0; // The batch is created before running. PENDING = 1; // The batch is running. RUNNING = 2; // The batch is cancelling. CANCELLING = 3; // The batch cancellation was successful. CANCELLED = 4; // The batch completed successfully. SUCCEEDED = 5; // The batch is no longer running due to an error. FAILED = 6; } // Historical state information. message StateHistory { // Output only. The state of the batch at this point in history. State state = 1 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. Details about the state at this point in history. string state_message = 2 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. The time when the batch entered the historical state. google.protobuf.Timestamp state_start_time = 3 [(google.api.field_behavior) = OUTPUT_ONLY]; } // Output only. The resource name of the batch. string name = 1 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. A batch UUID (Unique Universal Identifier). The service // generates this value when it creates the batch. string uuid = 2 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. The time when the batch was created. google.protobuf.Timestamp create_time = 3 [(google.api.field_behavior) = OUTPUT_ONLY]; // The application/framework-specific portion of the batch configuration. oneof batch_config { // Optional. PySpark batch config. PySparkBatch pyspark_batch = 4 [(google.api.field_behavior) = OPTIONAL]; // Optional. Spark batch config. SparkBatch spark_batch = 5 [(google.api.field_behavior) = OPTIONAL]; // Optional. SparkR batch config. SparkRBatch spark_r_batch = 6 [(google.api.field_behavior) = OPTIONAL]; // Optional. SparkSql batch config. SparkSqlBatch spark_sql_batch = 7 [(google.api.field_behavior) = OPTIONAL]; } // Output only. Runtime information about batch execution. RuntimeInfo runtime_info = 8 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. The state of the batch. State state = 9 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. Batch state details, such as a failure // description if the state is `FAILED`. string state_message = 10 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. The time when the batch entered a current state. google.protobuf.Timestamp state_time = 11 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. The email address of the user who created the batch. string creator = 12 [(google.api.field_behavior) = OUTPUT_ONLY]; // Optional. The labels to associate with this batch. // 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 batch. map labels = 13 [(google.api.field_behavior) = OPTIONAL]; // Optional. Runtime configuration for the batch execution. RuntimeConfig runtime_config = 14 [(google.api.field_behavior) = OPTIONAL]; // Optional. Environment configuration for the batch execution. EnvironmentConfig environment_config = 15 [(google.api.field_behavior) = OPTIONAL]; // Output only. The resource name of the operation associated with this batch. string operation = 16 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. Historical state information for the batch. repeated StateHistory state_history = 17 [(google.api.field_behavior) = OUTPUT_ONLY]; } // A configuration for running an // [Apache // PySpark](https://spark.apache.org/docs/latest/api/python/getting_started/quickstart.html) // batch workload. message PySparkBatch { // Required. The HCFS URI of the main Python file to use as the Spark driver. // Must be a .py file. string main_python_file_uri = 1 [(google.api.field_behavior) = REQUIRED]; // Optional. The arguments to pass to the driver. Do not include arguments // that can be set as batch properties, such as `--conf`, since a collision // can occur that causes an incorrect batch submission. repeated string args = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. HCFS file URIs of Python files to pass to the PySpark // framework. Supported file types: `.py`, `.egg`, and `.zip`. repeated string python_file_uris = 3 [(google.api.field_behavior) = OPTIONAL]; // Optional. HCFS URIs of jar files to add to the classpath of the // Spark driver and tasks. repeated string jar_file_uris = 4 [(google.api.field_behavior) = OPTIONAL]; // Optional. HCFS URIs of files to be placed in the working directory of // each executor. repeated string file_uris = 5 [(google.api.field_behavior) = OPTIONAL]; // 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`. repeated string archive_uris = 6 [(google.api.field_behavior) = OPTIONAL]; } // A configuration for running an [Apache Spark](https://spark.apache.org/) // batch workload. message SparkBatch { // The specification of the main method to call to drive the Spark // workload. Specify either the jar file that contains the main class or the // main class name. To pass both a main jar and a main class in that jar, add // the jar to `jar_file_uris`, and then specify the main class // name in `main_class`. oneof driver { // Optional. The HCFS URI of the jar file that contains the main class. string main_jar_file_uri = 1 [(google.api.field_behavior) = OPTIONAL]; // Optional. The name of the driver main class. The jar file that contains // the class must be in the classpath or specified in `jar_file_uris`. string main_class = 2 [(google.api.field_behavior) = OPTIONAL]; } // Optional. The arguments to pass to the driver. Do not include arguments // that can be set as batch properties, such as `--conf`, since a collision // can occur that causes an incorrect batch submission. repeated string args = 3 [(google.api.field_behavior) = OPTIONAL]; // Optional. HCFS URIs of jar files to add to the classpath of the // Spark driver and tasks. repeated string jar_file_uris = 4 [(google.api.field_behavior) = OPTIONAL]; // Optional. HCFS URIs of files to be placed in the working directory of // each executor. repeated string file_uris = 5 [(google.api.field_behavior) = OPTIONAL]; // 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`. repeated string archive_uris = 6 [(google.api.field_behavior) = OPTIONAL]; } // A configuration for running an // [Apache SparkR](https://spark.apache.org/docs/latest/sparkr.html) // batch workload. message SparkRBatch { // Required. The HCFS URI of the main R file to use as the driver. // Must be a `.R` or `.r` file. string main_r_file_uri = 1 [(google.api.field_behavior) = REQUIRED]; // Optional. The arguments to pass to the Spark driver. Do not include // arguments that can be set as batch properties, such as `--conf`, since a // collision can occur that causes an incorrect batch submission. repeated string args = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. HCFS URIs of files to be placed in the working directory of // each executor. repeated string file_uris = 3 [(google.api.field_behavior) = OPTIONAL]; // 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`. repeated string archive_uris = 4 [(google.api.field_behavior) = OPTIONAL]; } // A configuration for running // [Apache Spark SQL](https://spark.apache.org/sql/) queries as a batch // workload. message SparkSqlBatch { // Required. The HCFS URI of the script that contains Spark SQL queries to // execute. string query_file_uri = 1 [(google.api.field_behavior) = REQUIRED]; // Optional. Mapping of query variable names to values (equivalent to the // Spark SQL command: `SET name="value";`). map query_variables = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH. repeated string jar_file_uris = 3 [(google.api.field_behavior) = OPTIONAL]; }