feat(v1beta1): remove DOCKER/FLINK from Component enum; adds HBASE (#108)

Breaking change in v1beta1: 1. The `DOCKER` and `FLINK` values have been removed from the `Component` enum, and an `HBASE` value was added. Other changes: 1. There is a new `temp_bucket` field in `ClusterConfig`. 2. There is a new `preemptibility` field in `InstanceGroupConfig`. 3. The `project_id` field of `JobReference` is now optional instead of required. 4. There is a new `dag_timeout` field in `WorkflowTemplate`. 5. There are new `dag_timeout`, `dag_start_time`, and `dag_end_time` fields in `WorkflowMetadata`. 6. There are various updates to the doc comments.

Author: yoshi-automation

google/cloud/dataproc_v1/__init__.py

@@ -115,7 +115,6 @@
  "CancelJobRequest",
  "Cluster",
  "ClusterConfig",
- "ClusterControllerClient",
  "ClusterMetrics",
  "ClusterOperation",
  "ClusterOperationMetadata",
@@ -192,6 +191,7 @@
  "WorkflowNode",
  "WorkflowTemplate",
  "WorkflowTemplatePlacement",
- "YarnApplication",
  "WorkflowTemplateServiceClient",
+ "YarnApplication",
+ "ClusterControllerClient",
 )

google/cloud/dataproc_v1beta2/__init__.py

@@ -149,7 +149,6 @@
  "InstantiateInlineWorkflowTemplateRequest",
  "InstantiateWorkflowTemplateRequest",
  "Job",
- "JobControllerClient",
  "JobMetadata",
  "JobPlacement",
  "JobReference",
@@ -194,6 +193,7 @@
  "WorkflowNode",
  "WorkflowTemplate",
  "WorkflowTemplatePlacement",
- "YarnApplication",
  "WorkflowTemplateServiceClient",
+ "YarnApplication",
+ "JobControllerClient",
 )

google/cloud/dataproc_v1beta2/proto/autoscaling_policies.proto

@@ -36,10 +36,12 @@ option (google.api.resource_definition) = {
 // Cloud Dataproc API.
 service AutoscalingPolicyService {
  option (google.api.default_host) = "dataproc.googleapis.com";
- option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform";
+ option (google.api.oauth_scopes) =
+ "https://www.googleapis.com/auth/cloud-platform";
 
  // Creates new autoscaling policy.
- rpc CreateAutoscalingPolicy(CreateAutoscalingPolicyRequest) returns (AutoscalingPolicy) {
+ rpc CreateAutoscalingPolicy(CreateAutoscalingPolicyRequest)
+ returns (AutoscalingPolicy) {
  option (google.api.http) = {
  post: "/v1beta2/{parent=projects/*/locations/*}/autoscalingPolicies"
  body: "policy"
@@ -55,7 +57,8 @@ service AutoscalingPolicyService {
  //
  // Disabled check for update_mask, because all updates will be full
  // replacements.
- rpc UpdateAutoscalingPolicy(UpdateAutoscalingPolicyRequest) returns (AutoscalingPolicy) {
+ rpc UpdateAutoscalingPolicy(UpdateAutoscalingPolicyRequest)
+ returns (AutoscalingPolicy) {
  option (google.api.http) = {
  put: "/v1beta2/{policy.name=projects/*/locations/*/autoscalingPolicies/*}"
  body: "policy"
@@ -68,7 +71,8 @@ service AutoscalingPolicyService {
  }
 
  // Retrieves autoscaling policy.
- rpc GetAutoscalingPolicy(GetAutoscalingPolicyRequest) returns (AutoscalingPolicy) {
+ rpc GetAutoscalingPolicy(GetAutoscalingPolicyRequest)
+ returns (AutoscalingPolicy) {
  option (google.api.http) = {
  get: "/v1beta2/{name=projects/*/locations/*/autoscalingPolicies/*}"
  additional_bindings {
@@ -79,7 +83,8 @@ service AutoscalingPolicyService {
  }
 
  // Lists autoscaling policies in the project.
- rpc ListAutoscalingPolicies(ListAutoscalingPoliciesRequest) returns (ListAutoscalingPoliciesResponse) {
+ rpc ListAutoscalingPolicies(ListAutoscalingPoliciesRequest)
+ returns (ListAutoscalingPoliciesResponse) {
  option (google.api.http) = {
  get: "/v1beta2/{parent=projects/*/locations/*}/autoscalingPolicies"
  additional_bindings {
@@ -91,7 +96,8 @@ service AutoscalingPolicyService {
 
  // Deletes an autoscaling policy. It is an error to delete an autoscaling
  // policy that is in use by one or more clusters.
- rpc DeleteAutoscalingPolicy(DeleteAutoscalingPolicyRequest) returns (google.protobuf.Empty) {
+ rpc DeleteAutoscalingPolicy(DeleteAutoscalingPolicyRequest)
+ returns (google.protobuf.Empty) {
  option (google.api.http) = {
  delete: "/v1beta2/{name=projects/*/locations/*/autoscalingPolicies/*}"
  additional_bindings {
@@ -136,22 +142,26 @@ message AutoscalingPolicy {
  }
 
  // Required. Describes how the autoscaler will operate for primary workers.
- InstanceGroupAutoscalingPolicyConfig worker_config = 4 [(google.api.field_behavior) = REQUIRED];
+ InstanceGroupAutoscalingPolicyConfig worker_config = 4
+ [(google.api.field_behavior) = REQUIRED];
 
  // Optional. Describes how the autoscaler will operate for secondary workers.
- InstanceGroupAutoscalingPolicyConfig secondary_worker_config = 5 [(google.api.field_behavior) = OPTIONAL];
+ InstanceGroupAutoscalingPolicyConfig secondary_worker_config = 5
+ [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Basic algorithm for autoscaling.
 message BasicAutoscalingAlgorithm {
  // Required. YARN autoscaling configuration.
- BasicYarnAutoscalingConfig yarn_config = 1 [(google.api.field_behavior) = REQUIRED];
+ BasicYarnAutoscalingConfig yarn_config = 1
+ [(google.api.field_behavior) = REQUIRED];
 
  // Optional. Duration between scaling events. A scaling period starts after
  // the update operation from the previous event has completed.
  //
  // Bounds: [2m, 1d]. Default: 2m.
- google.protobuf.Duration cooldown_period = 2 [(google.api.field_behavior) = OPTIONAL];
+ google.protobuf.Duration cooldown_period = 2
+ [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Basic autoscaling configurations for YARN.
@@ -162,22 +172,29 @@ message BasicYarnAutoscalingConfig {
  // downscaling operations.
  //
  // Bounds: [0s, 1d].
- google.protobuf.Duration graceful_decommission_timeout = 5 [(google.api.field_behavior) = REQUIRED];
-
- // Required. Fraction of average pending memory in the last cooldown period
- // for which to add workers. A scale-up factor of 1.0 will result in scaling
- // up so that there is no pending memory remaining after the update (more
- // aggressive scaling). A scale-up factor closer to 0 will result in a smaller
- // magnitude of scaling up (less aggressive scaling).
+ google.protobuf.Duration graceful_decommission_timeout = 5
+ [(google.api.field_behavior) = REQUIRED];
+
+ // Required. Fraction of average YARN pending memory in the last cooldown
+ // period for which to add workers. A scale-up factor of 1.0 will result in
+ // scaling up so that there is no pending memory remaining after the update
+ // (more aggressive scaling). A scale-up factor closer to 0 will result in a
+ // smaller magnitude of scaling up (less aggressive scaling). See [How
+ // autoscaling
+ // works](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/autoscaling#how_autoscaling_works)
+ // for more information.
  //
  // Bounds: [0.0, 1.0].
  double scale_up_factor = 1 [(google.api.field_behavior) = REQUIRED];
 
- // Required. Fraction of average pending memory in the last cooldown period
- // for which to remove workers. A scale-down factor of 1 will result in
+ // Required. Fraction of average YARN pending memory in the last cooldown
+ // period for which to remove workers. A scale-down factor of 1 will result in
  // scaling down so that there is no available memory remaining after the
  // update (more aggressive scaling). A scale-down factor of 0 disables
  // removing workers, which can be beneficial for autoscaling a single job.
+ // See [How autoscaling
+ // works](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/autoscaling#how_autoscaling_works)
+ // for more information.
  //
  // Bounds: [0.0, 1.0].
  double scale_down_factor = 2 [(google.api.field_behavior) = REQUIRED];
@@ -189,7 +206,8 @@ message BasicYarnAutoscalingConfig {
  // on any recommended change.
  //
  // Bounds: [0.0, 1.0]. Default: 0.0.
- double scale_up_min_worker_fraction = 3 [(google.api.field_behavior) = OPTIONAL];
+ double scale_up_min_worker_fraction = 3
+ [(google.api.field_behavior) = OPTIONAL];
 
  // Optional. Minimum scale-down threshold as a fraction of total cluster size
  // before scaling occurs. For example, in a 20-worker cluster, a threshold of
@@ -198,7 +216,8 @@ message BasicYarnAutoscalingConfig {
  // on any recommended change.
  //
  // Bounds: [0.0, 1.0]. Default: 0.0.
- double scale_down_min_worker_fraction = 4 [(google.api.field_behavior) = OPTIONAL];
+ double scale_down_min_worker_fraction = 4
+ [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Configuration for the size bounds of an instance group, including its
@@ -341,7 +360,8 @@ message ListAutoscalingPoliciesRequest {
 // A response to a request to list autoscaling policies in a project.
 message ListAutoscalingPoliciesResponse {
  // Output only. Autoscaling policies list.
- repeated AutoscalingPolicy policies = 1 [(google.api.field_behavior) = OUTPUT_ONLY];
+ repeated AutoscalingPolicy policies = 1
+ [(google.api.field_behavior) = OUTPUT_ONLY];
 
  // Output only. This token is included in the response if there are more
  // results to fetch.

google/cloud/dataproc_v1beta2/proto/clusters.proto

@@ -171,6 +171,17 @@ message ClusterConfig {
  // bucket](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
  string config_bucket = 1 [(google.api.field_behavior) = OPTIONAL];
 
+ // 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.
+ string temp_bucket = 2 [(google.api.field_behavior) = OPTIONAL];
+
  // Optional. The shared Compute Engine config settings for
  // all instances in a cluster.
  GceClusterConfig gce_cluster_config = 8 [(google.api.field_behavior) = OPTIONAL];
@@ -330,7 +341,7 @@ message GceClusterConfig {
  bool internal_ip_only = 7 [(google.api.field_behavior) = OPTIONAL];
 
  // Optional. The [Dataproc service
- // account](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/service-accounts#service_accounts_in_cloud_dataproc)
+ // account](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/service-accounts#service_accounts_in_dataproc)
  // (also see [VM Data Plane
  // identity](https://cloud.google.com/dataproc/docs/concepts/iam/dataproc-principals#vm_service_account_data_plane_identity))
  // used by Dataproc cluster VM instances to access Google Cloud Platform
@@ -374,6 +385,27 @@ message GceClusterConfig {
 // The config settings for Compute Engine resources in
 // an instance group, such as a master or worker group.
 message InstanceGroupConfig {
+ // Controls the use of
+ // [preemptible instances]
+ // (https://cloud.google.com/compute/docs/instances/preemptible)
+ // within the group.
+ enum Preemptibility {
+ // Preemptibility is unspecified, the system will choose the
+ // appropriate setting for each instance group.
+ PREEMPTIBILITY_UNSPECIFIED = 0;
+
+ // Instances are non-preemptible.
+ //
+ // This option is allowed for all instance groups and is the only valid
+ // value for Master and Worker instance groups.
+ NON_PREEMPTIBLE = 1;
+
+ // Instances are preemptible.
+ //
+ // This option is allowed only for secondary worker groups.
+ PREEMPTIBLE = 2;
+ }
+
  // Optional. The number of VM instances in the instance group.
  // For master instance groups, must be set to 1.
  int32 num_instances = 1 [(google.api.field_behavior) = OPTIONAL];
@@ -424,6 +456,15 @@ message InstanceGroupConfig {
  // instances.
  bool is_preemptible = 6 [(google.api.field_behavior) = OUTPUT_ONLY];
 
+ // 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`.
+ Preemptibility preemptibility = 10 [(google.api.field_behavior) = OPTIONAL];
+
  // Output only. The config for Compute Engine Instance Group
  // Manager that manages this group.
  // This is only used for preemptible instance groups.
@@ -685,7 +726,7 @@ message ClusterStatus {
 message SoftwareConfig {
  // Optional. The version of software inside the cluster. It must be one of the
  // supported [Dataproc
- // Versions](https://cloud.google.com/dataproc/docs/concepts/versioning/dataproc-versions#supported_cloud_dataproc_versions),
+ // Versions](https://cloud.google.com/dataproc/docs/concepts/versioning/dataproc-versions#supported_dataproc_versions),
  // such as "1.2" (including a subminor version, such as "1.2.29"), or the
  // ["preview"
  // version](https://cloud.google.com/dataproc/docs/concepts/versioning/dataproc-versions#other_versions).

google/cloud/dataproc_v1beta2/proto/jobs.proto

@@ -224,12 +224,12 @@ message SparkJob {
  // Spark driver and tasks.
  repeated string jar_file_uris = 4 [(google.api.field_behavior) = OPTIONAL];
 
- // Optional. HCFS URIs of files to be copied to the working directory of
- // Spark drivers and distributed tasks. Useful for naively parallel tasks.
+ // Optional. HCFS URIs of files to be placed in the working directory of
+ // each executor. Useful for naively parallel tasks.
  repeated string file_uris = 5 [(google.api.field_behavior) = OPTIONAL];
 
- // Optional. HCFS URIs of archives to be extracted in the working directory
- // of Spark drivers and tasks. Supported file types:
+ // 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];
 
@@ -265,11 +265,12 @@ message PySparkJob {
  // Python driver and tasks.
  repeated string jar_file_uris = 4 [(google.api.field_behavior) = OPTIONAL];
 
- // Optional. HCFS URIs of files to be copied to the working directory of
- // Python drivers and distributed tasks. Useful for naively parallel tasks.
+ // Optional. HCFS URIs of files to be placed in the working directory of
+ // each executor. Useful for naively parallel tasks.
  repeated string file_uris = 5 [(google.api.field_behavior) = OPTIONAL];
 
- // Optional. HCFS URIs of archives to be extracted in the working directory of
+ // 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];
 
@@ -414,12 +415,12 @@ message SparkRJob {
  // occur that causes an incorrect job submission.
  repeated string args = 2 [(google.api.field_behavior) = OPTIONAL];
 
- // Optional. HCFS URIs of files to be copied to the working directory of
- // R drivers and distributed tasks. Useful for naively parallel tasks.
+ // Optional. HCFS URIs of files to be placed in the working directory of
+ // each executor. Useful for naively parallel tasks.
  repeated string file_uris = 3 [(google.api.field_behavior) = OPTIONAL];
 
- // Optional. HCFS URIs of archives to be extracted in the working directory of
- // Spark drivers and tasks. Supported file types:
+ // 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];
 
@@ -562,9 +563,9 @@ message JobStatus {
 
 // Encapsulates the full scoping used to reference a job.
 message JobReference {
- // Required. The ID of the Google Cloud Platform project that the job
- // belongs to.
- string project_id = 1 [(google.api.field_behavior) = REQUIRED];
+ // Optional. The ID of the Google Cloud Platform project that the job belongs to. If
+ // specified, must match the request project ID.
+ string project_id = 1 [(google.api.field_behavior) = OPTIONAL];
 
  // Optional. The job ID, which must be unique within the project.
  // The ID must contain only letters (a-z, A-Z), numbers (0-9),

google/cloud/dataproc_v1beta2/proto/shared.proto

@@ -25,20 +25,17 @@ option java_package = "com.google.cloud.dataproc.v1beta2";
 
 // Cluster components that can be activated.
 enum Component {
- // Unspecified component.
+ // Unspecified component. Specifying this will cause Cluster creation to fail.
  COMPONENT_UNSPECIFIED = 0;
 
  // The Anaconda python distribution.
  ANACONDA = 5;
 
- // Docker
- DOCKER = 13;
-
  // The Druid query engine.
  DRUID = 9;
 
- // Flink
- FLINK = 14;
+ // HBase.
+ HBASE = 11;
 
  // The Hive Web HCatalog (the REST service for accessing HCatalog).
  HIVE_WEBHCAT = 3;