chore: Update discovery artifacts (#1195)
* chore(accesscontextmanager): update the api
* chore(adexchangebuyer2): update the api
* chore(admin): update the api
* chore(alertcenter): update the api
* chore(analyticsadmin): update the api
* chore(analyticsdata): update the api
* chore(androidmanagement): update the api
* chore(apigateway): update the api
* chore(apigee): update the api
* chore(appengine): update the api
* chore(area120tables): update the api
* chore(artifactregistry): update the api
* chore(bigquery): update the api
* chore(bigqueryconnection): update the api
* chore(bigqueryreservation): update the api
* chore(billingbudgets): update the api
* chore(binaryauthorization): update the api
* chore(blogger): update the api
* chore(calendar): update the api
* chore(chat): update the api
* chore(cloudasset): update the api
* chore(cloudbuild): update the api
* chore(cloudfunctions): update the api
* chore(cloudidentity): update the api
* chore(cloudkms): update the api
* chore(cloudresourcemanager): update the api
* chore(cloudscheduler): update the api
* chore(cloudtasks): update the api
* chore(composer): update the api
* chore(compute): update the api
* chore(container): update the api
* chore(containeranalysis): update the api
* chore(content): update the api
* chore(datacatalog): update the api
* chore(dataflow): update the api
* chore(datafusion): update the api
* chore(datamigration): update the api
* chore(dataproc): update the api
* chore(deploymentmanager): update the api
* chore(dialogflow): update the api
* chore(displayvideo): update the api
* chore(dlp): update the api
* chore(dns): update the api
* chore(documentai): update the api
* chore(eventarc): update the api
* chore(file): update the api
* chore(firebaseml): update the api
* chore(games): update the api
* chore(gameservices): update the api
* chore(genomics): update the api
* chore(healthcare): update the api
* chore(homegraph): update the api
* chore(iam): update the api
* chore(iap): update the api
* chore(jobs): update the api
* chore(lifesciences): update the api
* chore(localservices): update the api
* chore(managedidentities): update the api
* chore(manufacturers): update the api
* chore(memcache): update the api
* chore(ml): update the api
* chore(monitoring): update the api
* chore(notebooks): update the api
* chore(osconfig): update the api
* chore(pagespeedonline): update the api
* chore(people): update the api
* chore(privateca): update the api
* chore(prod_tt_sasportal): update the api
* chore(pubsub): update the api
* chore(pubsublite): update the api
* chore(recommender): update the api
* chore(remotebuildexecution): update the api
* chore(reseller): update the api
* chore(run): update the api
* chore(safebrowsing): update the api
* chore(sasportal): update the api
* chore(searchconsole): update the api
* chore(secretmanager): update the api
* chore(securitycenter): update the api
* chore(serviceconsumermanagement): update the api
* chore(servicecontrol): update the api
* chore(servicenetworking): update the api
* chore(serviceusage): update the api
* chore(sheets): update the api
* chore(slides): update the api
* chore(spanner): update the api
* chore(speech): update the api
* chore(sqladmin): update the api
* chore(storage): update the api
* chore(storagetransfer): update the api
* chore(sts): update the api
* chore(tagmanager): update the api
* chore(testing): update the api
* chore(toolresults): update the api
* chore(transcoder): update the api
* chore(vectortile): update the api
* chore(videointelligence): update the api
* chore(vision): update the api
* chore(webmasters): update the api
* chore(workflowexecutions): update the api
* chore(youtube): update the api
diff --git a/docs/dyn/dataproc_v1.projects.regions.workflowTemplates.html b/docs/dyn/dataproc_v1.projects.regions.workflowTemplates.html
index 94d3cd6..51fb0b6 100644
--- a/docs/dyn/dataproc_v1.projects.regions.workflowTemplates.html
+++ b/docs/dyn/dataproc_v1.projects.regions.workflowTemplates.html
@@ -127,6 +127,7 @@
{ # A Dataproc workflow template resource.
"createTime": "A String", # Output only. The time template was created.
+ "dagTimeout": "A String", # Optional. Timeout duration for the DAG of jobs, expressed in seconds (see JSON representation of duration (https://developers.google.com/protocol-buffers/docs/proto3#json)). The timeout duration must be from 10 minutes ("600s") to 24 hours ("86400s"). The timer begins when the first job is submitted. If the workflow is running at the end of the timeout period, any remaining jobs are cancelled, the workflow is ended, and if the workflow was running on a managed cluster, the cluster is deleted.
"id": "A String",
"jobs": [ # Required. The Directed Acyclic Graph of Jobs to submit.
{ # A job executed by the workflow.
@@ -250,7 +251,7 @@
},
"scheduling": { # Job scheduling options. # Optional. Job scheduling configuration.
"maxFailuresPerHour": 42, # Optional. Maximum number of times per hour a driver may be restarted as a result of driver exiting 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.
- "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240
+ "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240.
},
"sparkJob": { # A Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Optional. Job is a Spark job.
"archiveUris": [ # 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.
@@ -359,7 +360,7 @@
"autoscalingConfig": { # Autoscaling Policy config associated with the cluster. # Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset.
"policyUri": "A String", # Optional. The autoscaling policy used by the cluster.Only resource names including projectid and location (region) are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id] projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]Note that the policy must be in the same project and Dataproc region.
},
- "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
+ "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"encryptionConfig": { # Encryption settings for the cluster. # Optional. Encryption settings for the cluster.
"gcePdKmsKeyName": "A String", # Optional. The Cloud KMS key name to use for PD disk encryption for all instances in the cluster.
},
@@ -390,6 +391,11 @@
"serviceAccountScopes": [ # 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.writeIf 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
"A String",
],
+ "shieldedInstanceConfig": { # Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm). # Optional. Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm).
+ "enableIntegrityMonitoring": True or False, # Optional. Defines whether instances have integrity monitoring enabled.
+ "enableSecureBoot": True or False, # Optional. Defines whether instances have Secure Boot enabled.
+ "enableVtpm": True or False, # Optional. Defines whether instances have the vTPM enabled.
+ },
"subnetworkUri": "A String", # 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/us-east1/subnetworks/sub0 projects/[project_id]/regions/us-east1/subnetworks/sub0 sub0
"tags": [ # The Compute Engine tags to add to all instances (see Tagging instances (https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).
"A String",
@@ -405,7 +411,7 @@
"lifecycleConfig": { # Specifies the cluster auto-delete schedule configuration. # Optional. Lifecycle setting for the cluster.
"autoDeleteTime": "A String", # Optional. The time when cluster will be auto-deleted (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).
"autoDeleteTtl": "A String", # 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)).
- "idleDeleteTtl": "A String", # 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).
+ "idleDeleteTtl": "A String", # 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)).
"idleStartTime": "A String", # 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)).
},
"masterConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for the master instance in a cluster.
@@ -417,7 +423,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -428,6 +434,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -440,6 +447,9 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
+ "metastoreConfig": { # Specifies a Metastore configuration. # Optional. Metastore configuration.
+ "dataprocMetastoreService": "A String", # Required. Resource name of an existing Dataproc Metastore service.Example: projects/[project_id]/locations/[dataproc_region]/services/[service-name]
+ },
"secondaryWorkerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for additional worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -449,7 +459,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -460,6 +470,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -472,8 +483,8 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
- "securityConfig": { # Security related configuration, including Kerberos. # Optional. Security settings for the cluster.
- "kerberosConfig": { # Specifies Kerberos related configuration. # Kerberos related configuration.
+ "securityConfig": { # Security related configuration, including encryption, Kerberos, etc. # Optional. Security settings for the cluster.
+ "kerberosConfig": { # Specifies Kerberos related configuration. # Optional. Kerberos related configuration.
"crossRealmTrustAdminServer": "A String", # Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustKdc": "A String", # Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustRealm": "A String", # Optional. The remote realm the Dataproc on-cluster KDC will trust, should the user enable cross realm trust.
@@ -500,7 +511,7 @@
"a_key": "A String",
},
},
- "tempBucket": "A String", # 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.
+ "tempBucket": "A String", # 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. This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"workerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -510,7 +521,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -521,6 +532,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -553,6 +565,7 @@
{ # A Dataproc workflow template resource.
"createTime": "A String", # Output only. The time template was created.
+ "dagTimeout": "A String", # Optional. Timeout duration for the DAG of jobs, expressed in seconds (see JSON representation of duration (https://developers.google.com/protocol-buffers/docs/proto3#json)). The timeout duration must be from 10 minutes ("600s") to 24 hours ("86400s"). The timer begins when the first job is submitted. If the workflow is running at the end of the timeout period, any remaining jobs are cancelled, the workflow is ended, and if the workflow was running on a managed cluster, the cluster is deleted.
"id": "A String",
"jobs": [ # Required. The Directed Acyclic Graph of Jobs to submit.
{ # A job executed by the workflow.
@@ -676,7 +689,7 @@
},
"scheduling": { # Job scheduling options. # Optional. Job scheduling configuration.
"maxFailuresPerHour": 42, # Optional. Maximum number of times per hour a driver may be restarted as a result of driver exiting 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.
- "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240
+ "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240.
},
"sparkJob": { # A Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Optional. Job is a Spark job.
"archiveUris": [ # 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.
@@ -785,7 +798,7 @@
"autoscalingConfig": { # Autoscaling Policy config associated with the cluster. # Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset.
"policyUri": "A String", # Optional. The autoscaling policy used by the cluster.Only resource names including projectid and location (region) are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id] projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]Note that the policy must be in the same project and Dataproc region.
},
- "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
+ "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"encryptionConfig": { # Encryption settings for the cluster. # Optional. Encryption settings for the cluster.
"gcePdKmsKeyName": "A String", # Optional. The Cloud KMS key name to use for PD disk encryption for all instances in the cluster.
},
@@ -816,6 +829,11 @@
"serviceAccountScopes": [ # 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.writeIf 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
"A String",
],
+ "shieldedInstanceConfig": { # Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm). # Optional. Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm).
+ "enableIntegrityMonitoring": True or False, # Optional. Defines whether instances have integrity monitoring enabled.
+ "enableSecureBoot": True or False, # Optional. Defines whether instances have Secure Boot enabled.
+ "enableVtpm": True or False, # Optional. Defines whether instances have the vTPM enabled.
+ },
"subnetworkUri": "A String", # 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/us-east1/subnetworks/sub0 projects/[project_id]/regions/us-east1/subnetworks/sub0 sub0
"tags": [ # The Compute Engine tags to add to all instances (see Tagging instances (https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).
"A String",
@@ -831,7 +849,7 @@
"lifecycleConfig": { # Specifies the cluster auto-delete schedule configuration. # Optional. Lifecycle setting for the cluster.
"autoDeleteTime": "A String", # Optional. The time when cluster will be auto-deleted (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).
"autoDeleteTtl": "A String", # 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)).
- "idleDeleteTtl": "A String", # 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).
+ "idleDeleteTtl": "A String", # 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)).
"idleStartTime": "A String", # 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)).
},
"masterConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for the master instance in a cluster.
@@ -843,7 +861,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -854,6 +872,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -866,6 +885,9 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
+ "metastoreConfig": { # Specifies a Metastore configuration. # Optional. Metastore configuration.
+ "dataprocMetastoreService": "A String", # Required. Resource name of an existing Dataproc Metastore service.Example: projects/[project_id]/locations/[dataproc_region]/services/[service-name]
+ },
"secondaryWorkerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for additional worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -875,7 +897,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -886,6 +908,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -898,8 +921,8 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
- "securityConfig": { # Security related configuration, including Kerberos. # Optional. Security settings for the cluster.
- "kerberosConfig": { # Specifies Kerberos related configuration. # Kerberos related configuration.
+ "securityConfig": { # Security related configuration, including encryption, Kerberos, etc. # Optional. Security settings for the cluster.
+ "kerberosConfig": { # Specifies Kerberos related configuration. # Optional. Kerberos related configuration.
"crossRealmTrustAdminServer": "A String", # Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustKdc": "A String", # Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustRealm": "A String", # Optional. The remote realm the Dataproc on-cluster KDC will trust, should the user enable cross realm trust.
@@ -926,7 +949,7 @@
"a_key": "A String",
},
},
- "tempBucket": "A String", # 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.
+ "tempBucket": "A String", # 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. This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"workerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -936,7 +959,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -947,6 +970,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -1006,6 +1030,7 @@
{ # A Dataproc workflow template resource.
"createTime": "A String", # Output only. The time template was created.
+ "dagTimeout": "A String", # Optional. Timeout duration for the DAG of jobs, expressed in seconds (see JSON representation of duration (https://developers.google.com/protocol-buffers/docs/proto3#json)). The timeout duration must be from 10 minutes ("600s") to 24 hours ("86400s"). The timer begins when the first job is submitted. If the workflow is running at the end of the timeout period, any remaining jobs are cancelled, the workflow is ended, and if the workflow was running on a managed cluster, the cluster is deleted.
"id": "A String",
"jobs": [ # Required. The Directed Acyclic Graph of Jobs to submit.
{ # A job executed by the workflow.
@@ -1129,7 +1154,7 @@
},
"scheduling": { # Job scheduling options. # Optional. Job scheduling configuration.
"maxFailuresPerHour": 42, # Optional. Maximum number of times per hour a driver may be restarted as a result of driver exiting 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.
- "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240
+ "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240.
},
"sparkJob": { # A Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Optional. Job is a Spark job.
"archiveUris": [ # 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.
@@ -1238,7 +1263,7 @@
"autoscalingConfig": { # Autoscaling Policy config associated with the cluster. # Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset.
"policyUri": "A String", # Optional. The autoscaling policy used by the cluster.Only resource names including projectid and location (region) are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id] projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]Note that the policy must be in the same project and Dataproc region.
},
- "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
+ "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"encryptionConfig": { # Encryption settings for the cluster. # Optional. Encryption settings for the cluster.
"gcePdKmsKeyName": "A String", # Optional. The Cloud KMS key name to use for PD disk encryption for all instances in the cluster.
},
@@ -1269,6 +1294,11 @@
"serviceAccountScopes": [ # 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.writeIf 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
"A String",
],
+ "shieldedInstanceConfig": { # Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm). # Optional. Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm).
+ "enableIntegrityMonitoring": True or False, # Optional. Defines whether instances have integrity monitoring enabled.
+ "enableSecureBoot": True or False, # Optional. Defines whether instances have Secure Boot enabled.
+ "enableVtpm": True or False, # Optional. Defines whether instances have the vTPM enabled.
+ },
"subnetworkUri": "A String", # 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/us-east1/subnetworks/sub0 projects/[project_id]/regions/us-east1/subnetworks/sub0 sub0
"tags": [ # The Compute Engine tags to add to all instances (see Tagging instances (https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).
"A String",
@@ -1284,7 +1314,7 @@
"lifecycleConfig": { # Specifies the cluster auto-delete schedule configuration. # Optional. Lifecycle setting for the cluster.
"autoDeleteTime": "A String", # Optional. The time when cluster will be auto-deleted (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).
"autoDeleteTtl": "A String", # 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)).
- "idleDeleteTtl": "A String", # 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).
+ "idleDeleteTtl": "A String", # 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)).
"idleStartTime": "A String", # 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)).
},
"masterConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for the master instance in a cluster.
@@ -1296,7 +1326,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -1307,6 +1337,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -1319,6 +1350,9 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
+ "metastoreConfig": { # Specifies a Metastore configuration. # Optional. Metastore configuration.
+ "dataprocMetastoreService": "A String", # Required. Resource name of an existing Dataproc Metastore service.Example: projects/[project_id]/locations/[dataproc_region]/services/[service-name]
+ },
"secondaryWorkerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for additional worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -1328,7 +1362,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -1339,6 +1373,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -1351,8 +1386,8 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
- "securityConfig": { # Security related configuration, including Kerberos. # Optional. Security settings for the cluster.
- "kerberosConfig": { # Specifies Kerberos related configuration. # Kerberos related configuration.
+ "securityConfig": { # Security related configuration, including encryption, Kerberos, etc. # Optional. Security settings for the cluster.
+ "kerberosConfig": { # Specifies Kerberos related configuration. # Optional. Kerberos related configuration.
"crossRealmTrustAdminServer": "A String", # Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustKdc": "A String", # Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustRealm": "A String", # Optional. The remote realm the Dataproc on-cluster KDC will trust, should the user enable cross realm trust.
@@ -1379,7 +1414,7 @@
"a_key": "A String",
},
},
- "tempBucket": "A String", # 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.
+ "tempBucket": "A String", # 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. This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"workerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -1389,7 +1424,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -1400,6 +1435,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -1449,7 +1485,6 @@
{ # An Identity and Access Management (IAM) policy, which specifies access controls for Google Cloud resources.A Policy is a collection of bindings. A binding binds one or more members to a single role. Members can be user accounts, service accounts, Google 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 Google Cloud 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://cloud.google.com/iam/help/conditions/resource-policies).JSON example: { "bindings": [ { "role": "roles/resourcemanager.organizationAdmin", "members": [ "user:mike@example.com", "group:admins@example.com", "domain:google.com", "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 < timestamp('2020-10-01T00:00:00.000Z')", } } ], "etag": "BwWWja0YfJA=", "version": 3 } YAML example: bindings: - members: - user:mike@example.com - group:admins@example.com - domain:google.com - 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 < timestamp('2020-10-01T00:00:00.000Z') - etag: BwWWja0YfJA= - version: 3 For a description of IAM and its features, see the IAM documentation (https://cloud.google.com/iam/docs/).
"bindings": [ # Associates a list of members to 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 member.
{ # Associates members with a role.
- "bindingId": "A String",
"condition": { # 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() < 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. # 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 members in this binding.To learn which resources support conditions in their IAM policies, see the IAM documentation (https://cloud.google.com/iam/help/conditions/resource-policies).
"description": "A String", # Optional. Description of the expression. This is a longer text which describes the expression, e.g. when hovered over it in a UI.
"expression": "A String", # Textual representation of an expression in Common Expression Language syntax.
@@ -1524,6 +1559,7 @@
{ # A Dataproc workflow template resource.
"createTime": "A String", # Output only. The time template was created.
+ "dagTimeout": "A String", # Optional. Timeout duration for the DAG of jobs, expressed in seconds (see JSON representation of duration (https://developers.google.com/protocol-buffers/docs/proto3#json)). The timeout duration must be from 10 minutes ("600s") to 24 hours ("86400s"). The timer begins when the first job is submitted. If the workflow is running at the end of the timeout period, any remaining jobs are cancelled, the workflow is ended, and if the workflow was running on a managed cluster, the cluster is deleted.
"id": "A String",
"jobs": [ # Required. The Directed Acyclic Graph of Jobs to submit.
{ # A job executed by the workflow.
@@ -1647,7 +1683,7 @@
},
"scheduling": { # Job scheduling options. # Optional. Job scheduling configuration.
"maxFailuresPerHour": 42, # Optional. Maximum number of times per hour a driver may be restarted as a result of driver exiting 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.
- "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240
+ "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240.
},
"sparkJob": { # A Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Optional. Job is a Spark job.
"archiveUris": [ # 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.
@@ -1756,7 +1792,7 @@
"autoscalingConfig": { # Autoscaling Policy config associated with the cluster. # Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset.
"policyUri": "A String", # Optional. The autoscaling policy used by the cluster.Only resource names including projectid and location (region) are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id] projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]Note that the policy must be in the same project and Dataproc region.
},
- "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
+ "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"encryptionConfig": { # Encryption settings for the cluster. # Optional. Encryption settings for the cluster.
"gcePdKmsKeyName": "A String", # Optional. The Cloud KMS key name to use for PD disk encryption for all instances in the cluster.
},
@@ -1787,6 +1823,11 @@
"serviceAccountScopes": [ # 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.writeIf 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
"A String",
],
+ "shieldedInstanceConfig": { # Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm). # Optional. Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm).
+ "enableIntegrityMonitoring": True or False, # Optional. Defines whether instances have integrity monitoring enabled.
+ "enableSecureBoot": True or False, # Optional. Defines whether instances have Secure Boot enabled.
+ "enableVtpm": True or False, # Optional. Defines whether instances have the vTPM enabled.
+ },
"subnetworkUri": "A String", # 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/us-east1/subnetworks/sub0 projects/[project_id]/regions/us-east1/subnetworks/sub0 sub0
"tags": [ # The Compute Engine tags to add to all instances (see Tagging instances (https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).
"A String",
@@ -1802,7 +1843,7 @@
"lifecycleConfig": { # Specifies the cluster auto-delete schedule configuration. # Optional. Lifecycle setting for the cluster.
"autoDeleteTime": "A String", # Optional. The time when cluster will be auto-deleted (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).
"autoDeleteTtl": "A String", # 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)).
- "idleDeleteTtl": "A String", # 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).
+ "idleDeleteTtl": "A String", # 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)).
"idleStartTime": "A String", # 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)).
},
"masterConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for the master instance in a cluster.
@@ -1814,7 +1855,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -1825,6 +1866,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -1837,6 +1879,9 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
+ "metastoreConfig": { # Specifies a Metastore configuration. # Optional. Metastore configuration.
+ "dataprocMetastoreService": "A String", # Required. Resource name of an existing Dataproc Metastore service.Example: projects/[project_id]/locations/[dataproc_region]/services/[service-name]
+ },
"secondaryWorkerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for additional worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -1846,7 +1891,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -1857,6 +1902,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -1869,8 +1915,8 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
- "securityConfig": { # Security related configuration, including Kerberos. # Optional. Security settings for the cluster.
- "kerberosConfig": { # Specifies Kerberos related configuration. # Kerberos related configuration.
+ "securityConfig": { # Security related configuration, including encryption, Kerberos, etc. # Optional. Security settings for the cluster.
+ "kerberosConfig": { # Specifies Kerberos related configuration. # Optional. Kerberos related configuration.
"crossRealmTrustAdminServer": "A String", # Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustKdc": "A String", # Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustRealm": "A String", # Optional. The remote realm the Dataproc on-cluster KDC will trust, should the user enable cross realm trust.
@@ -1897,7 +1943,7 @@
"a_key": "A String",
},
},
- "tempBucket": "A String", # 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.
+ "tempBucket": "A String", # 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. This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"workerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -1907,7 +1953,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -1918,6 +1964,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -1991,6 +2038,7 @@
"templates": [ # Output only. WorkflowTemplates list.
{ # A Dataproc workflow template resource.
"createTime": "A String", # Output only. The time template was created.
+ "dagTimeout": "A String", # Optional. Timeout duration for the DAG of jobs, expressed in seconds (see JSON representation of duration (https://developers.google.com/protocol-buffers/docs/proto3#json)). The timeout duration must be from 10 minutes ("600s") to 24 hours ("86400s"). The timer begins when the first job is submitted. If the workflow is running at the end of the timeout period, any remaining jobs are cancelled, the workflow is ended, and if the workflow was running on a managed cluster, the cluster is deleted.
"id": "A String",
"jobs": [ # Required. The Directed Acyclic Graph of Jobs to submit.
{ # A job executed by the workflow.
@@ -2114,7 +2162,7 @@
},
"scheduling": { # Job scheduling options. # Optional. Job scheduling configuration.
"maxFailuresPerHour": 42, # Optional. Maximum number of times per hour a driver may be restarted as a result of driver exiting 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.
- "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240
+ "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240.
},
"sparkJob": { # A Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Optional. Job is a Spark job.
"archiveUris": [ # 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.
@@ -2223,7 +2271,7 @@
"autoscalingConfig": { # Autoscaling Policy config associated with the cluster. # Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset.
"policyUri": "A String", # Optional. The autoscaling policy used by the cluster.Only resource names including projectid and location (region) are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id] projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]Note that the policy must be in the same project and Dataproc region.
},
- "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
+ "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"encryptionConfig": { # Encryption settings for the cluster. # Optional. Encryption settings for the cluster.
"gcePdKmsKeyName": "A String", # Optional. The Cloud KMS key name to use for PD disk encryption for all instances in the cluster.
},
@@ -2254,6 +2302,11 @@
"serviceAccountScopes": [ # 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.writeIf 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
"A String",
],
+ "shieldedInstanceConfig": { # Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm). # Optional. Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm).
+ "enableIntegrityMonitoring": True or False, # Optional. Defines whether instances have integrity monitoring enabled.
+ "enableSecureBoot": True or False, # Optional. Defines whether instances have Secure Boot enabled.
+ "enableVtpm": True or False, # Optional. Defines whether instances have the vTPM enabled.
+ },
"subnetworkUri": "A String", # 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/us-east1/subnetworks/sub0 projects/[project_id]/regions/us-east1/subnetworks/sub0 sub0
"tags": [ # The Compute Engine tags to add to all instances (see Tagging instances (https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).
"A String",
@@ -2269,7 +2322,7 @@
"lifecycleConfig": { # Specifies the cluster auto-delete schedule configuration. # Optional. Lifecycle setting for the cluster.
"autoDeleteTime": "A String", # Optional. The time when cluster will be auto-deleted (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).
"autoDeleteTtl": "A String", # 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)).
- "idleDeleteTtl": "A String", # 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).
+ "idleDeleteTtl": "A String", # 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)).
"idleStartTime": "A String", # 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)).
},
"masterConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for the master instance in a cluster.
@@ -2281,7 +2334,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -2292,6 +2345,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -2304,6 +2358,9 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
+ "metastoreConfig": { # Specifies a Metastore configuration. # Optional. Metastore configuration.
+ "dataprocMetastoreService": "A String", # Required. Resource name of an existing Dataproc Metastore service.Example: projects/[project_id]/locations/[dataproc_region]/services/[service-name]
+ },
"secondaryWorkerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for additional worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -2313,7 +2370,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -2324,6 +2381,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -2336,8 +2394,8 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
- "securityConfig": { # Security related configuration, including Kerberos. # Optional. Security settings for the cluster.
- "kerberosConfig": { # Specifies Kerberos related configuration. # Kerberos related configuration.
+ "securityConfig": { # Security related configuration, including encryption, Kerberos, etc. # Optional. Security settings for the cluster.
+ "kerberosConfig": { # Specifies Kerberos related configuration. # Optional. Kerberos related configuration.
"crossRealmTrustAdminServer": "A String", # Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustKdc": "A String", # Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustRealm": "A String", # Optional. The remote realm the Dataproc on-cluster KDC will trust, should the user enable cross realm trust.
@@ -2364,7 +2422,7 @@
"a_key": "A String",
},
},
- "tempBucket": "A String", # 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.
+ "tempBucket": "A String", # 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. This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"workerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -2374,7 +2432,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -2385,6 +2443,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -2437,7 +2496,6 @@
"policy": { # An Identity and Access Management (IAM) policy, which specifies access controls for Google Cloud resources.A Policy is a collection of bindings. A binding binds one or more members to a single role. Members can be user accounts, service accounts, Google 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 Google Cloud 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://cloud.google.com/iam/help/conditions/resource-policies).JSON example: { "bindings": [ { "role": "roles/resourcemanager.organizationAdmin", "members": [ "user:mike@example.com", "group:admins@example.com", "domain:google.com", "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 < timestamp('2020-10-01T00:00:00.000Z')", } } ], "etag": "BwWWja0YfJA=", "version": 3 } YAML example: bindings: - members: - user:mike@example.com - group:admins@example.com - domain:google.com - 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 < timestamp('2020-10-01T00:00:00.000Z') - etag: BwWWja0YfJA= - version: 3 For a description of IAM and its features, see the IAM documentation (https://cloud.google.com/iam/docs/). # 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 Platform services (such as Projects) might reject them.
"bindings": [ # Associates a list of members to 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 member.
{ # Associates members with a role.
- "bindingId": "A String",
"condition": { # 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() < 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. # 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 members in this binding.To learn which resources support conditions in their IAM policies, see the IAM documentation (https://cloud.google.com/iam/help/conditions/resource-policies).
"description": "A String", # Optional. Description of the expression. This is a longer text which describes the expression, e.g. when hovered over it in a UI.
"expression": "A String", # Textual representation of an expression in Common Expression Language syntax.
@@ -2466,7 +2524,6 @@
{ # An Identity and Access Management (IAM) policy, which specifies access controls for Google Cloud resources.A Policy is a collection of bindings. A binding binds one or more members to a single role. Members can be user accounts, service accounts, Google 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 Google Cloud 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://cloud.google.com/iam/help/conditions/resource-policies).JSON example: { "bindings": [ { "role": "roles/resourcemanager.organizationAdmin", "members": [ "user:mike@example.com", "group:admins@example.com", "domain:google.com", "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 < timestamp('2020-10-01T00:00:00.000Z')", } } ], "etag": "BwWWja0YfJA=", "version": 3 } YAML example: bindings: - members: - user:mike@example.com - group:admins@example.com - domain:google.com - 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 < timestamp('2020-10-01T00:00:00.000Z') - etag: BwWWja0YfJA= - version: 3 For a description of IAM and its features, see the IAM documentation (https://cloud.google.com/iam/docs/).
"bindings": [ # Associates a list of members to 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 member.
{ # Associates members with a role.
- "bindingId": "A String",
"condition": { # 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() < 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. # 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 members in this binding.To learn which resources support conditions in their IAM policies, see the IAM documentation (https://cloud.google.com/iam/help/conditions/resource-policies).
"description": "A String", # Optional. Description of the expression. This is a longer text which describes the expression, e.g. when hovered over it in a UI.
"expression": "A String", # Textual representation of an expression in Common Expression Language syntax.
@@ -2525,6 +2582,7 @@
{ # A Dataproc workflow template resource.
"createTime": "A String", # Output only. The time template was created.
+ "dagTimeout": "A String", # Optional. Timeout duration for the DAG of jobs, expressed in seconds (see JSON representation of duration (https://developers.google.com/protocol-buffers/docs/proto3#json)). The timeout duration must be from 10 minutes ("600s") to 24 hours ("86400s"). The timer begins when the first job is submitted. If the workflow is running at the end of the timeout period, any remaining jobs are cancelled, the workflow is ended, and if the workflow was running on a managed cluster, the cluster is deleted.
"id": "A String",
"jobs": [ # Required. The Directed Acyclic Graph of Jobs to submit.
{ # A job executed by the workflow.
@@ -2648,7 +2706,7 @@
},
"scheduling": { # Job scheduling options. # Optional. Job scheduling configuration.
"maxFailuresPerHour": 42, # Optional. Maximum number of times per hour a driver may be restarted as a result of driver exiting 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.
- "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240
+ "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240.
},
"sparkJob": { # A Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Optional. Job is a Spark job.
"archiveUris": [ # 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.
@@ -2757,7 +2815,7 @@
"autoscalingConfig": { # Autoscaling Policy config associated with the cluster. # Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset.
"policyUri": "A String", # Optional. The autoscaling policy used by the cluster.Only resource names including projectid and location (region) are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id] projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]Note that the policy must be in the same project and Dataproc region.
},
- "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
+ "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"encryptionConfig": { # Encryption settings for the cluster. # Optional. Encryption settings for the cluster.
"gcePdKmsKeyName": "A String", # Optional. The Cloud KMS key name to use for PD disk encryption for all instances in the cluster.
},
@@ -2788,6 +2846,11 @@
"serviceAccountScopes": [ # 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.writeIf 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
"A String",
],
+ "shieldedInstanceConfig": { # Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm). # Optional. Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm).
+ "enableIntegrityMonitoring": True or False, # Optional. Defines whether instances have integrity monitoring enabled.
+ "enableSecureBoot": True or False, # Optional. Defines whether instances have Secure Boot enabled.
+ "enableVtpm": True or False, # Optional. Defines whether instances have the vTPM enabled.
+ },
"subnetworkUri": "A String", # 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/us-east1/subnetworks/sub0 projects/[project_id]/regions/us-east1/subnetworks/sub0 sub0
"tags": [ # The Compute Engine tags to add to all instances (see Tagging instances (https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).
"A String",
@@ -2803,7 +2866,7 @@
"lifecycleConfig": { # Specifies the cluster auto-delete schedule configuration. # Optional. Lifecycle setting for the cluster.
"autoDeleteTime": "A String", # Optional. The time when cluster will be auto-deleted (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).
"autoDeleteTtl": "A String", # 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)).
- "idleDeleteTtl": "A String", # 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).
+ "idleDeleteTtl": "A String", # 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)).
"idleStartTime": "A String", # 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)).
},
"masterConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for the master instance in a cluster.
@@ -2815,7 +2878,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -2826,6 +2889,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -2838,6 +2902,9 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
+ "metastoreConfig": { # Specifies a Metastore configuration. # Optional. Metastore configuration.
+ "dataprocMetastoreService": "A String", # Required. Resource name of an existing Dataproc Metastore service.Example: projects/[project_id]/locations/[dataproc_region]/services/[service-name]
+ },
"secondaryWorkerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for additional worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -2847,7 +2914,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -2858,6 +2925,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -2870,8 +2938,8 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
- "securityConfig": { # Security related configuration, including Kerberos. # Optional. Security settings for the cluster.
- "kerberosConfig": { # Specifies Kerberos related configuration. # Kerberos related configuration.
+ "securityConfig": { # Security related configuration, including encryption, Kerberos, etc. # Optional. Security settings for the cluster.
+ "kerberosConfig": { # Specifies Kerberos related configuration. # Optional. Kerberos related configuration.
"crossRealmTrustAdminServer": "A String", # Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustKdc": "A String", # Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustRealm": "A String", # Optional. The remote realm the Dataproc on-cluster KDC will trust, should the user enable cross realm trust.
@@ -2898,7 +2966,7 @@
"a_key": "A String",
},
},
- "tempBucket": "A String", # 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.
+ "tempBucket": "A String", # 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. This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"workerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -2908,7 +2976,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -2919,6 +2987,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -2951,6 +3020,7 @@
{ # A Dataproc workflow template resource.
"createTime": "A String", # Output only. The time template was created.
+ "dagTimeout": "A String", # Optional. Timeout duration for the DAG of jobs, expressed in seconds (see JSON representation of duration (https://developers.google.com/protocol-buffers/docs/proto3#json)). The timeout duration must be from 10 minutes ("600s") to 24 hours ("86400s"). The timer begins when the first job is submitted. If the workflow is running at the end of the timeout period, any remaining jobs are cancelled, the workflow is ended, and if the workflow was running on a managed cluster, the cluster is deleted.
"id": "A String",
"jobs": [ # Required. The Directed Acyclic Graph of Jobs to submit.
{ # A job executed by the workflow.
@@ -3074,7 +3144,7 @@
},
"scheduling": { # Job scheduling options. # Optional. Job scheduling configuration.
"maxFailuresPerHour": 42, # Optional. Maximum number of times per hour a driver may be restarted as a result of driver exiting 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.
- "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240
+ "maxFailuresTotal": 42, # Optional. Maximum number of times in total a driver may be restarted as a result of driver exiting with non-zero code before job is reported failed. Maximum value is 240.
},
"sparkJob": { # A Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Optional. Job is a Spark job.
"archiveUris": [ # 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.
@@ -3183,7 +3253,7 @@
"autoscalingConfig": { # Autoscaling Policy config associated with the cluster. # Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset.
"policyUri": "A String", # Optional. The autoscaling policy used by the cluster.Only resource names including projectid and location (region) are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id] projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]Note that the policy must be in the same project and Dataproc region.
},
- "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
+ "configBucket": "A String", # 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 bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"encryptionConfig": { # Encryption settings for the cluster. # Optional. Encryption settings for the cluster.
"gcePdKmsKeyName": "A String", # Optional. The Cloud KMS key name to use for PD disk encryption for all instances in the cluster.
},
@@ -3214,6 +3284,11 @@
"serviceAccountScopes": [ # 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.writeIf 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
"A String",
],
+ "shieldedInstanceConfig": { # Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm). # Optional. Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm).
+ "enableIntegrityMonitoring": True or False, # Optional. Defines whether instances have integrity monitoring enabled.
+ "enableSecureBoot": True or False, # Optional. Defines whether instances have Secure Boot enabled.
+ "enableVtpm": True or False, # Optional. Defines whether instances have the vTPM enabled.
+ },
"subnetworkUri": "A String", # 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/us-east1/subnetworks/sub0 projects/[project_id]/regions/us-east1/subnetworks/sub0 sub0
"tags": [ # The Compute Engine tags to add to all instances (see Tagging instances (https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).
"A String",
@@ -3229,7 +3304,7 @@
"lifecycleConfig": { # Specifies the cluster auto-delete schedule configuration. # Optional. Lifecycle setting for the cluster.
"autoDeleteTime": "A String", # Optional. The time when cluster will be auto-deleted (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).
"autoDeleteTtl": "A String", # 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)).
- "idleDeleteTtl": "A String", # 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).
+ "idleDeleteTtl": "A String", # 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)).
"idleStartTime": "A String", # 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)).
},
"masterConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for the master instance in a cluster.
@@ -3241,7 +3316,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -3252,6 +3327,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -3264,6 +3340,9 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
+ "metastoreConfig": { # Specifies a Metastore configuration. # Optional. Metastore configuration.
+ "dataprocMetastoreService": "A String", # Required. Resource name of an existing Dataproc Metastore service.Example: projects/[project_id]/locations/[dataproc_region]/services/[service-name]
+ },
"secondaryWorkerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for additional worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -3273,7 +3352,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -3284,6 +3363,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.
@@ -3296,8 +3376,8 @@
"numInstances": 42, # Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
"preemptibility": "A String", # 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.
},
- "securityConfig": { # Security related configuration, including Kerberos. # Optional. Security settings for the cluster.
- "kerberosConfig": { # Specifies Kerberos related configuration. # Kerberos related configuration.
+ "securityConfig": { # Security related configuration, including encryption, Kerberos, etc. # Optional. Security settings for the cluster.
+ "kerberosConfig": { # Specifies Kerberos related configuration. # Optional. Kerberos related configuration.
"crossRealmTrustAdminServer": "A String", # Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustKdc": "A String", # Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
"crossRealmTrustRealm": "A String", # Optional. The remote realm the Dataproc on-cluster KDC will trust, should the user enable cross realm trust.
@@ -3324,7 +3404,7 @@
"a_key": "A String",
},
},
- "tempBucket": "A String", # 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.
+ "tempBucket": "A String", # 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. This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
"workerConfig": { # The config settings for Compute Engine resources in an instance group, such as a master or worker group. # Optional. The Compute Engine config settings for worker instances in a cluster.
"accelerators": [ # Optional. The Compute Engine accelerator configuration for these instances.
{ # Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).
@@ -3334,7 +3414,7 @@
],
"diskConfig": { # Specifies the config of disk options for a group of VM instances. # Optional. Disk option config settings.
"bootDiskSizeGb": 42, # Optional. Size in GB of the boot disk (default is 500GB).
- "bootDiskType": "A String", # Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
+ "bootDiskType": "A String", # 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://cloud.google.com/compute/docs/disks#disk-types).
"numLocalSsds": 42, # 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.
},
"imageUri": "A String", # 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/beta/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. Dataproc will use the most recent image from the family: https://www.googleapis.com/compute/beta/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.
@@ -3345,6 +3425,7 @@
{ # A reference to a Compute Engine instance.
"instanceId": "A String", # The unique identifier of the Compute Engine instance.
"instanceName": "A String", # The user-friendly name of the Compute Engine instance.
+ "publicKey": "A String", # The public key used for sharing data with this instance.
},
],
"isPreemptible": True or False, # Output only. Specifies that this instance group contains preemptible instances.