NAME
    gcloud beta dataproc clusters create - create a cluster

SYNOPSIS
    gcloud beta dataproc clusters create (CLUSTER : --region=REGION) [--async]
        [--autoscaling-policy=AUTOSCALING_POLICY] [--bucket=BUCKET]
        [--cluster-type=TYPE] [--delete-max-idle=DELETE_MAX_IDLE]
        [--driver-pool-accelerator=[type=TYPE,[count=COUNT],...]]
        [--driver-pool-boot-disk-size=DRIVER_POOL_BOOT_DISK_SIZE]
        [--driver-pool-boot-disk-type=DRIVER_POOL_BOOT_DISK_TYPE]
        [--driver-pool-id=DRIVER_POOL_ID]
        [--driver-pool-local-ssd-interface=DRIVER_POOL_LOCAL_SSD_INTERFACE]
        [--driver-pool-machine-type=DRIVER_POOL_MACHINE_TYPE]
        [--driver-pool-min-cpu-platform=PLATFORM]
        [--driver-pool-size=DRIVER_POOL_SIZE] [--enable-component-gateway]
        [--engine=ENGINE]
        [--initialization-action-timeout=TIMEOUT; default="10m"]
        [--initialization-actions=CLOUD_STORAGE_URI,[...]]
        [--labels=[KEY=VALUE,...]]
        [--master-accelerator=[type=TYPE,[count=COUNT],...]]
        [--master-attached-disks=MASTER_ATTACHED_DISKS]
        [--master-boot-disk-provisioned-iops=MASTER_BOOT_DISK_PROVISIONED_IOPS]
        [--master-boot-disk-provisioned-throughput=MASTER_BOOT_DISK_PROVISIONED_THROUGHPUT]
        [--master-boot-disk-size=MASTER_BOOT_DISK_SIZE]
        [--master-boot-disk-type=MASTER_BOOT_DISK_TYPE]
        [--master-local-ssd-interface=MASTER_LOCAL_SSD_INTERFACE]
        [--master-machine-type=MASTER_MACHINE_TYPE]
        [--master-min-cpu-platform=PLATFORM]
        [--min-secondary-worker-fraction=MIN_SECONDARY_WORKER_FRACTION]
        [--node-group=NODE_GROUP]
        [--num-driver-pool-local-ssds=NUM_DRIVER_POOL_LOCAL_SSDS]
        [--num-master-local-ssds=NUM_MASTER_LOCAL_SSDS]
        [--num-masters=NUM_MASTERS]
        [--num-secondary-worker-local-ssds=NUM_SECONDARY_WORKER_LOCAL_SSDS]
        [--num-worker-local-ssds=NUM_WORKER_LOCAL_SSDS]
        [--optional-components=[COMPONENT,...]]
        [--private-ipv6-google-access-type=PRIVATE_IPV6_GOOGLE_ACCESS_TYPE]
        [--properties=[PREFIX:PROPERTY=VALUE,...]]
        [--secondary-worker-accelerator=[type=TYPE,[count=COUNT],...]]
        [--secondary-worker-attached-disks=SECONDARY_WORKER_ATTACHED_DISKS]
        [--secondary-worker-boot-disk-size=SECONDARY_WORKER_BOOT_DISK_SIZE]
        [--secondary-worker-boot-disk-type=SECONDARY_WORKER_BOOT_DISK_TYPE]
        [--secondary-worker-local-ssd-interface=SECONDARY_WORKER_LOCAL_SSD_INTERFACE]
        [--secondary-worker-machine-types=type=MACHINE_TYPE[,
          type=MACHINE_TYPE...][,rank=RANK]]
        [--secondary-worker-standard-capacity-base=SECONDARY_WORKER_STANDARD_CAPACITY_BASE]
        [--secondary-worker-standard-capacity-percent-above-base=SECONDARY_WORKER_STANDARD_CAPACITY_PERCENT_ABOVE_BASE]
        [--shielded-integrity-monitoring] [--shielded-secure-boot]
        [--shielded-vtpm] [--stop-max-idle=STOP_MAX_IDLE]
        [--temp-bucket=TEMP_BUCKET]
        [--worker-accelerator=[type=TYPE,[count=COUNT],...]]
        [--worker-attached-disks=WORKER_ATTACHED_DISKS]
        [--worker-boot-disk-provisioned-iops=WORKER_BOOT_DISK_PROVISIONED_IOPS]
        [--worker-boot-disk-provisioned-throughput=WORKER_BOOT_DISK_PROVISIONED_THROUGHPUT]
        [--worker-boot-disk-size=WORKER_BOOT_DISK_SIZE]
        [--worker-boot-disk-type=WORKER_BOOT_DISK_TYPE]
        [--worker-local-ssd-interface=WORKER_LOCAL_SSD_INTERFACE]
        [--worker-min-cpu-platform=PLATFORM]
        [--auto-zone-exclude-zones=[ZONE,...] | --zone=ZONE, -z ZONE]
        [--dataproc-metastore=DATAPROC_METASTORE | --bigquery-metastore
          --bigquery-metastore-database-location=BIGQUERY_METASTORE_DATABASE_LOCATION --bigquery-metastore-project-id=BIGQUERY_METASTORE_PROJECT_ID]
        [--delete-expiration-time=DELETE_EXPIRATION_TIME
          | --delete-max-age=DELETE_MAX_AGE]
        [--gce-pd-kms-key=GCE_PD_KMS_KEY
          : --gce-pd-kms-key-keyring=GCE_PD_KMS_KEY_KEYRING
          --gce-pd-kms-key-location=GCE_PD_KMS_KEY_LOCATION
          --gce-pd-kms-key-project=GCE_PD_KMS_KEY_PROJECT]
        [--metadata=KEY=VALUE,[KEY=VALUE,...]
          --resource-manager-tags=KEY=VALUE,[KEY=VALUE,...]
          --scopes=SCOPE,[SCOPE,...] --service-account=SERVICE_ACCOUNT
          --tags=TAG,[TAG,...] --network=NETWORK | --subnet=SUBNET
          --reservation=RESERVATION
          --reservation-affinity=RESERVATION_AFFINITY; default="any"]
        [--image=IMAGE | --image-version=VERSION]
        [--kerberos-config-file=KERBEROS_CONFIG_FILE | --enable-kerberos
          --kerberos-root-principal-password-uri=KERBEROS_ROOT_PRINCIPAL_PASSWORD_URI [--kerberos-kms-key=KERBEROS_KMS_KEY : --kerberos-kms-key-keyring=KERBEROS_KMS_KEY_KEYRING --kerberos-kms-key-location=KERBEROS_KMS_KEY_LOCATION --kerberos-kms-key-project=KERBEROS_KMS_KEY_PROJECT]]
        [--kms-key=KMS_KEY : --kms-keyring=KMS_KEYRING
          --kms-location=KMS_LOCATION --kms-project=KMS_PROJECT]
        [--no-address | --public-ip-address]
        [--single-node | --min-num-workers=MIN_NUM_WORKERS
          --num-secondary-workers=NUM_SECONDARY_WORKERS
          --num-workers=NUM_WORKERS
          --secondary-worker-type=TYPE; default="preemptible"]
        [--stop-expiration-time=STOP_EXPIRATION_TIME
          | --stop-max-age=STOP_MAX_AGE]
        [--worker-machine-type=WORKER_MACHINE_TYPE
          | --worker-machine-types=type=MACHINE_TYPE[,
          type=MACHINE_TYPE...][,rank=RANK]] [GCLOUD_WIDE_FLAG ...]

DESCRIPTION
    (BETA) Create a cluster.

EXAMPLES
    To create a cluster, run:

        $ gcloud beta dataproc clusters create my-cluster \
            --region=us-central1

POSITIONAL ARGUMENTS
     Cluster resource - The name of the cluster to create. The arguments in
     this group can be used to specify the attributes of this resource. (NOTE)
     Some attributes are not given arguments in this group but can be set in
     other ways.

     To set the project attribute:
      ◆ provide the argument cluster on the command line with a fully
        specified name;
      ◆ provide the argument --project on the command line;
      ◆ set the property core/project.

     This must be specified.

       CLUSTER
          ID of the cluster or fully qualified identifier for the cluster.

          To set the cluster attribute:
          ▸ provide the argument cluster on the command line.

          This positional argument must be specified if any of the other
          arguments in this group are specified.

       --region=REGION
          Dataproc region for the cluster. Each Dataproc region constitutes an
          independent resource namespace constrained to deploying instances
          into Compute Engine zones inside the region. Overrides the default
          dataproc/region property value for this command invocation.

          To set the region attribute:
          ▸ provide the argument cluster on the command line with a fully
            specified name;
          ▸ provide the argument --region on the command line;
          ▸ set the property dataproc/region.

FLAGS
     --async
        Return immediately, without waiting for the operation in progress to
        complete.

     --autoscaling-policy=AUTOSCALING_POLICY
        ID of the autoscaling policy or fully qualified identifier for the
        autoscaling policy.

        To set the autoscaling_policy attribute:
        ◆ provide the argument --autoscaling-policy on the command line.

     --bucket=BUCKET
        The Google Cloud Storage bucket to use by default to stage job
        dependencies, miscellaneous config files, and job driver console output
        when using this cluster.

     --cluster-type=TYPE
        The type of cluster. TYPE must be one of: standard, single-node,
        zero-scale.

     --delete-max-idle=DELETE_MAX_IDLE
        The duration after the last job completes to auto-delete the cluster,
        such as "2h" or "1d". See $ gcloud topic datetimes for information on
        duration formats.

     --driver-pool-accelerator=[type=TYPE,[count=COUNT],...]
        Attaches accelerators, such as GPUs, to the driver-pool instance(s).

         type
            The specific type of accelerator to attach to the instances, such
            as nvidia-tesla-t4 for NVIDIA T4. Use gcloud compute
            accelerator-types list to display available accelerator types.

         count
            The number of accelerators to attach to each instance. The default
            value is 1.

     --driver-pool-boot-disk-size=DRIVER_POOL_BOOT_DISK_SIZE
        The size of the boot disk. The value must be a whole number followed by
        a size unit of KB for kilobyte, MB for megabyte, GB for gigabyte, or TB
        for terabyte. For example, 10GB will produce a 10 gigabyte disk. The
        minimum size a boot disk can have is 10 GB. Disk size must be a
        multiple of 1 GB.

     --driver-pool-boot-disk-type=DRIVER_POOL_BOOT_DISK_TYPE
        The type of the boot disk. The value must be pd-balanced, pd-ssd, or
        pd-standard.

     --driver-pool-id=DRIVER_POOL_ID
        Custom identifier for the DRIVER Node Group being created. If not
        provided, a random string is generated.

     --driver-pool-local-ssd-interface=DRIVER_POOL_LOCAL_SSD_INTERFACE
        Interface to use to attach local SSDs to cluster driver pool node(s).

     --driver-pool-machine-type=DRIVER_POOL_MACHINE_TYPE
        The type of machine to use for the cluster driver pool nodes. Defaults
        to server-specified.

     --driver-pool-min-cpu-platform=PLATFORM
        When specified, the VM is scheduled on the host with a specified CPU
        architecture or a more recent CPU platform that's available in that
        zone. To list available CPU platforms in a zone, run:

            $ gcloud compute zones describe ZONE

        CPU platform selection may not be available in a zone. Zones that
        support CPU platform selection provide an availableCpuPlatforms field,
        which contains the list of available CPU platforms in the zone (see
        Availability of CPU platforms for more information).

     --driver-pool-size=DRIVER_POOL_SIZE
        The size of the cluster driver pool.

     --enable-component-gateway
        Enable access to the web UIs of selected components on the cluster
        through the component gateway.

     --engine=ENGINE
        Cluster engine. ENGINE must be one of: default, lightning.

     --initialization-action-timeout=TIMEOUT; default="10m"
        The maximum duration of each initialization action. See $ gcloud topic
        datetimes for information on duration formats.

     --initialization-actions=CLOUD_STORAGE_URI,[...]
        A list of Google Cloud Storage URIs of executables to run on each node
        in the cluster.

     --labels=[KEY=VALUE,...]
        List of label KEY=VALUE pairs to add.

        Keys must start with a lowercase character and contain only hyphens
        (-), underscores (_), lowercase characters, and numbers. Values must
        contain only hyphens (-), underscores (_), lowercase characters, and
        numbers.

     --master-accelerator=[type=TYPE,[count=COUNT],...]
        Attaches accelerators, such as GPUs, to the master instance(s).

         type
            The specific type of accelerator to attach to the instances, such
            as nvidia-tesla-t4 for NVIDIA T4. Use gcloud compute
            accelerator-types list to display available accelerator types.

         count
            The number of accelerators to attach to each instance. The default
            value is 1.

     --master-attached-disks=MASTER_ATTACHED_DISKS
        A list of disk configurations to attach to each instance in this group.
        Disk configurations are separated by semicolons. Each disk
        configuration is a comma-separated list of the following parameters.

            type - required
               The type of disk to attach to the instances
               (https://cloud.google.com/compute/docs/disks/hyperdisks).
               Allowed disk types are: hyperdisk-balanced, hyperdisk-extreme,
               hyperdisk-ml, hyperdisk-throughput.

            size - optional
               The size of the disk. The value must be a whole number followed by
               a size unit GB for gigabyte, or TB for terabyte. For example,
               10GB produces a 10 gigabyte disk.

            iops - optional
               Indicates the IOPS
               (https://cloud.google.com/compute/docs/disks/hyperdisks#iops) to
               provision for the attached hyperdisk. This parameter sets the limit
               for disk I/O operations per second.

            throughput - optional
               Indicates the throughput
               (https://cloud.google.com/compute/docs/disks/hyperdisks#throughput)
               to provision for the attached hyperdisk. This parameter sets the
               limit for throughput in MiB per second.

            Example:
              type='hyperdisk-balanced,iops=5000,throughput=200,size=100G;type=hyperdisk-throughput,size=9000G'

            Attaches two disks to the instances. The first disk is a
            hyperdisk-balanced disk with 5000 IOPS, 200 MiB/s throughput, and 100
            GiB size. The second disk is a hyperdisk-throughput disk with 9000
            GiB size.

     --master-boot-disk-provisioned-iops=MASTER_BOOT_DISK_PROVISIONED_IOPS
        Indicates the IOPS
        (https://cloud.google.com/compute/docs/disks/hyperdisks#iops) to
        provision for the disk. This sets the limit for disk I/O operations per
        second. This is only supported if the bootdisk type is
        hyperdisk-balanced
        (https://cloud.google.com/compute/docs/disks/hyperdisks).

     --master-boot-disk-provisioned-throughput=MASTER_BOOT_DISK_PROVISIONED_THROUGHPUT
        Indicates the throughput
        (https://cloud.google.com/compute/docs/disks/hyperdisks#throughput) to
        provision for the disk. This sets the limit for throughput in MiB per
        second. This is only supported if the bootdisk type is
        hyperdisk-balanced
        (https://cloud.google.com/compute/docs/disks/hyperdisks).

     --master-boot-disk-size=MASTER_BOOT_DISK_SIZE
        The size of the boot disk. The value must be a whole number followed by
        a size unit of KB for kilobyte, MB for megabyte, GB for gigabyte, or TB
        for terabyte. For example, 10GB will produce a 10 gigabyte disk. The
        minimum size a boot disk can have is 10 GB. Disk size must be a
        multiple of 1 GB.

     --master-boot-disk-type=MASTER_BOOT_DISK_TYPE
        The type of the boot disk. The value must be pd-balanced, pd-ssd, or
        pd-standard.

     --master-local-ssd-interface=MASTER_LOCAL_SSD_INTERFACE
        Interface to use to attach local SSDs to master node(s) in a cluster.

     --master-machine-type=MASTER_MACHINE_TYPE
        The type of machine to use for the master. Defaults to
        server-specified.

     --master-min-cpu-platform=PLATFORM
        When specified, the VM is scheduled on the host with a specified CPU
        architecture or a more recent CPU platform that's available in that
        zone. To list available CPU platforms in a zone, run:

            $ gcloud compute zones describe ZONE

        CPU platform selection may not be available in a zone. Zones that
        support CPU platform selection provide an availableCpuPlatforms field,
        which contains the list of available CPU platforms in the zone (see
        Availability of CPU platforms for more information).

     --min-secondary-worker-fraction=MIN_SECONDARY_WORKER_FRACTION
        Minimum fraction of secondary worker nodes required to create the
        cluster. If it is not met, cluster creation will fail. Must be a
        decimal value between 0 and 1. The number of required secondary workers
        is calculated by ceil(min-secondary-worker-fraction *
        num_secondary_workers). Defaults to 0.0001.

     --node-group=NODE_GROUP
        The name of the sole-tenant node group to create the cluster on. Can be
        a short name ("node-group-name") or in the format
        "projects/{project-id}/zones/{zone}/nodeGroups/{node-group-name}".

     --num-driver-pool-local-ssds=NUM_DRIVER_POOL_LOCAL_SSDS
        The number of local SSDs to attach to each cluster driver pool node.

     --num-master-local-ssds=NUM_MASTER_LOCAL_SSDS
        The number of local SSDs to attach to the master in a cluster.

     --num-masters=NUM_MASTERS
        The number of master nodes in the cluster.

          Number of Masters  Cluster Mode
          1                  Standard
          3                  High Availability

     --num-secondary-worker-local-ssds=NUM_SECONDARY_WORKER_LOCAL_SSDS
        The number of local SSDs to attach to each preemptible worker in a
        cluster.

     --num-worker-local-ssds=NUM_WORKER_LOCAL_SSDS
        The number of local SSDs to attach to each worker in a cluster.

     --optional-components=[COMPONENT,...]
        List of optional components to be installed on cluster machines.

        The following page documents the optional components that can be
        installed:
        https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/optional-components.

     --private-ipv6-google-access-type=PRIVATE_IPV6_GOOGLE_ACCESS_TYPE
        The private IPv6 Google access type for the cluster.
        PRIVATE_IPV6_GOOGLE_ACCESS_TYPE must be one of: inherit-subnetwork,
        outbound, bidirectional.

     --properties=[PREFIX:PROPERTY=VALUE,...]
        Specifies configuration properties for installed packages, such as
        Hadoop and Spark.

        Properties are mapped to configuration files by specifying a prefix,
        such as "core:io.serializations". The following are supported prefixes
        and their mappings:

          Prefix              File                    Purpose of file
          capacity-scheduler  capacity-scheduler.xml  Hadoop YARN Capacity
                                                      Scheduler configuration
          core                core-site.xml           Hadoop general
                                                      configuration
          distcp              distcp-default.xml      Hadoop Distributed Copy
                                                      configuration
          hadoop-env          hadoop-env.sh           Hadoop specific
                                                      environment variables
          hdfs                hdfs-site.xml           Hadoop HDFS configuration
          hive                hive-site.xml           Hive configuration
          mapred              mapred-site.xml         Hadoop MapReduce
                                                      configuration
          mapred-env          mapred-env.sh           Hadoop MapReduce specific
                                                      environment variables
          pig                 pig.properties          Pig configuration
          spark               spark-defaults.conf     Spark configuration
          spark-env           spark-env.sh            Spark specific environment
                                                      variables
          yarn                yarn-site.xml           Hadoop YARN configuration
          yarn-env            yarn-env.sh             Hadoop YARN specific
                                                      environment variables

        See
        https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/cluster-properties
        for more information.

     --secondary-worker-accelerator=[type=TYPE,[count=COUNT],...]
        Attaches accelerators, such as GPUs, to the secondary-worker
        instance(s).

         type
            The specific type of accelerator to attach to the instances, such
            as nvidia-tesla-t4 for NVIDIA T4. Use gcloud compute
            accelerator-types list to display available accelerator types.

         count
            The number of accelerators to attach to each instance. The default
            value is 1.

     --secondary-worker-attached-disks=SECONDARY_WORKER_ATTACHED_DISKS
        A list of disk configurations to attach to each instance in this group.
        Disk configurations are separated by semicolons. Each disk
        configuration is a comma-separated list of the following parameters.

            type - required
               The type of disk to attach to the instances
               (https://cloud.google.com/compute/docs/disks/hyperdisks).
               Allowed disk types are: hyperdisk-balanced, hyperdisk-extreme,
               hyperdisk-ml, hyperdisk-throughput.

            size - optional
               The size of the disk. The value must be a whole number followed by
               a size unit GB for gigabyte, or TB for terabyte. For example,
               10GB produces a 10 gigabyte disk.

            iops - optional
               Indicates the IOPS
               (https://cloud.google.com/compute/docs/disks/hyperdisks#iops) to
               provision for the attached hyperdisk. This parameter sets the limit
               for disk I/O operations per second.

            throughput - optional
               Indicates the throughput
               (https://cloud.google.com/compute/docs/disks/hyperdisks#throughput)
               to provision for the attached hyperdisk. This parameter sets the
               limit for throughput in MiB per second.

            Example:
              type='hyperdisk-balanced,iops=5000,throughput=200,size=100G;type=hyperdisk-throughput,size=9000G'

            Attaches two disks to the instances. The first disk is a
            hyperdisk-balanced disk with 5000 IOPS, 200 MiB/s throughput, and 100
            GiB size. The second disk is a hyperdisk-throughput disk with 9000
            GiB size.

     --secondary-worker-boot-disk-size=SECONDARY_WORKER_BOOT_DISK_SIZE
        The size of the boot disk. The value must be a whole number followed by
        a size unit of KB for kilobyte, MB for megabyte, GB for gigabyte, or TB
        for terabyte. For example, 10GB will produce a 10 gigabyte disk. The
        minimum size a boot disk can have is 10 GB. Disk size must be a
        multiple of 1 GB.

     --secondary-worker-boot-disk-type=SECONDARY_WORKER_BOOT_DISK_TYPE
        The type of the boot disk. The value must be pd-balanced, pd-ssd, or
        pd-standard.

     --secondary-worker-local-ssd-interface=SECONDARY_WORKER_LOCAL_SSD_INTERFACE
        Interface to use to attach local SSDs to each secondary worker in a
        cluster.

     --secondary-worker-machine-types=type=MACHINE_TYPE[,type=MACHINE_TYPE...][,rank=RANK]
        Types of machines with optional rank for secondary workers to use.
        Defaults to server-specified.eg.
        --secondary-worker-machine-types="type=e2-standard-8,type=t2d-standard-8,rank=0"

     --secondary-worker-standard-capacity-base=SECONDARY_WORKER_STANDARD_CAPACITY_BASE
        This flag sets the base number of Standard VMs to use for secondary
        workers
        (https://cloud.google.com/dataproc/docs/concepts/compute/secondary-vms#preemptible_and_non-preemptible_secondary_workers).
        Dataproc will create only standard VMs until it reaches this number,
        then it will mix Spot and Standard VMs according to
        SECONDARY_WORKER_STANDARD_CAPACITY_PERCENT_ABOVE_BASE.

     --secondary-worker-standard-capacity-percent-above-base=SECONDARY_WORKER_STANDARD_CAPACITY_PERCENT_ABOVE_BASE
        When combining Standard and Spot VMs for secondary-workers
        (https://cloud.google.com/dataproc/docs/concepts/compute/secondary-vms#preemptible_and_non-preemptible_secondary_workers)
        once the number of Standard VMs specified by
        SECONDARY_WORKER_STANDARD_CAPACITY_BASE has been used, this flag
        specifies the percentage of the total number of additional Standard VMs
        secondary workers will use. Spot VMs will be used for the remaining
        percentage.

     --shielded-integrity-monitoring
        Enables monitoring and attestation of the boot integrity of the
        cluster's VMs. vTPM (virtual Trusted Platform Module) must also be
        enabled. A TPM is a hardware module that can be used for different
        security operations, such as remote attestation, encryption, and
        sealing of keys.

     --shielded-secure-boot
        The cluster's VMs will boot with secure boot enabled.

     --shielded-vtpm
        The cluster's VMs will boot with the TPM (Trusted Platform Module)
        enabled. A TPM is a hardware module that can be used for different
        security operations, such as remote attestation, encryption, and
        sealing of keys.

     --stop-max-idle=STOP_MAX_IDLE
        The duration after the last job completes to auto-stop the cluster,
        such as "2h" or "1d". See $ gcloud topic datetimes for information on
        duration formats.

     --temp-bucket=TEMP_BUCKET
        The Google Cloud Storage bucket to use by default to store ephemeral
        cluster and jobs data, such as Spark and MapReduce history files.

     --worker-accelerator=[type=TYPE,[count=COUNT],...]
        Attaches accelerators, such as GPUs, to the worker instance(s).

         type
            The specific type of accelerator to attach to the instances, such
            as nvidia-tesla-t4 for NVIDIA T4. Use gcloud compute
            accelerator-types list to display available accelerator types.

         count
            The number of accelerators to attach to each instance. The default
            value is 1.

     --worker-attached-disks=WORKER_ATTACHED_DISKS
        A list of disk configurations to attach to each instance in this group.
        Disk configurations are separated by semicolons. Each disk
        configuration is a comma-separated list of the following parameters.

            type - required
               The type of disk to attach to the instances
               (https://cloud.google.com/compute/docs/disks/hyperdisks).
               Allowed disk types are: hyperdisk-balanced, hyperdisk-extreme,
               hyperdisk-ml, hyperdisk-throughput.

            size - optional
               The size of the disk. The value must be a whole number followed by
               a size unit GB for gigabyte, or TB for terabyte. For example,
               10GB produces a 10 gigabyte disk.

            iops - optional
               Indicates the IOPS
               (https://cloud.google.com/compute/docs/disks/hyperdisks#iops) to
               provision for the attached hyperdisk. This parameter sets the limit
               for disk I/O operations per second.

            throughput - optional
               Indicates the throughput
               (https://cloud.google.com/compute/docs/disks/hyperdisks#throughput)
               to provision for the attached hyperdisk. This parameter sets the
               limit for throughput in MiB per second.

            Example:
              type='hyperdisk-balanced,iops=5000,throughput=200,size=100G;type=hyperdisk-throughput,size=9000G'

            Attaches two disks to the instances. The first disk is a
            hyperdisk-balanced disk with 5000 IOPS, 200 MiB/s throughput, and 100
            GiB size. The second disk is a hyperdisk-throughput disk with 9000
            GiB size.

     --worker-boot-disk-provisioned-iops=WORKER_BOOT_DISK_PROVISIONED_IOPS
        Indicates the IOPS
        (https://cloud.google.com/compute/docs/disks/hyperdisks#iops) to
        provision for the disk. This sets the limit for disk I/O operations per
        second. This is only supported if the bootdisk type is
        hyperdisk-balanced
        (https://cloud.google.com/compute/docs/disks/hyperdisks).

     --worker-boot-disk-provisioned-throughput=WORKER_BOOT_DISK_PROVISIONED_THROUGHPUT
        Indicates the throughput
        (https://cloud.google.com/compute/docs/disks/hyperdisks#throughput) to
        provision for the disk. This sets the limit for throughput in MiB per
        second. This is only supported if the bootdisk type is
        hyperdisk-balanced
        (https://cloud.google.com/compute/docs/disks/hyperdisks).

     --worker-boot-disk-size=WORKER_BOOT_DISK_SIZE
        The size of the boot disk. The value must be a whole number followed by
        a size unit of KB for kilobyte, MB for megabyte, GB for gigabyte, or TB
        for terabyte. For example, 10GB will produce a 10 gigabyte disk. The
        minimum size a boot disk can have is 10 GB. Disk size must be a
        multiple of 1 GB.

     --worker-boot-disk-type=WORKER_BOOT_DISK_TYPE
        The type of the boot disk. The value must be pd-balanced, pd-ssd, or
        pd-standard.

     --worker-local-ssd-interface=WORKER_LOCAL_SSD_INTERFACE
        Interface to use to attach local SSDs to each worker in a cluster.

     --worker-min-cpu-platform=PLATFORM
        When specified, the VM is scheduled on the host with a specified CPU
        architecture or a more recent CPU platform that's available in that
        zone. To list available CPU platforms in a zone, run:

            $ gcloud compute zones describe ZONE

        CPU platform selection may not be available in a zone. Zones that
        support CPU platform selection provide an availableCpuPlatforms field,
        which contains the list of available CPU platforms in the zone (see
        Availability of CPU platforms for more information).

     At most one of these can be specified:

       --auto-zone-exclude-zones=[ZONE,...]
          A comma-separated list of compute zones (such as us-central1-a) to
          exclude when Dataproc Auto Zone placement
          (https://docs.cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone)
          picks the zone for the cluster.

       --zone=ZONE, -z ZONE
          The compute zone (such as us-central1-a) for the cluster. If empty
          and --region is set to a value other than global, Dataproc Auto Zone
          placement
          (https://docs.cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone)
          will pick a zone in the region. Overrides the default compute/zone
          property value for this command invocation.

     At most one of these can be specified:

       --dataproc-metastore=DATAPROC_METASTORE
          Specify the name of a Dataproc Metastore service to be used as an
          external metastore in the format:
          "projects/{project-id}/locations/{region}/services/{service-name}".

       Or at least one of these can be specified:

         BQMS flags

         --bigquery-metastore
            Indicates that BigQuery metastore is to be used.

         --bigquery-metastore-database-location=BIGQUERY_METASTORE_DATABASE_LOCATION
            Location of the BigQuery metastore database to be used as an
            external metastore.

         --bigquery-metastore-project-id=BIGQUERY_METASTORE_PROJECT_ID
            The project ID of the BigQuery metastore database to be used as an
            external metastore.

     At most one of these can be specified:

       --delete-expiration-time=DELETE_EXPIRATION_TIME
          The time when the cluster will be auto-deleted, such as
          "2017-08-29T18:52:51.142Z." See $ gcloud topic datetimes for
          information on time formats.

       --delete-max-age=DELETE_MAX_AGE
          The lifespan of the cluster, with auto-deletion upon completion, such
          as "2h" or "1d". See $ gcloud topic datetimes for information on
          duration formats.

     Key resource - The Cloud KMS (Key Management Service) cryptokey that will
     be used to protect the cluster. The 'Compute Engine Service Agent' service
     account must hold permission 'Cloud KMS CryptoKey Encrypter/Decrypter'.
     The arguments in this group can be used to specify the attributes of this
     resource.

     --gce-pd-kms-key=GCE_PD_KMS_KEY
        ID of the key or fully qualified identifier for the key.

        To set the kms-key attribute:
        ◆ provide the argument --gce-pd-kms-key on the command line.

        This flag argument must be specified if any of the other arguments in
        this group are specified.

     --gce-pd-kms-key-keyring=GCE_PD_KMS_KEY_KEYRING
        The KMS keyring of the key.

        To set the kms-keyring attribute:
        ◆ provide the argument --gce-pd-kms-key on the command line with a
          fully specified name;
        ◆ provide the argument --gce-pd-kms-key-keyring on the command line.

     --gce-pd-kms-key-location=GCE_PD_KMS_KEY_LOCATION
        The Google Cloud location for the key.

        To set the kms-location attribute:
        ◆ provide the argument --gce-pd-kms-key on the command line with a
          fully specified name;
        ◆ provide the argument --gce-pd-kms-key-location on the command line.

     --gce-pd-kms-key-project=GCE_PD_KMS_KEY_PROJECT
        The Google Cloud project for the key.

        To set the kms-project attribute:
        ◆ provide the argument --gce-pd-kms-key on the command line with a
          fully specified name;
        ◆ provide the argument --gce-pd-kms-key-project on the command line;
        ◆ set the property core/project.

     At most one of these can be specified:

       Compute Engine options for Dataproc clusters.

       --metadata=KEY=VALUE,[KEY=VALUE,...]
          Metadata to be made available to the guest operating system running
          on the instances

       --resource-manager-tags=KEY=VALUE,[KEY=VALUE,...]
          Specifies a list of resource manager tags to apply to each cluster
          node (master and worker nodes).

       --scopes=SCOPE,[SCOPE,...]
          Specifies scopes for the node instances. Multiple SCOPEs can be
          specified, separated by commas. Examples:

              $ gcloud beta dataproc clusters create example-cluster \
                  --scopes https://www.googleapis.com/auth/bigtable.admin

              $ gcloud beta dataproc clusters create example-cluster \
                  --scopes sqlservice,bigquery

          The following minimum scopes are necessary for the cluster to
          function properly and are always added, even if not explicitly
          specified:

              https://www.googleapis.com/auth/devstorage.read_write
              https://www.googleapis.com/auth/logging.write

          If the --scopes flag is not specified, the following default scopes
          are also included:

              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

          If you want to enable all scopes use the 'cloud-platform' scope.

          SCOPE can be either the full URI of the scope or an alias. Default
          scopes are assigned to all instances. Available aliases are:

            Alias                  URI
            bigquery               https://www.googleapis.com/auth/bigquery
            cloud-platform         https://www.googleapis.com/auth/cloud-platform
            cloud-source-repos     https://www.googleapis.com/auth/source.full_control
            cloud-source-repos-ro  https://www.googleapis.com/auth/source.read_only
            compute-ro             https://www.googleapis.com/auth/compute.readonly
            compute-rw             https://www.googleapis.com/auth/compute
            datastore              https://www.googleapis.com/auth/datastore
            default                https://www.googleapis.com/auth/devstorage.read_only
                                   https://www.googleapis.com/auth/logging.write
                                   https://www.googleapis.com/auth/monitoring.write
                                   https://www.googleapis.com/auth/pubsub
                                   https://www.googleapis.com/auth/service.management.readonly
                                   https://www.googleapis.com/auth/servicecontrol
                                   https://www.googleapis.com/auth/trace.append
            gke-default            https://www.googleapis.com/auth/devstorage.read_only
                                   https://www.googleapis.com/auth/logging.write
                                   https://www.googleapis.com/auth/monitoring
                                   https://www.googleapis.com/auth/service.management.readonly
                                   https://www.googleapis.com/auth/servicecontrol
                                   https://www.googleapis.com/auth/trace.append
            logging-write          https://www.googleapis.com/auth/logging.write
            monitoring             https://www.googleapis.com/auth/monitoring
            monitoring-read        https://www.googleapis.com/auth/monitoring.read
            monitoring-write       https://www.googleapis.com/auth/monitoring.write
            pubsub                 https://www.googleapis.com/auth/pubsub
            service-control        https://www.googleapis.com/auth/servicecontrol
            service-management     https://www.googleapis.com/auth/service.management.readonly
            sql (deprecated)       https://www.googleapis.com/auth/sqlservice
            sql-admin              https://www.googleapis.com/auth/sqlservice.admin
            storage-full           https://www.googleapis.com/auth/devstorage.full_control
            storage-ro             https://www.googleapis.com/auth/devstorage.read_only
            storage-rw             https://www.googleapis.com/auth/devstorage.read_write
            taskqueue              https://www.googleapis.com/auth/taskqueue
            trace                  https://www.googleapis.com/auth/trace.append
            userinfo-email         https://www.googleapis.com/auth/userinfo.email

          DEPRECATION WARNING: https://www.googleapis.com/auth/sqlservice
          account scope and sql alias do not provide SQL instance management
          capabilities and have been deprecated. Please, use
          https://www.googleapis.com/auth/sqlservice.admin or sql-admin to
          manage your Google SQL Service instances.

       --service-account=SERVICE_ACCOUNT
          The Google Cloud IAM service account to be authenticated as.

       --tags=TAG,[TAG,...]
          Specifies a list of tags to apply to the instance. These tags allow
          network firewall rules and routes to be applied to specified VM
          instances. See gcloud compute firewall-rules create(1) for more
          details.

          To read more about configuring network tags, read this guide:
          https://cloud.google.com/vpc/docs/add-remove-network-tags

          To list instances with their respective status and tags, run:

              $ gcloud compute instances list \
                  --format='table(name,status,tags.list())'

          To list instances tagged with a specific tag, tag1, run:

              $ gcloud compute instances list --filter='tags:tag1'

       At most one of these can be specified:

         --network=NETWORK
            The Compute Engine network that the VM instances of the cluster
            will be part of. This is mutually exclusive with --subnet. If
            neither is specified, this defaults to the "default" network.

         --subnet=SUBNET
            Specifies the subnet that the cluster will be part of. This is
            mutally exclusive with --network.

       Specifies the reservation for the instance.

       --reservation=RESERVATION
          The name of the reservation, required when
          --reservation-affinity=specific.

       --reservation-affinity=RESERVATION_AFFINITY; default="any"
          The type of reservation for the instance. RESERVATION_AFFINITY must
          be one of: any, none, specific.

     At most one of these can be specified:

       --image=IMAGE
          The custom image used to create the cluster. It can be the image
          name, the image URI, or the image family URI, which selects the
          latest image from the family.

       --image-version=VERSION
          The image version to use for the cluster. Defaults to the latest
          version.

     Specifying these flags will enable Kerberos for the cluster.

     At most one of these can be specified:

       --kerberos-config-file=KERBEROS_CONFIG_FILE
          Path to a YAML (or JSON) file containing the configuration for
          Kerberos on the cluster. If you pass - as the value of the flag the
          file content will be read from stdin.

          The YAML file is formatted as follows:

                # Optional. Flag to indicate whether to Kerberize the cluster.
                # The default value is true.
                enable_kerberos: true

                # Optional. The Google Cloud Storage URI of a KMS encrypted file
                # containing the root principal password.
                root_principal_password_uri: gs://bucket/password.encrypted

                # Optional. The URI of the Cloud KMS key used to encrypt
                # sensitive files.
                kms_key_uri:
                  projects/myproject/locations/global/keyRings/mykeyring/cryptoKeys/my-key

                # Configuration of SSL encryption. If specified, all sub-fields
                # are required. Otherwise, Dataproc will provide a self-signed
                # certificate and generate the passwords.
                ssl:
                  # Optional. The Google Cloud Storage URI of the keystore file.
                  keystore_uri: gs://bucket/keystore.jks

                  # Optional. The Google Cloud Storage URI of a KMS encrypted
                  # file containing the password to the keystore.
                  keystore_password_uri: gs://bucket/keystore_password.encrypted

                  # Optional. The Google Cloud Storage URI of a KMS encrypted
                  # file containing the password to the user provided key.
                  key_password_uri: gs://bucket/key_password.encrypted

                  # Optional. The Google Cloud Storage URI of the truststore
                  # file.
                  truststore_uri: gs://bucket/truststore.jks

                  # Optional. The Google Cloud Storage URI of a KMS encrypted
                  # file containing the password to the user provided
                  # truststore.
                  truststore_password_uri:
                    gs://bucket/truststore_password.encrypted

                # Configuration of cross realm trust.
                cross_realm_trust:
                  # Optional. The remote realm the Dataproc on-cluster KDC will
                  # trust, should the user enable cross realm trust.
                  realm: REMOTE.REALM

                  # Optional. The KDC (IP or hostname) for the remote trusted
                  # realm in a cross realm trust relationship.
                  kdc: kdc.remote.realm

                  # Optional. The admin server (IP or hostname) for the remote
                  # trusted realm in a cross realm trust relationship.
                  admin_server: admin-server.remote.realm

                  # Optional. The Google Cloud Storage URI of a KMS encrypted
                  # file containing the shared password between the on-cluster
                  # Kerberos realm and the remote trusted realm, in a cross
                  # realm trust relationship.
                  shared_password_uri:
                    gs://bucket/cross-realm.password.encrypted

                # Optional. The Google Cloud Storage URI of a KMS encrypted file
                # containing the master key of the KDC database.
                kdc_db_key_uri: gs://bucket/kdc_db_key.encrypted

                # Optional. The lifetime of the ticket granting ticket, in
                # hours. If not specified, or user specifies 0, then default
                # value 10 will be used.
                tgt_lifetime_hours: 1

                # Optional. The name of the Kerberos realm. If not specified,
                # the uppercased domain name of the cluster will be used.
                realm: REALM.NAME

       Or at least one of these can be specified:

         --enable-kerberos
            Enable Kerberos on the cluster.

         --kerberos-root-principal-password-uri=KERBEROS_ROOT_PRINCIPAL_PASSWORD_URI
            Google Cloud Storage URI of a KMS encrypted file containing the
            root principal password. Must be a Cloud Storage URL beginning with
            'gs://'.

         Key resource - The Cloud KMS (Key Management Service) cryptokey that
         will be used to protect the password. The 'Compute Engine Service
         Agent' service account must hold permission 'Cloud KMS CryptoKey
         Encrypter/Decrypter'. The arguments in this group can be used to
         specify the attributes of this resource.

         --kerberos-kms-key=KERBEROS_KMS_KEY
            ID of the key or fully qualified identifier for the key.

            To set the kms-key attribute:
            ▫ provide the argument --kerberos-kms-key on the command line.

            This flag argument must be specified if any of the other arguments
            in this group are specified.

         --kerberos-kms-key-keyring=KERBEROS_KMS_KEY_KEYRING
            The KMS keyring of the key.

            To set the kms-keyring attribute:
            ▫ provide the argument --kerberos-kms-key on the command line
              with a fully specified name;
            ▫ provide the argument --kerberos-kms-key-keyring on the command
              line.

         --kerberos-kms-key-location=KERBEROS_KMS_KEY_LOCATION
            The Google Cloud location for the key.

            To set the kms-location attribute:
            ▫ provide the argument --kerberos-kms-key on the command line
              with a fully specified name;
            ▫ provide the argument --kerberos-kms-key-location on the command
              line.

         --kerberos-kms-key-project=KERBEROS_KMS_KEY_PROJECT
            The Google Cloud project for the key.

            To set the kms-project attribute:
            ▫ provide the argument --kerberos-kms-key on the command line
              with a fully specified name;
            ▫ provide the argument --kerberos-kms-key-project on the command
              line;
            ▫ set the property core/project.

     Key resource - The Cloud KMS (Key Management Service) cryptokey that will
     be used to protect the cluster. The 'Compute Engine Service Agent' service
     account must hold permission 'Cloud KMS CryptoKey Encrypter/Decrypter'.
     The arguments in this group can be used to specify the attributes of this
     resource.

     --kms-key=KMS_KEY
        ID of the key or fully qualified identifier for the key.

        To set the kms-key attribute:
        ◆ provide the argument --kms-key on the command line.

        This flag argument must be specified if any of the other arguments in
        this group are specified.

     --kms-keyring=KMS_KEYRING
        The KMS keyring of the key.

        To set the kms-keyring attribute:
        ◆ provide the argument --kms-key on the command line with a fully
          specified name;
        ◆ provide the argument --kms-keyring on the command line.

     --kms-location=KMS_LOCATION
        The Google Cloud location for the key.

        To set the kms-location attribute:
        ◆ provide the argument --kms-key on the command line with a fully
          specified name;
        ◆ provide the argument --kms-location on the command line.

     --kms-project=KMS_PROJECT
        The Google Cloud project for the key.

        To set the kms-project attribute:
        ◆ provide the argument --kms-key on the command line with a fully
          specified name;
        ◆ provide the argument --kms-project on the command line;
        ◆ set the property core/project.

     At most one of these can be specified:

       --no-address
          If provided, the instances in the cluster will not be assigned
          external IP addresses.

          If omitted, then the Dataproc service will apply a default policy to
          determine if each instance in the cluster gets an external IP address
          or not.

          Note: Dataproc VMs need access to the Dataproc API. This can be
          achieved without external IP addresses using Private Google Access
          (https://cloud.google.com/compute/docs/private-google-access).

       --public-ip-address
          If provided, cluster instances are assigned external IP addresses.

          If omitted, the Dataproc service applies a default policy to
          determine whether or not each instance in the cluster gets an
          external IP address.

          Note: Dataproc VMs need access to the Dataproc API. This can be
          achieved without external IP addresses using Private Google Access
          (https://cloud.google.com/compute/docs/private-google-access).

     At most one of these can be specified:

       --single-node
          Create a single node cluster.

          A single node cluster has all master and worker components. It cannot
          have any separate worker nodes. If this flag is not specified, a
          cluster with separate workers is created.

       Or at least one of these can be specified:

         Multi-node cluster flags

         --min-num-workers=MIN_NUM_WORKERS
            Minimum number of primary worker nodes to provision for cluster
            creation to succeed.

         --num-secondary-workers=NUM_SECONDARY_WORKERS
            The number of secondary worker nodes in the cluster.

         --num-workers=NUM_WORKERS
            The number of worker nodes in the cluster. Defaults to
            server-specified.

         --secondary-worker-type=TYPE; default="preemptible"
            The type of the secondary worker group. TYPE must be one of:
            preemptible, non-preemptible, spot.

     At most one of these can be specified:

       --stop-expiration-time=STOP_EXPIRATION_TIME
          The time when the cluster will be auto-stopped, such as
          "2017-08-29T18:52:51.142Z." See $ gcloud topic datetimes for
          information on time formats.

       --stop-max-age=STOP_MAX_AGE
          The lifespan of the cluster, with auto-stop upon completion, such as
          "2h" or "1d". See $ gcloud topic datetimes for information on
          duration formats.

     At most one of these can be specified:

       --worker-machine-type=WORKER_MACHINE_TYPE
          The type of machine to use for primary workers. Defaults to
          server-specified.

       --worker-machine-types=type=MACHINE_TYPE[,type=MACHINE_TYPE...][,rank=RANK]
          Machine types
          (https://cloud.google.com/dataproc/docs/concepts/compute/supported-machine-types)
          for primary worker nodes to use with optional rank. A lower rank
          number is given higher preference. Based on availablilty, Dataproc
          tries to create primary worker VMs using the worker machine type with
          the lowest rank, and then tries to use machine types with higher
          ranks as necessary. Machine types with the same rank are given the
          same preference. Example use:
          --worker-machine-types="type=e2-standard-8,type=n2-standard-8,rank=0".
          For more information, see Dataproc Flexible VMs
          (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/flexible-vms)

GCLOUD WIDE FLAGS
    These flags are available to all commands: --access-token-file, --account,
    --billing-project, --configuration, --flags-file, --flatten, --format,
    --help, --impersonate-service-account, --log-http, --project, --quiet,
    --trace-token, --user-output-enabled, --verbosity.

    Run $ gcloud help for details.

NOTES
    This command is currently in beta and might change without notice. These
    variants are also available:

        $ gcloud dataproc clusters create

        $ gcloud alpha dataproc clusters create

