1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349
|
// Code generated by smithy-go-codegen DO NOT EDIT.
package emr
import (
"context"
"fmt"
awsmiddleware "github.com/aws/aws-sdk-go-v2/aws/middleware"
"github.com/aws/aws-sdk-go-v2/aws/signer/v4"
"github.com/aws/aws-sdk-go-v2/service/emr/types"
"github.com/aws/smithy-go/middleware"
smithyhttp "github.com/aws/smithy-go/transport/http"
)
// RunJobFlow creates and starts running a new cluster (job flow). The cluster
// runs the steps specified. After the steps complete, the cluster stops and the
// HDFS partition is lost. To prevent loss of data, configure the last step of the
// job flow to store results in Amazon S3. If the JobFlowInstancesConfig
// KeepJobFlowAliveWhenNoSteps parameter is set to TRUE , the cluster transitions
// to the WAITING state rather than shutting down after the steps have completed.
// For additional protection, you can set the JobFlowInstancesConfig
// TerminationProtected parameter to TRUE to lock the cluster and prevent it from
// being terminated by API call, user intervention, or in the event of a job flow
// error. A maximum of 256 steps are allowed in each job flow. If your cluster is
// long-running (such as a Hive data warehouse) or complex, you may require more
// than 256 steps to process your data. You can bypass the 256-step limitation in
// various ways, including using the SSH shell to connect to the master node and
// submitting queries directly to the software running on the master node, such as
// Hive and Hadoop. For long-running clusters, we recommend that you periodically
// store your results. The instance fleets configuration is available only in
// Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions. The RunJobFlow
// request can contain InstanceFleets parameters or InstanceGroups parameters, but
// not both.
func (c *Client) RunJobFlow(ctx context.Context, params *RunJobFlowInput, optFns ...func(*Options)) (*RunJobFlowOutput, error) {
if params == nil {
params = &RunJobFlowInput{}
}
result, metadata, err := c.invokeOperation(ctx, "RunJobFlow", params, optFns, c.addOperationRunJobFlowMiddlewares)
if err != nil {
return nil, err
}
out := result.(*RunJobFlowOutput)
out.ResultMetadata = metadata
return out, nil
}
// Input to the RunJobFlow operation.
type RunJobFlowInput struct {
// A specification of the number and type of Amazon EC2 instances.
//
// This member is required.
Instances *types.JobFlowInstancesConfig
// The name of the job flow.
//
// This member is required.
Name *string
// A JSON string for selecting additional features.
AdditionalInfo *string
// Applies only to Amazon EMR AMI versions 3.x and 2.x. For Amazon EMR releases
// 4.0 and later, ReleaseLabel is used. To specify a custom AMI, use CustomAmiID .
AmiVersion *string
// Applies to Amazon EMR releases 4.0 and later. A case-insensitive list of
// applications for Amazon EMR to install and configure when launching the cluster.
// For a list of applications available for each Amazon EMR release version, see
// the Amazon EMRRelease Guide (https://docs.aws.amazon.com/emr/latest/ReleaseGuide/)
// .
Applications []types.Application
// An IAM role for automatic scaling policies. The default role is
// EMR_AutoScaling_DefaultRole . The IAM role provides permissions that the
// automatic scaling feature requires to launch and terminate Amazon EC2 instances
// in an instance group.
AutoScalingRole *string
// An auto-termination policy for an Amazon EMR cluster. An auto-termination
// policy defines the amount of idle time in seconds after which a cluster
// automatically terminates. For alternative cluster termination options, see
// Control cluster termination (https://docs.aws.amazon.com/emr/latest/ManagementGuide/emr-plan-termination.html)
// .
AutoTerminationPolicy *types.AutoTerminationPolicy
// A list of bootstrap actions to run before Hadoop starts on the cluster nodes.
BootstrapActions []types.BootstrapActionConfig
// For Amazon EMR releases 4.0 and later. The list of configurations supplied for
// the Amazon EMR cluster that you are creating.
Configurations []types.Configuration
// Available only in Amazon EMR releases 5.7.0 and later. The ID of a custom
// Amazon EBS-backed Linux AMI. If specified, Amazon EMR uses this AMI when it
// launches cluster Amazon EC2 instances. For more information about custom AMIs in
// Amazon EMR, see Using a Custom AMI (https://docs.aws.amazon.com/emr/latest/ManagementGuide/emr-custom-ami.html)
// in the Amazon EMR Management Guide. If omitted, the cluster uses the base Linux
// AMI for the ReleaseLabel specified. For Amazon EMR releases 2.x and 3.x, use
// AmiVersion instead. For information about creating a custom AMI, see Creating
// an Amazon EBS-Backed Linux AMI (https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/creating-an-ami-ebs.html)
// in the Amazon Elastic Compute Cloud User Guide for Linux Instances. For
// information about finding an AMI ID, see Finding a Linux AMI (https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/finding-an-ami.html)
// .
CustomAmiId *string
// The IOPS, of the Amazon EBS root device volume of the Linux AMI that is used
// for each Amazon EC2 instance. Available in Amazon EMR releases 6.15.0 and later.
EbsRootVolumeIops *int32
// The size, in GiB, of the Amazon EBS root device volume of the Linux AMI that is
// used for each Amazon EC2 instance. Available in Amazon EMR releases 4.x and
// later.
EbsRootVolumeSize *int32
// The throughput, in MiB/s, of the Amazon EBS root device volume of the Linux AMI
// that is used for each Amazon EC2 instance. Available in Amazon EMR releases
// 6.15.0 and later.
EbsRootVolumeThroughput *int32
// Also called instance profile and Amazon EC2 role. An IAM role for an Amazon EMR
// cluster. The Amazon EC2 instances of the cluster assume this role. The default
// role is EMR_EC2_DefaultRole . In order to use the default role, you must have
// already created it using the CLI or console.
JobFlowRole *string
// Attributes for Kerberos configuration when Kerberos authentication is enabled
// using a security configuration. For more information see Use Kerberos
// Authentication (https://docs.aws.amazon.com/emr/latest/ManagementGuide/emr-kerberos.html)
// in the Amazon EMR Management Guide.
KerberosAttributes *types.KerberosAttributes
// The KMS key used for encrypting log files. If a value is not provided, the logs
// remain encrypted by AES-256. This attribute is only available with Amazon EMR
// releases 5.30.0 and later, excluding Amazon EMR 6.0.0.
LogEncryptionKmsKeyId *string
// The location in Amazon S3 to write the log files of the job flow. If a value is
// not provided, logs are not created.
LogUri *string
// The specified managed scaling policy for an Amazon EMR cluster.
ManagedScalingPolicy *types.ManagedScalingPolicy
// For Amazon EMR releases 3.x and 2.x. For Amazon EMR releases 4.x and later, use
// Applications. A list of strings that indicates third-party software to use with
// the job flow that accepts a user argument list. Amazon EMR accepts and forwards
// the argument list to the corresponding installation script as bootstrap action
// arguments. For more information, see "Launch a Job Flow on the MapR Distribution
// for Hadoop" in the Amazon EMR Developer Guide (https://docs.aws.amazon.com/emr/latest/DeveloperGuide/emr-dg.pdf)
// . Supported values are:
// - "mapr-m3" - launch the cluster using MapR M3 Edition.
// - "mapr-m5" - launch the cluster using MapR M5 Edition.
// - "mapr" with the user arguments specifying "--edition,m3" or "--edition,m5"
// - launch the job flow using MapR M3 or M5 Edition respectively.
// - "mapr-m7" - launch the cluster using MapR M7 Edition.
// - "hunk" - launch the cluster with the Hunk Big Data Analytics Platform.
// - "hue"- launch the cluster with Hue installed.
// - "spark" - launch the cluster with Apache Spark installed.
// - "ganglia" - launch the cluster with the Ganglia Monitoring System
// installed.
NewSupportedProducts []types.SupportedProductConfig
// Specifies a particular Amazon Linux release for all nodes in a cluster launch
// RunJobFlow request. If a release is not specified, Amazon EMR uses the latest
// validated Amazon Linux release for cluster launch.
OSReleaseLabel *string
// The specified placement group configuration for an Amazon EMR cluster.
PlacementGroupConfigs []types.PlacementGroupConfig
// The Amazon EMR release label, which determines the version of open-source
// application packages installed on the cluster. Release labels are in the form
// emr-x.x.x , where x.x.x is an Amazon EMR release version such as emr-5.14.0 .
// For more information about Amazon EMR release versions and included application
// versions and features, see https://docs.aws.amazon.com/emr/latest/ReleaseGuide/ (https://docs.aws.amazon.com/emr/latest/ReleaseGuide/)
// . The release label applies only to Amazon EMR releases version 4.0 and later.
// Earlier versions use AmiVersion .
ReleaseLabel *string
// Applies only when CustomAmiID is used. Specifies which updates from the Amazon
// Linux AMI package repositories to apply automatically when the instance boots
// using the AMI. If omitted, the default is SECURITY , which indicates that only
// security updates are applied. If NONE is specified, no updates are applied, and
// all updates must be applied manually.
RepoUpgradeOnBoot types.RepoUpgradeOnBoot
// Specifies the way that individual Amazon EC2 instances terminate when an
// automatic scale-in activity occurs or an instance group is resized.
// TERMINATE_AT_INSTANCE_HOUR indicates that Amazon EMR terminates nodes at the
// instance-hour boundary, regardless of when the request to terminate the instance
// was submitted. This option is only available with Amazon EMR 5.1.0 and later and
// is the default for clusters created using that version.
// TERMINATE_AT_TASK_COMPLETION indicates that Amazon EMR adds nodes to a deny list
// and drains tasks from nodes before terminating the Amazon EC2 instances,
// regardless of the instance-hour boundary. With either behavior, Amazon EMR
// removes the least active nodes first and blocks instance termination if it could
// lead to HDFS corruption. TERMINATE_AT_TASK_COMPLETION available only in Amazon
// EMR releases 4.1.0 and later, and is the default for releases of Amazon EMR
// earlier than 5.1.0.
ScaleDownBehavior types.ScaleDownBehavior
// The name of a security configuration to apply to the cluster.
SecurityConfiguration *string
// The IAM role that Amazon EMR assumes in order to access Amazon Web Services
// resources on your behalf. If you've created a custom service role path, you must
// specify it for the service role when you launch your cluster.
ServiceRole *string
// Specifies the number of steps that can be executed concurrently. The default
// value is 1 . The maximum value is 256 .
StepConcurrencyLevel *int32
// A list of steps to run.
Steps []types.StepConfig
// For Amazon EMR releases 3.x and 2.x. For Amazon EMR releases 4.x and later, use
// Applications. A list of strings that indicates third-party software to use. For
// more information, see the Amazon EMR Developer Guide (https://docs.aws.amazon.com/emr/latest/DeveloperGuide/emr-dg.pdf)
// . Currently supported values are:
// - "mapr-m3" - launch the job flow using MapR M3 Edition.
// - "mapr-m5" - launch the job flow using MapR M5 Edition.
SupportedProducts []string
// A list of tags to associate with a cluster and propagate to Amazon EC2
// instances.
Tags []types.Tag
// The VisibleToAllUsers parameter is no longer supported. By default, the value
// is set to true . Setting it to false now has no effect. Set this value to true
// so that IAM principals in the Amazon Web Services account associated with the
// cluster can perform Amazon EMR actions on the cluster that their IAM policies
// allow. This value defaults to true for clusters created using the Amazon EMR
// API or the CLI create-cluster (https://docs.aws.amazon.com/cli/latest/reference/emr/create-cluster.html)
// command. When set to false , only the IAM principal that created the cluster and
// the Amazon Web Services account root user can perform Amazon EMR actions for the
// cluster, regardless of the IAM permissions policies attached to other IAM
// principals. For more information, see Understanding the Amazon EMR cluster
// VisibleToAllUsers setting (https://docs.aws.amazon.com/emr/latest/ManagementGuide/security_IAM_emr-with-IAM.html#security_set_visible_to_all_users)
// in the Amazon EMR Management Guide.
VisibleToAllUsers *bool
noSmithyDocumentSerde
}
// The result of the RunJobFlow operation.
type RunJobFlowOutput struct {
// The Amazon Resource Name (ARN) of the cluster.
ClusterArn *string
// A unique identifier for the job flow.
JobFlowId *string
// Metadata pertaining to the operation's result.
ResultMetadata middleware.Metadata
noSmithyDocumentSerde
}
func (c *Client) addOperationRunJobFlowMiddlewares(stack *middleware.Stack, options Options) (err error) {
if err := stack.Serialize.Add(&setOperationInputMiddleware{}, middleware.After); err != nil {
return err
}
err = stack.Serialize.Add(&awsAwsjson11_serializeOpRunJobFlow{}, middleware.After)
if err != nil {
return err
}
err = stack.Deserialize.Add(&awsAwsjson11_deserializeOpRunJobFlow{}, middleware.After)
if err != nil {
return err
}
if err := addProtocolFinalizerMiddlewares(stack, options, "RunJobFlow"); err != nil {
return fmt.Errorf("add protocol finalizers: %v", err)
}
if err = addlegacyEndpointContextSetter(stack, options); err != nil {
return err
}
if err = addSetLoggerMiddleware(stack, options); err != nil {
return err
}
if err = awsmiddleware.AddClientRequestIDMiddleware(stack); err != nil {
return err
}
if err = smithyhttp.AddComputeContentLengthMiddleware(stack); err != nil {
return err
}
if err = addResolveEndpointMiddleware(stack, options); err != nil {
return err
}
if err = v4.AddComputePayloadSHA256Middleware(stack); err != nil {
return err
}
if err = addRetryMiddlewares(stack, options); err != nil {
return err
}
if err = awsmiddleware.AddRawResponseToMetadata(stack); err != nil {
return err
}
if err = awsmiddleware.AddRecordResponseTiming(stack); err != nil {
return err
}
if err = addClientUserAgent(stack, options); err != nil {
return err
}
if err = smithyhttp.AddErrorCloseResponseBodyMiddleware(stack); err != nil {
return err
}
if err = smithyhttp.AddCloseResponseBodyMiddleware(stack); err != nil {
return err
}
if err = addSetLegacyContextSigningOptionsMiddleware(stack); err != nil {
return err
}
if err = addOpRunJobFlowValidationMiddleware(stack); err != nil {
return err
}
if err = stack.Initialize.Add(newServiceMetadataMiddleware_opRunJobFlow(options.Region), middleware.Before); err != nil {
return err
}
if err = awsmiddleware.AddRecursionDetection(stack); err != nil {
return err
}
if err = addRequestIDRetrieverMiddleware(stack); err != nil {
return err
}
if err = addResponseErrorMiddleware(stack); err != nil {
return err
}
if err = addRequestResponseLogging(stack, options); err != nil {
return err
}
if err = addDisableHTTPSMiddleware(stack, options); err != nil {
return err
}
return nil
}
func newServiceMetadataMiddleware_opRunJobFlow(region string) *awsmiddleware.RegisterServiceMetadata {
return &awsmiddleware.RegisterServiceMetadata{
Region: region,
ServiceID: ServiceID,
OperationName: "RunJobFlow",
}
}
|