aws-sdk-glue 1.138.0 → 1.140.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +10 -0
- data/VERSION +1 -1
- data/lib/aws-sdk-glue/client.rb +99 -55
- data/lib/aws-sdk-glue/client_api.rb +2 -0
- data/lib/aws-sdk-glue/types.rb +216 -86
- data/lib/aws-sdk-glue.rb +1 -1
- metadata +4 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 0da8ad2caf540a0d00e14f9b4cd40d0a0ad6773149d6e8f4f37e60105ab36780
|
4
|
+
data.tar.gz: cf31d17c7b19b906e7c54a56deab98ac4d56078b603d446892fb28ccc5ffc5af
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 31857ac560958f529d82839fe46bfe0eb3438291cf1e8a37bca08a37c9c8ef2d2aa96494d37f6d8315d5ef2eccfb8d6aa449c9b4c721ffca2daab16e6ee53480
|
7
|
+
data.tar.gz: bed0eb69137bb27f84e20a3d35b5e57767b63f2338e184d27eb86d2aa85a209633c286565ec919098f7def968e9fc19799601d6dd99c3257382a55de0aabb385
|
data/CHANGELOG.md
CHANGED
@@ -1,6 +1,16 @@
|
|
1
1
|
Unreleased Changes
|
2
2
|
------------------
|
3
3
|
|
4
|
+
1.140.0 (2023-05-31)
|
5
|
+
------------------
|
6
|
+
|
7
|
+
* Feature - Code Generated Changes, see `./build_tools` or `aws-sdk-core`'s CHANGELOG.md for details.
|
8
|
+
|
9
|
+
1.139.0 (2023-05-30)
|
10
|
+
------------------
|
11
|
+
|
12
|
+
* Feature - Added Runtime parameter to allow selection of Ray Runtime
|
13
|
+
|
4
14
|
1.138.0 (2023-05-25)
|
5
15
|
------------------
|
6
16
|
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
1.
|
1
|
+
1.140.0
|
data/lib/aws-sdk-glue/client.rb
CHANGED
@@ -275,6 +275,11 @@ module Aws::Glue
|
|
275
275
|
# in the future.
|
276
276
|
#
|
277
277
|
#
|
278
|
+
# @option options [String] :sdk_ua_app_id
|
279
|
+
# A unique and opaque application ID that is appended to the
|
280
|
+
# User-Agent header as app/<sdk_ua_app_id>. It should have a
|
281
|
+
# maximum length of 50.
|
282
|
+
#
|
278
283
|
# @option options [String] :secret_access_key
|
279
284
|
#
|
280
285
|
# @option options [String] :session_token
|
@@ -960,7 +965,7 @@ module Aws::Glue
|
|
960
965
|
# resp.dev_endpoints[0].zeppelin_remote_spark_interpreter_port #=> Integer
|
961
966
|
# resp.dev_endpoints[0].public_address #=> String
|
962
967
|
# resp.dev_endpoints[0].status #=> String
|
963
|
-
# resp.dev_endpoints[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
968
|
+
# resp.dev_endpoints[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
964
969
|
# resp.dev_endpoints[0].glue_version #=> String
|
965
970
|
# resp.dev_endpoints[0].number_of_workers #=> Integer
|
966
971
|
# resp.dev_endpoints[0].number_of_nodes #=> Integer
|
@@ -1024,6 +1029,7 @@ module Aws::Glue
|
|
1024
1029
|
# resp.jobs[0].command.name #=> String
|
1025
1030
|
# resp.jobs[0].command.script_location #=> String
|
1026
1031
|
# resp.jobs[0].command.python_version #=> String
|
1032
|
+
# resp.jobs[0].command.runtime #=> String
|
1027
1033
|
# resp.jobs[0].default_arguments #=> Hash
|
1028
1034
|
# resp.jobs[0].default_arguments["GenericString"] #=> String
|
1029
1035
|
# resp.jobs[0].non_overridable_arguments #=> Hash
|
@@ -1034,7 +1040,7 @@ module Aws::Glue
|
|
1034
1040
|
# resp.jobs[0].allocated_capacity #=> Integer
|
1035
1041
|
# resp.jobs[0].timeout #=> Integer
|
1036
1042
|
# resp.jobs[0].max_capacity #=> Float
|
1037
|
-
# resp.jobs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
1043
|
+
# resp.jobs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
1038
1044
|
# resp.jobs[0].number_of_workers #=> Integer
|
1039
1045
|
# resp.jobs[0].security_configuration #=> String
|
1040
1046
|
# resp.jobs[0].notification_property.notify_delay_after #=> Integer
|
@@ -2067,7 +2073,7 @@ module Aws::Glue
|
|
2067
2073
|
# resp.workflows[0].last_run.graph.nodes[0].job_details.job_runs[0].execution_time #=> Integer
|
2068
2074
|
# resp.workflows[0].last_run.graph.nodes[0].job_details.job_runs[0].timeout #=> Integer
|
2069
2075
|
# resp.workflows[0].last_run.graph.nodes[0].job_details.job_runs[0].max_capacity #=> Float
|
2070
|
-
# resp.workflows[0].last_run.graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
2076
|
+
# resp.workflows[0].last_run.graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
2071
2077
|
# resp.workflows[0].last_run.graph.nodes[0].job_details.job_runs[0].number_of_workers #=> Integer
|
2072
2078
|
# resp.workflows[0].last_run.graph.nodes[0].job_details.job_runs[0].security_configuration #=> String
|
2073
2079
|
# resp.workflows[0].last_run.graph.nodes[0].job_details.job_runs[0].log_group_name #=> String
|
@@ -2135,7 +2141,7 @@ module Aws::Glue
|
|
2135
2141
|
# resp.workflows[0].graph.nodes[0].job_details.job_runs[0].execution_time #=> Integer
|
2136
2142
|
# resp.workflows[0].graph.nodes[0].job_details.job_runs[0].timeout #=> Integer
|
2137
2143
|
# resp.workflows[0].graph.nodes[0].job_details.job_runs[0].max_capacity #=> Float
|
2138
|
-
# resp.workflows[0].graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
2144
|
+
# resp.workflows[0].graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
2139
2145
|
# resp.workflows[0].graph.nodes[0].job_details.job_runs[0].number_of_workers #=> Integer
|
2140
2146
|
# resp.workflows[0].graph.nodes[0].job_details.job_runs[0].security_configuration #=> String
|
2141
2147
|
# resp.workflows[0].graph.nodes[0].job_details.job_runs[0].log_group_name #=> String
|
@@ -3112,7 +3118,7 @@ module Aws::Glue
|
|
3112
3118
|
# public_key: "GenericString",
|
3113
3119
|
# public_keys: ["GenericString"],
|
3114
3120
|
# number_of_nodes: 1,
|
3115
|
-
# worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X, G.4X, G.8X
|
3121
|
+
# worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X, G.4X, G.8X, Z.2X
|
3116
3122
|
# glue_version: "GlueVersionString",
|
3117
3123
|
# number_of_workers: 1,
|
3118
3124
|
# extra_python_libs_s3_path: "GenericString",
|
@@ -3137,7 +3143,7 @@ module Aws::Glue
|
|
3137
3143
|
# resp.yarn_endpoint_address #=> String
|
3138
3144
|
# resp.zeppelin_remote_spark_interpreter_port #=> Integer
|
3139
3145
|
# resp.number_of_nodes #=> Integer
|
3140
|
-
# resp.worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
3146
|
+
# resp.worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
3141
3147
|
# resp.glue_version #=> String
|
3142
3148
|
# resp.number_of_workers #=> Integer
|
3143
3149
|
# resp.availability_zone #=> String
|
@@ -3183,7 +3189,8 @@ module Aws::Glue
|
|
3183
3189
|
# The `JobCommand` that runs this job.
|
3184
3190
|
#
|
3185
3191
|
# @option params [Hash<String,String>] :default_arguments
|
3186
|
-
# The default arguments for this job
|
3192
|
+
# The default arguments for every run of this job, specified as
|
3193
|
+
# name-value pairs.
|
3187
3194
|
#
|
3188
3195
|
# You can specify arguments here that your own job-execution script
|
3189
3196
|
# consumes, as well as arguments that Glue itself consumes.
|
@@ -3197,17 +3204,23 @@ module Aws::Glue
|
|
3197
3204
|
# arguments, see the [Calling Glue APIs in Python][1] topic in the
|
3198
3205
|
# developer guide.
|
3199
3206
|
#
|
3200
|
-
# For information about the
|
3201
|
-
#
|
3207
|
+
# For information about the arguments you can provide to this field when
|
3208
|
+
# configuring Spark jobs, see the [Special Parameters Used by Glue][2]
|
3209
|
+
# topic in the developer guide.
|
3210
|
+
#
|
3211
|
+
# For information about the arguments you can provide to this field when
|
3212
|
+
# configuring Ray jobs, see [Using job parameters in Ray jobs][3] in the
|
3202
3213
|
# developer guide.
|
3203
3214
|
#
|
3204
3215
|
#
|
3205
3216
|
#
|
3206
3217
|
# [1]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html
|
3207
3218
|
# [2]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
|
3219
|
+
# [3]: https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-job-parameters.html
|
3208
3220
|
#
|
3209
3221
|
# @option params [Hash<String,String>] :non_overridable_arguments
|
3210
|
-
#
|
3222
|
+
# Arguments for this job that are not overridden when providing job
|
3223
|
+
# arguments in a job run, specified as name-value pairs.
|
3211
3224
|
#
|
3212
3225
|
# @option params [Types::ConnectionsList] :connections
|
3213
3226
|
# The connections used for this job.
|
@@ -3238,12 +3251,17 @@ module Aws::Glue
|
|
3238
3251
|
# the number of Glue data processing units (DPUs) that can be allocated
|
3239
3252
|
# when this job runs. A DPU is a relative measure of processing power
|
3240
3253
|
# that consists of 4 vCPUs of compute capacity and 16 GB of memory. For
|
3241
|
-
# more information, see the [Glue pricing page][1].
|
3254
|
+
# more information, see the [ Glue pricing page][1].
|
3242
3255
|
#
|
3243
|
-
#
|
3256
|
+
# For Glue version 2.0+ jobs, you cannot specify a `Maximum capacity`.
|
3257
|
+
# Instead, you should specify a `Worker type` and the `Number of
|
3258
|
+
# workers`.
|
3259
|
+
#
|
3260
|
+
# Do not set `MaxCapacity` if using `WorkerType` and `NumberOfWorkers`.
|
3244
3261
|
#
|
3245
3262
|
# The value that can be allocated for `MaxCapacity` depends on whether
|
3246
|
-
# you are running a Python shell job
|
3263
|
+
# you are running a Python shell job, an Apache Spark ETL job, or an
|
3264
|
+
# Apache Spark streaming ETL job:
|
3247
3265
|
#
|
3248
3266
|
# * When you specify a Python shell job
|
3249
3267
|
# (`JobCommand.Name`="pythonshell"), you can allocate either 0.0625
|
@@ -3251,14 +3269,10 @@ module Aws::Glue
|
|
3251
3269
|
#
|
3252
3270
|
# * When you specify an Apache Spark ETL job
|
3253
3271
|
# (`JobCommand.Name`="glueetl") or Apache Spark streaming ETL job
|
3254
|
-
# (`JobCommand.Name`="gluestreaming"), you can allocate
|
3255
|
-
#
|
3272
|
+
# (`JobCommand.Name`="gluestreaming"), you can allocate from 2 to
|
3273
|
+
# 100 DPUs. The default is 10 DPUs. This job type cannot have a
|
3256
3274
|
# fractional DPU allocation.
|
3257
3275
|
#
|
3258
|
-
# For Glue version 2.0 jobs, you cannot instead specify a `Maximum
|
3259
|
-
# capacity`. Instead, you should specify a `Worker type` and the `Number
|
3260
|
-
# of workers`.
|
3261
|
-
#
|
3262
3276
|
#
|
3263
3277
|
#
|
3264
3278
|
# [1]: https://aws.amazon.com/glue/pricing/
|
@@ -3280,9 +3294,13 @@ module Aws::Glue
|
|
3280
3294
|
# Specifies configuration properties of a job notification.
|
3281
3295
|
#
|
3282
3296
|
# @option params [String] :glue_version
|
3283
|
-
#
|
3284
|
-
# Glue
|
3285
|
-
# jobs of type Spark.
|
3297
|
+
# In Spark jobs, `GlueVersion` determines the versions of Apache Spark
|
3298
|
+
# and Python that Glue available in a job. The Python version indicates
|
3299
|
+
# the version supported for jobs of type Spark.
|
3300
|
+
#
|
3301
|
+
# Ray jobs should set `GlueVersion` to `4.0` or greater. However, the
|
3302
|
+
# versions of Ray, Python and additional libraries available in your Ray
|
3303
|
+
# job are determined by the `Runtime` parameter of the Job command.
|
3286
3304
|
#
|
3287
3305
|
# For more information about the available Glue versions and
|
3288
3306
|
# corresponding Spark and Python versions, see [Glue version][1] in the
|
@@ -3301,7 +3319,8 @@ module Aws::Glue
|
|
3301
3319
|
#
|
3302
3320
|
# @option params [String] :worker_type
|
3303
3321
|
# The type of predefined worker that is allocated when a job runs.
|
3304
|
-
# Accepts a value of Standard, G.1X, G.2X, or G.025X.
|
3322
|
+
# Accepts a value of Standard, G.1X, G.2X, or G.025X for Spark jobs.
|
3323
|
+
# Accepts the value Z.2X for Ray jobs.
|
3305
3324
|
#
|
3306
3325
|
# * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
|
3307
3326
|
# of memory and a 50GB disk, and 2 executors per worker.
|
@@ -3319,6 +3338,10 @@ module Aws::Glue
|
|
3319
3338
|
# recommend this worker type for low volume streaming jobs. This
|
3320
3339
|
# worker type is only available for Glue version 3.0 streaming jobs.
|
3321
3340
|
#
|
3341
|
+
# * For the `Z.2X` worker type, each worker maps to 2 M-DPU (8vCPU, 64
|
3342
|
+
# GB of m emory, 128 GB disk), and provides up to 8 Ray workers based
|
3343
|
+
# on the autoscaler.
|
3344
|
+
#
|
3322
3345
|
# @option params [Hash<String,Types::CodeGenConfigurationNode>] :code_gen_configuration_nodes
|
3323
3346
|
# The representation of a directed acyclic graph on which both the Glue
|
3324
3347
|
# Studio visual component and Glue Studio code generation is based.
|
@@ -3539,7 +3562,7 @@ module Aws::Glue
|
|
3539
3562
|
# role: "RoleString", # required
|
3540
3563
|
# glue_version: "GlueVersionString",
|
3541
3564
|
# max_capacity: 1.0,
|
3542
|
-
# worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X, G.4X, G.8X
|
3565
|
+
# worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X, G.4X, G.8X, Z.2X
|
3543
3566
|
# number_of_workers: 1,
|
3544
3567
|
# timeout: 1,
|
3545
3568
|
# max_retries: 1,
|
@@ -4113,7 +4136,7 @@ module Aws::Glue
|
|
4113
4136
|
# },
|
4114
4137
|
# max_capacity: 1.0,
|
4115
4138
|
# number_of_workers: 1,
|
4116
|
-
# worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X, G.4X, G.8X
|
4139
|
+
# worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X, G.4X, G.8X, Z.2X
|
4117
4140
|
# security_configuration: "NameString",
|
4118
4141
|
# glue_version: "GlueVersionString",
|
4119
4142
|
# tags: {
|
@@ -6638,7 +6661,7 @@ module Aws::Glue
|
|
6638
6661
|
# resp.dev_endpoint.zeppelin_remote_spark_interpreter_port #=> Integer
|
6639
6662
|
# resp.dev_endpoint.public_address #=> String
|
6640
6663
|
# resp.dev_endpoint.status #=> String
|
6641
|
-
# resp.dev_endpoint.worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
6664
|
+
# resp.dev_endpoint.worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
6642
6665
|
# resp.dev_endpoint.glue_version #=> String
|
6643
6666
|
# resp.dev_endpoint.number_of_workers #=> Integer
|
6644
6667
|
# resp.dev_endpoint.number_of_nodes #=> Integer
|
@@ -6709,7 +6732,7 @@ module Aws::Glue
|
|
6709
6732
|
# resp.dev_endpoints[0].zeppelin_remote_spark_interpreter_port #=> Integer
|
6710
6733
|
# resp.dev_endpoints[0].public_address #=> String
|
6711
6734
|
# resp.dev_endpoints[0].status #=> String
|
6712
|
-
# resp.dev_endpoints[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
6735
|
+
# resp.dev_endpoints[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
6713
6736
|
# resp.dev_endpoints[0].glue_version #=> String
|
6714
6737
|
# resp.dev_endpoints[0].number_of_workers #=> Integer
|
6715
6738
|
# resp.dev_endpoints[0].number_of_nodes #=> Integer
|
@@ -6765,6 +6788,7 @@ module Aws::Glue
|
|
6765
6788
|
# resp.job.command.name #=> String
|
6766
6789
|
# resp.job.command.script_location #=> String
|
6767
6790
|
# resp.job.command.python_version #=> String
|
6791
|
+
# resp.job.command.runtime #=> String
|
6768
6792
|
# resp.job.default_arguments #=> Hash
|
6769
6793
|
# resp.job.default_arguments["GenericString"] #=> String
|
6770
6794
|
# resp.job.non_overridable_arguments #=> Hash
|
@@ -6775,7 +6799,7 @@ module Aws::Glue
|
|
6775
6799
|
# resp.job.allocated_capacity #=> Integer
|
6776
6800
|
# resp.job.timeout #=> Integer
|
6777
6801
|
# resp.job.max_capacity #=> Float
|
6778
|
-
# resp.job.worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
6802
|
+
# resp.job.worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
6779
6803
|
# resp.job.number_of_workers #=> Integer
|
6780
6804
|
# resp.job.security_configuration #=> String
|
6781
6805
|
# resp.job.notification_property.notify_delay_after #=> Integer
|
@@ -7646,7 +7670,7 @@ module Aws::Glue
|
|
7646
7670
|
# resp.job_run.execution_time #=> Integer
|
7647
7671
|
# resp.job_run.timeout #=> Integer
|
7648
7672
|
# resp.job_run.max_capacity #=> Float
|
7649
|
-
# resp.job_run.worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
7673
|
+
# resp.job_run.worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
7650
7674
|
# resp.job_run.number_of_workers #=> Integer
|
7651
7675
|
# resp.job_run.security_configuration #=> String
|
7652
7676
|
# resp.job_run.log_group_name #=> String
|
@@ -7712,7 +7736,7 @@ module Aws::Glue
|
|
7712
7736
|
# resp.job_runs[0].execution_time #=> Integer
|
7713
7737
|
# resp.job_runs[0].timeout #=> Integer
|
7714
7738
|
# resp.job_runs[0].max_capacity #=> Float
|
7715
|
-
# resp.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
7739
|
+
# resp.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
7716
7740
|
# resp.job_runs[0].number_of_workers #=> Integer
|
7717
7741
|
# resp.job_runs[0].security_configuration #=> String
|
7718
7742
|
# resp.job_runs[0].log_group_name #=> String
|
@@ -7766,6 +7790,7 @@ module Aws::Glue
|
|
7766
7790
|
# resp.jobs[0].command.name #=> String
|
7767
7791
|
# resp.jobs[0].command.script_location #=> String
|
7768
7792
|
# resp.jobs[0].command.python_version #=> String
|
7793
|
+
# resp.jobs[0].command.runtime #=> String
|
7769
7794
|
# resp.jobs[0].default_arguments #=> Hash
|
7770
7795
|
# resp.jobs[0].default_arguments["GenericString"] #=> String
|
7771
7796
|
# resp.jobs[0].non_overridable_arguments #=> Hash
|
@@ -7776,7 +7801,7 @@ module Aws::Glue
|
|
7776
7801
|
# resp.jobs[0].allocated_capacity #=> Integer
|
7777
7802
|
# resp.jobs[0].timeout #=> Integer
|
7778
7803
|
# resp.jobs[0].max_capacity #=> Float
|
7779
|
-
# resp.jobs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
7804
|
+
# resp.jobs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
7780
7805
|
# resp.jobs[0].number_of_workers #=> Integer
|
7781
7806
|
# resp.jobs[0].security_configuration #=> String
|
7782
7807
|
# resp.jobs[0].notification_property.notify_delay_after #=> Integer
|
@@ -8773,7 +8798,7 @@ module Aws::Glue
|
|
8773
8798
|
# resp.role #=> String
|
8774
8799
|
# resp.glue_version #=> String
|
8775
8800
|
# resp.max_capacity #=> Float
|
8776
|
-
# resp.worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
8801
|
+
# resp.worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
8777
8802
|
# resp.number_of_workers #=> Integer
|
8778
8803
|
# resp.timeout #=> Integer
|
8779
8804
|
# resp.max_retries #=> Integer
|
@@ -8883,7 +8908,7 @@ module Aws::Glue
|
|
8883
8908
|
# resp.transforms[0].role #=> String
|
8884
8909
|
# resp.transforms[0].glue_version #=> String
|
8885
8910
|
# resp.transforms[0].max_capacity #=> Float
|
8886
|
-
# resp.transforms[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
8911
|
+
# resp.transforms[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
8887
8912
|
# resp.transforms[0].number_of_workers #=> Integer
|
8888
8913
|
# resp.transforms[0].timeout #=> Integer
|
8889
8914
|
# resp.transforms[0].max_retries #=> Integer
|
@@ -11249,7 +11274,7 @@ module Aws::Glue
|
|
11249
11274
|
# resp.workflow.last_run.graph.nodes[0].job_details.job_runs[0].execution_time #=> Integer
|
11250
11275
|
# resp.workflow.last_run.graph.nodes[0].job_details.job_runs[0].timeout #=> Integer
|
11251
11276
|
# resp.workflow.last_run.graph.nodes[0].job_details.job_runs[0].max_capacity #=> Float
|
11252
|
-
# resp.workflow.last_run.graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
11277
|
+
# resp.workflow.last_run.graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
11253
11278
|
# resp.workflow.last_run.graph.nodes[0].job_details.job_runs[0].number_of_workers #=> Integer
|
11254
11279
|
# resp.workflow.last_run.graph.nodes[0].job_details.job_runs[0].security_configuration #=> String
|
11255
11280
|
# resp.workflow.last_run.graph.nodes[0].job_details.job_runs[0].log_group_name #=> String
|
@@ -11317,7 +11342,7 @@ module Aws::Glue
|
|
11317
11342
|
# resp.workflow.graph.nodes[0].job_details.job_runs[0].execution_time #=> Integer
|
11318
11343
|
# resp.workflow.graph.nodes[0].job_details.job_runs[0].timeout #=> Integer
|
11319
11344
|
# resp.workflow.graph.nodes[0].job_details.job_runs[0].max_capacity #=> Float
|
11320
|
-
# resp.workflow.graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
11345
|
+
# resp.workflow.graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
11321
11346
|
# resp.workflow.graph.nodes[0].job_details.job_runs[0].number_of_workers #=> Integer
|
11322
11347
|
# resp.workflow.graph.nodes[0].job_details.job_runs[0].security_configuration #=> String
|
11323
11348
|
# resp.workflow.graph.nodes[0].job_details.job_runs[0].log_group_name #=> String
|
@@ -11438,7 +11463,7 @@ module Aws::Glue
|
|
11438
11463
|
# resp.run.graph.nodes[0].job_details.job_runs[0].execution_time #=> Integer
|
11439
11464
|
# resp.run.graph.nodes[0].job_details.job_runs[0].timeout #=> Integer
|
11440
11465
|
# resp.run.graph.nodes[0].job_details.job_runs[0].max_capacity #=> Float
|
11441
|
-
# resp.run.graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
11466
|
+
# resp.run.graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
11442
11467
|
# resp.run.graph.nodes[0].job_details.job_runs[0].number_of_workers #=> Integer
|
11443
11468
|
# resp.run.graph.nodes[0].job_details.job_runs[0].security_configuration #=> String
|
11444
11469
|
# resp.run.graph.nodes[0].job_details.job_runs[0].log_group_name #=> String
|
@@ -11599,7 +11624,7 @@ module Aws::Glue
|
|
11599
11624
|
# resp.runs[0].graph.nodes[0].job_details.job_runs[0].execution_time #=> Integer
|
11600
11625
|
# resp.runs[0].graph.nodes[0].job_details.job_runs[0].timeout #=> Integer
|
11601
11626
|
# resp.runs[0].graph.nodes[0].job_details.job_runs[0].max_capacity #=> Float
|
11602
|
-
# resp.runs[0].graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X"
|
11627
|
+
# resp.runs[0].graph.nodes[0].job_details.job_runs[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X", "G.025X", "G.4X", "G.8X", "Z.2X"
|
11603
11628
|
# resp.runs[0].graph.nodes[0].job_details.job_runs[0].number_of_workers #=> Integer
|
11604
11629
|
# resp.runs[0].graph.nodes[0].job_details.job_runs[0].security_configuration #=> String
|
11605
11630
|
# resp.runs[0].graph.nodes[0].job_details.job_runs[0].log_group_name #=> String
|
@@ -13740,7 +13765,7 @@ module Aws::Glue
|
|
13740
13765
|
# The ID of a previous `JobRun` to retry.
|
13741
13766
|
#
|
13742
13767
|
# @option params [Hash<String,String>] :arguments
|
13743
|
-
# The job arguments
|
13768
|
+
# The job arguments associated with this run. For this job run, they
|
13744
13769
|
# replace the default arguments set in the job definition itself.
|
13745
13770
|
#
|
13746
13771
|
# You can specify arguments here that your own job-execution script
|
@@ -13755,14 +13780,19 @@ module Aws::Glue
|
|
13755
13780
|
# arguments, see the [Calling Glue APIs in Python][1] topic in the
|
13756
13781
|
# developer guide.
|
13757
13782
|
#
|
13758
|
-
# For information about the
|
13759
|
-
#
|
13783
|
+
# For information about the arguments you can provide to this field when
|
13784
|
+
# configuring Spark jobs, see the [Special Parameters Used by Glue][2]
|
13785
|
+
# topic in the developer guide.
|
13786
|
+
#
|
13787
|
+
# For information about the arguments you can provide to this field when
|
13788
|
+
# configuring Ray jobs, see [Using job parameters in Ray jobs][3] in the
|
13760
13789
|
# developer guide.
|
13761
13790
|
#
|
13762
13791
|
#
|
13763
13792
|
#
|
13764
13793
|
# [1]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html
|
13765
13794
|
# [2]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
|
13795
|
+
# [3]: https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-job-parameters.html
|
13766
13796
|
#
|
13767
13797
|
# @option params [Integer] :allocated_capacity
|
13768
13798
|
# This field is deprecated. Use `MaxCapacity` instead.
|
@@ -13786,24 +13816,31 @@ module Aws::Glue
|
|
13786
13816
|
# jobs is 2,880 minutes (48 hours).
|
13787
13817
|
#
|
13788
13818
|
# @option params [Float] :max_capacity
|
13789
|
-
#
|
13819
|
+
# For Glue version 1.0 or earlier jobs, using the standard worker type,
|
13820
|
+
# the number of Glue data processing units (DPUs) that can be allocated
|
13790
13821
|
# when this job runs. A DPU is a relative measure of processing power
|
13791
13822
|
# that consists of 4 vCPUs of compute capacity and 16 GB of memory. For
|
13792
|
-
# more information, see the [Glue pricing page][1].
|
13823
|
+
# more information, see the [ Glue pricing page][1].
|
13824
|
+
#
|
13825
|
+
# For Glue version 2.0+ jobs, you cannot specify a `Maximum capacity`.
|
13826
|
+
# Instead, you should specify a `Worker type` and the `Number of
|
13827
|
+
# workers`.
|
13793
13828
|
#
|
13794
|
-
# Do not set `
|
13829
|
+
# Do not set `MaxCapacity` if using `WorkerType` and `NumberOfWorkers`.
|
13795
13830
|
#
|
13796
13831
|
# The value that can be allocated for `MaxCapacity` depends on whether
|
13797
|
-
# you are running a Python shell job,
|
13832
|
+
# you are running a Python shell job, an Apache Spark ETL job, or an
|
13833
|
+
# Apache Spark streaming ETL job:
|
13798
13834
|
#
|
13799
13835
|
# * When you specify a Python shell job
|
13800
13836
|
# (`JobCommand.Name`="pythonshell"), you can allocate either 0.0625
|
13801
13837
|
# or 1 DPU. The default is 0.0625 DPU.
|
13802
13838
|
#
|
13803
13839
|
# * When you specify an Apache Spark ETL job
|
13804
|
-
# (`JobCommand.Name`="glueetl")
|
13805
|
-
#
|
13806
|
-
#
|
13840
|
+
# (`JobCommand.Name`="glueetl") or Apache Spark streaming ETL job
|
13841
|
+
# (`JobCommand.Name`="gluestreaming"), you can allocate from 2 to
|
13842
|
+
# 100 DPUs. The default is 10 DPUs. This job type cannot have a
|
13843
|
+
# fractional DPU allocation.
|
13807
13844
|
#
|
13808
13845
|
#
|
13809
13846
|
#
|
@@ -13818,22 +13855,29 @@ module Aws::Glue
|
|
13818
13855
|
#
|
13819
13856
|
# @option params [String] :worker_type
|
13820
13857
|
# The type of predefined worker that is allocated when a job runs.
|
13821
|
-
# Accepts a value of Standard, G.1X, G.2X, or G.025X.
|
13858
|
+
# Accepts a value of Standard, G.1X, G.2X, or G.025X for Spark jobs.
|
13859
|
+
# Accepts the value Z.2X for Ray jobs.
|
13822
13860
|
#
|
13823
13861
|
# * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
|
13824
13862
|
# of memory and a 50GB disk, and 2 executors per worker.
|
13825
13863
|
#
|
13826
|
-
# * For the `G.1X` worker type, each worker
|
13827
|
-
# memory
|
13864
|
+
# * For the `G.1X` worker type, each worker maps to 1 DPU (4 vCPU, 16 GB
|
13865
|
+
# of memory, 64 GB disk), and provides 1 executor per worker. We
|
13866
|
+
# recommend this worker type for memory-intensive jobs.
|
13828
13867
|
#
|
13829
|
-
# * For the `G.2X` worker type, each worker
|
13830
|
-
# memory
|
13868
|
+
# * For the `G.2X` worker type, each worker maps to 2 DPU (8 vCPU, 32 GB
|
13869
|
+
# of memory, 128 GB disk), and provides 1 executor per worker. We
|
13870
|
+
# recommend this worker type for memory-intensive jobs.
|
13831
13871
|
#
|
13832
13872
|
# * For the `G.025X` worker type, each worker maps to 0.25 DPU (2 vCPU,
|
13833
13873
|
# 4 GB of memory, 64 GB disk), and provides 1 executor per worker. We
|
13834
13874
|
# recommend this worker type for low volume streaming jobs. This
|
13835
13875
|
# worker type is only available for Glue version 3.0 streaming jobs.
|
13836
13876
|
#
|
13877
|
+
# * For the `Z.2X` worker type, each worker maps to 2 DPU (8vCPU, 64 GB
|
13878
|
+
# of m emory, 128 GB disk), and provides up to 8 Ray workers (one per
|
13879
|
+
# vCPU) based on the autoscaler.
|
13880
|
+
#
|
13837
13881
|
# @option params [Integer] :number_of_workers
|
13838
13882
|
# The number of workers of a defined `workerType` that are allocated
|
13839
13883
|
# when a job runs.
|
@@ -13869,7 +13913,7 @@ module Aws::Glue
|
|
13869
13913
|
# notification_property: {
|
13870
13914
|
# notify_delay_after: 1,
|
13871
13915
|
# },
|
13872
|
-
# worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X, G.4X, G.8X
|
13916
|
+
# worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X, G.4X, G.8X, Z.2X
|
13873
13917
|
# number_of_workers: 1,
|
13874
13918
|
# execution_class: "FLEX", # accepts FLEX, STANDARD
|
13875
13919
|
# })
|
@@ -15195,7 +15239,7 @@ module Aws::Glue
|
|
15195
15239
|
# role: "RoleString",
|
15196
15240
|
# glue_version: "GlueVersionString",
|
15197
15241
|
# max_capacity: 1.0,
|
15198
|
-
# worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X, G.4X, G.8X
|
15242
|
+
# worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X, G.4X, G.8X, Z.2X
|
15199
15243
|
# number_of_workers: 1,
|
15200
15244
|
# timeout: 1,
|
15201
15245
|
# max_retries: 1,
|
@@ -15824,7 +15868,7 @@ module Aws::Glue
|
|
15824
15868
|
params: params,
|
15825
15869
|
config: config)
|
15826
15870
|
context[:gem_name] = 'aws-sdk-glue'
|
15827
|
-
context[:gem_version] = '1.
|
15871
|
+
context[:gem_version] = '1.140.0'
|
15828
15872
|
Seahorse::Client::Request.new(handlers, context)
|
15829
15873
|
end
|
15830
15874
|
|
@@ -881,6 +881,7 @@ module Aws::Glue
|
|
881
881
|
RunId = Shapes::StringShape.new(name: 'RunId')
|
882
882
|
RunStatementRequest = Shapes::StructureShape.new(name: 'RunStatementRequest')
|
883
883
|
RunStatementResponse = Shapes::StructureShape.new(name: 'RunStatementResponse')
|
884
|
+
RuntimeNameString = Shapes::StringShape.new(name: 'RuntimeNameString')
|
884
885
|
S3CatalogDeltaSource = Shapes::StructureShape.new(name: 'S3CatalogDeltaSource')
|
885
886
|
S3CatalogHudiSource = Shapes::StructureShape.new(name: 'S3CatalogHudiSource')
|
886
887
|
S3CatalogSource = Shapes::StructureShape.new(name: 'S3CatalogSource')
|
@@ -3639,6 +3640,7 @@ module Aws::Glue
|
|
3639
3640
|
JobCommand.add_member(:name, Shapes::ShapeRef.new(shape: GenericString, location_name: "Name"))
|
3640
3641
|
JobCommand.add_member(:script_location, Shapes::ShapeRef.new(shape: ScriptLocationString, location_name: "ScriptLocation"))
|
3641
3642
|
JobCommand.add_member(:python_version, Shapes::ShapeRef.new(shape: PythonVersionString, location_name: "PythonVersion"))
|
3643
|
+
JobCommand.add_member(:runtime, Shapes::ShapeRef.new(shape: RuntimeNameString, location_name: "Runtime"))
|
3642
3644
|
JobCommand.struct_class = Types::JobCommand
|
3643
3645
|
|
3644
3646
|
JobList.member = Shapes::ShapeRef.new(shape: Job)
|
data/lib/aws-sdk-glue/types.rb
CHANGED
@@ -4251,7 +4251,8 @@ module Aws::Glue
|
|
4251
4251
|
# @return [Types::JobCommand]
|
4252
4252
|
#
|
4253
4253
|
# @!attribute [rw] default_arguments
|
4254
|
-
# The default arguments for this job
|
4254
|
+
# The default arguments for every run of this job, specified as
|
4255
|
+
# name-value pairs.
|
4255
4256
|
#
|
4256
4257
|
# You can specify arguments here that your own job-execution script
|
4257
4258
|
# consumes, as well as arguments that Glue itself consumes.
|
@@ -4265,19 +4266,24 @@ module Aws::Glue
|
|
4265
4266
|
# arguments, see the [Calling Glue APIs in Python][1] topic in the
|
4266
4267
|
# developer guide.
|
4267
4268
|
#
|
4268
|
-
# For information about the
|
4269
|
-
#
|
4270
|
-
# the developer guide.
|
4269
|
+
# For information about the arguments you can provide to this field
|
4270
|
+
# when configuring Spark jobs, see the [Special Parameters Used by
|
4271
|
+
# Glue][2] topic in the developer guide.
|
4272
|
+
#
|
4273
|
+
# For information about the arguments you can provide to this field
|
4274
|
+
# when configuring Ray jobs, see [Using job parameters in Ray jobs][3]
|
4275
|
+
# in the developer guide.
|
4271
4276
|
#
|
4272
4277
|
#
|
4273
4278
|
#
|
4274
4279
|
# [1]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html
|
4275
4280
|
# [2]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
|
4281
|
+
# [3]: https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-job-parameters.html
|
4276
4282
|
# @return [Hash<String,String>]
|
4277
4283
|
#
|
4278
4284
|
# @!attribute [rw] non_overridable_arguments
|
4279
|
-
#
|
4280
|
-
# pairs.
|
4285
|
+
# Arguments for this job that are not overridden when providing job
|
4286
|
+
# arguments in a job run, specified as name-value pairs.
|
4281
4287
|
# @return [Hash<String,String>]
|
4282
4288
|
#
|
4283
4289
|
# @!attribute [rw] connections
|
@@ -4313,13 +4319,18 @@ module Aws::Glue
|
|
4313
4319
|
# type, the number of Glue data processing units (DPUs) that can be
|
4314
4320
|
# allocated when this job runs. A DPU is a relative measure of
|
4315
4321
|
# processing power that consists of 4 vCPUs of compute capacity and 16
|
4316
|
-
# GB of memory. For more information, see the [Glue pricing page][1].
|
4322
|
+
# GB of memory. For more information, see the [ Glue pricing page][1].
|
4317
4323
|
#
|
4318
|
-
#
|
4324
|
+
# For Glue version 2.0+ jobs, you cannot specify a `Maximum capacity`.
|
4325
|
+
# Instead, you should specify a `Worker type` and the `Number of
|
4326
|
+
# workers`.
|
4327
|
+
#
|
4328
|
+
# Do not set `MaxCapacity` if using `WorkerType` and
|
4319
4329
|
# `NumberOfWorkers`.
|
4320
4330
|
#
|
4321
4331
|
# The value that can be allocated for `MaxCapacity` depends on whether
|
4322
|
-
# you are running a Python shell job
|
4332
|
+
# you are running a Python shell job, an Apache Spark ETL job, or an
|
4333
|
+
# Apache Spark streaming ETL job:
|
4323
4334
|
#
|
4324
4335
|
# * When you specify a Python shell job
|
4325
4336
|
# (`JobCommand.Name`="pythonshell"), you can allocate either
|
@@ -4327,14 +4338,10 @@ module Aws::Glue
|
|
4327
4338
|
#
|
4328
4339
|
# * When you specify an Apache Spark ETL job
|
4329
4340
|
# (`JobCommand.Name`="glueetl") or Apache Spark streaming ETL job
|
4330
|
-
# (`JobCommand.Name`="gluestreaming"), you can allocate
|
4331
|
-
#
|
4341
|
+
# (`JobCommand.Name`="gluestreaming"), you can allocate from 2 to
|
4342
|
+
# 100 DPUs. The default is 10 DPUs. This job type cannot have a
|
4332
4343
|
# fractional DPU allocation.
|
4333
4344
|
#
|
4334
|
-
# For Glue version 2.0 jobs, you cannot instead specify a `Maximum
|
4335
|
-
# capacity`. Instead, you should specify a `Worker type` and the
|
4336
|
-
# `Number of workers`.
|
4337
|
-
#
|
4338
4345
|
#
|
4339
4346
|
#
|
4340
4347
|
# [1]: https://aws.amazon.com/glue/pricing/
|
@@ -4360,9 +4367,14 @@ module Aws::Glue
|
|
4360
4367
|
# @return [Types::NotificationProperty]
|
4361
4368
|
#
|
4362
4369
|
# @!attribute [rw] glue_version
|
4363
|
-
#
|
4364
|
-
# Glue
|
4365
|
-
# for jobs of type Spark.
|
4370
|
+
# In Spark jobs, `GlueVersion` determines the versions of Apache Spark
|
4371
|
+
# and Python that Glue available in a job. The Python version
|
4372
|
+
# indicates the version supported for jobs of type Spark.
|
4373
|
+
#
|
4374
|
+
# Ray jobs should set `GlueVersion` to `4.0` or greater. However, the
|
4375
|
+
# versions of Ray, Python and additional libraries available in your
|
4376
|
+
# Ray job are determined by the `Runtime` parameter of the Job
|
4377
|
+
# command.
|
4366
4378
|
#
|
4367
4379
|
# For more information about the available Glue versions and
|
4368
4380
|
# corresponding Spark and Python versions, see [Glue version][1] in
|
@@ -4383,7 +4395,8 @@ module Aws::Glue
|
|
4383
4395
|
#
|
4384
4396
|
# @!attribute [rw] worker_type
|
4385
4397
|
# The type of predefined worker that is allocated when a job runs.
|
4386
|
-
# Accepts a value of Standard, G.1X, G.2X, or G.025X.
|
4398
|
+
# Accepts a value of Standard, G.1X, G.2X, or G.025X for Spark jobs.
|
4399
|
+
# Accepts the value Z.2X for Ray jobs.
|
4387
4400
|
#
|
4388
4401
|
# * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
|
4389
4402
|
# of memory and a 50GB disk, and 2 executors per worker.
|
@@ -4401,6 +4414,10 @@ module Aws::Glue
|
|
4401
4414
|
# worker. We recommend this worker type for low volume streaming
|
4402
4415
|
# jobs. This worker type is only available for Glue version 3.0
|
4403
4416
|
# streaming jobs.
|
4417
|
+
#
|
4418
|
+
# * For the `Z.2X` worker type, each worker maps to 2 M-DPU (8vCPU, 64
|
4419
|
+
# GB of m emory, 128 GB disk), and provides up to 8 Ray workers
|
4420
|
+
# based on the autoscaler.
|
4404
4421
|
# @return [String]
|
4405
4422
|
#
|
4406
4423
|
# @!attribute [rw] code_gen_configuration_nodes
|
@@ -12165,28 +12182,39 @@ module Aws::Glue
|
|
12165
12182
|
# @return [Types::JobCommand]
|
12166
12183
|
#
|
12167
12184
|
# @!attribute [rw] default_arguments
|
12168
|
-
# The default arguments for this job, specified as
|
12185
|
+
# The default arguments for every run of this job, specified as
|
12186
|
+
# name-value pairs.
|
12169
12187
|
#
|
12170
12188
|
# You can specify arguments here that your own job-execution script
|
12171
12189
|
# consumes, as well as arguments that Glue itself consumes.
|
12172
12190
|
#
|
12191
|
+
# Job arguments may be logged. Do not pass plaintext secrets as
|
12192
|
+
# arguments. Retrieve secrets from a Glue Connection, Secrets Manager
|
12193
|
+
# or other secret management mechanism if you intend to keep them
|
12194
|
+
# within the Job.
|
12195
|
+
#
|
12173
12196
|
# For information about how to specify and consume your own Job
|
12174
12197
|
# arguments, see the [Calling Glue APIs in Python][1] topic in the
|
12175
12198
|
# developer guide.
|
12176
12199
|
#
|
12177
|
-
# For information about the
|
12178
|
-
#
|
12179
|
-
# the developer guide.
|
12200
|
+
# For information about the arguments you can provide to this field
|
12201
|
+
# when configuring Spark jobs, see the [Special Parameters Used by
|
12202
|
+
# Glue][2] topic in the developer guide.
|
12203
|
+
#
|
12204
|
+
# For information about the arguments you can provide to this field
|
12205
|
+
# when configuring Ray jobs, see [Using job parameters in Ray jobs][3]
|
12206
|
+
# in the developer guide.
|
12180
12207
|
#
|
12181
12208
|
#
|
12182
12209
|
#
|
12183
12210
|
# [1]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html
|
12184
12211
|
# [2]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
|
12212
|
+
# [3]: https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-job-parameters.html
|
12185
12213
|
# @return [Hash<String,String>]
|
12186
12214
|
#
|
12187
12215
|
# @!attribute [rw] non_overridable_arguments
|
12188
|
-
#
|
12189
|
-
# pairs.
|
12216
|
+
# Arguments for this job that are not overridden when providing job
|
12217
|
+
# arguments in a job run, specified as name-value pairs.
|
12190
12218
|
# @return [Hash<String,String>]
|
12191
12219
|
#
|
12192
12220
|
# @!attribute [rw] connections
|
@@ -12224,7 +12252,7 @@ module Aws::Glue
|
|
12224
12252
|
# type, the number of Glue data processing units (DPUs) that can be
|
12225
12253
|
# allocated when this job runs. A DPU is a relative measure of
|
12226
12254
|
# processing power that consists of 4 vCPUs of compute capacity and 16
|
12227
|
-
# GB of memory. For more information, see the [Glue pricing page][1].
|
12255
|
+
# GB of memory. For more information, see the [ Glue pricing page][1].
|
12228
12256
|
#
|
12229
12257
|
# For Glue version 2.0 or later jobs, you cannot specify a `Maximum
|
12230
12258
|
# capacity`. Instead, you should specify a `Worker type` and the
|
@@ -12254,7 +12282,8 @@ module Aws::Glue
|
|
12254
12282
|
#
|
12255
12283
|
# @!attribute [rw] worker_type
|
12256
12284
|
# The type of predefined worker that is allocated when a job runs.
|
12257
|
-
# Accepts a value of Standard, G.1X, G.2X, or G.025X
|
12285
|
+
# Accepts a value of Standard, G.1X, G.2X, G.4X, G.8X, or G.025X for
|
12286
|
+
# Spark jobs. Accepts the value Z.2X for Ray jobs.
|
12258
12287
|
#
|
12259
12288
|
# * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
|
12260
12289
|
# of memory and a 50GB disk, and 2 executors per worker.
|
@@ -12275,20 +12304,30 @@ module Aws::Glue
|
|
12275
12304
|
# GB of memory, 256 GB disk), and provides 1 executor per worker. We
|
12276
12305
|
# recommend this worker type for jobs whose workloads contain your
|
12277
12306
|
# most demanding transforms, aggregations, joins, and queries. This
|
12278
|
-
# worker type is available only for Glue version 3.0 or later
|
12307
|
+
# worker type is available only for Glue version 3.0 or later Spark
|
12308
|
+
# ETL jobs in the following Amazon Web Services Regions: US East
|
12309
|
+
# (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific
|
12310
|
+
# (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada
|
12311
|
+
# (Central), Europe (Frankfurt), Europe (Ireland), and Europe
|
12312
|
+
# (Stockholm).
|
12279
12313
|
#
|
12280
12314
|
# * For the `G.8X` worker type, each worker maps to 8 DPU (32 vCPU,
|
12281
12315
|
# 128 GB of memory, 512 GB disk), and provides 1 executor per
|
12282
12316
|
# worker. We recommend this worker type for jobs whose workloads
|
12283
12317
|
# contain your most demanding transforms, aggregations, joins, and
|
12284
12318
|
# queries. This worker type is available only for Glue version 3.0
|
12285
|
-
# or later jobs
|
12319
|
+
# or later Spark ETL jobs, in the same Amazon Web Services Regions
|
12320
|
+
# as supported for the `G.4X` worker type.
|
12286
12321
|
#
|
12287
12322
|
# * For the `G.025X` worker type, each worker maps to 0.25 DPU (2
|
12288
12323
|
# vCPU, 4 GB of memory, 64 GB disk), and provides 1 executor per
|
12289
12324
|
# worker. We recommend this worker type for low volume streaming
|
12290
12325
|
# jobs. This worker type is only available for Glue version 3.0
|
12291
12326
|
# streaming jobs.
|
12327
|
+
#
|
12328
|
+
# * For the `Z.2X` worker type, each worker maps to 2 M-DPU (8vCPU, 64
|
12329
|
+
# GB of m emory, 128 GB disk), and provides a default of 8 Ray
|
12330
|
+
# workers (1 per vCPU).
|
12292
12331
|
# @return [String]
|
12293
12332
|
#
|
12294
12333
|
# @!attribute [rw] number_of_workers
|
@@ -12306,9 +12345,14 @@ module Aws::Glue
|
|
12306
12345
|
# @return [Types::NotificationProperty]
|
12307
12346
|
#
|
12308
12347
|
# @!attribute [rw] glue_version
|
12309
|
-
#
|
12310
|
-
# Glue
|
12311
|
-
# for jobs of type Spark.
|
12348
|
+
# In Spark jobs, `GlueVersion` determines the versions of Apache Spark
|
12349
|
+
# and Python that Glue available in a job. The Python version
|
12350
|
+
# indicates the version supported for jobs of type Spark.
|
12351
|
+
#
|
12352
|
+
# Ray jobs should set `GlueVersion` to `4.0` or greater. However, the
|
12353
|
+
# versions of Ray, Python and additional libraries available in your
|
12354
|
+
# Ray job are determined by the `Runtime` parameter of the Job
|
12355
|
+
# command.
|
12312
12356
|
#
|
12313
12357
|
# For more information about the available Glue versions and
|
12314
12358
|
# corresponding Spark and Python versions, see [Glue version][1] in
|
@@ -12446,7 +12490,8 @@ module Aws::Glue
|
|
12446
12490
|
# @!attribute [rw] name
|
12447
12491
|
# The name of the job command. For an Apache Spark ETL job, this must
|
12448
12492
|
# be `glueetl`. For a Python shell job, it must be `pythonshell`. For
|
12449
|
-
# an Apache Spark streaming ETL job, this must be `gluestreaming`.
|
12493
|
+
# an Apache Spark streaming ETL job, this must be `gluestreaming`. For
|
12494
|
+
# a Ray job, this must be `glueray`.
|
12450
12495
|
# @return [String]
|
12451
12496
|
#
|
12452
12497
|
# @!attribute [rw] script_location
|
@@ -12459,12 +12504,24 @@ module Aws::Glue
|
|
12459
12504
|
# values are 2 or 3.
|
12460
12505
|
# @return [String]
|
12461
12506
|
#
|
12507
|
+
# @!attribute [rw] runtime
|
12508
|
+
# In Ray jobs, Runtime is used to specify the versions of Ray, Python
|
12509
|
+
# and additional libraries available in your environment. This field
|
12510
|
+
# is not used in other job types. For supported runtime environment
|
12511
|
+
# values, see [Working with Ray jobs][1] in the Glue Developer Guide.
|
12512
|
+
#
|
12513
|
+
#
|
12514
|
+
#
|
12515
|
+
# [1]: https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-runtimes.html
|
12516
|
+
# @return [String]
|
12517
|
+
#
|
12462
12518
|
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/JobCommand AWS API Documentation
|
12463
12519
|
#
|
12464
12520
|
class JobCommand < Struct.new(
|
12465
12521
|
:name,
|
12466
12522
|
:script_location,
|
12467
|
-
:python_version
|
12523
|
+
:python_version,
|
12524
|
+
:runtime)
|
12468
12525
|
SENSITIVE = []
|
12469
12526
|
include Aws::Structure
|
12470
12527
|
end
|
@@ -12535,18 +12592,28 @@ module Aws::Glue
|
|
12535
12592
|
# You can specify arguments here that your own job-execution script
|
12536
12593
|
# consumes, as well as arguments that Glue itself consumes.
|
12537
12594
|
#
|
12538
|
-
#
|
12595
|
+
# Job arguments may be logged. Do not pass plaintext secrets as
|
12596
|
+
# arguments. Retrieve secrets from a Glue Connection, Secrets Manager
|
12597
|
+
# or other secret management mechanism if you intend to keep them
|
12598
|
+
# within the Job.
|
12599
|
+
#
|
12600
|
+
# For information about how to specify and consume your own Job
|
12539
12601
|
# arguments, see the [Calling Glue APIs in Python][1] topic in the
|
12540
12602
|
# developer guide.
|
12541
12603
|
#
|
12542
|
-
# For information about the
|
12543
|
-
#
|
12544
|
-
# the developer guide.
|
12604
|
+
# For information about the arguments you can provide to this field
|
12605
|
+
# when configuring Spark jobs, see the [Special Parameters Used by
|
12606
|
+
# Glue][2] topic in the developer guide.
|
12607
|
+
#
|
12608
|
+
# For information about the arguments you can provide to this field
|
12609
|
+
# when configuring Ray jobs, see [Using job parameters in Ray jobs][3]
|
12610
|
+
# in the developer guide.
|
12545
12611
|
#
|
12546
12612
|
#
|
12547
12613
|
#
|
12548
12614
|
# [1]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html
|
12549
12615
|
# [2]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
|
12616
|
+
# [3]: https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-job-parameters.html
|
12550
12617
|
# @return [Hash<String,String>]
|
12551
12618
|
#
|
12552
12619
|
# @!attribute [rw] error_message
|
@@ -12586,24 +12653,31 @@ module Aws::Glue
|
|
12586
12653
|
# @return [Integer]
|
12587
12654
|
#
|
12588
12655
|
# @!attribute [rw] max_capacity
|
12589
|
-
#
|
12656
|
+
# For Glue version 1.0 or earlier jobs, using the standard worker
|
12657
|
+
# type, the number of Glue data processing units (DPUs) that can be
|
12590
12658
|
# allocated when this job runs. A DPU is a relative measure of
|
12591
12659
|
# processing power that consists of 4 vCPUs of compute capacity and 16
|
12592
|
-
# GB of memory. For more information, see the [Glue pricing page][1].
|
12660
|
+
# GB of memory. For more information, see the [ Glue pricing page][1].
|
12661
|
+
#
|
12662
|
+
# For Glue version 2.0+ jobs, you cannot specify a `Maximum capacity`.
|
12663
|
+
# Instead, you should specify a `Worker type` and the `Number of
|
12664
|
+
# workers`.
|
12593
12665
|
#
|
12594
|
-
# Do not set `
|
12666
|
+
# Do not set `MaxCapacity` if using `WorkerType` and
|
12595
12667
|
# `NumberOfWorkers`.
|
12596
12668
|
#
|
12597
12669
|
# The value that can be allocated for `MaxCapacity` depends on whether
|
12598
|
-
# you are running a Python shell job
|
12670
|
+
# you are running a Python shell job, an Apache Spark ETL job, or an
|
12671
|
+
# Apache Spark streaming ETL job:
|
12599
12672
|
#
|
12600
12673
|
# * When you specify a Python shell job
|
12601
12674
|
# (`JobCommand.Name`="pythonshell"), you can allocate either
|
12602
12675
|
# 0.0625 or 1 DPU. The default is 0.0625 DPU.
|
12603
12676
|
#
|
12604
12677
|
# * When you specify an Apache Spark ETL job
|
12605
|
-
# (`JobCommand.Name`="glueetl")
|
12606
|
-
#
|
12678
|
+
# (`JobCommand.Name`="glueetl") or Apache Spark streaming ETL job
|
12679
|
+
# (`JobCommand.Name`="gluestreaming"), you can allocate from 2 to
|
12680
|
+
# 100 DPUs. The default is 10 DPUs. This job type cannot have a
|
12607
12681
|
# fractional DPU allocation.
|
12608
12682
|
#
|
12609
12683
|
#
|
@@ -12613,22 +12687,29 @@ module Aws::Glue
|
|
12613
12687
|
#
|
12614
12688
|
# @!attribute [rw] worker_type
|
12615
12689
|
# The type of predefined worker that is allocated when a job runs.
|
12616
|
-
# Accepts a value of Standard, G.1X, G.2X, or G.025X.
|
12690
|
+
# Accepts a value of Standard, G.1X, G.2X, or G.025X for Spark jobs.
|
12691
|
+
# Accepts the value Z.2X for Ray jobs.
|
12617
12692
|
#
|
12618
12693
|
# * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
|
12619
12694
|
# of memory and a 50GB disk, and 2 executors per worker.
|
12620
12695
|
#
|
12621
|
-
# * For the `G.1X` worker type, each worker
|
12622
|
-
# memory
|
12696
|
+
# * For the `G.1X` worker type, each worker maps to 1 DPU (4 vCPU, 16
|
12697
|
+
# GB of memory, 64 GB disk), and provides 1 executor per worker. We
|
12698
|
+
# recommend this worker type for memory-intensive jobs.
|
12623
12699
|
#
|
12624
|
-
# * For the `G.2X` worker type, each worker
|
12625
|
-
# memory
|
12700
|
+
# * For the `G.2X` worker type, each worker maps to 2 DPU (8 vCPU, 32
|
12701
|
+
# GB of memory, 128 GB disk), and provides 1 executor per worker. We
|
12702
|
+
# recommend this worker type for memory-intensive jobs.
|
12626
12703
|
#
|
12627
12704
|
# * For the `G.025X` worker type, each worker maps to 0.25 DPU (2
|
12628
12705
|
# vCPU, 4 GB of memory, 64 GB disk), and provides 1 executor per
|
12629
12706
|
# worker. We recommend this worker type for low volume streaming
|
12630
12707
|
# jobs. This worker type is only available for Glue version 3.0
|
12631
12708
|
# streaming jobs.
|
12709
|
+
#
|
12710
|
+
# * For the `Z.2X` worker type, each worker maps to 2 M-DPU (8vCPU, 64
|
12711
|
+
# GB of m emory, 128 GB disk), and provides up to 8 Ray workers (one
|
12712
|
+
# per vCPU) based on the autoscaler.
|
12632
12713
|
# @return [String]
|
12633
12714
|
#
|
12634
12715
|
# @!attribute [rw] number_of_workers
|
@@ -12656,9 +12737,14 @@ module Aws::Glue
|
|
12656
12737
|
# @return [Types::NotificationProperty]
|
12657
12738
|
#
|
12658
12739
|
# @!attribute [rw] glue_version
|
12659
|
-
#
|
12660
|
-
# Glue
|
12661
|
-
# for jobs of type Spark.
|
12740
|
+
# In Spark jobs, `GlueVersion` determines the versions of Apache Spark
|
12741
|
+
# and Python that Glue available in a job. The Python version
|
12742
|
+
# indicates the version supported for jobs of type Spark.
|
12743
|
+
#
|
12744
|
+
# Ray jobs should set `GlueVersion` to `4.0` or greater. However, the
|
12745
|
+
# versions of Ray, Python and additional libraries available in your
|
12746
|
+
# Ray job are determined by the `Runtime` parameter of the Job
|
12747
|
+
# command.
|
12662
12748
|
#
|
12663
12749
|
# For more information about the available Glue versions and
|
12664
12750
|
# corresponding Spark and Python versions, see [Glue version][1] in
|
@@ -12755,28 +12841,39 @@ module Aws::Glue
|
|
12755
12841
|
# @return [Types::JobCommand]
|
12756
12842
|
#
|
12757
12843
|
# @!attribute [rw] default_arguments
|
12758
|
-
# The default arguments for this job
|
12844
|
+
# The default arguments for every run of this job, specified as
|
12845
|
+
# name-value pairs.
|
12759
12846
|
#
|
12760
12847
|
# You can specify arguments here that your own job-execution script
|
12761
12848
|
# consumes, as well as arguments that Glue itself consumes.
|
12762
12849
|
#
|
12850
|
+
# Job arguments may be logged. Do not pass plaintext secrets as
|
12851
|
+
# arguments. Retrieve secrets from a Glue Connection, Secrets Manager
|
12852
|
+
# or other secret management mechanism if you intend to keep them
|
12853
|
+
# within the Job.
|
12854
|
+
#
|
12763
12855
|
# For information about how to specify and consume your own Job
|
12764
12856
|
# arguments, see the [Calling Glue APIs in Python][1] topic in the
|
12765
12857
|
# developer guide.
|
12766
12858
|
#
|
12767
|
-
# For information about the
|
12768
|
-
#
|
12769
|
-
# the developer guide.
|
12859
|
+
# For information about the arguments you can provide to this field
|
12860
|
+
# when configuring Spark jobs, see the [Special Parameters Used by
|
12861
|
+
# Glue][2] topic in the developer guide.
|
12862
|
+
#
|
12863
|
+
# For information about the arguments you can provide to this field
|
12864
|
+
# when configuring Ray jobs, see [Using job parameters in Ray jobs][3]
|
12865
|
+
# in the developer guide.
|
12770
12866
|
#
|
12771
12867
|
#
|
12772
12868
|
#
|
12773
12869
|
# [1]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html
|
12774
12870
|
# [2]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
|
12871
|
+
# [3]: https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-job-parameters.html
|
12775
12872
|
# @return [Hash<String,String>]
|
12776
12873
|
#
|
12777
12874
|
# @!attribute [rw] non_overridable_arguments
|
12778
|
-
#
|
12779
|
-
# pairs.
|
12875
|
+
# Arguments for this job that are not overridden when providing job
|
12876
|
+
# arguments in a job run, specified as name-value pairs.
|
12780
12877
|
# @return [Hash<String,String>]
|
12781
12878
|
#
|
12782
12879
|
# @!attribute [rw] connections
|
@@ -12812,13 +12909,18 @@ module Aws::Glue
|
|
12812
12909
|
# type, the number of Glue data processing units (DPUs) that can be
|
12813
12910
|
# allocated when this job runs. A DPU is a relative measure of
|
12814
12911
|
# processing power that consists of 4 vCPUs of compute capacity and 16
|
12815
|
-
# GB of memory. For more information, see the [Glue pricing page][1].
|
12912
|
+
# GB of memory. For more information, see the [ Glue pricing page][1].
|
12913
|
+
#
|
12914
|
+
# For Glue version 2.0+ jobs, you cannot specify a `Maximum capacity`.
|
12915
|
+
# Instead, you should specify a `Worker type` and the `Number of
|
12916
|
+
# workers`.
|
12816
12917
|
#
|
12817
|
-
# Do not set `
|
12918
|
+
# Do not set `MaxCapacity` if using `WorkerType` and
|
12818
12919
|
# `NumberOfWorkers`.
|
12819
12920
|
#
|
12820
12921
|
# The value that can be allocated for `MaxCapacity` depends on whether
|
12821
|
-
# you are running a Python shell job
|
12922
|
+
# you are running a Python shell job, an Apache Spark ETL job, or an
|
12923
|
+
# Apache Spark streaming ETL job:
|
12822
12924
|
#
|
12823
12925
|
# * When you specify a Python shell job
|
12824
12926
|
# (`JobCommand.Name`="pythonshell"), you can allocate either
|
@@ -12826,14 +12928,10 @@ module Aws::Glue
|
|
12826
12928
|
#
|
12827
12929
|
# * When you specify an Apache Spark ETL job
|
12828
12930
|
# (`JobCommand.Name`="glueetl") or Apache Spark streaming ETL job
|
12829
|
-
# (`JobCommand.Name`="gluestreaming"), you can allocate
|
12830
|
-
#
|
12931
|
+
# (`JobCommand.Name`="gluestreaming"), you can allocate from 2 to
|
12932
|
+
# 100 DPUs. The default is 10 DPUs. This job type cannot have a
|
12831
12933
|
# fractional DPU allocation.
|
12832
12934
|
#
|
12833
|
-
# For Glue version 2.0 jobs, you cannot instead specify a `Maximum
|
12834
|
-
# capacity`. Instead, you should specify a `Worker type` and the
|
12835
|
-
# `Number of workers`.
|
12836
|
-
#
|
12837
12935
|
#
|
12838
12936
|
#
|
12839
12937
|
# [1]: https://aws.amazon.com/glue/pricing/
|
@@ -12841,7 +12939,8 @@ module Aws::Glue
|
|
12841
12939
|
#
|
12842
12940
|
# @!attribute [rw] worker_type
|
12843
12941
|
# The type of predefined worker that is allocated when a job runs.
|
12844
|
-
# Accepts a value of Standard, G.1X, G.2X, or G.025X.
|
12942
|
+
# Accepts a value of Standard, G.1X, G.2X, or G.025X for Spark jobs.
|
12943
|
+
# Accepts the value Z.2X for Ray jobs.
|
12845
12944
|
#
|
12846
12945
|
# * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
|
12847
12946
|
# of memory and a 50GB disk, and 2 executors per worker.
|
@@ -12859,6 +12958,10 @@ module Aws::Glue
|
|
12859
12958
|
# worker. We recommend this worker type for low volume streaming
|
12860
12959
|
# jobs. This worker type is only available for Glue version 3.0
|
12861
12960
|
# streaming jobs.
|
12961
|
+
#
|
12962
|
+
# * For the `Z.2X` worker type, each worker maps to 2 M-DPU (8vCPU, 64
|
12963
|
+
# GB of m emory, 128 GB disk), and provides up to 8 Ray workers
|
12964
|
+
# based on the autoscaler.
|
12862
12965
|
# @return [String]
|
12863
12966
|
#
|
12864
12967
|
# @!attribute [rw] number_of_workers
|
@@ -12876,14 +12979,22 @@ module Aws::Glue
|
|
12876
12979
|
# @return [Types::NotificationProperty]
|
12877
12980
|
#
|
12878
12981
|
# @!attribute [rw] glue_version
|
12879
|
-
#
|
12880
|
-
# Glue
|
12881
|
-
# for jobs of type Spark.
|
12982
|
+
# In Spark jobs, `GlueVersion` determines the versions of Apache Spark
|
12983
|
+
# and Python that Glue available in a job. The Python version
|
12984
|
+
# indicates the version supported for jobs of type Spark.
|
12985
|
+
#
|
12986
|
+
# Ray jobs should set `GlueVersion` to `4.0` or greater. However, the
|
12987
|
+
# versions of Ray, Python and additional libraries available in your
|
12988
|
+
# Ray job are determined by the `Runtime` parameter of the Job
|
12989
|
+
# command.
|
12882
12990
|
#
|
12883
12991
|
# For more information about the available Glue versions and
|
12884
12992
|
# corresponding Spark and Python versions, see [Glue version][1] in
|
12885
12993
|
# the developer guide.
|
12886
12994
|
#
|
12995
|
+
# Jobs that are created without specifying a Glue version default to
|
12996
|
+
# Glue 0.9.
|
12997
|
+
#
|
12887
12998
|
#
|
12888
12999
|
#
|
12889
13000
|
# [1]: https://docs.aws.amazon.com/glue/latest/dg/add-job.html
|
@@ -18340,7 +18451,7 @@ module Aws::Glue
|
|
18340
18451
|
# @return [String]
|
18341
18452
|
#
|
18342
18453
|
# @!attribute [rw] arguments
|
18343
|
-
# The job arguments
|
18454
|
+
# The job arguments associated with this run. For this job run, they
|
18344
18455
|
# replace the default arguments set in the job definition itself.
|
18345
18456
|
#
|
18346
18457
|
# You can specify arguments here that your own job-execution script
|
@@ -18355,14 +18466,19 @@ module Aws::Glue
|
|
18355
18466
|
# arguments, see the [Calling Glue APIs in Python][1] topic in the
|
18356
18467
|
# developer guide.
|
18357
18468
|
#
|
18358
|
-
# For information about the
|
18359
|
-
#
|
18360
|
-
# the developer guide.
|
18469
|
+
# For information about the arguments you can provide to this field
|
18470
|
+
# when configuring Spark jobs, see the [Special Parameters Used by
|
18471
|
+
# Glue][2] topic in the developer guide.
|
18472
|
+
#
|
18473
|
+
# For information about the arguments you can provide to this field
|
18474
|
+
# when configuring Ray jobs, see [Using job parameters in Ray jobs][3]
|
18475
|
+
# in the developer guide.
|
18361
18476
|
#
|
18362
18477
|
#
|
18363
18478
|
#
|
18364
18479
|
# [1]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html
|
18365
18480
|
# [2]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
|
18481
|
+
# [3]: https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-job-parameters.html
|
18366
18482
|
# @return [Hash<String,String>]
|
18367
18483
|
#
|
18368
18484
|
# @!attribute [rw] allocated_capacity
|
@@ -18390,24 +18506,31 @@ module Aws::Glue
|
|
18390
18506
|
# @return [Integer]
|
18391
18507
|
#
|
18392
18508
|
# @!attribute [rw] max_capacity
|
18393
|
-
#
|
18509
|
+
# For Glue version 1.0 or earlier jobs, using the standard worker
|
18510
|
+
# type, the number of Glue data processing units (DPUs) that can be
|
18394
18511
|
# allocated when this job runs. A DPU is a relative measure of
|
18395
18512
|
# processing power that consists of 4 vCPUs of compute capacity and 16
|
18396
|
-
# GB of memory. For more information, see the [Glue pricing page][1].
|
18513
|
+
# GB of memory. For more information, see the [ Glue pricing page][1].
|
18397
18514
|
#
|
18398
|
-
#
|
18515
|
+
# For Glue version 2.0+ jobs, you cannot specify a `Maximum capacity`.
|
18516
|
+
# Instead, you should specify a `Worker type` and the `Number of
|
18517
|
+
# workers`.
|
18518
|
+
#
|
18519
|
+
# Do not set `MaxCapacity` if using `WorkerType` and
|
18399
18520
|
# `NumberOfWorkers`.
|
18400
18521
|
#
|
18401
18522
|
# The value that can be allocated for `MaxCapacity` depends on whether
|
18402
|
-
# you are running a Python shell job,
|
18523
|
+
# you are running a Python shell job, an Apache Spark ETL job, or an
|
18524
|
+
# Apache Spark streaming ETL job:
|
18403
18525
|
#
|
18404
18526
|
# * When you specify a Python shell job
|
18405
18527
|
# (`JobCommand.Name`="pythonshell"), you can allocate either
|
18406
18528
|
# 0.0625 or 1 DPU. The default is 0.0625 DPU.
|
18407
18529
|
#
|
18408
18530
|
# * When you specify an Apache Spark ETL job
|
18409
|
-
# (`JobCommand.Name`="glueetl")
|
18410
|
-
#
|
18531
|
+
# (`JobCommand.Name`="glueetl") or Apache Spark streaming ETL job
|
18532
|
+
# (`JobCommand.Name`="gluestreaming"), you can allocate from 2 to
|
18533
|
+
# 100 DPUs. The default is 10 DPUs. This job type cannot have a
|
18411
18534
|
# fractional DPU allocation.
|
18412
18535
|
#
|
18413
18536
|
#
|
@@ -18426,22 +18549,29 @@ module Aws::Glue
|
|
18426
18549
|
#
|
18427
18550
|
# @!attribute [rw] worker_type
|
18428
18551
|
# The type of predefined worker that is allocated when a job runs.
|
18429
|
-
# Accepts a value of Standard, G.1X, G.2X, or G.025X.
|
18552
|
+
# Accepts a value of Standard, G.1X, G.2X, or G.025X for Spark jobs.
|
18553
|
+
# Accepts the value Z.2X for Ray jobs.
|
18430
18554
|
#
|
18431
18555
|
# * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
|
18432
18556
|
# of memory and a 50GB disk, and 2 executors per worker.
|
18433
18557
|
#
|
18434
|
-
# * For the `G.1X` worker type, each worker
|
18435
|
-
# memory
|
18558
|
+
# * For the `G.1X` worker type, each worker maps to 1 DPU (4 vCPU, 16
|
18559
|
+
# GB of memory, 64 GB disk), and provides 1 executor per worker. We
|
18560
|
+
# recommend this worker type for memory-intensive jobs.
|
18436
18561
|
#
|
18437
|
-
# * For the `G.2X` worker type, each worker
|
18438
|
-
# memory
|
18562
|
+
# * For the `G.2X` worker type, each worker maps to 2 DPU (8 vCPU, 32
|
18563
|
+
# GB of memory, 128 GB disk), and provides 1 executor per worker. We
|
18564
|
+
# recommend this worker type for memory-intensive jobs.
|
18439
18565
|
#
|
18440
18566
|
# * For the `G.025X` worker type, each worker maps to 0.25 DPU (2
|
18441
18567
|
# vCPU, 4 GB of memory, 64 GB disk), and provides 1 executor per
|
18442
18568
|
# worker. We recommend this worker type for low volume streaming
|
18443
18569
|
# jobs. This worker type is only available for Glue version 3.0
|
18444
18570
|
# streaming jobs.
|
18571
|
+
#
|
18572
|
+
# * For the `Z.2X` worker type, each worker maps to 2 DPU (8vCPU, 64
|
18573
|
+
# GB of m emory, 128 GB disk), and provides up to 8 Ray workers (one
|
18574
|
+
# per vCPU) based on the autoscaler.
|
18445
18575
|
# @return [String]
|
18446
18576
|
#
|
18447
18577
|
# @!attribute [rw] number_of_workers
|
data/lib/aws-sdk-glue.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: aws-sdk-glue
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.140.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Amazon Web Services
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2023-05-
|
11
|
+
date: 2023-05-31 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: aws-sdk-core
|
@@ -19,7 +19,7 @@ dependencies:
|
|
19
19
|
version: '3'
|
20
20
|
- - ">="
|
21
21
|
- !ruby/object:Gem::Version
|
22
|
-
version: 3.
|
22
|
+
version: 3.174.0
|
23
23
|
type: :runtime
|
24
24
|
prerelease: false
|
25
25
|
version_requirements: !ruby/object:Gem::Requirement
|
@@ -29,7 +29,7 @@ dependencies:
|
|
29
29
|
version: '3'
|
30
30
|
- - ">="
|
31
31
|
- !ruby/object:Gem::Version
|
32
|
-
version: 3.
|
32
|
+
version: 3.174.0
|
33
33
|
- !ruby/object:Gem::Dependency
|
34
34
|
name: aws-sigv4
|
35
35
|
requirement: !ruby/object:Gem::Requirement
|