Clean and regen docs (#401)
diff --git a/docs/dyn/dataflow_v1b3.projects.jobs.html b/docs/dyn/dataflow_v1b3.projects.jobs.html
index cf4b668..596aac6 100644
--- a/docs/dyn/dataflow_v1b3.projects.jobs.html
+++ b/docs/dyn/dataflow_v1b3.projects.jobs.html
@@ -141,10 +141,21 @@
#
# The name must match the regular expression
# `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
- "currentStateTime": "A String", # The timestamp associated with the current state.
+ "location": "A String", # The location that contains this job.
"replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
# `JOB_STATE_UPDATED`), this field contains the ID of that job.
"projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
+ "currentState": "A String", # The current state of the job.
+ #
+ # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+ # specified.
+ #
+ # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+ # terminal state. After a job has reached a terminal state, no
+ # further state updates may be made.
+ #
+ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
"labels": { # User-defined labels for this job.
#
# The labels map can contain no more than 64 entries. Entries of the labels
@@ -156,13 +167,14 @@
# size.
"a_key": "A String",
},
- "location": "A String", # The location that contains this job.
- "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
- # Cloud Dataflow service.
"transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
# corresponding name prefixes of the new job.
"a_key": "A String",
},
+ "id": "A String", # The unique ID of this job.
+ #
+ # This field is set by the Cloud Dataflow service when the Job is
+ # created, and is immutable for the life of the job.
"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
"version": { # A structure describing which components and their versions of the service
# are required in order to run the job.
@@ -216,49 +228,6 @@
# multiple pools, in order to match the various computational
# requirements of the various stages of the job.
"diskSourceImage": "A String", # Fully qualified source image for disks.
- "ipConfiguration": "A String", # Configuration for VM IPs.
- "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
- # are supported.
- "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
- # service will attempt to choose a reasonable default.
- "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
- # the service will use the network "default".
- "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
- # will attempt to choose a reasonable default.
- "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
- "metadata": { # Metadata to set on the Google Compute Engine VMs.
- "a_key": "A String",
- },
- "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
- # Compute Engine API.
- "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
- # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
- # `TEARDOWN_NEVER`.
- # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
- # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
- # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
- # down.
- #
- # If the workers are not torn down by the service, they will
- # continue to run and use Google Compute Engine VM resources in the
- # user's project until they are explicitly terminated by the user.
- # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
- # policy except for small, manually supervised test jobs.
- #
- # If unknown or unspecified, the service will attempt to choose a reasonable
- # default.
- "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
- # service will choose a number of threads (according to the number of cores
- # on the selected machine type for batch, or 1 by convention for streaming).
- "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
- # the form "regions/REGION/subnetworks/SUBNETWORK".
- "poolArgs": { # Extra arguments for this worker pool.
- "a_key": "", # Properties of the object. Contains field @type with type URL.
- },
- "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
- # execute the job. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
# using the standard Dataflow task runner. Users should ignore
# this field.
@@ -271,17 +240,7 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
- "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "root".
"commandlinesFileName": "A String", # The file to store preprocessing commands in.
- "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
- "vmId": "A String", # The ID string of the VM.
- "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
- "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
- "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
- # access the Cloud Dataflow API.
- "A String",
- ],
"parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
"reportingEnabled": True or False, # Whether to send work progress updates to the service.
"shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
@@ -308,14 +267,15 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
},
- "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "wheel".
- "languageHint": "A String", # The suggested backend language.
- "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
- # console.
- "streamingWorkerMainClass": "A String", # The streaming worker main class name.
- "logDir": "A String", # The directory on the VM to store logs.
- "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
+ "vmId": "A String", # The ID string of the VM.
+ "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
+ "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
+ "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
+ # access the Cloud Dataflow API.
+ "A String",
+ ],
+ "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "root".
"baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
#
# When workers access Google Cloud APIs, they logically do so via
@@ -325,6 +285,14 @@
# Locators".
#
# If not specified, the default value is "http://www.googleapis.com/"
+ "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "wheel".
+ "languageHint": "A String", # The suggested backend language.
+ "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+ # console.
+ "streamingWorkerMainClass": "A String", # The streaming worker main class name.
+ "logDir": "A String", # The directory on the VM to store logs.
+ "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
"harnessCommand": "A String", # The command to launch the worker harness.
"tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
# temporary storage.
@@ -334,33 +302,18 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
+ "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
},
- "defaultPackageSet": "A String", # The default package set to install. This allows the service to
- # select a default set of packages which are useful to worker
- # harnesses written in a particular language.
- "packages": [ # Packages to be installed on workers.
- { # The packages that must be installed in order for a worker to run the
- # steps of the Cloud Dataflow job that will be assigned to its worker
- # pool.
- #
- # This is the mechanism by which the Cloud Dataflow SDK causes code to
- # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
- # might use this to install jars containing the user's code and all of the
- # various dependencies (libraries, data files, etc.) required in order
- # for that code to run.
- "name": "A String", # The name of the package.
- "location": "A String", # The resource to read the package from. The supported resource type is:
- #
- # Google Cloud Storage:
- #
- # storage.googleapis.com/{bucket}
- # bucket.storage.googleapis.com/
- },
- ],
- "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
- "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
- "algorithm": "A String", # The algorithm to use for autoscaling.
- },
+ "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
+ # are supported.
+ "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
+ # service will attempt to choose a reasonable default.
+ "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
+ # the service will use the network "default".
+ "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
+ # will attempt to choose a reasonable default.
+ "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
+ # attempt to choose a reasonable default.
"dataDisks": [ # Data disks that are used by a VM in this workflow.
{ # Describes the data disk used by a workflow job.
"mountPoint": "A String", # Directory in a VM where disk is mounted.
@@ -386,10 +339,69 @@
# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
},
],
- "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
+ # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+ # `TEARDOWN_NEVER`.
+ # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+ # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+ # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+ # down.
+ #
+ # If the workers are not torn down by the service, they will
+ # continue to run and use Google Compute Engine VM resources in the
+ # user's project until they are explicitly terminated by the user.
+ # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+ # policy except for small, manually supervised test jobs.
+ #
+ # If unknown or unspecified, the service will attempt to choose a reasonable
+ # default.
+ "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
+ # Compute Engine API.
+ "ipConfiguration": "A String", # Configuration for VM IPs.
+ "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
+ # service will choose a number of threads (according to the number of cores
+ # on the selected machine type for batch, or 1 by convention for streaming).
+ "poolArgs": { # Extra arguments for this worker pool.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
+ # execute the job. If zero or unspecified, the service will
# attempt to choose a reasonable default.
"workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
# harness, residing in Google Container Registry.
+ "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
+ # the form "regions/REGION/subnetworks/SUBNETWORK".
+ "packages": [ # Packages to be installed on workers.
+ { # The packages that must be installed in order for a worker to run the
+ # steps of the Cloud Dataflow job that will be assigned to its worker
+ # pool.
+ #
+ # This is the mechanism by which the Cloud Dataflow SDK causes code to
+ # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+ # might use this to install jars containing the user's code and all of the
+ # various dependencies (libraries, data files, etc.) required in order
+ # for that code to run.
+ "location": "A String", # The resource to read the package from. The supported resource type is:
+ #
+ # Google Cloud Storage:
+ #
+ # storage.googleapis.com/{bucket}
+ # bucket.storage.googleapis.com/
+ "name": "A String", # The name of the package.
+ },
+ ],
+ "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+ "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
+ "algorithm": "A String", # The algorithm to use for autoscaling.
+ },
+ "defaultPackageSet": "A String", # The default package set to install. This allows the service to
+ # select a default set of packages which are useful to worker
+ # harnesses written in a particular language.
+ "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ # attempt to choose a reasonable default.
+ "metadata": { # Metadata to set on the Google Compute Engine VMs.
+ "a_key": "A String",
+ },
},
],
},
@@ -408,16 +420,13 @@
],
"displayData": [ # Transform-specific display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -428,8 +437,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"outputCollectionName": [ # User names for all collection outputs to this transform.
@@ -440,16 +452,13 @@
],
"displayData": [ # Pipeline level display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -460,8 +469,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"executionPipelineStage": [ # Description of each stage of execution of the pipeline.
@@ -545,17 +557,7 @@
# step with respect to all other steps in the Cloud Dataflow job.
},
],
- "currentState": "A String", # The current state of the job.
- #
- # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
- # specified.
- #
- # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
- # terminal state. After a job has reached a terminal state, no
- # further state updates may be made.
- #
- # This field may be mutated by the Cloud Dataflow service;
- # callers cannot mutate it.
+ "currentStateTime": "A String", # The timestamp associated with the current state.
"tempFiles": [ # A set of files the system should be aware of that are used
# for temporary storage. These temporary files will be
# removed on job completion.
@@ -570,11 +572,17 @@
# bucket.storage.googleapis.com/{object}
"A String",
],
+ "stageStates": [ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
+ { # A message describing the state of a particular execution stage.
+ "executionStageName": "A String", # The name of the execution stage.
+ "executionStageState": "A String", # Executions stage states allow the same set of values as JobState.
+ "currentStateTime": "A String", # The time at which the stage transitioned to this state.
+ },
+ ],
"type": "A String", # The type of Cloud Dataflow job.
- "id": "A String", # The unique ID of this job.
- #
- # This field is set by the Cloud Dataflow service when the Job is
- # created, and is immutable for the life of the job.
+ "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
+ # Cloud Dataflow service.
"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
# of the job it replaced.
#
@@ -631,10 +639,21 @@
#
# The name must match the regular expression
# `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
- "currentStateTime": "A String", # The timestamp associated with the current state.
+ "location": "A String", # The location that contains this job.
"replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
# `JOB_STATE_UPDATED`), this field contains the ID of that job.
"projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
+ "currentState": "A String", # The current state of the job.
+ #
+ # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+ # specified.
+ #
+ # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+ # terminal state. After a job has reached a terminal state, no
+ # further state updates may be made.
+ #
+ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
"labels": { # User-defined labels for this job.
#
# The labels map can contain no more than 64 entries. Entries of the labels
@@ -646,13 +665,14 @@
# size.
"a_key": "A String",
},
- "location": "A String", # The location that contains this job.
- "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
- # Cloud Dataflow service.
"transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
# corresponding name prefixes of the new job.
"a_key": "A String",
},
+ "id": "A String", # The unique ID of this job.
+ #
+ # This field is set by the Cloud Dataflow service when the Job is
+ # created, and is immutable for the life of the job.
"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
"version": { # A structure describing which components and their versions of the service
# are required in order to run the job.
@@ -706,49 +726,6 @@
# multiple pools, in order to match the various computational
# requirements of the various stages of the job.
"diskSourceImage": "A String", # Fully qualified source image for disks.
- "ipConfiguration": "A String", # Configuration for VM IPs.
- "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
- # are supported.
- "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
- # service will attempt to choose a reasonable default.
- "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
- # the service will use the network "default".
- "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
- # will attempt to choose a reasonable default.
- "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
- "metadata": { # Metadata to set on the Google Compute Engine VMs.
- "a_key": "A String",
- },
- "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
- # Compute Engine API.
- "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
- # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
- # `TEARDOWN_NEVER`.
- # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
- # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
- # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
- # down.
- #
- # If the workers are not torn down by the service, they will
- # continue to run and use Google Compute Engine VM resources in the
- # user's project until they are explicitly terminated by the user.
- # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
- # policy except for small, manually supervised test jobs.
- #
- # If unknown or unspecified, the service will attempt to choose a reasonable
- # default.
- "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
- # service will choose a number of threads (according to the number of cores
- # on the selected machine type for batch, or 1 by convention for streaming).
- "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
- # the form "regions/REGION/subnetworks/SUBNETWORK".
- "poolArgs": { # Extra arguments for this worker pool.
- "a_key": "", # Properties of the object. Contains field @type with type URL.
- },
- "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
- # execute the job. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
# using the standard Dataflow task runner. Users should ignore
# this field.
@@ -761,17 +738,7 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
- "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "root".
"commandlinesFileName": "A String", # The file to store preprocessing commands in.
- "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
- "vmId": "A String", # The ID string of the VM.
- "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
- "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
- "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
- # access the Cloud Dataflow API.
- "A String",
- ],
"parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
"reportingEnabled": True or False, # Whether to send work progress updates to the service.
"shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
@@ -798,14 +765,15 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
},
- "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "wheel".
- "languageHint": "A String", # The suggested backend language.
- "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
- # console.
- "streamingWorkerMainClass": "A String", # The streaming worker main class name.
- "logDir": "A String", # The directory on the VM to store logs.
- "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
+ "vmId": "A String", # The ID string of the VM.
+ "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
+ "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
+ "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
+ # access the Cloud Dataflow API.
+ "A String",
+ ],
+ "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "root".
"baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
#
# When workers access Google Cloud APIs, they logically do so via
@@ -815,6 +783,14 @@
# Locators".
#
# If not specified, the default value is "http://www.googleapis.com/"
+ "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "wheel".
+ "languageHint": "A String", # The suggested backend language.
+ "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+ # console.
+ "streamingWorkerMainClass": "A String", # The streaming worker main class name.
+ "logDir": "A String", # The directory on the VM to store logs.
+ "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
"harnessCommand": "A String", # The command to launch the worker harness.
"tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
# temporary storage.
@@ -824,33 +800,18 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
+ "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
},
- "defaultPackageSet": "A String", # The default package set to install. This allows the service to
- # select a default set of packages which are useful to worker
- # harnesses written in a particular language.
- "packages": [ # Packages to be installed on workers.
- { # The packages that must be installed in order for a worker to run the
- # steps of the Cloud Dataflow job that will be assigned to its worker
- # pool.
- #
- # This is the mechanism by which the Cloud Dataflow SDK causes code to
- # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
- # might use this to install jars containing the user's code and all of the
- # various dependencies (libraries, data files, etc.) required in order
- # for that code to run.
- "name": "A String", # The name of the package.
- "location": "A String", # The resource to read the package from. The supported resource type is:
- #
- # Google Cloud Storage:
- #
- # storage.googleapis.com/{bucket}
- # bucket.storage.googleapis.com/
- },
- ],
- "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
- "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
- "algorithm": "A String", # The algorithm to use for autoscaling.
- },
+ "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
+ # are supported.
+ "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
+ # service will attempt to choose a reasonable default.
+ "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
+ # the service will use the network "default".
+ "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
+ # will attempt to choose a reasonable default.
+ "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
+ # attempt to choose a reasonable default.
"dataDisks": [ # Data disks that are used by a VM in this workflow.
{ # Describes the data disk used by a workflow job.
"mountPoint": "A String", # Directory in a VM where disk is mounted.
@@ -876,10 +837,69 @@
# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
},
],
- "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
+ # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+ # `TEARDOWN_NEVER`.
+ # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+ # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+ # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+ # down.
+ #
+ # If the workers are not torn down by the service, they will
+ # continue to run and use Google Compute Engine VM resources in the
+ # user's project until they are explicitly terminated by the user.
+ # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+ # policy except for small, manually supervised test jobs.
+ #
+ # If unknown or unspecified, the service will attempt to choose a reasonable
+ # default.
+ "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
+ # Compute Engine API.
+ "ipConfiguration": "A String", # Configuration for VM IPs.
+ "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
+ # service will choose a number of threads (according to the number of cores
+ # on the selected machine type for batch, or 1 by convention for streaming).
+ "poolArgs": { # Extra arguments for this worker pool.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
+ # execute the job. If zero or unspecified, the service will
# attempt to choose a reasonable default.
"workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
# harness, residing in Google Container Registry.
+ "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
+ # the form "regions/REGION/subnetworks/SUBNETWORK".
+ "packages": [ # Packages to be installed on workers.
+ { # The packages that must be installed in order for a worker to run the
+ # steps of the Cloud Dataflow job that will be assigned to its worker
+ # pool.
+ #
+ # This is the mechanism by which the Cloud Dataflow SDK causes code to
+ # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+ # might use this to install jars containing the user's code and all of the
+ # various dependencies (libraries, data files, etc.) required in order
+ # for that code to run.
+ "location": "A String", # The resource to read the package from. The supported resource type is:
+ #
+ # Google Cloud Storage:
+ #
+ # storage.googleapis.com/{bucket}
+ # bucket.storage.googleapis.com/
+ "name": "A String", # The name of the package.
+ },
+ ],
+ "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+ "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
+ "algorithm": "A String", # The algorithm to use for autoscaling.
+ },
+ "defaultPackageSet": "A String", # The default package set to install. This allows the service to
+ # select a default set of packages which are useful to worker
+ # harnesses written in a particular language.
+ "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ # attempt to choose a reasonable default.
+ "metadata": { # Metadata to set on the Google Compute Engine VMs.
+ "a_key": "A String",
+ },
},
],
},
@@ -898,16 +918,13 @@
],
"displayData": [ # Transform-specific display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -918,8 +935,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"outputCollectionName": [ # User names for all collection outputs to this transform.
@@ -930,16 +950,13 @@
],
"displayData": [ # Pipeline level display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -950,8 +967,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"executionPipelineStage": [ # Description of each stage of execution of the pipeline.
@@ -1035,17 +1055,7 @@
# step with respect to all other steps in the Cloud Dataflow job.
},
],
- "currentState": "A String", # The current state of the job.
- #
- # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
- # specified.
- #
- # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
- # terminal state. After a job has reached a terminal state, no
- # further state updates may be made.
- #
- # This field may be mutated by the Cloud Dataflow service;
- # callers cannot mutate it.
+ "currentStateTime": "A String", # The timestamp associated with the current state.
"tempFiles": [ # A set of files the system should be aware of that are used
# for temporary storage. These temporary files will be
# removed on job completion.
@@ -1060,11 +1070,17 @@
# bucket.storage.googleapis.com/{object}
"A String",
],
+ "stageStates": [ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
+ { # A message describing the state of a particular execution stage.
+ "executionStageName": "A String", # The name of the execution stage.
+ "executionStageState": "A String", # Executions stage states allow the same set of values as JobState.
+ "currentStateTime": "A String", # The time at which the stage transitioned to this state.
+ },
+ ],
"type": "A String", # The type of Cloud Dataflow job.
- "id": "A String", # The unique ID of this job.
- #
- # This field is set by the Cloud Dataflow service when the Job is
- # created, and is immutable for the life of the job.
+ "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
+ # Cloud Dataflow service.
"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
# of the job it replaced.
#
@@ -1128,10 +1144,21 @@
#
# The name must match the regular expression
# `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
- "currentStateTime": "A String", # The timestamp associated with the current state.
+ "location": "A String", # The location that contains this job.
"replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
# `JOB_STATE_UPDATED`), this field contains the ID of that job.
"projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
+ "currentState": "A String", # The current state of the job.
+ #
+ # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+ # specified.
+ #
+ # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+ # terminal state. After a job has reached a terminal state, no
+ # further state updates may be made.
+ #
+ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
"labels": { # User-defined labels for this job.
#
# The labels map can contain no more than 64 entries. Entries of the labels
@@ -1143,13 +1170,14 @@
# size.
"a_key": "A String",
},
- "location": "A String", # The location that contains this job.
- "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
- # Cloud Dataflow service.
"transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
# corresponding name prefixes of the new job.
"a_key": "A String",
},
+ "id": "A String", # The unique ID of this job.
+ #
+ # This field is set by the Cloud Dataflow service when the Job is
+ # created, and is immutable for the life of the job.
"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
"version": { # A structure describing which components and their versions of the service
# are required in order to run the job.
@@ -1203,49 +1231,6 @@
# multiple pools, in order to match the various computational
# requirements of the various stages of the job.
"diskSourceImage": "A String", # Fully qualified source image for disks.
- "ipConfiguration": "A String", # Configuration for VM IPs.
- "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
- # are supported.
- "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
- # service will attempt to choose a reasonable default.
- "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
- # the service will use the network "default".
- "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
- # will attempt to choose a reasonable default.
- "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
- "metadata": { # Metadata to set on the Google Compute Engine VMs.
- "a_key": "A String",
- },
- "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
- # Compute Engine API.
- "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
- # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
- # `TEARDOWN_NEVER`.
- # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
- # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
- # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
- # down.
- #
- # If the workers are not torn down by the service, they will
- # continue to run and use Google Compute Engine VM resources in the
- # user's project until they are explicitly terminated by the user.
- # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
- # policy except for small, manually supervised test jobs.
- #
- # If unknown or unspecified, the service will attempt to choose a reasonable
- # default.
- "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
- # service will choose a number of threads (according to the number of cores
- # on the selected machine type for batch, or 1 by convention for streaming).
- "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
- # the form "regions/REGION/subnetworks/SUBNETWORK".
- "poolArgs": { # Extra arguments for this worker pool.
- "a_key": "", # Properties of the object. Contains field @type with type URL.
- },
- "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
- # execute the job. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
# using the standard Dataflow task runner. Users should ignore
# this field.
@@ -1258,17 +1243,7 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
- "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "root".
"commandlinesFileName": "A String", # The file to store preprocessing commands in.
- "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
- "vmId": "A String", # The ID string of the VM.
- "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
- "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
- "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
- # access the Cloud Dataflow API.
- "A String",
- ],
"parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
"reportingEnabled": True or False, # Whether to send work progress updates to the service.
"shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
@@ -1295,14 +1270,15 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
},
- "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "wheel".
- "languageHint": "A String", # The suggested backend language.
- "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
- # console.
- "streamingWorkerMainClass": "A String", # The streaming worker main class name.
- "logDir": "A String", # The directory on the VM to store logs.
- "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
+ "vmId": "A String", # The ID string of the VM.
+ "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
+ "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
+ "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
+ # access the Cloud Dataflow API.
+ "A String",
+ ],
+ "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "root".
"baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
#
# When workers access Google Cloud APIs, they logically do so via
@@ -1312,6 +1288,14 @@
# Locators".
#
# If not specified, the default value is "http://www.googleapis.com/"
+ "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "wheel".
+ "languageHint": "A String", # The suggested backend language.
+ "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+ # console.
+ "streamingWorkerMainClass": "A String", # The streaming worker main class name.
+ "logDir": "A String", # The directory on the VM to store logs.
+ "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
"harnessCommand": "A String", # The command to launch the worker harness.
"tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
# temporary storage.
@@ -1321,33 +1305,18 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
+ "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
},
- "defaultPackageSet": "A String", # The default package set to install. This allows the service to
- # select a default set of packages which are useful to worker
- # harnesses written in a particular language.
- "packages": [ # Packages to be installed on workers.
- { # The packages that must be installed in order for a worker to run the
- # steps of the Cloud Dataflow job that will be assigned to its worker
- # pool.
- #
- # This is the mechanism by which the Cloud Dataflow SDK causes code to
- # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
- # might use this to install jars containing the user's code and all of the
- # various dependencies (libraries, data files, etc.) required in order
- # for that code to run.
- "name": "A String", # The name of the package.
- "location": "A String", # The resource to read the package from. The supported resource type is:
- #
- # Google Cloud Storage:
- #
- # storage.googleapis.com/{bucket}
- # bucket.storage.googleapis.com/
- },
- ],
- "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
- "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
- "algorithm": "A String", # The algorithm to use for autoscaling.
- },
+ "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
+ # are supported.
+ "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
+ # service will attempt to choose a reasonable default.
+ "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
+ # the service will use the network "default".
+ "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
+ # will attempt to choose a reasonable default.
+ "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
+ # attempt to choose a reasonable default.
"dataDisks": [ # Data disks that are used by a VM in this workflow.
{ # Describes the data disk used by a workflow job.
"mountPoint": "A String", # Directory in a VM where disk is mounted.
@@ -1373,10 +1342,69 @@
# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
},
],
- "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
+ # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+ # `TEARDOWN_NEVER`.
+ # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+ # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+ # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+ # down.
+ #
+ # If the workers are not torn down by the service, they will
+ # continue to run and use Google Compute Engine VM resources in the
+ # user's project until they are explicitly terminated by the user.
+ # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+ # policy except for small, manually supervised test jobs.
+ #
+ # If unknown or unspecified, the service will attempt to choose a reasonable
+ # default.
+ "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
+ # Compute Engine API.
+ "ipConfiguration": "A String", # Configuration for VM IPs.
+ "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
+ # service will choose a number of threads (according to the number of cores
+ # on the selected machine type for batch, or 1 by convention for streaming).
+ "poolArgs": { # Extra arguments for this worker pool.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
+ # execute the job. If zero or unspecified, the service will
# attempt to choose a reasonable default.
"workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
# harness, residing in Google Container Registry.
+ "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
+ # the form "regions/REGION/subnetworks/SUBNETWORK".
+ "packages": [ # Packages to be installed on workers.
+ { # The packages that must be installed in order for a worker to run the
+ # steps of the Cloud Dataflow job that will be assigned to its worker
+ # pool.
+ #
+ # This is the mechanism by which the Cloud Dataflow SDK causes code to
+ # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+ # might use this to install jars containing the user's code and all of the
+ # various dependencies (libraries, data files, etc.) required in order
+ # for that code to run.
+ "location": "A String", # The resource to read the package from. The supported resource type is:
+ #
+ # Google Cloud Storage:
+ #
+ # storage.googleapis.com/{bucket}
+ # bucket.storage.googleapis.com/
+ "name": "A String", # The name of the package.
+ },
+ ],
+ "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+ "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
+ "algorithm": "A String", # The algorithm to use for autoscaling.
+ },
+ "defaultPackageSet": "A String", # The default package set to install. This allows the service to
+ # select a default set of packages which are useful to worker
+ # harnesses written in a particular language.
+ "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ # attempt to choose a reasonable default.
+ "metadata": { # Metadata to set on the Google Compute Engine VMs.
+ "a_key": "A String",
+ },
},
],
},
@@ -1395,16 +1423,13 @@
],
"displayData": [ # Transform-specific display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -1415,8 +1440,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"outputCollectionName": [ # User names for all collection outputs to this transform.
@@ -1427,16 +1455,13 @@
],
"displayData": [ # Pipeline level display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -1447,8 +1472,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"executionPipelineStage": [ # Description of each stage of execution of the pipeline.
@@ -1532,17 +1560,7 @@
# step with respect to all other steps in the Cloud Dataflow job.
},
],
- "currentState": "A String", # The current state of the job.
- #
- # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
- # specified.
- #
- # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
- # terminal state. After a job has reached a terminal state, no
- # further state updates may be made.
- #
- # This field may be mutated by the Cloud Dataflow service;
- # callers cannot mutate it.
+ "currentStateTime": "A String", # The timestamp associated with the current state.
"tempFiles": [ # A set of files the system should be aware of that are used
# for temporary storage. These temporary files will be
# removed on job completion.
@@ -1557,11 +1575,17 @@
# bucket.storage.googleapis.com/{object}
"A String",
],
+ "stageStates": [ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
+ { # A message describing the state of a particular execution stage.
+ "executionStageName": "A String", # The name of the execution stage.
+ "executionStageState": "A String", # Executions stage states allow the same set of values as JobState.
+ "currentStateTime": "A String", # The time at which the stage transitioned to this state.
+ },
+ ],
"type": "A String", # The type of Cloud Dataflow job.
- "id": "A String", # The unique ID of this job.
- #
- # This field is set by the Cloud Dataflow service when the Job is
- # created, and is immutable for the life of the job.
+ "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
+ # Cloud Dataflow service.
"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
# of the job it replaced.
#
@@ -1615,12 +1639,9 @@
# This holds the count of the aggregated values and is used in combination
# with mean_sum above to obtain the actual mean aggregate value.
# The only possible value type is Long.
- "kind": "A String", # Metric aggregation kind. The possible metric aggregation kinds are
- # "Sum", "Max", "Min", "Mean", "Set", "And", and "Or".
- # The specified aggregation kind is case-insensitive.
- #
- # If omitted, this is not an aggregated value but instead
- # a single metric sample value.
+ "updateTime": "A String", # Timestamp associated with the metric value. Optional when workers are
+ # reporting work progress; it will be filled in responses from the
+ # metrics API.
"set": "", # Worker-computed aggregate value for the "Set" aggregation kind. The only
# possible value type is a list of Values whose type can be Long, Double,
# or String, according to the metric's type. All Values in the list must
@@ -1639,19 +1660,23 @@
"a_key": "A String",
},
},
- "meanSum": "", # Worker-computed aggregate value for the "Mean" aggregation kind.
- # This holds the sum of the aggregated values and is used in combination
- # with mean_count below to obtain the actual mean aggregate value.
- # The only possible value types are Long and Double.
"cumulative": True or False, # True if this metric is reported as the total cumulative aggregate
# value accumulated since the worker started working on this WorkItem.
# By default this is false, indicating that this metric is reported
# as a delta that is not associated with any WorkItem.
- "updateTime": "A String", # Timestamp associated with the metric value. Optional when workers are
- # reporting work progress; it will be filled in responses from the
- # metrics API.
+ "kind": "A String", # Metric aggregation kind. The possible metric aggregation kinds are
+ # "Sum", "Max", "Min", "Mean", "Set", "And", "Or", and "Distribution".
+ # The specified aggregation kind is case-insensitive.
+ #
+ # If omitted, this is not an aggregated value but instead
+ # a single metric sample value.
"scalar": "", # Worker-computed aggregate value for aggregation kinds "Sum", "Max", "Min",
# "And", and "Or". The possible value types are Long, Double, and Boolean.
+ "meanSum": "", # Worker-computed aggregate value for the "Mean" aggregation kind.
+ # This holds the sum of the aggregated values and is used in combination
+ # with mean_count below to obtain the actual mean aggregate value.
+ # The only possible value types are Long and Double.
+ "distribution": "", # A struct value describing properties of a distribution of numeric values.
"internal": "", # Worker-computed aggregate value for internal use by the Dataflow
# service.
},
@@ -1685,6 +1710,11 @@
{ # Response to a request to list Cloud Dataflow jobs. This may be a partial
# response, depending on the page size in the ListJobsRequest.
"nextPageToken": "A String", # Set if there may be more results than fit in this response.
+ "failedLocation": [ # Zero or more messages describing locations that failed to respond.
+ { # Indicates which location failed to respond to a request for data.
+ "name": "A String", # The name of the failed location.
+ },
+ ],
"jobs": [ # A subset of the requested job information.
{ # Defines a job to be run by the Cloud Dataflow service.
"clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts.
@@ -1710,10 +1740,21 @@
#
# The name must match the regular expression
# `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
- "currentStateTime": "A String", # The timestamp associated with the current state.
+ "location": "A String", # The location that contains this job.
"replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
# `JOB_STATE_UPDATED`), this field contains the ID of that job.
"projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
+ "currentState": "A String", # The current state of the job.
+ #
+ # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+ # specified.
+ #
+ # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+ # terminal state. After a job has reached a terminal state, no
+ # further state updates may be made.
+ #
+ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
"labels": { # User-defined labels for this job.
#
# The labels map can contain no more than 64 entries. Entries of the labels
@@ -1725,13 +1766,14 @@
# size.
"a_key": "A String",
},
- "location": "A String", # The location that contains this job.
- "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
- # Cloud Dataflow service.
"transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
# corresponding name prefixes of the new job.
"a_key": "A String",
},
+ "id": "A String", # The unique ID of this job.
+ #
+ # This field is set by the Cloud Dataflow service when the Job is
+ # created, and is immutable for the life of the job.
"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
"version": { # A structure describing which components and their versions of the service
# are required in order to run the job.
@@ -1785,49 +1827,6 @@
# multiple pools, in order to match the various computational
# requirements of the various stages of the job.
"diskSourceImage": "A String", # Fully qualified source image for disks.
- "ipConfiguration": "A String", # Configuration for VM IPs.
- "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
- # are supported.
- "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
- # service will attempt to choose a reasonable default.
- "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
- # the service will use the network "default".
- "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
- # will attempt to choose a reasonable default.
- "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
- "metadata": { # Metadata to set on the Google Compute Engine VMs.
- "a_key": "A String",
- },
- "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
- # Compute Engine API.
- "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
- # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
- # `TEARDOWN_NEVER`.
- # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
- # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
- # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
- # down.
- #
- # If the workers are not torn down by the service, they will
- # continue to run and use Google Compute Engine VM resources in the
- # user's project until they are explicitly terminated by the user.
- # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
- # policy except for small, manually supervised test jobs.
- #
- # If unknown or unspecified, the service will attempt to choose a reasonable
- # default.
- "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
- # service will choose a number of threads (according to the number of cores
- # on the selected machine type for batch, or 1 by convention for streaming).
- "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
- # the form "regions/REGION/subnetworks/SUBNETWORK".
- "poolArgs": { # Extra arguments for this worker pool.
- "a_key": "", # Properties of the object. Contains field @type with type URL.
- },
- "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
- # execute the job. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
# using the standard Dataflow task runner. Users should ignore
# this field.
@@ -1840,17 +1839,7 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
- "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "root".
"commandlinesFileName": "A String", # The file to store preprocessing commands in.
- "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
- "vmId": "A String", # The ID string of the VM.
- "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
- "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
- "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
- # access the Cloud Dataflow API.
- "A String",
- ],
"parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
"reportingEnabled": True or False, # Whether to send work progress updates to the service.
"shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
@@ -1877,14 +1866,15 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
},
- "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "wheel".
- "languageHint": "A String", # The suggested backend language.
- "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
- # console.
- "streamingWorkerMainClass": "A String", # The streaming worker main class name.
- "logDir": "A String", # The directory on the VM to store logs.
- "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
+ "vmId": "A String", # The ID string of the VM.
+ "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
+ "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
+ "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
+ # access the Cloud Dataflow API.
+ "A String",
+ ],
+ "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "root".
"baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
#
# When workers access Google Cloud APIs, they logically do so via
@@ -1894,6 +1884,14 @@
# Locators".
#
# If not specified, the default value is "http://www.googleapis.com/"
+ "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "wheel".
+ "languageHint": "A String", # The suggested backend language.
+ "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+ # console.
+ "streamingWorkerMainClass": "A String", # The streaming worker main class name.
+ "logDir": "A String", # The directory on the VM to store logs.
+ "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
"harnessCommand": "A String", # The command to launch the worker harness.
"tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
# temporary storage.
@@ -1903,33 +1901,18 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
+ "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
},
- "defaultPackageSet": "A String", # The default package set to install. This allows the service to
- # select a default set of packages which are useful to worker
- # harnesses written in a particular language.
- "packages": [ # Packages to be installed on workers.
- { # The packages that must be installed in order for a worker to run the
- # steps of the Cloud Dataflow job that will be assigned to its worker
- # pool.
- #
- # This is the mechanism by which the Cloud Dataflow SDK causes code to
- # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
- # might use this to install jars containing the user's code and all of the
- # various dependencies (libraries, data files, etc.) required in order
- # for that code to run.
- "name": "A String", # The name of the package.
- "location": "A String", # The resource to read the package from. The supported resource type is:
- #
- # Google Cloud Storage:
- #
- # storage.googleapis.com/{bucket}
- # bucket.storage.googleapis.com/
- },
- ],
- "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
- "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
- "algorithm": "A String", # The algorithm to use for autoscaling.
- },
+ "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
+ # are supported.
+ "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
+ # service will attempt to choose a reasonable default.
+ "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
+ # the service will use the network "default".
+ "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
+ # will attempt to choose a reasonable default.
+ "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
+ # attempt to choose a reasonable default.
"dataDisks": [ # Data disks that are used by a VM in this workflow.
{ # Describes the data disk used by a workflow job.
"mountPoint": "A String", # Directory in a VM where disk is mounted.
@@ -1955,10 +1938,69 @@
# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
},
],
- "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
+ # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+ # `TEARDOWN_NEVER`.
+ # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+ # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+ # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+ # down.
+ #
+ # If the workers are not torn down by the service, they will
+ # continue to run and use Google Compute Engine VM resources in the
+ # user's project until they are explicitly terminated by the user.
+ # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+ # policy except for small, manually supervised test jobs.
+ #
+ # If unknown or unspecified, the service will attempt to choose a reasonable
+ # default.
+ "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
+ # Compute Engine API.
+ "ipConfiguration": "A String", # Configuration for VM IPs.
+ "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
+ # service will choose a number of threads (according to the number of cores
+ # on the selected machine type for batch, or 1 by convention for streaming).
+ "poolArgs": { # Extra arguments for this worker pool.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
+ # execute the job. If zero or unspecified, the service will
# attempt to choose a reasonable default.
"workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
# harness, residing in Google Container Registry.
+ "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
+ # the form "regions/REGION/subnetworks/SUBNETWORK".
+ "packages": [ # Packages to be installed on workers.
+ { # The packages that must be installed in order for a worker to run the
+ # steps of the Cloud Dataflow job that will be assigned to its worker
+ # pool.
+ #
+ # This is the mechanism by which the Cloud Dataflow SDK causes code to
+ # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+ # might use this to install jars containing the user's code and all of the
+ # various dependencies (libraries, data files, etc.) required in order
+ # for that code to run.
+ "location": "A String", # The resource to read the package from. The supported resource type is:
+ #
+ # Google Cloud Storage:
+ #
+ # storage.googleapis.com/{bucket}
+ # bucket.storage.googleapis.com/
+ "name": "A String", # The name of the package.
+ },
+ ],
+ "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+ "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
+ "algorithm": "A String", # The algorithm to use for autoscaling.
+ },
+ "defaultPackageSet": "A String", # The default package set to install. This allows the service to
+ # select a default set of packages which are useful to worker
+ # harnesses written in a particular language.
+ "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ # attempt to choose a reasonable default.
+ "metadata": { # Metadata to set on the Google Compute Engine VMs.
+ "a_key": "A String",
+ },
},
],
},
@@ -1977,16 +2019,13 @@
],
"displayData": [ # Transform-specific display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -1997,8 +2036,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"outputCollectionName": [ # User names for all collection outputs to this transform.
@@ -2009,16 +2051,13 @@
],
"displayData": [ # Pipeline level display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -2029,8 +2068,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"executionPipelineStage": [ # Description of each stage of execution of the pipeline.
@@ -2114,17 +2156,7 @@
# step with respect to all other steps in the Cloud Dataflow job.
},
],
- "currentState": "A String", # The current state of the job.
- #
- # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
- # specified.
- #
- # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
- # terminal state. After a job has reached a terminal state, no
- # further state updates may be made.
- #
- # This field may be mutated by the Cloud Dataflow service;
- # callers cannot mutate it.
+ "currentStateTime": "A String", # The timestamp associated with the current state.
"tempFiles": [ # A set of files the system should be aware of that are used
# for temporary storage. These temporary files will be
# removed on job completion.
@@ -2139,11 +2171,17 @@
# bucket.storage.googleapis.com/{object}
"A String",
],
+ "stageStates": [ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
+ { # A message describing the state of a particular execution stage.
+ "executionStageName": "A String", # The name of the execution stage.
+ "executionStageState": "A String", # Executions stage states allow the same set of values as JobState.
+ "currentStateTime": "A String", # The time at which the stage transitioned to this state.
+ },
+ ],
"type": "A String", # The type of Cloud Dataflow job.
- "id": "A String", # The unique ID of this job.
- #
- # This field is set by the Cloud Dataflow service when the Job is
- # created, and is immutable for the life of the job.
+ "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
+ # Cloud Dataflow service.
"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
# of the job it replaced.
#
@@ -2165,11 +2203,6 @@
},
},
],
- "failedLocation": [ # Zero or more messages describing locations that failed to respond.
- { # Indicates which location failed to respond to a request for data.
- "name": "A String", # The name of the failed location.
- },
- ],
}</pre>
</div>
@@ -2221,10 +2254,21 @@
#
# The name must match the regular expression
# `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
- "currentStateTime": "A String", # The timestamp associated with the current state.
+ "location": "A String", # The location that contains this job.
"replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
# `JOB_STATE_UPDATED`), this field contains the ID of that job.
"projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
+ "currentState": "A String", # The current state of the job.
+ #
+ # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+ # specified.
+ #
+ # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+ # terminal state. After a job has reached a terminal state, no
+ # further state updates may be made.
+ #
+ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
"labels": { # User-defined labels for this job.
#
# The labels map can contain no more than 64 entries. Entries of the labels
@@ -2236,13 +2280,14 @@
# size.
"a_key": "A String",
},
- "location": "A String", # The location that contains this job.
- "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
- # Cloud Dataflow service.
"transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
# corresponding name prefixes of the new job.
"a_key": "A String",
},
+ "id": "A String", # The unique ID of this job.
+ #
+ # This field is set by the Cloud Dataflow service when the Job is
+ # created, and is immutable for the life of the job.
"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
"version": { # A structure describing which components and their versions of the service
# are required in order to run the job.
@@ -2296,49 +2341,6 @@
# multiple pools, in order to match the various computational
# requirements of the various stages of the job.
"diskSourceImage": "A String", # Fully qualified source image for disks.
- "ipConfiguration": "A String", # Configuration for VM IPs.
- "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
- # are supported.
- "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
- # service will attempt to choose a reasonable default.
- "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
- # the service will use the network "default".
- "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
- # will attempt to choose a reasonable default.
- "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
- "metadata": { # Metadata to set on the Google Compute Engine VMs.
- "a_key": "A String",
- },
- "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
- # Compute Engine API.
- "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
- # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
- # `TEARDOWN_NEVER`.
- # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
- # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
- # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
- # down.
- #
- # If the workers are not torn down by the service, they will
- # continue to run and use Google Compute Engine VM resources in the
- # user's project until they are explicitly terminated by the user.
- # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
- # policy except for small, manually supervised test jobs.
- #
- # If unknown or unspecified, the service will attempt to choose a reasonable
- # default.
- "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
- # service will choose a number of threads (according to the number of cores
- # on the selected machine type for batch, or 1 by convention for streaming).
- "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
- # the form "regions/REGION/subnetworks/SUBNETWORK".
- "poolArgs": { # Extra arguments for this worker pool.
- "a_key": "", # Properties of the object. Contains field @type with type URL.
- },
- "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
- # execute the job. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
# using the standard Dataflow task runner. Users should ignore
# this field.
@@ -2351,17 +2353,7 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
- "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "root".
"commandlinesFileName": "A String", # The file to store preprocessing commands in.
- "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
- "vmId": "A String", # The ID string of the VM.
- "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
- "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
- "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
- # access the Cloud Dataflow API.
- "A String",
- ],
"parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
"reportingEnabled": True or False, # Whether to send work progress updates to the service.
"shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
@@ -2388,14 +2380,15 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
},
- "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "wheel".
- "languageHint": "A String", # The suggested backend language.
- "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
- # console.
- "streamingWorkerMainClass": "A String", # The streaming worker main class name.
- "logDir": "A String", # The directory on the VM to store logs.
- "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
+ "vmId": "A String", # The ID string of the VM.
+ "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
+ "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
+ "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
+ # access the Cloud Dataflow API.
+ "A String",
+ ],
+ "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "root".
"baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
#
# When workers access Google Cloud APIs, they logically do so via
@@ -2405,6 +2398,14 @@
# Locators".
#
# If not specified, the default value is "http://www.googleapis.com/"
+ "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "wheel".
+ "languageHint": "A String", # The suggested backend language.
+ "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+ # console.
+ "streamingWorkerMainClass": "A String", # The streaming worker main class name.
+ "logDir": "A String", # The directory on the VM to store logs.
+ "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
"harnessCommand": "A String", # The command to launch the worker harness.
"tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
# temporary storage.
@@ -2414,33 +2415,18 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
+ "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
},
- "defaultPackageSet": "A String", # The default package set to install. This allows the service to
- # select a default set of packages which are useful to worker
- # harnesses written in a particular language.
- "packages": [ # Packages to be installed on workers.
- { # The packages that must be installed in order for a worker to run the
- # steps of the Cloud Dataflow job that will be assigned to its worker
- # pool.
- #
- # This is the mechanism by which the Cloud Dataflow SDK causes code to
- # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
- # might use this to install jars containing the user's code and all of the
- # various dependencies (libraries, data files, etc.) required in order
- # for that code to run.
- "name": "A String", # The name of the package.
- "location": "A String", # The resource to read the package from. The supported resource type is:
- #
- # Google Cloud Storage:
- #
- # storage.googleapis.com/{bucket}
- # bucket.storage.googleapis.com/
- },
- ],
- "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
- "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
- "algorithm": "A String", # The algorithm to use for autoscaling.
- },
+ "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
+ # are supported.
+ "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
+ # service will attempt to choose a reasonable default.
+ "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
+ # the service will use the network "default".
+ "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
+ # will attempt to choose a reasonable default.
+ "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
+ # attempt to choose a reasonable default.
"dataDisks": [ # Data disks that are used by a VM in this workflow.
{ # Describes the data disk used by a workflow job.
"mountPoint": "A String", # Directory in a VM where disk is mounted.
@@ -2466,10 +2452,69 @@
# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
},
],
- "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
+ # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+ # `TEARDOWN_NEVER`.
+ # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+ # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+ # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+ # down.
+ #
+ # If the workers are not torn down by the service, they will
+ # continue to run and use Google Compute Engine VM resources in the
+ # user's project until they are explicitly terminated by the user.
+ # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+ # policy except for small, manually supervised test jobs.
+ #
+ # If unknown or unspecified, the service will attempt to choose a reasonable
+ # default.
+ "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
+ # Compute Engine API.
+ "ipConfiguration": "A String", # Configuration for VM IPs.
+ "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
+ # service will choose a number of threads (according to the number of cores
+ # on the selected machine type for batch, or 1 by convention for streaming).
+ "poolArgs": { # Extra arguments for this worker pool.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
+ # execute the job. If zero or unspecified, the service will
# attempt to choose a reasonable default.
"workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
# harness, residing in Google Container Registry.
+ "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
+ # the form "regions/REGION/subnetworks/SUBNETWORK".
+ "packages": [ # Packages to be installed on workers.
+ { # The packages that must be installed in order for a worker to run the
+ # steps of the Cloud Dataflow job that will be assigned to its worker
+ # pool.
+ #
+ # This is the mechanism by which the Cloud Dataflow SDK causes code to
+ # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+ # might use this to install jars containing the user's code and all of the
+ # various dependencies (libraries, data files, etc.) required in order
+ # for that code to run.
+ "location": "A String", # The resource to read the package from. The supported resource type is:
+ #
+ # Google Cloud Storage:
+ #
+ # storage.googleapis.com/{bucket}
+ # bucket.storage.googleapis.com/
+ "name": "A String", # The name of the package.
+ },
+ ],
+ "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+ "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
+ "algorithm": "A String", # The algorithm to use for autoscaling.
+ },
+ "defaultPackageSet": "A String", # The default package set to install. This allows the service to
+ # select a default set of packages which are useful to worker
+ # harnesses written in a particular language.
+ "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ # attempt to choose a reasonable default.
+ "metadata": { # Metadata to set on the Google Compute Engine VMs.
+ "a_key": "A String",
+ },
},
],
},
@@ -2488,16 +2533,13 @@
],
"displayData": [ # Transform-specific display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -2508,8 +2550,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"outputCollectionName": [ # User names for all collection outputs to this transform.
@@ -2520,16 +2565,13 @@
],
"displayData": [ # Pipeline level display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -2540,8 +2582,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"executionPipelineStage": [ # Description of each stage of execution of the pipeline.
@@ -2625,17 +2670,7 @@
# step with respect to all other steps in the Cloud Dataflow job.
},
],
- "currentState": "A String", # The current state of the job.
- #
- # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
- # specified.
- #
- # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
- # terminal state. After a job has reached a terminal state, no
- # further state updates may be made.
- #
- # This field may be mutated by the Cloud Dataflow service;
- # callers cannot mutate it.
+ "currentStateTime": "A String", # The timestamp associated with the current state.
"tempFiles": [ # A set of files the system should be aware of that are used
# for temporary storage. These temporary files will be
# removed on job completion.
@@ -2650,11 +2685,17 @@
# bucket.storage.googleapis.com/{object}
"A String",
],
+ "stageStates": [ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
+ { # A message describing the state of a particular execution stage.
+ "executionStageName": "A String", # The name of the execution stage.
+ "executionStageState": "A String", # Executions stage states allow the same set of values as JobState.
+ "currentStateTime": "A String", # The time at which the stage transitioned to this state.
+ },
+ ],
"type": "A String", # The type of Cloud Dataflow job.
- "id": "A String", # The unique ID of this job.
- #
- # This field is set by the Cloud Dataflow service when the Job is
- # created, and is immutable for the life of the job.
+ "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
+ # Cloud Dataflow service.
"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
# of the job it replaced.
#
@@ -2709,10 +2750,21 @@
#
# The name must match the regular expression
# `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
- "currentStateTime": "A String", # The timestamp associated with the current state.
+ "location": "A String", # The location that contains this job.
"replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
# `JOB_STATE_UPDATED`), this field contains the ID of that job.
"projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
+ "currentState": "A String", # The current state of the job.
+ #
+ # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+ # specified.
+ #
+ # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+ # terminal state. After a job has reached a terminal state, no
+ # further state updates may be made.
+ #
+ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
"labels": { # User-defined labels for this job.
#
# The labels map can contain no more than 64 entries. Entries of the labels
@@ -2724,13 +2776,14 @@
# size.
"a_key": "A String",
},
- "location": "A String", # The location that contains this job.
- "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
- # Cloud Dataflow service.
"transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
# corresponding name prefixes of the new job.
"a_key": "A String",
},
+ "id": "A String", # The unique ID of this job.
+ #
+ # This field is set by the Cloud Dataflow service when the Job is
+ # created, and is immutable for the life of the job.
"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
"version": { # A structure describing which components and their versions of the service
# are required in order to run the job.
@@ -2784,49 +2837,6 @@
# multiple pools, in order to match the various computational
# requirements of the various stages of the job.
"diskSourceImage": "A String", # Fully qualified source image for disks.
- "ipConfiguration": "A String", # Configuration for VM IPs.
- "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
- # are supported.
- "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
- # service will attempt to choose a reasonable default.
- "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
- # the service will use the network "default".
- "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
- # will attempt to choose a reasonable default.
- "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
- "metadata": { # Metadata to set on the Google Compute Engine VMs.
- "a_key": "A String",
- },
- "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
- # Compute Engine API.
- "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
- # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
- # `TEARDOWN_NEVER`.
- # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
- # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
- # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
- # down.
- #
- # If the workers are not torn down by the service, they will
- # continue to run and use Google Compute Engine VM resources in the
- # user's project until they are explicitly terminated by the user.
- # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
- # policy except for small, manually supervised test jobs.
- #
- # If unknown or unspecified, the service will attempt to choose a reasonable
- # default.
- "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
- # service will choose a number of threads (according to the number of cores
- # on the selected machine type for batch, or 1 by convention for streaming).
- "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
- # the form "regions/REGION/subnetworks/SUBNETWORK".
- "poolArgs": { # Extra arguments for this worker pool.
- "a_key": "", # Properties of the object. Contains field @type with type URL.
- },
- "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
- # execute the job. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
# using the standard Dataflow task runner. Users should ignore
# this field.
@@ -2839,17 +2849,7 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
- "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "root".
"commandlinesFileName": "A String", # The file to store preprocessing commands in.
- "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
- "vmId": "A String", # The ID string of the VM.
- "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
- "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
- "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
- # access the Cloud Dataflow API.
- "A String",
- ],
"parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
"reportingEnabled": True or False, # Whether to send work progress updates to the service.
"shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
@@ -2876,14 +2876,15 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
},
- "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "wheel".
- "languageHint": "A String", # The suggested backend language.
- "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
- # console.
- "streamingWorkerMainClass": "A String", # The streaming worker main class name.
- "logDir": "A String", # The directory on the VM to store logs.
- "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
+ "vmId": "A String", # The ID string of the VM.
+ "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
+ "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
+ "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
+ # access the Cloud Dataflow API.
+ "A String",
+ ],
+ "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "root".
"baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
#
# When workers access Google Cloud APIs, they logically do so via
@@ -2893,6 +2894,14 @@
# Locators".
#
# If not specified, the default value is "http://www.googleapis.com/"
+ "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "wheel".
+ "languageHint": "A String", # The suggested backend language.
+ "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+ # console.
+ "streamingWorkerMainClass": "A String", # The streaming worker main class name.
+ "logDir": "A String", # The directory on the VM to store logs.
+ "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
"harnessCommand": "A String", # The command to launch the worker harness.
"tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
# temporary storage.
@@ -2902,33 +2911,18 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
+ "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
},
- "defaultPackageSet": "A String", # The default package set to install. This allows the service to
- # select a default set of packages which are useful to worker
- # harnesses written in a particular language.
- "packages": [ # Packages to be installed on workers.
- { # The packages that must be installed in order for a worker to run the
- # steps of the Cloud Dataflow job that will be assigned to its worker
- # pool.
- #
- # This is the mechanism by which the Cloud Dataflow SDK causes code to
- # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
- # might use this to install jars containing the user's code and all of the
- # various dependencies (libraries, data files, etc.) required in order
- # for that code to run.
- "name": "A String", # The name of the package.
- "location": "A String", # The resource to read the package from. The supported resource type is:
- #
- # Google Cloud Storage:
- #
- # storage.googleapis.com/{bucket}
- # bucket.storage.googleapis.com/
- },
- ],
- "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
- "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
- "algorithm": "A String", # The algorithm to use for autoscaling.
- },
+ "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
+ # are supported.
+ "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
+ # service will attempt to choose a reasonable default.
+ "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
+ # the service will use the network "default".
+ "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
+ # will attempt to choose a reasonable default.
+ "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
+ # attempt to choose a reasonable default.
"dataDisks": [ # Data disks that are used by a VM in this workflow.
{ # Describes the data disk used by a workflow job.
"mountPoint": "A String", # Directory in a VM where disk is mounted.
@@ -2954,10 +2948,69 @@
# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
},
],
- "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
+ # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+ # `TEARDOWN_NEVER`.
+ # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+ # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+ # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+ # down.
+ #
+ # If the workers are not torn down by the service, they will
+ # continue to run and use Google Compute Engine VM resources in the
+ # user's project until they are explicitly terminated by the user.
+ # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+ # policy except for small, manually supervised test jobs.
+ #
+ # If unknown or unspecified, the service will attempt to choose a reasonable
+ # default.
+ "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
+ # Compute Engine API.
+ "ipConfiguration": "A String", # Configuration for VM IPs.
+ "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
+ # service will choose a number of threads (according to the number of cores
+ # on the selected machine type for batch, or 1 by convention for streaming).
+ "poolArgs": { # Extra arguments for this worker pool.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
+ # execute the job. If zero or unspecified, the service will
# attempt to choose a reasonable default.
"workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
# harness, residing in Google Container Registry.
+ "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
+ # the form "regions/REGION/subnetworks/SUBNETWORK".
+ "packages": [ # Packages to be installed on workers.
+ { # The packages that must be installed in order for a worker to run the
+ # steps of the Cloud Dataflow job that will be assigned to its worker
+ # pool.
+ #
+ # This is the mechanism by which the Cloud Dataflow SDK causes code to
+ # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+ # might use this to install jars containing the user's code and all of the
+ # various dependencies (libraries, data files, etc.) required in order
+ # for that code to run.
+ "location": "A String", # The resource to read the package from. The supported resource type is:
+ #
+ # Google Cloud Storage:
+ #
+ # storage.googleapis.com/{bucket}
+ # bucket.storage.googleapis.com/
+ "name": "A String", # The name of the package.
+ },
+ ],
+ "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+ "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
+ "algorithm": "A String", # The algorithm to use for autoscaling.
+ },
+ "defaultPackageSet": "A String", # The default package set to install. This allows the service to
+ # select a default set of packages which are useful to worker
+ # harnesses written in a particular language.
+ "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ # attempt to choose a reasonable default.
+ "metadata": { # Metadata to set on the Google Compute Engine VMs.
+ "a_key": "A String",
+ },
},
],
},
@@ -2976,16 +3029,13 @@
],
"displayData": [ # Transform-specific display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -2996,8 +3046,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"outputCollectionName": [ # User names for all collection outputs to this transform.
@@ -3008,16 +3061,13 @@
],
"displayData": [ # Pipeline level display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -3028,8 +3078,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"executionPipelineStage": [ # Description of each stage of execution of the pipeline.
@@ -3113,17 +3166,7 @@
# step with respect to all other steps in the Cloud Dataflow job.
},
],
- "currentState": "A String", # The current state of the job.
- #
- # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
- # specified.
- #
- # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
- # terminal state. After a job has reached a terminal state, no
- # further state updates may be made.
- #
- # This field may be mutated by the Cloud Dataflow service;
- # callers cannot mutate it.
+ "currentStateTime": "A String", # The timestamp associated with the current state.
"tempFiles": [ # A set of files the system should be aware of that are used
# for temporary storage. These temporary files will be
# removed on job completion.
@@ -3138,11 +3181,17 @@
# bucket.storage.googleapis.com/{object}
"A String",
],
+ "stageStates": [ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
+ { # A message describing the state of a particular execution stage.
+ "executionStageName": "A String", # The name of the execution stage.
+ "executionStageState": "A String", # Executions stage states allow the same set of values as JobState.
+ "currentStateTime": "A String", # The time at which the stage transitioned to this state.
+ },
+ ],
"type": "A String", # The type of Cloud Dataflow job.
- "id": "A String", # The unique ID of this job.
- #
- # This field is set by the Cloud Dataflow service when the Job is
- # created, and is immutable for the life of the job.
+ "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
+ # Cloud Dataflow service.
"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
# of the job it replaced.
#