Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(2189)

Unified Diff: discovery/googleapis_beta/dataflow__v1b3.json

Issue 2987103002: Api-Roll 52: 2017-07-31 (Closed)
Patch Set: Created 3 years, 5 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
Index: discovery/googleapis_beta/dataflow__v1b3.json
diff --git a/discovery/googleapis_beta/dataflow__v1b3.json b/discovery/googleapis_beta/dataflow__v1b3.json
index 7e8d2e5a29e0e254faba1f31129e504121760341..e61d9ca8e89ce9fde6b76df3cc699ee555be0e06 100644
--- a/discovery/googleapis_beta/dataflow__v1b3.json
+++ b/discovery/googleapis_beta/dataflow__v1b3.json
@@ -33,27 +33,16 @@
"ownerDomain": "google.com",
"ownerName": "Google",
"parameters": {
- "quotaUser": {
- "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.",
+ "oauth_token": {
+ "description": "OAuth 2.0 token for the current user.",
"location": "query",
"type": "string"
},
- "pp": {
- "default": "true",
- "description": "Pretty-print response.",
- "location": "query",
- "type": "boolean"
- },
"bearer_token": {
"description": "OAuth bearer token.",
"location": "query",
"type": "string"
},
- "oauth_token": {
- "description": "OAuth 2.0 token for the current user.",
- "location": "query",
- "type": "string"
- },
"upload_protocol": {
"description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
"location": "query",
@@ -65,13 +54,13 @@
"location": "query",
"type": "boolean"
},
- "uploadType": {
- "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
+ "fields": {
+ "description": "Selector specifying which fields to include in a partial response.",
"location": "query",
"type": "string"
},
- "fields": {
- "description": "Selector specifying which fields to include in a partial response.",
+ "uploadType": {
+ "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
"location": "query",
"type": "string"
},
@@ -109,15 +98,26 @@
"location": "query",
"type": "string"
},
+ "key": {
+ "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.",
+ "location": "query",
+ "type": "string"
+ },
"access_token": {
"description": "OAuth access token.",
"location": "query",
"type": "string"
},
- "key": {
- "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.",
+ "quotaUser": {
+ "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.",
"location": "query",
"type": "string"
+ },
+ "pp": {
+ "default": "true",
+ "description": "Pretty-print response.",
+ "location": "query",
+ "type": "boolean"
}
},
"protocol": "rest",
@@ -166,14 +166,14 @@
"location"
],
"parameters": {
- "projectId": {
- "description": "The project to send the WorkerMessages to.",
+ "location": {
+ "description": "The location which contains the job",
"location": "path",
"required": true,
"type": "string"
},
- "location": {
- "description": "The location which contains the job",
+ "projectId": {
+ "description": "The project to send the WorkerMessages to.",
"location": "path",
"required": true,
"type": "string"
@@ -197,23 +197,26 @@
"resources": {
"templates": {
"methods": {
- "get": {
- "description": "Get the template associated with a template.",
- "httpMethod": "GET",
- "id": "dataflow.projects.locations.templates.get",
+ "launch": {
+ "description": "Launch a template.",
+ "httpMethod": "POST",
+ "id": "dataflow.projects.locations.templates.launch",
"parameterOrder": [
"projectId",
"location"
],
"parameters": {
- "view": {
- "description": "The view to retrieve. Defaults to METADATA_ONLY.",
- "enum": [
- "METADATA_ONLY"
- ],
- "location": "query",
+ "location": {
+ "description": "The location to which to direct the request.",
+ "location": "path",
+ "required": true,
"type": "string"
},
+ "validateOnly": {
+ "description": "If true, the request is validated but not actually executed.\nDefaults to false.",
+ "location": "query",
+ "type": "boolean"
+ },
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
@@ -221,20 +224,17 @@
"type": "string"
},
"gcsPath": {
- "description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
+ "description": "Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
"location": "query",
"type": "string"
- },
- "location": {
- "description": "The location to which to direct the request.",
- "location": "path",
- "required": true,
- "type": "string"
}
},
- "path": "v1b3/projects/{projectId}/locations/{location}/templates:get",
+ "path": "v1b3/projects/{projectId}/locations/{location}/templates:launch",
+ "request": {
+ "$ref": "LaunchTemplateParameters"
+ },
"response": {
- "$ref": "GetTemplateResponse"
+ "$ref": "LaunchTemplateResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
@@ -243,10 +243,10 @@
"https://www.googleapis.com/auth/userinfo.email"
]
},
- "create": {
- "description": "Creates a Cloud Dataflow job from a template.",
- "httpMethod": "POST",
- "id": "dataflow.projects.locations.templates.create",
+ "get": {
+ "description": "Get the template associated with a template.",
+ "httpMethod": "GET",
+ "id": "dataflow.projects.locations.templates.get",
"parameterOrder": [
"projectId",
"location"
@@ -258,19 +258,29 @@
"required": true,
"type": "string"
},
+ "view": {
+ "description": "The view to retrieve. Defaults to METADATA_ONLY.",
+ "enum": [
+ "METADATA_ONLY"
+ ],
+ "location": "query",
+ "type": "string"
+ },
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
+ },
+ "gcsPath": {
+ "description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
+ "location": "query",
+ "type": "string"
}
},
- "path": "v1b3/projects/{projectId}/locations/{location}/templates",
- "request": {
- "$ref": "CreateJobFromTemplateRequest"
- },
+ "path": "v1b3/projects/{projectId}/locations/{location}/templates:get",
"response": {
- "$ref": "Job"
+ "$ref": "GetTemplateResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
@@ -279,44 +289,34 @@
"https://www.googleapis.com/auth/userinfo.email"
]
},
- "launch": {
- "description": "Launch a template.",
+ "create": {
+ "description": "Creates a Cloud Dataflow job from a template.",
"httpMethod": "POST",
- "id": "dataflow.projects.locations.templates.launch",
+ "id": "dataflow.projects.locations.templates.create",
"parameterOrder": [
"projectId",
"location"
],
"parameters": {
- "gcsPath": {
- "description": "Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
- "location": "query",
- "type": "string"
- },
- "location": {
- "description": "The location to which to direct the request.",
+ "projectId": {
+ "description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
},
- "validateOnly": {
- "description": "If true, the request is validated but not actually executed.\nDefaults to false.",
- "location": "query",
- "type": "boolean"
- },
- "projectId": {
- "description": "Required. The ID of the Cloud Platform project that the job belongs to.",
+ "location": {
+ "description": "The location to which to direct the request.",
"location": "path",
"required": true,
"type": "string"
}
},
- "path": "v1b3/projects/{projectId}/locations/{location}/templates:launch",
+ "path": "v1b3/projects/{projectId}/locations/{location}/templates",
"request": {
- "$ref": "LaunchTemplateParameters"
+ "$ref": "CreateJobFromTemplateRequest"
},
"response": {
- "$ref": "LaunchTemplateResponse"
+ "$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
@@ -451,6 +451,12 @@
"jobId"
],
"parameters": {
+ "location": {
+ "description": "The location that contains this job.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
"view": {
"description": "The level of information requested in response.",
"enum": [
@@ -473,12 +479,6 @@
"location": "path",
"required": true,
"type": "string"
- },
- "location": {
- "description": "The location that contains this job.",
- "location": "path",
- "required": true,
- "type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
@@ -544,6 +544,12 @@
"location"
],
"parameters": {
+ "location": {
+ "description": "The location that contains this job.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
"replaceJobId": {
"description": "Deprecated. This field is now in the Job message.",
"location": "query",
@@ -565,12 +571,6 @@
"location": "path",
"required": true,
"type": "string"
- },
- "location": {
- "description": "The location that contains this job.",
- "location": "path",
- "required": true,
- "type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs",
@@ -601,6 +601,25 @@
"jobId"
],
"parameters": {
+ "pageSize": {
+ "description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results.",
+ "format": "int32",
+ "location": "query",
+ "type": "integer"
+ },
+ "minimumImportance": {
+ "description": "Filter to only get messages with importance >= level",
+ "enum": [
+ "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
+ "JOB_MESSAGE_DEBUG",
+ "JOB_MESSAGE_DETAILED",
+ "JOB_MESSAGE_BASIC",
+ "JOB_MESSAGE_WARNING",
+ "JOB_MESSAGE_ERROR"
+ ],
+ "location": "query",
+ "type": "string"
+ },
"projectId": {
"description": "A project id.",
"location": "path",
@@ -635,25 +654,6 @@
"description": "If supplied, this should be the value of next_page_token returned\nby an earlier call. This will cause the next page of results to\nbe returned.",
"location": "query",
"type": "string"
- },
- "pageSize": {
- "description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results.",
- "format": "int32",
- "location": "query",
- "type": "integer"
- },
- "minimumImportance": {
- "description": "Filter to only get messages with importance >= level",
- "enum": [
- "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
- "JOB_MESSAGE_DEBUG",
- "JOB_MESSAGE_DETAILED",
- "JOB_MESSAGE_BASIC",
- "JOB_MESSAGE_WARNING",
- "JOB_MESSAGE_ERROR"
- ],
- "location": "query",
- "type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages",
@@ -671,41 +671,41 @@
},
"workItems": {
"methods": {
- "lease": {
- "description": "Leases a dataflow WorkItem to run.",
+ "reportStatus": {
+ "description": "Reports the status of dataflow WorkItems leased by a worker.",
"httpMethod": "POST",
- "id": "dataflow.projects.locations.jobs.workItems.lease",
+ "id": "dataflow.projects.locations.jobs.workItems.reportStatus",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
- "jobId": {
- "description": "Identifies the workflow job this worker belongs to.",
+ "location": {
+ "description": "The location which contains the WorkItem's job.",
"location": "path",
"required": true,
"type": "string"
},
- "projectId": {
- "description": "Identifies the project this worker belongs to.",
+ "jobId": {
+ "description": "The job which the WorkItem is part of.",
"location": "path",
"required": true,
"type": "string"
},
- "location": {
- "description": "The location which contains the WorkItem's job.",
+ "projectId": {
+ "description": "The project which owns the WorkItem's job.",
"location": "path",
"required": true,
"type": "string"
}
},
- "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease",
+ "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus",
"request": {
- "$ref": "LeaseWorkItemRequest"
+ "$ref": "ReportWorkItemStatusRequest"
},
"response": {
- "$ref": "LeaseWorkItemResponse"
+ "$ref": "ReportWorkItemStatusResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
@@ -714,41 +714,41 @@
"https://www.googleapis.com/auth/userinfo.email"
]
},
- "reportStatus": {
- "description": "Reports the status of dataflow WorkItems leased by a worker.",
+ "lease": {
+ "description": "Leases a dataflow WorkItem to run.",
"httpMethod": "POST",
- "id": "dataflow.projects.locations.jobs.workItems.reportStatus",
+ "id": "dataflow.projects.locations.jobs.workItems.lease",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
- "jobId": {
- "description": "The job which the WorkItem is part of.",
+ "location": {
+ "description": "The location which contains the WorkItem's job.",
"location": "path",
"required": true,
"type": "string"
},
- "projectId": {
- "description": "The project which owns the WorkItem's job.",
+ "jobId": {
+ "description": "Identifies the workflow job this worker belongs to.",
"location": "path",
"required": true,
"type": "string"
},
- "location": {
- "description": "The location which contains the WorkItem's job.",
+ "projectId": {
+ "description": "Identifies the project this worker belongs to.",
"location": "path",
"required": true,
"type": "string"
}
},
- "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus",
+ "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease",
"request": {
- "$ref": "ReportWorkItemStatusRequest"
+ "$ref": "LeaseWorkItemRequest"
},
"response": {
- "$ref": "ReportWorkItemStatusResponse"
+ "$ref": "LeaseWorkItemResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
@@ -771,20 +771,20 @@
"jobId"
],
"parameters": {
- "location": {
- "description": "The location which contains the job specified by job_id.",
+ "jobId": {
+ "description": "The job id.",
"location": "path",
"required": true,
"type": "string"
},
- "jobId": {
- "description": "The job id.",
+ "projectId": {
+ "description": "The project id.",
"location": "path",
"required": true,
"type": "string"
},
- "projectId": {
- "description": "The project id.",
+ "location": {
+ "description": "The location which contains the job specified by job_id.",
"location": "path",
"required": true,
"type": "string"
@@ -855,42 +855,42 @@
},
"templates": {
"methods": {
- "launch": {
- "description": "Launch a template.",
- "httpMethod": "POST",
- "id": "dataflow.projects.templates.launch",
+ "get": {
+ "description": "Get the template associated with a template.",
+ "httpMethod": "GET",
+ "id": "dataflow.projects.templates.get",
"parameterOrder": [
"projectId"
],
"parameters": {
- "gcsPath": {
- "description": "Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
- "location": "query",
- "type": "string"
- },
"location": {
"description": "The location to which to direct the request.",
"location": "query",
"type": "string"
},
- "validateOnly": {
- "description": "If true, the request is validated but not actually executed.\nDefaults to false.",
+ "view": {
+ "description": "The view to retrieve. Defaults to METADATA_ONLY.",
+ "enum": [
+ "METADATA_ONLY"
+ ],
"location": "query",
- "type": "boolean"
+ "type": "string"
},
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
+ },
+ "gcsPath": {
+ "description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
+ "location": "query",
+ "type": "string"
}
},
- "path": "v1b3/projects/{projectId}/templates:launch",
- "request": {
- "$ref": "LaunchTemplateParameters"
- },
+ "path": "v1b3/projects/{projectId}/templates:get",
"response": {
- "$ref": "LaunchTemplateResponse"
+ "$ref": "GetTemplateResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
@@ -899,42 +899,27 @@
"https://www.googleapis.com/auth/userinfo.email"
]
},
- "get": {
- "description": "Get the template associated with a template.",
- "httpMethod": "GET",
- "id": "dataflow.projects.templates.get",
+ "create": {
+ "description": "Creates a Cloud Dataflow job from a template.",
+ "httpMethod": "POST",
+ "id": "dataflow.projects.templates.create",
"parameterOrder": [
"projectId"
],
"parameters": {
- "view": {
- "description": "The view to retrieve. Defaults to METADATA_ONLY.",
- "enum": [
- "METADATA_ONLY"
- ],
- "location": "query",
- "type": "string"
- },
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
- },
- "gcsPath": {
- "description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
- "location": "query",
- "type": "string"
- },
- "location": {
- "description": "The location to which to direct the request.",
- "location": "query",
- "type": "string"
}
},
- "path": "v1b3/projects/{projectId}/templates:get",
+ "path": "v1b3/projects/{projectId}/templates",
+ "request": {
+ "$ref": "CreateJobFromTemplateRequest"
+ },
"response": {
- "$ref": "GetTemplateResponse"
+ "$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
@@ -943,27 +928,42 @@
"https://www.googleapis.com/auth/userinfo.email"
]
},
- "create": {
- "description": "Creates a Cloud Dataflow job from a template.",
+ "launch": {
+ "description": "Launch a template.",
"httpMethod": "POST",
- "id": "dataflow.projects.templates.create",
+ "id": "dataflow.projects.templates.launch",
"parameterOrder": [
"projectId"
],
"parameters": {
+ "location": {
+ "description": "The location to which to direct the request.",
+ "location": "query",
+ "type": "string"
+ },
+ "validateOnly": {
+ "description": "If true, the request is validated but not actually executed.\nDefaults to false.",
+ "location": "query",
+ "type": "boolean"
+ },
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
+ },
+ "gcsPath": {
+ "description": "Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
+ "location": "query",
+ "type": "string"
}
},
- "path": "v1b3/projects/{projectId}/templates",
+ "path": "v1b3/projects/{projectId}/templates:launch",
"request": {
- "$ref": "CreateJobFromTemplateRequest"
+ "$ref": "LaunchTemplateParameters"
},
"response": {
- "$ref": "Job"
+ "$ref": "LaunchTemplateResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
@@ -976,6 +976,50 @@
},
"jobs": {
"methods": {
+ "getMetrics": {
+ "description": "Request the job status.",
+ "httpMethod": "GET",
+ "id": "dataflow.projects.jobs.getMetrics",
+ "parameterOrder": [
+ "projectId",
+ "jobId"
+ ],
+ "parameters": {
+ "startTime": {
+ "description": "Return only metric data that has changed since this time.\nDefault is to return all information about all metrics for the job.",
+ "format": "google-datetime",
+ "location": "query",
+ "type": "string"
+ },
+ "jobId": {
+ "description": "The job to get messages for.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "projectId": {
+ "description": "A project id.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "location": {
+ "description": "The location which contains the job specified by job_id.",
+ "location": "query",
+ "type": "string"
+ }
+ },
+ "path": "v1b3/projects/{projectId}/jobs/{jobId}/metrics",
+ "response": {
+ "$ref": "JobMetrics"
+ },
+ "scopes": [
+ "https://www.googleapis.com/auth/cloud-platform",
+ "https://www.googleapis.com/auth/compute",
+ "https://www.googleapis.com/auth/compute.readonly",
+ "https://www.googleapis.com/auth/userinfo.email"
+ ]
+ },
"list": {
"description": "List the jobs of a project.",
"httpMethod": "GET",
@@ -1098,6 +1142,11 @@
"jobId"
],
"parameters": {
+ "location": {
+ "description": "The location that contains this job.",
+ "location": "query",
+ "type": "string"
+ },
"jobId": {
"description": "The job ID.",
"location": "path",
@@ -1109,11 +1158,6 @@
"location": "path",
"required": true,
"type": "string"
- },
- "location": {
- "description": "The location that contains this job.",
- "location": "query",
- "type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}",
@@ -1138,11 +1182,6 @@
"projectId"
],
"parameters": {
- "location": {
- "description": "The location that contains this job.",
- "location": "query",
- "type": "string"
- },
"replaceJobId": {
"description": "Deprecated. This field is now in the Job message.",
"location": "query",
@@ -1164,6 +1203,11 @@
"location": "path",
"required": true,
"type": "string"
+ },
+ "location": {
+ "description": "The location that contains this job.",
+ "location": "query",
+ "type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs",
@@ -1179,50 +1223,6 @@
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
- },
- "getMetrics": {
- "description": "Request the job status.",
- "httpMethod": "GET",
- "id": "dataflow.projects.jobs.getMetrics",
- "parameterOrder": [
- "projectId",
- "jobId"
- ],
- "parameters": {
- "location": {
- "description": "The location which contains the job specified by job_id.",
- "location": "query",
- "type": "string"
- },
- "startTime": {
- "description": "Return only metric data that has changed since this time.\nDefault is to return all information about all metrics for the job.",
- "format": "google-datetime",
- "location": "query",
- "type": "string"
- },
- "jobId": {
- "description": "The job to get messages for.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "projectId": {
- "description": "A project id.",
- "location": "path",
- "required": true,
- "type": "string"
- }
- },
- "path": "v1b3/projects/{projectId}/jobs/{jobId}/metrics",
- "response": {
- "$ref": "JobMetrics"
- },
- "scopes": [
- "https://www.googleapis.com/auth/cloud-platform",
- "https://www.googleapis.com/auth/compute",
- "https://www.googleapis.com/auth/compute.readonly",
- "https://www.googleapis.com/auth/userinfo.email"
- ]
}
},
"resources": {
@@ -1389,6 +1389,25 @@
"jobId"
],
"parameters": {
+ "pageSize": {
+ "description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results.",
+ "format": "int32",
+ "location": "query",
+ "type": "integer"
+ },
+ "minimumImportance": {
+ "description": "Filter to only get messages with importance >= level",
+ "enum": [
+ "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
+ "JOB_MESSAGE_DEBUG",
+ "JOB_MESSAGE_DETAILED",
+ "JOB_MESSAGE_BASIC",
+ "JOB_MESSAGE_WARNING",
+ "JOB_MESSAGE_ERROR"
+ ],
+ "location": "query",
+ "type": "string"
+ },
"projectId": {
"description": "A project id.",
"location": "path",
@@ -1422,25 +1441,6 @@
"description": "If supplied, this should be the value of next_page_token returned\nby an earlier call. This will cause the next page of results to\nbe returned.",
"location": "query",
"type": "string"
- },
- "pageSize": {
- "description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results.",
- "format": "int32",
- "location": "query",
- "type": "integer"
- },
- "minimumImportance": {
- "description": "Filter to only get messages with importance >= level",
- "enum": [
- "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
- "JOB_MESSAGE_DEBUG",
- "JOB_MESSAGE_DETAILED",
- "JOB_MESSAGE_BASIC",
- "JOB_MESSAGE_WARNING",
- "JOB_MESSAGE_ERROR"
- ],
- "location": "query",
- "type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}/messages",
@@ -1461,17 +1461,83 @@
}
}
},
- "revision": "20170701",
+ "revision": "20170718",
"rootUrl": "https://dataflow.googleapis.com/",
"schemas": {
- "ComponentSource": {
- "description": "Description of an interstitial value between transforms in an execution\nstage.",
- "id": "ComponentSource",
+ "WorkItemStatus": {
+ "description": "Conveys a worker's progress through the work described by a WorkItem.",
+ "id": "WorkItemStatus",
"properties": {
- "userName": {
- "description": "Human-readable name for this transform; may be user or system generated.",
+ "workItemId": {
+ "description": "Identifies the WorkItem.",
+ "type": "string"
+ },
+ "errors": {
+ "description": "Specifies errors which occurred during processing. If errors are\nprovided, and completed = true, then the WorkItem is considered\nto have failed.",
+ "items": {
+ "$ref": "Status"
+ },
+ "type": "array"
+ },
+ "metricUpdates": {
+ "description": "DEPRECATED in favor of counter_updates.",
+ "items": {
+ "$ref": "MetricUpdate"
+ },
+ "type": "array"
+ },
+ "dynamicSourceSplit": {
+ "$ref": "DynamicSourceSplit",
+ "description": "See documentation of stop_position."
+ },
+ "sourceOperationResponse": {
+ "$ref": "SourceOperationResponse",
+ "description": "If the work item represented a SourceOperationRequest, and the work\nis completed, contains the result of the operation."
+ },
+ "progress": {
+ "$ref": "ApproximateProgress",
+ "description": "DEPRECATED in favor of reported_progress."
+ },
+ "requestedLeaseDuration": {
+ "description": "Amount of time the worker requests for its lease.",
+ "format": "google-duration",
+ "type": "string"
+ },
+ "reportIndex": {
+ "description": "The report index. When a WorkItem is leased, the lease will\ncontain an initial report index. When a WorkItem's status is\nreported to the system, the report should be sent with\nthat report index, and the response will contain the index the\nworker should use for the next report. Reports received with\nunexpected index values will be rejected by the service.\n\nIn order to preserve idempotency, the worker should not alter the\ncontents of a report, even if the worker must submit the same\nreport multiple times before getting back a response. The worker\nshould not submit a subsequent report until the response for the\nprevious report had been received from the service.",
+ "format": "int64",
"type": "string"
},
+ "stopPosition": {
+ "$ref": "Position",
+ "description": "A worker may split an active map task in two parts, \"primary\" and\n\"residual\", continuing to process the primary part and returning the\nresidual part into the pool of available work.\nThis event is called a \"dynamic split\" and is critical to the dynamic\nwork rebalancing feature. The two obtained sub-tasks are called\n\"parts\" of the split.\nThe parts, if concatenated, must represent the same input as would\nbe read by the current task if the split did not happen.\nThe exact way in which the original task is decomposed into the two\nparts is specified either as a position demarcating them\n(stop_position), or explicitly as two DerivedSources, if this\ntask consumes a user-defined source type (dynamic_source_split).\n\nThe \"current\" task is adjusted as a result of the split: after a task\nwith range [A, B) sends a stop_position update at C, its range is\nconsidered to be [A, C), e.g.:\n* Progress should be interpreted relative to the new range, e.g.\n \"75% completed\" means \"75% of [A, C) completed\"\n* The worker should interpret proposed_stop_position relative to the\n new range, e.g. \"split at 68%\" should be interpreted as\n \"split at 68% of [A, C)\".\n* If the worker chooses to split again using stop_position, only\n stop_positions in [A, C) will be accepted.\n* Etc.\ndynamic_source_split has similar semantics: e.g., if a task with\nsource S splits using dynamic_source_split into {P, R}\n(where P and R must be together equivalent to S), then subsequent\nprogress and proposed_stop_position should be interpreted relative\nto P, and in a potential subsequent dynamic_source_split into {P', R'},\nP' and R' must be together equivalent to P, etc."
+ },
+ "completed": {
+ "description": "True if the WorkItem was completed (successfully or unsuccessfully).",
+ "type": "boolean"
+ },
+ "reportedProgress": {
+ "$ref": "ApproximateReportedProgress",
+ "description": "The worker's progress through this WorkItem."
+ },
+ "sourceFork": {
+ "$ref": "SourceFork",
+ "description": "DEPRECATED in favor of dynamic_source_split."
+ },
+ "counterUpdates": {
+ "description": "Worker output counters for this WorkItem.",
+ "items": {
+ "$ref": "CounterUpdate"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "ComponentSource": {
+ "description": "Description of an interstitial value between transforms in an execution\nstage.",
+ "id": "ComponentSource",
+ "properties": {
"originalTransformOrCollection": {
"description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
"type": "string"
@@ -1479,6 +1545,10 @@
"name": {
"description": "Dataflow service generated name for this source.",
"type": "string"
+ },
+ "userName": {
+ "description": "Human-readable name for this transform; may be user or system generated.",
+ "type": "string"
}
},
"type": "object"
@@ -1487,22 +1557,6 @@
"description": "The Dataflow service's idea of the current state of a WorkItem\nbeing processed by a worker.",
"id": "WorkItemServiceState",
"properties": {
- "metricShortId": {
- "description": "The short ids that workers should use in subsequent metric updates.\nWorkers should strive to use short ids whenever possible, but it is ok\nto request the short_id again if a worker lost track of it\n(e.g. if the worker is recovering from a crash).\nNOTE: it is possible that the response may have short ids for a subset\nof the metrics.",
- "items": {
- "$ref": "MetricShortId"
- },
- "type": "array"
- },
- "nextReportIndex": {
- "description": "The index value to use for the next report sent by the worker.\nNote: If the report call fails for whatever reason, the worker should\nreuse this index for subsequent report attempts.",
- "format": "int64",
- "type": "string"
- },
- "suggestedStopPoint": {
- "$ref": "ApproximateProgress",
- "description": "DEPRECATED in favor of split_request."
- },
"splitRequest": {
"$ref": "ApproximateSplitRequest",
"description": "The progress point in the WorkItem where the Dataflow service\nsuggests that the worker truncate the task."
@@ -1528,6 +1582,22 @@
"description": "Time at which the current lease will expire.",
"format": "google-datetime",
"type": "string"
+ },
+ "metricShortId": {
+ "description": "The short ids that workers should use in subsequent metric updates.\nWorkers should strive to use short ids whenever possible, but it is ok\nto request the short_id again if a worker lost track of it\n(e.g. if the worker is recovering from a crash).\nNOTE: it is possible that the response may have short ids for a subset\nof the metrics.",
+ "items": {
+ "$ref": "MetricShortId"
+ },
+ "type": "array"
+ },
+ "nextReportIndex": {
+ "description": "The index value to use for the next report sent by the worker.\nNote: If the report call fails for whatever reason, the worker should\nreuse this index for subsequent report attempts.",
+ "format": "int64",
+ "type": "string"
+ },
+ "suggestedStopPoint": {
+ "$ref": "ApproximateProgress",
+ "description": "DEPRECATED in favor of split_request."
}
},
"type": "object"
@@ -1536,13 +1606,6 @@
"description": "Identifies a metric, by describing the source which generated the\nmetric.",
"id": "MetricStructuredName",
"properties": {
- "context": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "Zero or more labeled fields which identify the part of the job this\nmetric is associated with, such as the name of a step or collection.\n\nFor example, built-in counters associated with steps will have\ncontext['step'] = <step-name>. Counters associated with PCollections\nin the SDK will have context['pcollection'] = <pcollection-name>.",
- "type": "object"
- },
"name": {
"description": "Worker-defined metric name.",
"type": "string"
@@ -1550,6 +1613,13 @@
"origin": {
"description": "Origin (namespace) of metric name. May be blank for user-define metrics;\nwill be \"dataflow\" for metrics defined by the Dataflow service or SDK.",
"type": "string"
+ },
+ "context": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Zero or more labeled fields which identify the part of the job this\nmetric is associated with, such as the name of a step or collection.\n\nFor example, built-in counters associated with steps will have\ncontext['step'] = <step-name>. Counters associated with PCollections\nin the SDK will have context['pcollection'] = <pcollection-name>.",
+ "type": "object"
}
},
"type": "object"
@@ -1587,6 +1657,14 @@
"description": "Location information for a specific key-range of a sharded computation.\nCurrently we only support UTF-8 character splits to simplify encoding into\nJSON.",
"id": "KeyRangeLocation",
"properties": {
+ "dataDisk": {
+ "description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
+ "type": "string"
+ },
+ "start": {
+ "description": "The start (inclusive) of the key range.",
+ "type": "string"
+ },
"end": {
"description": "The end (exclusive) of the key range.",
"type": "string"
@@ -1598,14 +1676,6 @@
"deliveryEndpoint": {
"description": "The physical location of this range assignment to be used for\nstreaming computation cross-worker message delivery.",
"type": "string"
- },
- "dataDisk": {
- "description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
- "type": "string"
- },
- "start": {
- "description": "The start (inclusive) of the key range.",
- "type": "string"
}
},
"type": "object"
@@ -1621,6 +1691,47 @@
},
"type": "object"
},
+ "SeqMapTask": {
+ "description": "Describes a particular function to invoke.",
+ "id": "SeqMapTask",
+ "properties": {
+ "name": {
+ "description": "The user-provided name of the SeqDo operation.",
+ "type": "string"
+ },
+ "outputInfos": {
+ "description": "Information about each of the outputs.",
+ "items": {
+ "$ref": "SeqMapTaskOutputInfo"
+ },
+ "type": "array"
+ },
+ "inputs": {
+ "description": "Information about each of the inputs.",
+ "items": {
+ "$ref": "SideInputInfo"
+ },
+ "type": "array"
+ },
+ "stageName": {
+ "description": "System-defined name of the stage containing the SeqDo operation.\nUnique across the workflow.",
+ "type": "string"
+ },
+ "systemName": {
+ "description": "System-defined name of the SeqDo operation.\nUnique across the workflow.",
+ "type": "string"
+ },
+ "userFn": {
+ "additionalProperties": {
+ "description": "Properties of the object.",
+ "type": "any"
+ },
+ "description": "The user function to invoke.",
+ "type": "object"
+ }
+ },
+ "type": "object"
+ },
"NameAndKind": {
"description": "Basic metadata about a counter.",
"id": "NameAndKind",
@@ -1658,51 +1769,14 @@
},
"type": "object"
},
- "SeqMapTask": {
- "description": "Describes a particular function to invoke.",
- "id": "SeqMapTask",
- "properties": {
- "systemName": {
- "description": "System-defined name of the SeqDo operation.\nUnique across the workflow.",
- "type": "string"
- },
- "stageName": {
- "description": "System-defined name of the stage containing the SeqDo operation.\nUnique across the workflow.",
- "type": "string"
- },
- "userFn": {
- "additionalProperties": {
- "description": "Properties of the object.",
- "type": "any"
- },
- "description": "The user function to invoke.",
- "type": "object"
- },
- "name": {
- "description": "The user-provided name of the SeqDo operation.",
- "type": "string"
- },
- "outputInfos": {
- "description": "Information about each of the outputs.",
- "items": {
- "$ref": "SeqMapTaskOutputInfo"
- },
- "type": "array"
- },
- "inputs": {
- "description": "Information about each of the inputs.",
- "items": {
- "$ref": "SideInputInfo"
- },
- "type": "array"
- }
- },
- "type": "object"
- },
"WorkerMessageCode": {
"description": "A message code is used to report status and error messages to the service.\nThe message codes are intended to be machine readable. The service will\ntake care of translating these into user understandable messages if\nnecessary.\n\nExample use cases:\n 1. Worker processes reporting successful startup.\n 2. Worker processes reporting specific errors (e.g. package staging\n failure).",
"id": "WorkerMessageCode",
"properties": {
+ "code": {
+ "description": "The code is a string intended for consumption by a machine that identifies\nthe type of message being sent.\nExamples:\n 1. \"HARNESS_STARTED\" might be used to indicate the worker harness has\n started.\n 2. \"GCS_DOWNLOAD_ERROR\" might be used to indicate an error downloading\n a GCS file as part of the boot process of one of the worker containers.\n\nThis is a string and not an enum to make it easy to add new codes without\nwaiting for an API change.",
+ "type": "string"
+ },
"parameters": {
"additionalProperties": {
"description": "Properties of the object.",
@@ -1710,10 +1784,6 @@
},
"description": "Parameters contains specific information about the code.\n\nThis is a struct to allow parameters of different types.\n\nExamples:\n 1. For a \"HARNESS_STARTED\" message parameters might provide the name\n of the worker and additional data like timing information.\n 2. For a \"GCS_DOWNLOAD_ERROR\" parameters might contain fields listing\n the GCS objects being downloaded and fields containing errors.\n\nIn general complex data structures should be avoided. If a worker\nneeds to send a specific and complicated data structure then please\nconsider defining a new proto and adding it to the data oneof in\nWorkerMessageResponse.\n\nConventions:\n Parameters should only be used for information that isn't typically passed\n as a label.\n hostname and other worker identifiers should almost always be passed\n as labels since they will be included on most messages.",
"type": "object"
- },
- "code": {
- "description": "The code is a string intended for consumption by a machine that identifies\nthe type of message being sent.\nExamples:\n 1. \"HARNESS_STARTED\" might be used to indicate the worker harness has\n started.\n 2. \"GCS_DOWNLOAD_ERROR\" might be used to indicate an error downloading\n a GCS file as part of the boot process of one of the worker containers.\n\nThis is a string and not an enum to make it easy to add new codes without\nwaiting for an API change.",
- "type": "string"
}
},
"type": "object"
@@ -1733,13 +1803,6 @@
"description": "MapTask consists of an ordered set of instructions, each of which\ndescribes one particular low-level operation for the worker to\nperform in order to accomplish the MapTask's WorkItem.\n\nEach instruction must appear in the list before any instructions which\ndepends on its output.",
"id": "MapTask",
"properties": {
- "instructions": {
- "description": "The instructions in the MapTask.",
- "items": {
- "$ref": "ParallelInstruction"
- },
- "type": "array"
- },
"stageName": {
"description": "System-defined name of the stage containing this MapTask.\nUnique across the workflow.",
"type": "string"
@@ -1747,6 +1810,13 @@
"systemName": {
"description": "System-defined name of this MapTask.\nUnique across the workflow.",
"type": "string"
+ },
+ "instructions": {
+ "description": "The instructions in the MapTask.",
+ "items": {
+ "$ref": "ParallelInstruction"
+ },
+ "type": "array"
}
},
"type": "object"
@@ -1785,10 +1855,6 @@
"description": "An output of an instruction.",
"id": "InstructionOutput",
"properties": {
- "onlyCountValueBytes": {
- "description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the value size.",
- "type": "boolean"
- },
"codec": {
"additionalProperties": {
"description": "Properties of the object.",
@@ -1812,6 +1878,10 @@
"onlyCountKeyBytes": {
"description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the key size.",
"type": "boolean"
+ },
+ "onlyCountValueBytes": {
+ "description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the value size.",
+ "type": "boolean"
}
},
"type": "object"
@@ -1850,13 +1920,13 @@
"description": "A representation of an integer mean metric contribution.",
"id": "IntegerMean",
"properties": {
- "count": {
- "$ref": "SplitInt64",
- "description": "The number of values being aggregated."
- },
"sum": {
"$ref": "SplitInt64",
"description": "The sum of all values being aggregated."
+ },
+ "count": {
+ "$ref": "SplitInt64",
+ "description": "The number of values being aggregated."
}
},
"type": "object"
@@ -1890,8 +1960,22 @@
"description": "All configuration data for a particular Computation.",
"id": "ComputationTopology",
"properties": {
- "systemStageName": {
- "description": "The system stage name.",
+ "outputs": {
+ "description": "The outputs from the computation.",
+ "items": {
+ "$ref": "StreamLocation"
+ },
+ "type": "array"
+ },
+ "stateFamilies": {
+ "description": "The state family values.",
+ "items": {
+ "$ref": "StateFamilyConfig"
+ },
+ "type": "array"
+ },
+ "systemStageName": {
+ "description": "The system stage name.",
"type": "string"
},
"computationId": {
@@ -1911,20 +1995,6 @@
"$ref": "KeyRangeLocation"
},
"type": "array"
- },
- "stateFamilies": {
- "description": "The state family values.",
- "items": {
- "$ref": "StateFamilyConfig"
- },
- "type": "array"
- },
- "outputs": {
- "description": "The outputs from the computation.",
- "items": {
- "$ref": "StreamLocation"
- },
- "type": "array"
}
},
"type": "object"
@@ -1933,15 +2003,6 @@
"description": "The environment values to set at runtime.",
"id": "RuntimeEnvironment",
"properties": {
- "maxWorkers": {
- "description": "The maximum number of Google Compute Engine instances to be made\navailable to your pipeline during execution, from 1 to 1000.",
- "format": "int32",
- "type": "integer"
- },
- "bypassTempDirValidation": {
- "description": "Whether to bypass the safety checks for the job's temporary directory.\nUse with caution.",
- "type": "boolean"
- },
"serviceAccountEmail": {
"description": "The email address of the service account to run the job as.",
"type": "string"
@@ -1950,6 +2011,10 @@
"description": "The Cloud Storage path to use for temporary files.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
"type": "string"
},
+ "bypassTempDirValidation": {
+ "description": "Whether to bypass the safety checks for the job's temporary directory.\nUse with caution.",
+ "type": "boolean"
+ },
"machineType": {
"description": "The machine type to use for the job. Defaults to the value from the\ntemplate if not specified.",
"type": "string"
@@ -1957,17 +2022,11 @@
"zone": {
"description": "The Compute Engine [availability\nzone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)\nfor launching worker instances to run your pipeline.",
"type": "string"
- }
- },
- "type": "object"
- },
- "MountedDataDisk": {
- "description": "Describes mounted data disk.",
- "id": "MountedDataDisk",
- "properties": {
- "dataDisk": {
- "description": "The name of the data disk.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
- "type": "string"
+ },
+ "maxWorkers": {
+ "description": "The maximum number of Google Compute Engine instances to be made\navailable to your pipeline during execution, from 1 to 1000.",
+ "format": "int32",
+ "type": "integer"
}
},
"type": "object"
@@ -1987,6 +2046,17 @@
},
"type": "object"
},
+ "MountedDataDisk": {
+ "description": "Describes mounted data disk.",
+ "id": "MountedDataDisk",
+ "properties": {
+ "dataDisk": {
+ "description": "The name of the data disk.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
"LaunchTemplateResponse": {
"description": "Response to the request to launch a template.",
"id": "LaunchTemplateResponse",
@@ -1998,10 +2068,113 @@
},
"type": "object"
},
+ "DerivedSource": {
+ "description": "Specification of one of the bundles produced as a result of splitting\na Source (e.g. when executing a SourceSplitRequest, or when\nsplitting an active task using WorkItemStatus.dynamic_source_split),\nrelative to the source being split.",
+ "id": "DerivedSource",
+ "properties": {
+ "derivationMode": {
+ "description": "What source to base the produced source on (if any).",
+ "enum": [
+ "SOURCE_DERIVATION_MODE_UNKNOWN",
+ "SOURCE_DERIVATION_MODE_INDEPENDENT",
+ "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
+ "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
+ ],
+ "enumDescriptions": [
+ "The source derivation is unknown, or unspecified.",
+ "Produce a completely independent Source with no base.",
+ "Produce a Source based on the Source being split.",
+ "Produce a Source based on the base of the Source being split."
+ ],
+ "type": "string"
+ },
+ "source": {
+ "$ref": "Source",
+ "description": "Specification of the source."
+ }
+ },
+ "type": "object"
+ },
+ "DynamicSourceSplit": {
+ "description": "When a task splits using WorkItemStatus.dynamic_source_split, this\nmessage describes the two parts of the split relative to the\ndescription of the current task's input.",
+ "id": "DynamicSourceSplit",
+ "properties": {
+ "residual": {
+ "$ref": "DerivedSource",
+ "description": "Residual part (returned to the pool of work).\nSpecified relative to the previously-current source."
+ },
+ "primary": {
+ "$ref": "DerivedSource",
+ "description": "Primary part (continued to be processed by worker).\nSpecified relative to the previously-current source.\nBecomes current."
+ }
+ },
+ "type": "object"
+ },
"Job": {
"description": "Defines a job to be run by the Cloud Dataflow service.",
"id": "Job",
"properties": {
+ "clientRequestId": {
+ "description": "The client's unique identifier of the job, re-used across retried attempts.\nIf this field is set, the service will ensure its uniqueness.\nThe request to create a job will fail if the service has knowledge of a\npreviously submitted job with the same client's ID and job name.\nThe caller may use this field to ensure idempotence of job\ncreation across retried attempts to create a job.\nBy default, the field is empty and, in that case, the service ignores it.",
+ "type": "string"
+ },
+ "name": {
+ "description": "The user-specified Cloud Dataflow job name.\n\nOnly one Job with a given name may exist in a project at any\ngiven time. If a caller attempts to create a Job with the same\nname as an already-existing Job, the attempt returns the\nexisting Job.\n\nThe name must match the regular expression\n`[a-z]([-a-z0-9]{0,38}[a-z0-9])?`",
+ "type": "string"
+ },
+ "steps": {
+ "description": "The top-level steps that constitute the entire job.",
+ "items": {
+ "$ref": "Step"
+ },
+ "type": "array"
+ },
+ "replacedByJobId": {
+ "description": "If another job is an update of this job (and thus, this job is in\n`JOB_STATE_UPDATED`), this field contains the ID of that job.",
+ "type": "string"
+ },
+ "executionInfo": {
+ "$ref": "JobExecutionInfo",
+ "description": "Deprecated."
+ },
+ "id": {
+ "description": "The unique ID of this job.\n\nThis field is set by the Cloud Dataflow service when the Job is\ncreated, and is immutable for the life of the job.",
+ "type": "string"
+ },
+ "currentState": {
+ "description": "The current state of the job.\n\nJobs are created in the `JOB_STATE_STOPPED` state unless otherwise\nspecified.\n\nA job in the `JOB_STATE_RUNNING` state may asynchronously enter a\nterminal state. After a job has reached a terminal state, no\nfurther state updates may be made.\n\nThis field may be mutated by the Cloud Dataflow service;\ncallers cannot mutate it.",
+ "enum": [
+ "JOB_STATE_UNKNOWN",
+ "JOB_STATE_STOPPED",
+ "JOB_STATE_RUNNING",
+ "JOB_STATE_DONE",
+ "JOB_STATE_FAILED",
+ "JOB_STATE_CANCELLED",
+ "JOB_STATE_UPDATED",
+ "JOB_STATE_DRAINING",
+ "JOB_STATE_DRAINED",
+ "JOB_STATE_PENDING",
+ "JOB_STATE_CANCELLING"
+ ],
+ "enumDescriptions": [
+ "The job's run state isn't specified.",
+ "`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
+ "`JOB_STATE_RUNNING` indicates that the job is currently running.",
+ "`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
+ "`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
+ "`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
+ "`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
+ "`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
+ "`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
+ "'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
+ "'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
+ ],
+ "type": "string"
+ },
+ "location": {
+ "description": "The location that contains this job.",
+ "type": "string"
+ },
"currentStateTime": {
"description": "The timestamp associated with the current state.",
"format": "google-datetime",
@@ -2037,6 +2210,10 @@
},
"type": "array"
},
+ "projectId": {
+ "description": "The ID of the Cloud Platform project that the job belongs to.",
+ "type": "string"
+ },
"type": {
"description": "The type of Cloud Dataflow job.",
"enum": [
@@ -2051,10 +2228,6 @@
],
"type": "string"
},
- "projectId": {
- "description": "The ID of the Cloud Platform project that the job belongs to.",
- "type": "string"
- },
"pipelineDescription": {
"$ref": "PipelineDescription",
"description": "Preliminary field: The format of this data may change at any time.\nA description of the user pipeline and stages through which it is executed.\nCreated by Cloud Dataflow service. Only retrieved with\nJOB_VIEW_DESCRIPTION or JOB_VIEW_ALL."
@@ -2099,109 +2272,6 @@
"type": "string"
},
"type": "array"
- },
- "clientRequestId": {
- "description": "The client's unique identifier of the job, re-used across retried attempts.\nIf this field is set, the service will ensure its uniqueness.\nThe request to create a job will fail if the service has knowledge of a\npreviously submitted job with the same client's ID and job name.\nThe caller may use this field to ensure idempotence of job\ncreation across retried attempts to create a job.\nBy default, the field is empty and, in that case, the service ignores it.",
- "type": "string"
- },
- "name": {
- "description": "The user-specified Cloud Dataflow job name.\n\nOnly one Job with a given name may exist in a project at any\ngiven time. If a caller attempts to create a Job with the same\nname as an already-existing Job, the attempt returns the\nexisting Job.\n\nThe name must match the regular expression\n`[a-z]([-a-z0-9]{0,38}[a-z0-9])?`",
- "type": "string"
- },
- "replacedByJobId": {
- "description": "If another job is an update of this job (and thus, this job is in\n`JOB_STATE_UPDATED`), this field contains the ID of that job.",
- "type": "string"
- },
- "steps": {
- "description": "The top-level steps that constitute the entire job.",
- "items": {
- "$ref": "Step"
- },
- "type": "array"
- },
- "executionInfo": {
- "$ref": "JobExecutionInfo",
- "description": "Deprecated."
- },
- "id": {
- "description": "The unique ID of this job.\n\nThis field is set by the Cloud Dataflow service when the Job is\ncreated, and is immutable for the life of the job.",
- "type": "string"
- },
- "currentState": {
- "description": "The current state of the job.\n\nJobs are created in the `JOB_STATE_STOPPED` state unless otherwise\nspecified.\n\nA job in the `JOB_STATE_RUNNING` state may asynchronously enter a\nterminal state. After a job has reached a terminal state, no\nfurther state updates may be made.\n\nThis field may be mutated by the Cloud Dataflow service;\ncallers cannot mutate it.",
- "enum": [
- "JOB_STATE_UNKNOWN",
- "JOB_STATE_STOPPED",
- "JOB_STATE_RUNNING",
- "JOB_STATE_DONE",
- "JOB_STATE_FAILED",
- "JOB_STATE_CANCELLED",
- "JOB_STATE_UPDATED",
- "JOB_STATE_DRAINING",
- "JOB_STATE_DRAINED",
- "JOB_STATE_PENDING",
- "JOB_STATE_CANCELLING"
- ],
- "enumDescriptions": [
- "The job's run state isn't specified.",
- "`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
- "`JOB_STATE_RUNNING` indicates that the job is currently running.",
- "`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
- "`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
- "`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
- "`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
- "`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
- "`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
- "'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
- "'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
- ],
- "type": "string"
- },
- "location": {
- "description": "The location that contains this job.",
- "type": "string"
- }
- },
- "type": "object"
- },
- "DynamicSourceSplit": {
- "description": "When a task splits using WorkItemStatus.dynamic_source_split, this\nmessage describes the two parts of the split relative to the\ndescription of the current task's input.",
- "id": "DynamicSourceSplit",
- "properties": {
- "residual": {
- "$ref": "DerivedSource",
- "description": "Residual part (returned to the pool of work).\nSpecified relative to the previously-current source."
- },
- "primary": {
- "$ref": "DerivedSource",
- "description": "Primary part (continued to be processed by worker).\nSpecified relative to the previously-current source.\nBecomes current."
- }
- },
- "type": "object"
- },
- "DerivedSource": {
- "description": "Specification of one of the bundles produced as a result of splitting\na Source (e.g. when executing a SourceSplitRequest, or when\nsplitting an active task using WorkItemStatus.dynamic_source_split),\nrelative to the source being split.",
- "id": "DerivedSource",
- "properties": {
- "derivationMode": {
- "description": "What source to base the produced source on (if any).",
- "enum": [
- "SOURCE_DERIVATION_MODE_UNKNOWN",
- "SOURCE_DERIVATION_MODE_INDEPENDENT",
- "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
- "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
- ],
- "enumDescriptions": [
- "The source derivation is unknown, or unspecified.",
- "Produce a completely independent Source with no base.",
- "Produce a Source based on the Source being split.",
- "Produce a Source based on the base of the Source being split."
- ],
- "type": "string"
- },
- "source": {
- "$ref": "Source",
- "description": "Specification of the source."
}
},
"type": "object"
@@ -2210,23 +2280,17 @@
"description": "The result of a SourceOperationRequest, specified in\nReportWorkItemStatusRequest.source_operation when the work item\nis completed.",
"id": "SourceOperationResponse",
"properties": {
- "getMetadata": {
- "$ref": "SourceGetMetadataResponse",
- "description": "A response to a request to get metadata about a source."
- },
"split": {
"$ref": "SourceSplitResponse",
"description": "A response to a request to split a source."
+ },
+ "getMetadata": {
+ "$ref": "SourceGetMetadataResponse",
+ "description": "A response to a request to get metadata about a source."
}
},
"type": "object"
},
- "SendDebugCaptureResponse": {
- "description": "Response to a send capture request.\nnothing",
- "id": "SendDebugCaptureResponse",
- "properties": {},
- "type": "object"
- },
"SideInputInfo": {
"description": "Information about a side input of a DoFn or an input of a SeqDoFn.",
"id": "SideInputInfo",
@@ -2253,17 +2317,23 @@
},
"type": "object"
},
- "CounterStructuredNameAndMetadata": {
- "description": "A single message which encapsulates structured name and metadata for a given\ncounter.",
- "id": "CounterStructuredNameAndMetadata",
+ "SendDebugCaptureResponse": {
+ "description": "Response to a send capture request.\nnothing",
+ "id": "SendDebugCaptureResponse",
+ "properties": {},
+ "type": "object"
+ },
+ "WriteInstruction": {
+ "description": "An instruction that writes records.\nTakes one input, produces no outputs.",
+ "id": "WriteInstruction",
"properties": {
- "name": {
- "$ref": "CounterStructuredName",
- "description": "Structured name of the counter."
+ "input": {
+ "$ref": "InstructionInput",
+ "description": "The input."
},
- "metadata": {
- "$ref": "CounterMetadata",
- "description": "Metadata associated with a counter"
+ "sink": {
+ "$ref": "Sink",
+ "description": "The sink to write to."
}
},
"type": "object"
@@ -2272,47 +2342,29 @@
"description": "A position that encapsulates an inner position and an index for the inner\nposition. A ConcatPosition can be used by a reader of a source that\nencapsulates a set of other sources.",
"id": "ConcatPosition",
"properties": {
- "index": {
- "description": "Index of the inner source.",
- "format": "int32",
- "type": "integer"
- },
"position": {
"$ref": "Position",
"description": "Position within the inner source."
- }
- },
- "type": "object"
- },
- "WriteInstruction": {
- "description": "An instruction that writes records.\nTakes one input, produces no outputs.",
- "id": "WriteInstruction",
- "properties": {
- "input": {
- "$ref": "InstructionInput",
- "description": "The input."
},
- "sink": {
- "$ref": "Sink",
- "description": "The sink to write to."
+ "index": {
+ "description": "Index of the inner source.",
+ "format": "int32",
+ "type": "integer"
}
},
"type": "object"
},
- "StreamingComputationRanges": {
- "description": "Describes full or partial data disk assignment information of the computation\nranges.",
- "id": "StreamingComputationRanges",
+ "CounterStructuredNameAndMetadata": {
+ "description": "A single message which encapsulates structured name and metadata for a given\ncounter.",
+ "id": "CounterStructuredNameAndMetadata",
"properties": {
- "rangeAssignments": {
- "description": "Data disk assignments for ranges from this computation.",
- "items": {
- "$ref": "KeyRangeDataDiskAssignment"
- },
- "type": "array"
+ "name": {
+ "$ref": "CounterStructuredName",
+ "description": "Structured name of the counter."
},
- "computationId": {
- "description": "The ID of the computation.",
- "type": "string"
+ "metadata": {
+ "$ref": "CounterMetadata",
+ "description": "Metadata associated with a counter"
}
},
"type": "object"
@@ -2343,6 +2395,24 @@
},
"type": "object"
},
+ "StreamingComputationRanges": {
+ "description": "Describes full or partial data disk assignment information of the computation\nranges.",
+ "id": "StreamingComputationRanges",
+ "properties": {
+ "computationId": {
+ "description": "The ID of the computation.",
+ "type": "string"
+ },
+ "rangeAssignments": {
+ "description": "Data disk assignments for ranges from this computation.",
+ "items": {
+ "$ref": "KeyRangeDataDiskAssignment"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
"ExecutionStageSummary": {
"description": "Description of the composing transforms, names/ids, and input/outputs of a\nstage of execution. Some composing transforms and sources may have been\ngenerated by the Dataflow service during execution planning.",
"id": "ExecutionStageSummary",
@@ -2412,36 +2482,36 @@
},
"type": "object"
},
+ "LogBucket": {
+ "description": "Bucket of values for Distribution's logarithmic histogram.",
+ "id": "LogBucket",
+ "properties": {
+ "count": {
+ "description": "Number of values in this bucket.",
+ "format": "int64",
+ "type": "string"
+ },
+ "log": {
+ "description": "floor(log2(value)); defined to be zero for nonpositive values.\n log(-1) = 0\n log(0) = 0\n log(1) = 0\n log(2) = 1\n log(3) = 1\n log(4) = 2\n log(5) = 2",
+ "format": "int32",
+ "type": "integer"
+ }
+ },
+ "type": "object"
+ },
"SendWorkerMessagesRequest": {
"description": "A request for sending worker messages to the service.",
"id": "SendWorkerMessagesRequest",
"properties": {
- "location": {
- "description": "The location which contains the job",
- "type": "string"
- },
"workerMessages": {
"description": "The WorkerMessages to send.",
"items": {
"$ref": "WorkerMessage"
},
"type": "array"
- }
- },
- "type": "object"
- },
- "LogBucket": {
- "description": "Bucket of values for Distribution's logarithmic histogram.",
- "id": "LogBucket",
- "properties": {
- "log": {
- "description": "floor(log2(value)); defined to be zero for nonpositive values.\n log(-1) = 0\n log(0) = 0\n log(1) = 0\n log(2) = 1\n log(3) = 1\n log(4) = 2\n log(5) = 2",
- "format": "int32",
- "type": "integer"
},
- "count": {
- "description": "Number of values in this bucket.",
- "format": "int64",
+ "location": {
+ "description": "The location which contains the job",
"type": "string"
}
},
@@ -2451,6 +2521,10 @@
"description": "DEPRECATED in favor of DerivedSource.",
"id": "SourceSplitShard",
"properties": {
+ "source": {
+ "$ref": "Source",
+ "description": "DEPRECATED"
+ },
"derivationMode": {
"description": "DEPRECATED",
"enum": [
@@ -2466,10 +2540,6 @@
"Produce a Source based on the base of the Source being split."
],
"type": "string"
- },
- "source": {
- "$ref": "Source",
- "description": "DEPRECATED"
}
},
"type": "object"
@@ -2478,11 +2548,6 @@
"description": "Modeled after information exposed by /proc/stat.",
"id": "CPUTime",
"properties": {
- "rate": {
- "description": "Average CPU utilization rate (% non-idle cpu / second) since previous\nsample.",
- "format": "double",
- "type": "number"
- },
"timestamp": {
"description": "Timestamp of the measurement.",
"format": "google-datetime",
@@ -2492,6 +2557,11 @@
"description": "Total active CPU time across all cores (ie., non-idle) in milliseconds\nsince start-up.",
"format": "uint64",
"type": "string"
+ },
+ "rate": {
+ "description": "Average CPU utilization rate (% non-idle cpu / second) since previous\nsample.",
+ "format": "double",
+ "type": "number"
}
},
"type": "object"
@@ -2500,20 +2570,24 @@
"description": "Describes the environment in which a Dataflow Job runs.",
"id": "Environment",
"properties": {
- "sdkPipelineOptions": {
+ "serviceAccountEmail": {
+ "description": "Identity to run virtual machines as. Defaults to the default account.",
+ "type": "string"
+ },
+ "userAgent": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
- "description": "The Cloud Dataflow SDK pipeline options specified by the user. These\noptions are passed through the service and are used to recreate the\nSDK pipeline options on the worker in a language agnostic and platform\nindependent way.",
+ "description": "A description of the process that generated the request.",
"type": "object"
},
- "userAgent": {
+ "sdkPipelineOptions": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
- "description": "A description of the process that generated the request.",
+ "description": "The Cloud Dataflow SDK pipeline options specified by the user. These\noptions are passed through the service and are used to recreate the\nSDK pipeline options on the worker in a language agnostic and platform\nindependent way.",
"type": "object"
},
"clusterManagerApiService": {
@@ -2557,10 +2631,6 @@
},
"description": "A structure describing which components and their versions of the service\nare required in order to run the job.",
"type": "object"
- },
- "serviceAccountEmail": {
- "description": "Identity to run virtual machines as. Defaults to the default account.",
- "type": "string"
}
},
"type": "object"
@@ -2569,6 +2639,13 @@
"description": "A task which describes what action should be performed for the specified\nstreaming computation ranges.",
"id": "StreamingComputationTask",
"properties": {
+ "computationRanges": {
+ "description": "Contains ranges of a streaming computation this task should apply to.",
+ "items": {
+ "$ref": "StreamingComputationRanges"
+ },
+ "type": "array"
+ },
"dataDisks": {
"description": "Describes the set of data disks this task should apply to.",
"items": {
@@ -2589,13 +2666,6 @@
"Start processing specified streaming computation range(s)."
],
"type": "string"
- },
- "computationRanges": {
- "description": "Contains ranges of a streaming computation this task should apply to.",
- "items": {
- "$ref": "StreamingComputationRanges"
- },
- "type": "array"
}
},
"type": "object"
@@ -2604,6 +2674,10 @@
"description": "Request to send encoded debug information.",
"id": "SendDebugCaptureRequest",
"properties": {
+ "componentId": {
+ "description": "The internal component id for which debug information is sent.",
+ "type": "string"
+ },
"workerId": {
"description": "The worker id, i.e., VM hostname.",
"type": "string"
@@ -2615,10 +2689,6 @@
"data": {
"description": "The encoded debug information.",
"type": "string"
- },
- "componentId": {
- "description": "The internal component id for which debug information is sent.",
- "type": "string"
}
},
"type": "object"
@@ -2682,6 +2752,10 @@
"description": "Identifies a pubsub location to use for transferring data into or\nout of a streaming Dataflow job.",
"id": "PubsubLocation",
"properties": {
+ "subscription": {
+ "description": "A pubsub subscription, in the form of\n\"pubsub.googleapis.com/subscriptions/<project-id>/<subscription-name>\"",
+ "type": "string"
+ },
"dropLateData": {
"description": "Indicates whether the pipeline allows late-arriving data.",
"type": "boolean"
@@ -2705,10 +2779,6 @@
"timestampLabel": {
"description": "If set, contains a pubsub label from which to extract record timestamps.\nIf left empty, record timestamps will be generated upon arrival.",
"type": "string"
- },
- "subscription": {
- "description": "A pubsub subscription, in the form of\n\"pubsub.googleapis.com/subscriptions/<project-id>/<subscription-name>\"",
- "type": "string"
}
},
"type": "object"
@@ -2717,11 +2787,6 @@
"description": "WorkerHealthReport contains information about the health of a worker.\n\nThe VM should be identified by the labels attached to the WorkerMessage that\nthis health ping belongs to.",
"id": "WorkerHealthReport",
"properties": {
- "vmStartupTime": {
- "description": "The time the VM was booted.",
- "format": "google-datetime",
- "type": "string"
- },
"reportInterval": {
"description": "The interval at which the worker is sending health reports.\nThe default value of 0 should be interpreted as the field is not being\nexplicitly set by the worker.",
"format": "google-duration",
@@ -2741,6 +2806,11 @@
"type": "object"
},
"type": "array"
+ },
+ "vmStartupTime": {
+ "description": "The time the VM was booted.",
+ "format": "google-datetime",
+ "type": "string"
}
},
"type": "object"
@@ -2749,15 +2819,6 @@
"description": "A particular message pertaining to a Dataflow job.",
"id": "JobMessage",
"properties": {
- "time": {
- "description": "The timestamp of the message.",
- "format": "google-datetime",
- "type": "string"
- },
- "id": {
- "description": "Deprecated.",
- "type": "string"
- },
"messageImportance": {
"description": "Importance level of the message.",
"enum": [
@@ -2781,6 +2842,15 @@
"messageText": {
"description": "The text of the message.",
"type": "string"
+ },
+ "time": {
+ "description": "The timestamp of the message.",
+ "format": "google-datetime",
+ "type": "string"
+ },
+ "id": {
+ "description": "Deprecated.",
+ "type": "string"
}
},
"type": "object"
@@ -2856,6 +2926,15 @@
"description": "A structured message reporting an autoscaling decision made by the Dataflow\nservice.",
"id": "AutoscalingEvent",
"properties": {
+ "time": {
+ "description": "The time this event was emitted to indicate a new target or current\nnum_workers value.",
+ "format": "google-datetime",
+ "type": "string"
+ },
+ "description": {
+ "$ref": "StructuredMessage",
+ "description": "A message describing why the system decided to adjust the current\nnumber of workers, why it failed, or why the system decided to\nnot make any changes to the number of workers."
+ },
"eventType": {
"description": "The type of autoscaling event to report.",
"enum": [
@@ -2883,15 +2962,6 @@
"description": "The current number of workers the job has.",
"format": "int64",
"type": "string"
- },
- "time": {
- "description": "The time this event was emitted to indicate a new target or current\nnum_workers value.",
- "format": "google-datetime",
- "type": "string"
- },
- "description": {
- "$ref": "StructuredMessage",
- "description": "A message describing why the system decided to adjust the current\nnumber of workers, why it failed, or why the system decided to\nnot make any changes to the number of workers."
}
},
"type": "object"
@@ -2933,30 +3003,18 @@
"description": "Taskrunner configuration settings.",
"id": "TaskRunnerSettings",
"properties": {
- "baseUrl": {
- "description": "The base URL for the taskrunner to use when accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
- "type": "string"
- },
- "logToSerialconsole": {
- "description": "Whether to send taskrunner log info to Google Compute Engine VM serial\nconsole.",
- "type": "boolean"
- },
- "continueOnException": {
- "description": "Whether to continue taskrunner if an exception is hit.",
- "type": "boolean"
- },
"parallelWorkerSettings": {
"$ref": "WorkerSettings",
"description": "The settings to pass to the parallel worker harness."
},
- "taskUser": {
- "description": "The UNIX user ID on the worker VM to use for tasks launched by\ntaskrunner; e.g. \"root\".",
- "type": "string"
- },
"vmId": {
"description": "The ID string of the VM.",
"type": "string"
},
+ "taskUser": {
+ "description": "The UNIX user ID on the worker VM to use for tasks launched by\ntaskrunner; e.g. \"root\".",
+ "type": "string"
+ },
"alsologtostderr": {
"description": "Whether to also send taskrunner log info to stderr.",
"type": "boolean"
@@ -2973,6 +3031,10 @@
"description": "The directory on the VM to store logs.",
"type": "string"
},
+ "dataflowApiVersion": {
+ "description": "The API version of endpoint, e.g. \"v1b3\"",
+ "type": "string"
+ },
"oauthScopes": {
"description": "The OAuth2 scopes to be requested by the taskrunner in order to\naccess the Cloud Dataflow API.",
"items": {
@@ -2980,37 +3042,45 @@
},
"type": "array"
},
- "dataflowApiVersion": {
- "description": "The API version of endpoint, e.g. \"v1b3\"",
+ "streamingWorkerMainClass": {
+ "description": "The streaming worker main class name.",
"type": "string"
},
"logUploadLocation": {
"description": "Indicates where to put logs. If this is not specified, the logs\nwill not be uploaded.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
"type": "string"
},
- "streamingWorkerMainClass": {
- "description": "The streaming worker main class name.",
- "type": "string"
- },
"workflowFileName": {
"description": "The file to store the workflow in.",
"type": "string"
},
+ "commandlinesFileName": {
+ "description": "The file to store preprocessing commands in.",
+ "type": "string"
+ },
"languageHint": {
"description": "The suggested backend language.",
"type": "string"
},
- "commandlinesFileName": {
- "description": "The file to store preprocessing commands in.",
+ "baseTaskDir": {
+ "description": "The location on the worker for task-specific subdirectories.",
"type": "string"
},
"tempStoragePrefix": {
"description": "The prefix of the resources the taskrunner should use for\ntemporary storage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
"type": "string"
},
- "baseTaskDir": {
- "description": "The location on the worker for task-specific subdirectories.",
+ "baseUrl": {
+ "description": "The base URL for the taskrunner to use when accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
"type": "string"
+ },
+ "logToSerialconsole": {
+ "description": "Whether to send taskrunner log info to Google Compute Engine VM serial\nconsole.",
+ "type": "boolean"
+ },
+ "continueOnException": {
+ "description": "Whether to continue taskrunner if an exception is hit.",
+ "type": "boolean"
}
},
"type": "object"
@@ -3069,6 +3139,21 @@
"description": "A source that records can be read and decoded from.",
"id": "Source",
"properties": {
+ "metadata": {
+ "$ref": "SourceMetadata",
+ "description": "Optionally, metadata for this source can be supplied right away,\navoiding a SourceGetMetadataOperation roundtrip\n(see SourceOperationRequest).\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated."
+ },
+ "baseSpecs": {
+ "description": "While splitting, sources may specify the produced bundles\nas differences against another source, in order to save backend-side\nmemory and allow bigger jobs. For details, see SourceSplitRequest.\nTo support this use case, the full set of parameters of the source\nis logically obtained by taking the latest explicitly specified value\nof each parameter in the order:\nbase_specs (later items win), spec (overrides anything in base_specs).",
+ "items": {
+ "additionalProperties": {
+ "description": "Properties of the object.",
+ "type": "any"
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
"doesNotNeedSplitting": {
"description": "Setting this value to true hints to the framework that the source\ndoesn't need splitting, and using SourceSplitRequest on it would\nyield SOURCE_SPLIT_OUTCOME_USE_CURRENT.\n\nE.g. a file splitter may set this to true when splitting a single file\ninto a set of byte ranges of appropriate size, and set this\nto false when splitting a filepattern into individual files.\nHowever, for efficiency, a file splitter may decide to produce\nfile subranges directly from the filepattern to avoid a splitting\nround-trip.\n\nSee SourceSplitRequest for an overview of the splitting process.\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated.",
"type": "boolean"
@@ -3088,21 +3173,6 @@
},
"description": "The source to read from, plus its parameters.",
"type": "object"
- },
- "metadata": {
- "$ref": "SourceMetadata",
- "description": "Optionally, metadata for this source can be supplied right away,\navoiding a SourceGetMetadataOperation roundtrip\n(see SourceOperationRequest).\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated."
- },
- "baseSpecs": {
- "description": "While splitting, sources may specify the produced bundles\nas differences against another source, in order to save backend-side\nmemory and allow bigger jobs. For details, see SourceSplitRequest.\nTo support this use case, the full set of parameters of the source\nis logically obtained by taking the latest explicitly specified value\nof each parameter in the order:\nbase_specs (later items win), spec (overrides anything in base_specs).",
- "items": {
- "additionalProperties": {
- "description": "Properties of the object.",
- "type": "any"
- },
- "type": "object"
- },
- "type": "array"
}
},
"type": "object"
@@ -3111,18 +3181,76 @@
"description": "Describes one particular pool of Cloud Dataflow workers to be\ninstantiated by the Cloud Dataflow service in order to perform the\ncomputations required by a job. Note that a workflow job may use\nmultiple pools, in order to match the various computational\nrequirements of the various stages of the job.",
"id": "WorkerPool",
"properties": {
- "workerHarnessContainerImage": {
- "description": "Required. Docker container image that executes the Cloud Dataflow worker\nharness, residing in Google Container Registry.",
+ "numThreadsPerWorker": {
+ "description": "The number of threads per worker harness. If empty or unspecified, the\nservice will choose a number of threads (according to the number of cores\non the selected machine type for batch, or 1 by convention for streaming).",
+ "format": "int32",
+ "type": "integer"
+ },
+ "numWorkers": {
+ "description": "Number of Google Compute Engine workers in this pool needed to\nexecute the job. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
+ "format": "int32",
+ "type": "integer"
+ },
+ "zone": {
+ "description": "Zone to run the worker pools in. If empty or unspecified, the service\nwill attempt to choose a reasonable default.",
"type": "string"
},
- "diskType": {
- "description": "Type of root disk for VMs. If empty or unspecified, the service will\nattempt to choose a reasonable default.",
+ "diskSourceImage": {
+ "description": "Fully qualified source image for disks.",
+ "type": "string"
+ },
+ "packages": {
+ "description": "Packages to be installed on workers.",
+ "items": {
+ "$ref": "Package"
+ },
+ "type": "array"
+ },
+ "teardownPolicy": {
+ "description": "Sets the policy for determining when to turndown worker pool.\nAllowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and\n`TEARDOWN_NEVER`.\n`TEARDOWN_ALWAYS` means workers are always torn down regardless of whether\nthe job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down\nif the job succeeds. `TEARDOWN_NEVER` means the workers are never torn\ndown.\n\nIf the workers are not torn down by the service, they will\ncontinue to run and use Google Compute Engine VM resources in the\nuser's project until they are explicitly terminated by the user.\nBecause of this, Google recommends using the `TEARDOWN_ALWAYS`\npolicy except for small, manually supervised test jobs.\n\nIf unknown or unspecified, the service will attempt to choose a reasonable\ndefault.",
+ "enum": [
+ "TEARDOWN_POLICY_UNKNOWN",
+ "TEARDOWN_ALWAYS",
+ "TEARDOWN_ON_SUCCESS",
+ "TEARDOWN_NEVER"
+ ],
+ "enumDescriptions": [
+ "The teardown policy isn't specified, or is unknown.",
+ "Always teardown the resource.",
+ "Teardown the resource on success. This is useful for debugging\nfailures.",
+ "Never teardown the resource. This is useful for debugging and\ndevelopment."
+ ],
+ "type": "string"
+ },
+ "onHostMaintenance": {
+ "description": "The action to take on host maintenance, as defined by the Google\nCompute Engine API.",
+ "type": "string"
+ },
+ "poolArgs": {
+ "additionalProperties": {
+ "description": "Properties of the object. Contains field @type with type URL.",
+ "type": "any"
+ },
+ "description": "Extra arguments for this worker pool.",
+ "type": "object"
+ },
+ "diskSizeGb": {
+ "description": "Size of root disk for VMs, in GB. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
+ "format": "int32",
+ "type": "integer"
+ },
+ "workerHarnessContainerImage": {
+ "description": "Required. Docker container image that executes the Cloud Dataflow worker\nharness, residing in Google Container Registry.",
"type": "string"
},
"machineType": {
"description": "Machine type (e.g. \"n1-standard-1\"). If empty or unspecified, the\nservice will attempt to choose a reasonable default.",
"type": "string"
},
+ "diskType": {
+ "description": "Type of root disk for VMs. If empty or unspecified, the service will\nattempt to choose a reasonable default.",
+ "type": "string"
+ },
"kind": {
"description": "The kind of the worker pool; currently only `harness` and `shuffle`\nare supported.",
"type": "string"
@@ -3152,98 +3280,40 @@
],
"type": "string"
},
- "taskrunnerSettings": {
- "$ref": "TaskRunnerSettings",
- "description": "Settings passed through to Google Compute Engine workers when\nusing the standard Dataflow task runner. Users should ignore\nthis field."
- },
"autoscalingSettings": {
"$ref": "AutoscalingSettings",
"description": "Settings for autoscaling of this WorkerPool."
},
+ "taskrunnerSettings": {
+ "$ref": "TaskRunnerSettings",
+ "description": "Settings passed through to Google Compute Engine workers when\nusing the standard Dataflow task runner. Users should ignore\nthis field."
+ },
"metadata": {
"additionalProperties": {
"type": "string"
},
"description": "Metadata to set on the Google Compute Engine VMs.",
"type": "object"
- },
- "network": {
- "description": "Network to which VMs will be assigned. If empty or unspecified,\nthe service will use the network \"default\".",
- "type": "string"
- },
- "defaultPackageSet": {
- "description": "The default package set to install. This allows the service to\nselect a default set of packages which are useful to worker\nharnesses written in a particular language.",
- "enum": [
- "DEFAULT_PACKAGE_SET_UNKNOWN",
- "DEFAULT_PACKAGE_SET_NONE",
- "DEFAULT_PACKAGE_SET_JAVA",
- "DEFAULT_PACKAGE_SET_PYTHON"
- ],
- "enumDescriptions": [
- "The default set of packages to stage is unknown, or unspecified.",
- "Indicates that no packages should be staged at the worker unless\nexplicitly specified by the job.",
- "Stage packages typically useful to workers written in Java.",
- "Stage pacakges typically useful to workers written in Python."
- ],
- "type": "string"
- },
- "numThreadsPerWorker": {
- "description": "The number of threads per worker harness. If empty or unspecified, the\nservice will choose a number of threads (according to the number of cores\non the selected machine type for batch, or 1 by convention for streaming).",
- "format": "int32",
- "type": "integer"
- },
- "numWorkers": {
- "description": "Number of Google Compute Engine workers in this pool needed to\nexecute the job. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
- "format": "int32",
- "type": "integer"
- },
- "zone": {
- "description": "Zone to run the worker pools in. If empty or unspecified, the service\nwill attempt to choose a reasonable default.",
- "type": "string"
- },
- "diskSourceImage": {
- "description": "Fully qualified source image for disks.",
- "type": "string"
- },
- "packages": {
- "description": "Packages to be installed on workers.",
- "items": {
- "$ref": "Package"
- },
- "type": "array"
- },
- "teardownPolicy": {
- "description": "Sets the policy for determining when to turndown worker pool.\nAllowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and\n`TEARDOWN_NEVER`.\n`TEARDOWN_ALWAYS` means workers are always torn down regardless of whether\nthe job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down\nif the job succeeds. `TEARDOWN_NEVER` means the workers are never torn\ndown.\n\nIf the workers are not torn down by the service, they will\ncontinue to run and use Google Compute Engine VM resources in the\nuser's project until they are explicitly terminated by the user.\nBecause of this, Google recommends using the `TEARDOWN_ALWAYS`\npolicy except for small, manually supervised test jobs.\n\nIf unknown or unspecified, the service will attempt to choose a reasonable\ndefault.",
+ },
+ "defaultPackageSet": {
+ "description": "The default package set to install. This allows the service to\nselect a default set of packages which are useful to worker\nharnesses written in a particular language.",
"enum": [
- "TEARDOWN_POLICY_UNKNOWN",
- "TEARDOWN_ALWAYS",
- "TEARDOWN_ON_SUCCESS",
- "TEARDOWN_NEVER"
+ "DEFAULT_PACKAGE_SET_UNKNOWN",
+ "DEFAULT_PACKAGE_SET_NONE",
+ "DEFAULT_PACKAGE_SET_JAVA",
+ "DEFAULT_PACKAGE_SET_PYTHON"
],
"enumDescriptions": [
- "The teardown policy isn't specified, or is unknown.",
- "Always teardown the resource.",
- "Teardown the resource on success. This is useful for debugging\nfailures.",
- "Never teardown the resource. This is useful for debugging and\ndevelopment."
+ "The default set of packages to stage is unknown, or unspecified.",
+ "Indicates that no packages should be staged at the worker unless\nexplicitly specified by the job.",
+ "Stage packages typically useful to workers written in Java.",
+ "Stage pacakges typically useful to workers written in Python."
],
"type": "string"
},
- "onHostMaintenance": {
- "description": "The action to take on host maintenance, as defined by the Google\nCompute Engine API.",
+ "network": {
+ "description": "Network to which VMs will be assigned. If empty or unspecified,\nthe service will use the network \"default\".",
"type": "string"
- },
- "poolArgs": {
- "additionalProperties": {
- "description": "Properties of the object. Contains field @type with type URL.",
- "type": "any"
- },
- "description": "Extra arguments for this worker pool.",
- "type": "object"
- },
- "diskSizeGb": {
- "description": "Size of root disk for VMs, in GB. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
- "format": "int32",
- "type": "integer"
}
},
"type": "object"
@@ -3267,6 +3337,10 @@
"description": "A rich message format, including a human readable string, a key for\nidentifying the message, and structured data associated with the message for\nprogrammatic consumption.",
"id": "StructuredMessage",
"properties": {
+ "messageKey": {
+ "description": "Idenfier for this message type. Used by external systems to\ninternationalize or personalize message.",
+ "type": "string"
+ },
"messageText": {
"description": "Human-readable version of message.",
"type": "string"
@@ -3277,10 +3351,6 @@
"$ref": "Parameter"
},
"type": "array"
- },
- "messageKey": {
- "description": "Idenfier for this message type. Used by external systems to\ninternationalize or personalize message.",
- "type": "string"
}
},
"type": "object"
@@ -3289,6 +3359,11 @@
"description": "WorkItem represents basic information about a WorkItem to be executed\nin the cloud.",
"id": "WorkItem",
"properties": {
+ "initialReportIndex": {
+ "description": "The initial index to use when reporting the status of the WorkItem.",
+ "format": "int64",
+ "type": "string"
+ },
"streamingComputationTask": {
"$ref": "StreamingComputationTask",
"description": "Additional information for StreamingComputationTask WorkItems."
@@ -3329,15 +3404,15 @@
"description": "Identifies the cloud project this WorkItem belongs to.",
"type": "string"
},
+ "streamingSetupTask": {
+ "$ref": "StreamingSetupTask",
+ "description": "Additional information for StreamingSetupTask WorkItems."
+ },
"reportStatusInterval": {
"description": "Recommended reporting interval.",
"format": "google-duration",
"type": "string"
},
- "streamingSetupTask": {
- "$ref": "StreamingSetupTask",
- "description": "Additional information for StreamingSetupTask WorkItems."
- },
"sourceOperationTask": {
"$ref": "SourceOperationRequest",
"description": "Additional information for source operation WorkItems."
@@ -3350,11 +3425,20 @@
"description": "Time when the lease on this Work will expire.",
"format": "google-datetime",
"type": "string"
- },
- "initialReportIndex": {
- "description": "The initial index to use when reporting the status of the WorkItem.",
- "format": "int64",
- "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "ResourceUtilizationReport": {
+ "description": "Worker metrics exported from workers. This contains resource utilization\nmetrics accumulated from a variety of sources. For more information, see\ngo/df-resource-signals.",
+ "id": "ResourceUtilizationReport",
+ "properties": {
+ "cpuTime": {
+ "description": "CPU utilization samples.",
+ "items": {
+ "$ref": "CPUTime"
+ },
+ "type": "array"
}
},
"type": "object"
@@ -3375,29 +3459,10 @@
},
"type": "object"
},
- "ResourceUtilizationReport": {
- "description": "Worker metrics exported from workers. This contains resource utilization\nmetrics accumulated from a variety of sources. For more information, see\ngo/df-resource-signals.",
- "id": "ResourceUtilizationReport",
- "properties": {
- "cpuTime": {
- "description": "CPU utilization samples.",
- "items": {
- "$ref": "CPUTime"
- },
- "type": "array"
- }
- },
- "type": "object"
- },
"TopologyConfig": {
"description": "Global topology of the streaming Dataflow job, including all\ncomputations and their sharded locations.",
"id": "TopologyConfig",
"properties": {
- "forwardingKeyBits": {
- "description": "The size (in bits) of keys that will be assigned to source messages.",
- "format": "int32",
- "type": "integer"
- },
"userStageToComputationNameMap": {
"additionalProperties": {
"type": "string"
@@ -3423,6 +3488,11 @@
"$ref": "DataDiskAssignment"
},
"type": "array"
+ },
+ "forwardingKeyBits": {
+ "description": "The size (in bits) of keys that will be assigned to source messages.",
+ "format": "int32",
+ "type": "integer"
}
},
"type": "object"
@@ -3459,18 +3529,22 @@
"description": "Provides data to pass through to the worker harness.",
"id": "WorkerSettings",
"properties": {
- "tempStoragePrefix": {
- "description": "The prefix of the resources the system should use for temporary\nstorage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
+ "workerId": {
+ "description": "The ID of the worker running this pipeline.",
"type": "string"
},
- "baseUrl": {
- "description": "The base URL for accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
+ "tempStoragePrefix": {
+ "description": "The prefix of the resources the system should use for temporary\nstorage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
"type": "string"
},
"reportingEnabled": {
"description": "Whether to send work progress updates to the service.",
"type": "boolean"
},
+ "baseUrl": {
+ "description": "The base URL for accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
+ "type": "string"
+ },
"servicePath": {
"description": "The Cloud Dataflow service path relative to the root URL, for example,\n\"dataflow/v1b3/projects\".",
"type": "string"
@@ -3478,10 +3552,6 @@
"shuffleServicePath": {
"description": "The Shuffle service path relative to the root URL, for example,\n\"shuffle/v1beta1\".",
"type": "string"
- },
- "workerId": {
- "description": "The ID of the worker running this pipeline.",
- "type": "string"
}
},
"type": "object"
@@ -3501,16 +3571,16 @@
"description": "Data disk assignment for a given VM instance.",
"id": "DataDiskAssignment",
"properties": {
- "vmInstance": {
- "description": "VM instance name the data disks mounted to, for example\n\"myproject-1014-104817-4c2-harness-0\".",
- "type": "string"
- },
"dataDisks": {
"description": "Mounted data disks. The order is important a data disk's 0-based index in\nthis list defines which persistent directory the disk is mounted to, for\nexample the list of { \"myproject-1014-104817-4c2-harness-0-disk-0\" },\n{ \"myproject-1014-104817-4c2-harness-0-disk-1\" }.",
"items": {
"type": "string"
},
"type": "array"
+ },
+ "vmInstance": {
+ "description": "VM instance name the data disks mounted to, for example\n\"myproject-1014-104817-4c2-harness-0\".",
+ "type": "string"
}
},
"type": "object"
@@ -3519,14 +3589,14 @@
"description": "A suggestion by the service to the worker to dynamically split the WorkItem.",
"id": "ApproximateSplitRequest",
"properties": {
+ "position": {
+ "$ref": "Position",
+ "description": "A Position at which to split the work item."
+ },
"fractionConsumed": {
"description": "A fraction at which to split the work item, from 0.0 (beginning of the\ninput) to 1.0 (end of the input).",
"format": "double",
"type": "number"
- },
- "position": {
- "$ref": "Position",
- "description": "A Position at which to split the work item."
}
},
"type": "object"
@@ -3535,17 +3605,8 @@
"description": "The `Status` type defines a logical error model that is suitable for different\nprogramming environments, including REST APIs and RPC APIs. It is used by\n[gRPC](https://github.com/grpc). The error model is designed to be:\n\n- Simple to use and understand for most users\n- Flexible enough to meet unexpected needs\n\n# Overview\n\nThe `Status` message contains three pieces of data: error code, error message,\nand error details. The error code should be an enum value of\ngoogle.rpc.Code, but it may accept additional error codes if needed. The\nerror message should be a developer-facing English message that helps\ndevelopers *understand* and *resolve* the error. If a localized user-facing\nerror message is needed, put the localized message in the error details or\nlocalize it in the client. The optional error details may contain arbitrary\ninformation about the error. There is a predefined set of error detail types\nin the package `google.rpc` that can be used for common error conditions.\n\n# Language mapping\n\nThe `Status` message is the logical representation of the error model, but it\nis not necessarily the actual wire format. When the `Status` message is\nexposed in different client libraries and different wire protocols, it can be\nmapped differently. For example, it will likely be mapped to some exceptions\nin Java, but more likely mapped to some error codes in C.\n\n# Other uses\n\nThe error model and the `Status` message can be used in a variety of\nenvironments, either with or without APIs, to provide a\nconsistent developer experience across different environments.\n\nExample uses of this error model include:\n\n- Partial errors. If a service needs to return partial errors to the client,\n it may embed the `Status` in the normal response to indicate the partial\n errors.\n\n- Workflow errors. A typical workflow has multiple steps. Each step may\n have a `Status` message for error reporting.\n\n- Batch operations. If a client uses batch request and batch response, the\n `Status` message should be used directly inside batch response, one for\n each error sub-response.\n\n- Asynchronous operations. If an API call embeds asynchronous operation\n results in its response, the status of those operations should be\n represented directly using the `Status` message.\n\n- Logging. If some API errors are stored in logs, the message `Status` could\n be used directly after any stripping needed for security/privacy reasons.",
"id": "Status",
"properties": {
- "code": {
- "description": "The status code, which should be an enum value of google.rpc.Code.",
- "format": "int32",
- "type": "integer"
- },
- "message": {
- "description": "A developer-facing error message, which should be in English. Any\nuser-facing error message should be localized and sent in the\ngoogle.rpc.Status.details field, or localized by the client.",
- "type": "string"
- },
"details": {
- "description": "A list of messages that carry the error details. There will be a\ncommon set of message types for APIs to use.",
+ "description": "A list of messages that carry the error details. There is a common set of\nmessage types for APIs to use.",
"items": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
@@ -3554,6 +3615,15 @@
"type": "object"
},
"type": "array"
+ },
+ "code": {
+ "description": "The status code, which should be an enum value of google.rpc.Code.",
+ "format": "int32",
+ "type": "integer"
+ },
+ "message": {
+ "description": "A developer-facing error message, which should be in English. Any\nuser-facing error message should be localized and sent in the\ngoogle.rpc.Status.details field, or localized by the client.",
+ "type": "string"
}
},
"type": "object"
@@ -3562,6 +3632,10 @@
"description": "A message describing the state of a particular execution stage.",
"id": "ExecutionStageState",
"properties": {
+ "executionStageName": {
+ "description": "The name of the execution stage.",
+ "type": "string"
+ },
"currentStateTime": {
"description": "The time at which the stage transitioned to this state.",
"format": "google-datetime",
@@ -3596,10 +3670,6 @@
"'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
],
"type": "string"
- },
- "executionStageName": {
- "description": "The name of the execution stage.",
- "type": "string"
}
},
"type": "object"
@@ -3608,6 +3678,10 @@
"description": "Describes a stream of data, either as input to be processed or as\noutput of a streaming Dataflow job.",
"id": "StreamLocation",
"properties": {
+ "customSourceLocation": {
+ "$ref": "CustomSourceLocation",
+ "description": "The stream is a custom source."
+ },
"sideInputLocation": {
"$ref": "StreamingSideInputLocation",
"description": "The stream is a streaming side input."
@@ -3619,10 +3693,6 @@
"streamingStageLocation": {
"$ref": "StreamingStageLocation",
"description": "The stream is part of another computation within the current\nstreaming Dataflow job."
- },
- "customSourceLocation": {
- "$ref": "CustomSourceLocation",
- "description": "The stream is a custom source."
}
},
"type": "object"
@@ -3659,6 +3729,17 @@
"description": "Description of the type, names/ids, and input/outputs for a transform.",
"id": "TransformSummary",
"properties": {
+ "inputCollectionName": {
+ "description": "User names for all collection inputs to this transform.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "name": {
+ "description": "User provided name for this transform instance.",
+ "type": "string"
+ },
"id": {
"description": "SDK generated id of this transform instance.",
"type": "string"
@@ -3702,17 +3783,6 @@
"Opening or closing a shuffle session, often as part of a GroupByKey."
],
"type": "string"
- },
- "inputCollectionName": {
- "description": "User names for all collection inputs to this transform.",
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- "name": {
- "description": "User provided name for this transform instance.",
- "type": "string"
}
},
"type": "object"
@@ -3721,10 +3791,6 @@
"description": "Configuration information for a single streaming computation.",
"id": "StreamingComputationConfig",
"properties": {
- "computationId": {
- "description": "Unique identifier for this computation.",
- "type": "string"
- },
"stageName": {
"description": "Stage name of this computation.",
"type": "string"
@@ -3739,6 +3805,10 @@
"$ref": "ParallelInstruction"
},
"type": "array"
+ },
+ "computationId": {
+ "description": "Unique identifier for this computation.",
+ "type": "string"
}
},
"type": "object"
@@ -3770,10 +3840,6 @@
"description": "Parameters to provide to the template being launched.",
"id": "LaunchTemplateParameters",
"properties": {
- "environment": {
- "$ref": "RuntimeEnvironment",
- "description": "The runtime environment for the job."
- },
"parameters": {
"additionalProperties": {
"type": "string"
@@ -3784,6 +3850,10 @@
"jobName": {
"description": "Required. The job name to use for the created job.",
"type": "string"
+ },
+ "environment": {
+ "$ref": "RuntimeEnvironment",
+ "description": "The runtime environment for the job."
}
},
"type": "object"
@@ -3806,25 +3876,6 @@
"description": "An instruction that does a partial group-by-key.\nOne input and one output.",
"id": "PartialGroupByKeyInstruction",
"properties": {
- "originalCombineValuesInputStoreName": {
- "description": "If this instruction includes a combining function this is the name of the\nintermediate store between the GBK and the CombineValues.",
- "type": "string"
- },
- "sideInputs": {
- "description": "Zero or more side inputs.",
- "items": {
- "$ref": "SideInputInfo"
- },
- "type": "array"
- },
- "originalCombineValuesStepName": {
- "description": "If this instruction includes a combining function, this is the name of the\nCombineValues instruction lifted into this instruction.",
- "type": "string"
- },
- "input": {
- "$ref": "InstructionInput",
- "description": "Describes the input to the partial group-by-key instruction."
- },
"inputElementCodec": {
"additionalProperties": {
"description": "Properties of the object.",
@@ -3840,6 +3891,25 @@
},
"description": "The value combining function to invoke.",
"type": "object"
+ },
+ "originalCombineValuesInputStoreName": {
+ "description": "If this instruction includes a combining function this is the name of the\nintermediate store between the GBK and the CombineValues.",
+ "type": "string"
+ },
+ "originalCombineValuesStepName": {
+ "description": "If this instruction includes a combining function, this is the name of the\nCombineValues instruction lifted into this instruction.",
+ "type": "string"
+ },
+ "sideInputs": {
+ "description": "Zero or more side inputs.",
+ "items": {
+ "$ref": "SideInputInfo"
+ },
+ "type": "array"
+ },
+ "input": {
+ "$ref": "InstructionInput",
+ "description": "Describes the input to the partial group-by-key instruction."
}
},
"type": "object"
@@ -3865,21 +3935,21 @@
"description": "Description of an input or output of an execution stage.",
"id": "StageSource",
"properties": {
- "sizeBytes": {
- "description": "Size of the source, if measurable.",
- "format": "int64",
+ "userName": {
+ "description": "Human-readable name for this source; may be user or system generated.",
"type": "string"
},
- "name": {
- "description": "Dataflow service generated name for this source.",
+ "originalTransformOrCollection": {
+ "description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
"type": "string"
},
- "userName": {
- "description": "Human-readable name for this source; may be user or system generated.",
+ "sizeBytes": {
+ "description": "Size of the source, if measurable.",
+ "format": "int64",
"type": "string"
},
- "originalTransformOrCollection": {
- "description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
+ "name": {
+ "description": "Dataflow service generated name for this source.",
"type": "string"
}
},
@@ -3903,33 +3973,20 @@
"description": "Data provided with a pipeline or transform to provide descriptive info.",
"id": "DisplayData",
"properties": {
- "timestampValue": {
- "description": "Contains value if the data is of timestamp type.",
- "format": "google-datetime",
- "type": "string"
- },
- "boolValue": {
- "description": "Contains value if the data is of a boolean type.",
- "type": "boolean"
- },
- "javaClassValue": {
- "description": "Contains value if the data is of java class type.",
- "type": "string"
- },
"strValue": {
"description": "Contains value if the data is of string type.",
"type": "string"
},
- "durationValue": {
- "description": "Contains value if the data is of duration type.",
- "format": "google-duration",
- "type": "string"
- },
"int64Value": {
"description": "Contains value if the data is of int64 type.",
"format": "int64",
"type": "string"
},
+ "durationValue": {
+ "description": "Contains value if the data is of duration type.",
+ "format": "google-duration",
+ "type": "string"
+ },
"namespace": {
"description": "The namespace for the key. This is usually a class name or programming\nlanguage namespace (i.e. python module) which defines the display data.\nThis allows a dax monitoring system to specially handle the data\nand perform custom rendering.",
"type": "string"
@@ -3947,13 +4004,26 @@
"description": "A possible additional shorter value to display.\nFor example a java_class_name_value of com.mypackage.MyDoFn\nwill be stored with MyDoFn as the short_str_value and\ncom.mypackage.MyDoFn as the java_class_name value.\nshort_str_value can be displayed and java_class_name_value\nwill be displayed as a tooltip.",
"type": "string"
},
+ "label": {
+ "description": "An optional label to display in a dax UI for the element.",
+ "type": "string"
+ },
"url": {
"description": "An optional full URL.",
"type": "string"
},
- "label": {
- "description": "An optional label to display in a dax UI for the element.",
+ "timestampValue": {
+ "description": "Contains value if the data is of timestamp type.",
+ "format": "google-datetime",
+ "type": "string"
+ },
+ "javaClassValue": {
+ "description": "Contains value if the data is of java class type.",
"type": "string"
+ },
+ "boolValue": {
+ "description": "Contains value if the data is of a boolean type.",
+ "type": "boolean"
}
},
"type": "object"
@@ -3962,10 +4032,6 @@
"description": "Request to get updated debug configuration for component.",
"id": "GetDebugConfigRequest",
"properties": {
- "componentId": {
- "description": "The internal component id for which debug configuration is\nrequested.",
- "type": "string"
- },
"workerId": {
"description": "The worker id, i.e., VM hostname.",
"type": "string"
@@ -3973,6 +4039,10 @@
"location": {
"description": "The location which contains the job specified by job_id.",
"type": "string"
+ },
+ "componentId": {
+ "description": "The internal component id for which debug configuration is\nrequested.",
+ "type": "string"
}
},
"type": "object"
@@ -3981,22 +4051,6 @@
"description": "Request to lease WorkItems.",
"id": "LeaseWorkItemRequest",
"properties": {
- "currentWorkerTime": {
- "description": "The current timestamp at the worker.",
- "format": "google-datetime",
- "type": "string"
- },
- "workItemTypes": {
- "description": "Filter for WorkItem type.",
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- "location": {
- "description": "The location which contains the WorkItem's job.",
- "type": "string"
- },
"workerCapabilities": {
"description": "Worker capabilities. WorkItems might be limited to workers with specific\ncapabilities.",
"items": {
@@ -4012,6 +4066,22 @@
"description": "The initial lease period.",
"format": "google-duration",
"type": "string"
+ },
+ "currentWorkerTime": {
+ "description": "The current timestamp at the worker.",
+ "format": "google-datetime",
+ "type": "string"
+ },
+ "workItemTypes": {
+ "description": "Filter for WorkItem type.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "location": {
+ "description": "The location which contains the WorkItem's job.",
+ "type": "string"
}
},
"type": "object"
@@ -4020,13 +4090,13 @@
"description": "The response to a GetTemplate request.",
"id": "GetTemplateResponse",
"properties": {
- "metadata": {
- "$ref": "TemplateMetadata",
- "description": "The template metadata describing the template name, available\nparameters, etc."
- },
"status": {
"$ref": "Status",
"description": "The status of the get template request. Any problems with the\nrequest will be indicated in the error_details."
+ },
+ "metadata": {
+ "$ref": "TemplateMetadata",
+ "description": "The template metadata describing the template name, available\nparameters, etc."
}
},
"type": "object"
@@ -4035,13 +4105,13 @@
"description": "Structured data associated with this message.",
"id": "Parameter",
"properties": {
- "value": {
- "description": "Value for this parameter.",
- "type": "any"
- },
"key": {
"description": "Key or name for this parameter.",
"type": "string"
+ },
+ "value": {
+ "description": "Value for this parameter.",
+ "type": "any"
}
},
"type": "object"
@@ -4073,17 +4143,40 @@
},
"type": "object"
},
- "PipelineDescription": {
- "description": "A descriptive representation of submitted pipeline as well as the executed\nform. This data is provided by the Dataflow service for ease of visualizing\nthe pipeline and interpretting Dataflow provided metrics.",
- "id": "PipelineDescription",
+ "StreamingConfigTask": {
+ "description": "A task that carries configuration information for streaming computations.",
+ "id": "StreamingConfigTask",
"properties": {
- "displayData": {
- "description": "Pipeline level display data.",
+ "windmillServiceEndpoint": {
+ "description": "If present, the worker must use this endpoint to communicate with Windmill\nService dispatchers, otherwise the worker must continue to use whatever\nendpoint it had been using.",
+ "type": "string"
+ },
+ "userStepToStateFamilyNameMap": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Map from user step names to state families.",
+ "type": "object"
+ },
+ "windmillServicePort": {
+ "description": "If present, the worker must use this port to communicate with Windmill\nService dispatchers. Only applicable when windmill_service_endpoint is\nspecified.",
+ "format": "int64",
+ "type": "string"
+ },
+ "streamingComputationConfigs": {
+ "description": "Set of computation configuration information.",
"items": {
- "$ref": "DisplayData"
+ "$ref": "StreamingComputationConfig"
},
"type": "array"
- },
+ }
+ },
+ "type": "object"
+ },
+ "PipelineDescription": {
+ "description": "A descriptive representation of submitted pipeline as well as the executed\nform. This data is provided by the Dataflow service for ease of visualizing\nthe pipeline and interpretting Dataflow provided metrics.",
+ "id": "PipelineDescription",
+ "properties": {
"executionPipelineStage": {
"description": "Description of each stage of execution of the pipeline.",
"items": {
@@ -4097,36 +4190,13 @@
"$ref": "TransformSummary"
},
"type": "array"
- }
- },
- "type": "object"
- },
- "StreamingConfigTask": {
- "description": "A task that carries configuration information for streaming computations.",
- "id": "StreamingConfigTask",
- "properties": {
- "windmillServicePort": {
- "description": "If present, the worker must use this port to communicate with Windmill\nService dispatchers. Only applicable when windmill_service_endpoint is\nspecified.",
- "format": "int64",
- "type": "string"
},
- "streamingComputationConfigs": {
- "description": "Set of computation configuration information.",
+ "displayData": {
+ "description": "Pipeline level display data.",
"items": {
- "$ref": "StreamingComputationConfig"
+ "$ref": "DisplayData"
},
"type": "array"
- },
- "windmillServiceEndpoint": {
- "description": "If present, the worker must use this endpoint to communicate with Windmill\nService dispatchers, otherwise the worker must continue to use whatever\nendpoint it had been using.",
- "type": "string"
- },
- "userStepToStateFamilyNameMap": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "Map from user step names to state families.",
- "type": "object"
}
},
"type": "object"
@@ -4199,10 +4269,39 @@
},
"type": "object"
},
+ "ListJobMessagesResponse": {
+ "description": "Response to a request to list job messages.",
+ "id": "ListJobMessagesResponse",
+ "properties": {
+ "jobMessages": {
+ "description": "Messages in ascending timestamp order.",
+ "items": {
+ "$ref": "JobMessage"
+ },
+ "type": "array"
+ },
+ "nextPageToken": {
+ "description": "The token to obtain the next page of results if there are more.",
+ "type": "string"
+ },
+ "autoscalingEvents": {
+ "description": "Autoscaling events in ascending timestamp order.",
+ "items": {
+ "$ref": "AutoscalingEvent"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
"CounterMetadata": {
"description": "CounterMetadata includes all static non-name non-value counter attributes.",
"id": "CounterMetadata",
"properties": {
+ "otherUnits": {
+ "description": "A string referring to the unit type.",
+ "type": "string"
+ },
"description": {
"description": "Human-readable description of the counter semantics.",
"type": "string"
@@ -4256,73 +4355,30 @@
"Counter returns a timestamp in nanoseconds."
],
"type": "string"
- },
- "otherUnits": {
- "description": "A string referring to the unit type.",
- "type": "string"
- }
- },
- "type": "object"
- },
- "ListJobMessagesResponse": {
- "description": "Response to a request to list job messages.",
- "id": "ListJobMessagesResponse",
- "properties": {
- "autoscalingEvents": {
- "description": "Autoscaling events in ascending timestamp order.",
- "items": {
- "$ref": "AutoscalingEvent"
- },
- "type": "array"
- },
- "jobMessages": {
- "description": "Messages in ascending timestamp order.",
- "items": {
- "$ref": "JobMessage"
- },
- "type": "array"
- },
- "nextPageToken": {
- "description": "The token to obtain the next page of results if there are more.",
- "type": "string"
}
},
"type": "object"
},
"ApproximateReportedProgress": {
"description": "A progress measurement of a WorkItem by a worker.",
- "id": "ApproximateReportedProgress",
- "properties": {
- "remainingParallelism": {
- "$ref": "ReportedParallelism",
- "description": "Total amount of parallelism in the input of this task that remains,\n(i.e. can be delegated to this task and any new tasks via dynamic\nsplitting). Always at least 1 for non-finished work items and 0 for\nfinished.\n\n\"Amount of parallelism\" refers to how many non-empty parts of the input\ncan be read in parallel. This does not necessarily equal number\nof records. An input that can be read in parallel down to the\nindividual records is called \"perfectly splittable\".\nAn example of non-perfectly parallelizable input is a block-compressed\nfile format where a block of records has to be read as a whole,\nbut different blocks can be read in parallel.\n\nExamples:\n* If we are processing record #30 (starting at 1) out of 50 in a perfectly\n splittable 50-record input, this value should be 21 (20 remaining + 1\n current).\n* If we are reading through block 3 in a block-compressed file consisting\n of 5 blocks, this value should be 3 (since blocks 4 and 5 can be\n processed in parallel by new tasks via dynamic splitting and the current\n task remains processing block 3).\n* If we are reading through the last block in a block-compressed file,\n or reading or processing the last record in a perfectly splittable\n input, this value should be 1, because apart from the current task, no\n additional remainder can be split off."
- },
- "position": {
- "$ref": "Position",
- "description": "A Position within the work to represent a progress."
- },
- "fractionConsumed": {
- "description": "Completion as fraction of the input consumed, from 0.0 (beginning, nothing\nconsumed), to 1.0 (end of the input, entire input consumed).",
- "format": "double",
- "type": "number"
- },
- "consumedParallelism": {
- "$ref": "ReportedParallelism",
- "description": "Total amount of parallelism in the portion of input of this task that has\nalready been consumed and is no longer active. In the first two examples\nabove (see remaining_parallelism), the value should be 29 or 2\nrespectively. The sum of remaining_parallelism and consumed_parallelism\nshould equal the total amount of parallelism in this work item. If\nspecified, must be finite."
- }
- },
- "type": "object"
- },
- "IntegerList": {
- "description": "A metric value representing a list of integers.",
- "id": "IntegerList",
- "properties": {
- "elements": {
- "description": "Elements of the list.",
- "items": {
- "$ref": "SplitInt64"
- },
- "type": "array"
+ "id": "ApproximateReportedProgress",
+ "properties": {
+ "fractionConsumed": {
+ "description": "Completion as fraction of the input consumed, from 0.0 (beginning, nothing\nconsumed), to 1.0 (end of the input, entire input consumed).",
+ "format": "double",
+ "type": "number"
+ },
+ "consumedParallelism": {
+ "$ref": "ReportedParallelism",
+ "description": "Total amount of parallelism in the portion of input of this task that has\nalready been consumed and is no longer active. In the first two examples\nabove (see remaining_parallelism), the value should be 29 or 2\nrespectively. The sum of remaining_parallelism and consumed_parallelism\nshould equal the total amount of parallelism in this work item. If\nspecified, must be finite."
+ },
+ "remainingParallelism": {
+ "$ref": "ReportedParallelism",
+ "description": "Total amount of parallelism in the input of this task that remains,\n(i.e. can be delegated to this task and any new tasks via dynamic\nsplitting). Always at least 1 for non-finished work items and 0 for\nfinished.\n\n\"Amount of parallelism\" refers to how many non-empty parts of the input\ncan be read in parallel. This does not necessarily equal number\nof records. An input that can be read in parallel down to the\nindividual records is called \"perfectly splittable\".\nAn example of non-perfectly parallelizable input is a block-compressed\nfile format where a block of records has to be read as a whole,\nbut different blocks can be read in parallel.\n\nExamples:\n* If we are processing record #30 (starting at 1) out of 50 in a perfectly\n splittable 50-record input, this value should be 21 (20 remaining + 1\n current).\n* If we are reading through block 3 in a block-compressed file consisting\n of 5 blocks, this value should be 3 (since blocks 4 and 5 can be\n processed in parallel by new tasks via dynamic splitting and the current\n task remains processing block 3).\n* If we are reading through the last block in a block-compressed file,\n or reading or processing the last record in a perfectly splittable\n input, this value should be 1, because apart from the current task, no\n additional remainder can be split off."
+ },
+ "position": {
+ "$ref": "Position",
+ "description": "A Position within the work to represent a progress."
}
},
"type": "object"
@@ -4342,6 +4398,20 @@
},
"type": "object"
},
+ "IntegerList": {
+ "description": "A metric value representing a list of integers.",
+ "id": "IntegerList",
+ "properties": {
+ "elements": {
+ "description": "Elements of the list.",
+ "items": {
+ "$ref": "SplitInt64"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
"ResourceUtilizationReportResponse": {
"description": "Service-side response to WorkerMessage reporting resource utilization.",
"id": "ResourceUtilizationReportResponse",
@@ -4387,14 +4457,18 @@
"description": "Describes a particular operation comprising a MapTask.",
"id": "ParallelInstruction",
"properties": {
- "parDo": {
- "$ref": "ParDoInstruction",
- "description": "Additional information for ParDo instructions."
+ "name": {
+ "description": "User-provided name of this operation.",
+ "type": "string"
},
"read": {
"$ref": "ReadInstruction",
"description": "Additional information for Read instructions."
},
+ "parDo": {
+ "$ref": "ParDoInstruction",
+ "description": "Additional information for ParDo instructions."
+ },
"originalName": {
"description": "System-defined name for the operation in the original workflow graph.",
"type": "string"
@@ -4403,14 +4477,14 @@
"$ref": "FlattenInstruction",
"description": "Additional information for Flatten instructions."
},
- "systemName": {
- "description": "System-defined name of this operation.\nUnique across the workflow.",
- "type": "string"
- },
"write": {
"$ref": "WriteInstruction",
"description": "Additional information for Write instructions."
},
+ "systemName": {
+ "description": "System-defined name of this operation.\nUnique across the workflow.",
+ "type": "string"
+ },
"partialGroupByKey": {
"$ref": "PartialGroupByKeyInstruction",
"description": "Additional information for PartialGroupByKey instructions."
@@ -4421,10 +4495,6 @@
"$ref": "InstructionOutput"
},
"type": "array"
- },
- "name": {
- "description": "User-provided name of this operation.",
- "type": "string"
}
},
"type": "object"
@@ -4433,13 +4503,13 @@
"description": "The packages that must be installed in order for a worker to run the\nsteps of the Cloud Dataflow job that will be assigned to its worker\npool.\n\nThis is the mechanism by which the Cloud Dataflow SDK causes code to\nbe loaded onto the workers. For example, the Cloud Dataflow Java SDK\nmight use this to install jars containing the user's code and all of the\nvarious dependencies (libraries, data files, etc.) required in order\nfor that code to run.",
"id": "Package",
"properties": {
- "location": {
- "description": "The resource to read the package from. The supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}\n bucket.storage.googleapis.com/",
- "type": "string"
- },
"name": {
"description": "The name of the package.",
"type": "string"
+ },
+ "location": {
+ "description": "The resource to read the package from. The supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}\n bucket.storage.googleapis.com/",
+ "type": "string"
}
},
"type": "object"
@@ -4448,6 +4518,10 @@
"description": "Data disk assignment information for a specific key-range of a sharded\ncomputation.\nCurrently we only support UTF-8 character splits to simplify encoding into\nJSON.",
"id": "KeyRangeDataDiskAssignment",
"properties": {
+ "end": {
+ "description": "The end (exclusive) of the key range.",
+ "type": "string"
+ },
"dataDisk": {
"description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
"type": "string"
@@ -4455,10 +4529,6 @@
"start": {
"description": "The start (inclusive) of the key range.",
"type": "string"
- },
- "end": {
- "description": "The end (exclusive) of the key range.",
- "type": "string"
}
},
"type": "object"
@@ -4467,6 +4537,13 @@
"description": "An instruction that does a ParDo operation.\nTakes one main input and zero or more side inputs, and produces\nzero or more outputs.\nRuns user code.",
"id": "ParDoInstruction",
"properties": {
+ "sideInputs": {
+ "description": "Zero or more side inputs.",
+ "items": {
+ "$ref": "SideInputInfo"
+ },
+ "type": "array"
+ },
"multiOutputInfos": {
"description": "Information about each of the outputs, if user_fn is a MultiDoFn.",
"items": {
@@ -4490,13 +4567,6 @@
"description": "The number of outputs.",
"format": "int32",
"type": "integer"
- },
- "sideInputs": {
- "description": "Zero or more side inputs.",
- "items": {
- "$ref": "SideInputInfo"
- },
- "type": "array"
}
},
"type": "object"
@@ -4505,6 +4575,10 @@
"description": "Describes the state of a metric.",
"id": "MetricUpdate",
"properties": {
+ "kind": {
+ "description": "Metric aggregation kind. The possible metric aggregation kinds are\n\"Sum\", \"Max\", \"Min\", \"Mean\", \"Set\", \"And\", \"Or\", and \"Distribution\".\nThe specified aggregation kind is case-insensitive.\n\nIf omitted, this is not an aggregated value but instead\na single metric sample value.",
+ "type": "string"
+ },
"scalar": {
"description": "Worker-computed aggregate value for aggregation kinds \"Sum\", \"Max\", \"Min\",\n\"And\", and \"Or\". The possible value types are Long, Double, and Boolean.",
"type": "any"
@@ -4541,10 +4615,6 @@
"internal": {
"description": "Worker-computed aggregate value for internal use by the Dataflow\nservice.",
"type": "any"
- },
- "kind": {
- "description": "Metric aggregation kind. The possible metric aggregation kinds are\n\"Sum\", \"Max\", \"Min\", \"Mean\", \"Set\", \"And\", \"Or\", and \"Distribution\".\nThe specified aggregation kind is case-insensitive.\n\nIf omitted, this is not an aggregated value but instead\na single metric sample value.",
- "type": "string"
}
},
"type": "object"
@@ -4583,14 +4653,6 @@
"description": "A string containing a more specific namespace of the counter's origin.",
"type": "string"
},
- "executionStepName": {
- "description": "Name of the stage. An execution step contains multiple component steps.",
- "type": "string"
- },
- "name": {
- "description": "Counter name. Not necessarily globally-unique, but unique within the\ncontext of the other fields.\nRequired.",
- "type": "string"
- },
"origin": {
"description": "One of the standard Origins defined above.",
"enum": [
@@ -4602,6 +4664,14 @@
"Counter was created by the user."
],
"type": "string"
+ },
+ "name": {
+ "description": "Counter name. Not necessarily globally-unique, but unique within the\ncontext of the other fields.\nRequired.",
+ "type": "string"
+ },
+ "executionStepName": {
+ "description": "Name of the stage. An execution step contains multiple component steps.",
+ "type": "string"
}
},
"type": "object"
@@ -4610,11 +4680,6 @@
"description": "Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest.",
"id": "ApproximateProgress",
"properties": {
- "percentComplete": {
- "description": "Obsolete.",
- "format": "float",
- "type": "number"
- },
"remainingTime": {
"description": "Obsolete.",
"format": "google-duration",
@@ -4623,6 +4688,11 @@
"position": {
"$ref": "Position",
"description": "Obsolete."
+ },
+ "percentComplete": {
+ "description": "Obsolete.",
+ "format": "float",
+ "type": "number"
}
},
"type": "object"
@@ -4668,6 +4738,13 @@
"description": "WorkerMessage provides information to the backend about a worker.",
"id": "WorkerMessage",
"properties": {
+ "labels": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Labels are used to group WorkerMessages.\nFor example, a worker_message about a particular container\nmight have the labels:\n{ \"JOB_ID\": \"2015-04-22\",\n \"WORKER_ID\": \"wordcount-vm-2015…\"\n \"CONTAINER_TYPE\": \"worker\",\n \"CONTAINER_ID\": \"ac1234def\"}\nLabel tags typically correspond to Label enum values. However, for ease\nof development other strings can be used as tags. LABEL_UNSPECIFIED should\nnot be used here.",
+ "type": "object"
+ },
"time": {
"description": "The timestamp of the worker_message.",
"format": "google-datetime",
@@ -4684,13 +4761,6 @@
"workerMessageCode": {
"$ref": "WorkerMessageCode",
"description": "A worker message code."
- },
- "labels": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "Labels are used to group WorkerMessages.\nFor example, a worker_message about a particular container\nmight have the labels:\n{ \"JOB_ID\": \"2015-04-22\",\n \"WORKER_ID\": \"wordcount-vm-2015…\"\n \"CONTAINER_TYPE\": \"worker\",\n \"CONTAINER_ID\": \"ac1234def\"}\nLabel tags typically correspond to Label enum values. However, for ease\nof development other strings can be used as tags. LABEL_UNSPECIFIED should\nnot be used here.",
- "type": "object"
}
},
"type": "object"
@@ -4733,23 +4803,6 @@
"description": "An update to a Counter sent from a worker.",
"id": "CounterUpdate",
"properties": {
- "nameAndKind": {
- "$ref": "NameAndKind",
- "description": "Counter name and aggregation type."
- },
- "distribution": {
- "$ref": "DistributionUpdate",
- "description": "Distribution data"
- },
- "stringList": {
- "$ref": "StringList",
- "description": "List of strings, for Set."
- },
- "shortId": {
- "description": "The service-generated short identifier for this counter.\nThe short_id -> (name, metadata) mapping is constant for the lifetime of\na job.",
- "format": "int64",
- "type": "string"
- },
"floatingPointList": {
"$ref": "FloatingPointList",
"description": "List of floating point numbers, for Set."
@@ -4790,6 +4843,23 @@
"boolean": {
"description": "Boolean value for And, Or.",
"type": "boolean"
+ },
+ "nameAndKind": {
+ "$ref": "NameAndKind",
+ "description": "Counter name and aggregation type."
+ },
+ "stringList": {
+ "$ref": "StringList",
+ "description": "List of strings, for Set."
+ },
+ "distribution": {
+ "$ref": "DistributionUpdate",
+ "description": "Distribution data"
+ },
+ "shortId": {
+ "description": "The service-generated short identifier for this counter.\nThe short_id -> (name, metadata) mapping is constant for the lifetime of\na job.",
+ "format": "int64",
+ "type": "string"
}
},
"type": "object"
@@ -4818,6 +4888,10 @@
"description": "A metric value representing a distribution.",
"id": "DistributionUpdate",
"properties": {
+ "sum": {
+ "$ref": "SplitInt64",
+ "description": "Use an int64 since we'd prefer the added precision. If overflow is a common\nproblem we can detect it and use an additional int64 or a double."
+ },
"max": {
"$ref": "SplitInt64",
"description": "The maximum value present in the distribution."
@@ -4833,18 +4907,14 @@
"$ref": "SplitInt64",
"description": "The count of the number of elements present in the distribution."
},
- "min": {
- "$ref": "SplitInt64",
- "description": "The minimum value present in the distribution."
- },
"sumOfSquares": {
"description": "Use a double since the sum of squares is likely to overflow int64.",
"format": "double",
"type": "number"
},
- "sum": {
+ "min": {
"$ref": "SplitInt64",
- "description": "Use an int64 since we'd prefer the added precision. If overflow is a common\nproblem we can detect it and use an additional int64 or a double."
+ "description": "The minimum value present in the distribution."
}
},
"type": "object"
@@ -4865,6 +4935,10 @@
"description": "DEPRECATED in favor of DynamicSourceSplit.",
"id": "SourceFork",
"properties": {
+ "residualSource": {
+ "$ref": "DerivedSource",
+ "description": "DEPRECATED"
+ },
"primary": {
"$ref": "SourceSplitShard",
"description": "DEPRECATED"
@@ -4876,80 +4950,6 @@
"residual": {
"$ref": "SourceSplitShard",
"description": "DEPRECATED"
- },
- "residualSource": {
- "$ref": "DerivedSource",
- "description": "DEPRECATED"
- }
- },
- "type": "object"
- },
- "WorkItemStatus": {
- "description": "Conveys a worker's progress through the work described by a WorkItem.",
- "id": "WorkItemStatus",
- "properties": {
- "reportIndex": {
- "description": "The report index. When a WorkItem is leased, the lease will\ncontain an initial report index. When a WorkItem's status is\nreported to the system, the report should be sent with\nthat report index, and the response will contain the index the\nworker should use for the next report. Reports received with\nunexpected index values will be rejected by the service.\n\nIn order to preserve idempotency, the worker should not alter the\ncontents of a report, even if the worker must submit the same\nreport multiple times before getting back a response. The worker\nshould not submit a subsequent report until the response for the\nprevious report had been received from the service.",
- "format": "int64",
- "type": "string"
- },
- "stopPosition": {
- "$ref": "Position",
- "description": "A worker may split an active map task in two parts, \"primary\" and\n\"residual\", continuing to process the primary part and returning the\nresidual part into the pool of available work.\nThis event is called a \"dynamic split\" and is critical to the dynamic\nwork rebalancing feature. The two obtained sub-tasks are called\n\"parts\" of the split.\nThe parts, if concatenated, must represent the same input as would\nbe read by the current task if the split did not happen.\nThe exact way in which the original task is decomposed into the two\nparts is specified either as a position demarcating them\n(stop_position), or explicitly as two DerivedSources, if this\ntask consumes a user-defined source type (dynamic_source_split).\n\nThe \"current\" task is adjusted as a result of the split: after a task\nwith range [A, B) sends a stop_position update at C, its range is\nconsidered to be [A, C), e.g.:\n* Progress should be interpreted relative to the new range, e.g.\n \"75% completed\" means \"75% of [A, C) completed\"\n* The worker should interpret proposed_stop_position relative to the\n new range, e.g. \"split at 68%\" should be interpreted as\n \"split at 68% of [A, C)\".\n* If the worker chooses to split again using stop_position, only\n stop_positions in [A, C) will be accepted.\n* Etc.\ndynamic_source_split has similar semantics: e.g., if a task with\nsource S splits using dynamic_source_split into {P, R}\n(where P and R must be together equivalent to S), then subsequent\nprogress and proposed_stop_position should be interpreted relative\nto P, and in a potential subsequent dynamic_source_split into {P', R'},\nP' and R' must be together equivalent to P, etc."
- },
- "completed": {
- "description": "True if the WorkItem was completed (successfully or unsuccessfully).",
- "type": "boolean"
- },
- "reportedProgress": {
- "$ref": "ApproximateReportedProgress",
- "description": "The worker's progress through this WorkItem."
- },
- "sourceFork": {
- "$ref": "SourceFork",
- "description": "DEPRECATED in favor of dynamic_source_split."
- },
- "counterUpdates": {
- "description": "Worker output counters for this WorkItem.",
- "items": {
- "$ref": "CounterUpdate"
- },
- "type": "array"
- },
- "workItemId": {
- "description": "Identifies the WorkItem.",
- "type": "string"
- },
- "errors": {
- "description": "Specifies errors which occurred during processing. If errors are\nprovided, and completed = true, then the WorkItem is considered\nto have failed.",
- "items": {
- "$ref": "Status"
- },
- "type": "array"
- },
- "metricUpdates": {
- "description": "DEPRECATED in favor of counter_updates.",
- "items": {
- "$ref": "MetricUpdate"
- },
- "type": "array"
- },
- "dynamicSourceSplit": {
- "$ref": "DynamicSourceSplit",
- "description": "See documentation of stop_position."
- },
- "sourceOperationResponse": {
- "$ref": "SourceOperationResponse",
- "description": "If the work item represented a SourceOperationRequest, and the work\nis completed, contains the result of the operation."
- },
- "progress": {
- "$ref": "ApproximateProgress",
- "description": "DEPRECATED in favor of reported_progress."
- },
- "requestedLeaseDuration": {
- "description": "Amount of time the worker requests for its lease.",
- "format": "google-duration",
- "type": "string"
}
},
"type": "object"
« no previous file with comments | « discovery/googleapis_beta/cloudresourcemanager__v1beta1.json ('k') | discovery/googleapis_beta/dataproc__v1beta1.json » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698