Index: discovery/googleapis_beta/dataflow__v1b3.json |
diff --git a/discovery/googleapis_beta/dataflow__v1b3.json b/discovery/googleapis_beta/dataflow__v1b3.json |
index 7393c174153f1eecb66fd2e0da059c7e4003baf1..c5e51a9215b7d46ef188321376b117bd14cf14f1 100644 |
--- a/discovery/googleapis_beta/dataflow__v1b3.json |
+++ b/discovery/googleapis_beta/dataflow__v1b3.json |
@@ -27,50 +27,19 @@ |
"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.", |
- "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", |
- "type": "string" |
- }, |
"prettyPrint": { |
"default": "true", |
"description": "Returns response with indentations and line breaks.", |
"location": "query", |
"type": "boolean" |
}, |
- "uploadType": { |
- "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", |
- "location": "query", |
- "type": "string" |
- }, |
"fields": { |
"description": "Selector specifying which fields to include in a partial response.", |
"location": "query", |
"type": "string" |
}, |
- "callback": { |
- "description": "JSONP", |
+ "uploadType": { |
+ "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", |
"location": "query", |
"type": "string" |
}, |
@@ -87,6 +56,11 @@ |
"location": "query", |
"type": "string" |
}, |
+ "callback": { |
+ "description": "JSONP", |
+ "location": "query", |
+ "type": "string" |
+ }, |
"alt": { |
"default": "json", |
"description": "Data format for response.", |
@@ -103,13 +77,39 @@ |
"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.", |
"location": "query", |
"type": "string" |
}, |
- "access_token": { |
- "description": "OAuth access 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" |
+ }, |
+ "oauth_token": { |
+ "description": "OAuth 2.0 token for the current user.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "bearer_token": { |
+ "description": "OAuth bearer token.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "upload_protocol": { |
+ "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", |
"location": "query", |
"type": "string" |
} |
@@ -151,50 +151,6 @@ |
"resources": { |
"jobs": { |
"methods": { |
- "getMetrics": { |
- "description": "Request the job status.", |
- "httpMethod": "GET", |
- "id": "dataflow.projects.locations.jobs.getMetrics", |
- "parameterOrder": [ |
- "projectId", |
- "location", |
- "jobId" |
- ], |
- "parameters": { |
- "location": { |
- "description": "The location which contains the job specified by job_id.", |
- "location": "path", |
- "required": true, |
- "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" |
- }, |
- "projectId": { |
- "description": "A project id.", |
- "location": "path", |
- "required": true, |
- "type": "string" |
- }, |
- "jobId": { |
- "description": "The job to get messages for.", |
- "location": "path", |
- "required": true, |
- "type": "string" |
- } |
- }, |
- "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics", |
- "response": { |
- "$ref": "JobMetrics" |
- }, |
- "scopes": [ |
- "https://www.googleapis.com/auth/cloud-platform", |
- "https://www.googleapis.com/auth/userinfo.email" |
- ] |
- }, |
"get": { |
"description": "Gets the state of the specified Cloud Dataflow job.", |
"httpMethod": "GET", |
@@ -228,7 +184,8 @@ |
"enum": [ |
"JOB_VIEW_UNKNOWN", |
"JOB_VIEW_SUMMARY", |
- "JOB_VIEW_ALL" |
+ "JOB_VIEW_ALL", |
+ "JOB_VIEW_DESCRIPTION" |
], |
"location": "query", |
"type": "string" |
@@ -291,7 +248,8 @@ |
"enum": [ |
"JOB_VIEW_UNKNOWN", |
"JOB_VIEW_SUMMARY", |
- "JOB_VIEW_ALL" |
+ "JOB_VIEW_ALL", |
+ "JOB_VIEW_DESCRIPTION" |
], |
"location": "query", |
"type": "string" |
@@ -356,6 +314,11 @@ |
"location" |
], |
"parameters": { |
+ "replaceJobId": { |
+ "description": "Deprecated. This field is now in the Job message.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
"projectId": { |
"description": "The ID of the Cloud Platform project that the job belongs to.", |
"location": "path", |
@@ -367,7 +330,8 @@ |
"enum": [ |
"JOB_VIEW_UNKNOWN", |
"JOB_VIEW_SUMMARY", |
- "JOB_VIEW_ALL" |
+ "JOB_VIEW_ALL", |
+ "JOB_VIEW_DESCRIPTION" |
], |
"location": "query", |
"type": "string" |
@@ -377,11 +341,6 @@ |
"location": "path", |
"required": true, |
"type": "string" |
- }, |
- "replaceJobId": { |
- "description": "Deprecated. This field is now in the Job message.", |
- "location": "query", |
- "type": "string" |
} |
}, |
"path": "v1b3/projects/{projectId}/locations/{location}/jobs", |
@@ -395,56 +354,137 @@ |
"https://www.googleapis.com/auth/cloud-platform", |
"https://www.googleapis.com/auth/userinfo.email" |
] |
+ }, |
+ "getMetrics": { |
+ "description": "Request the job status.", |
+ "httpMethod": "GET", |
+ "id": "dataflow.projects.locations.jobs.getMetrics", |
+ "parameterOrder": [ |
+ "projectId", |
+ "location", |
+ "jobId" |
+ ], |
+ "parameters": { |
+ "projectId": { |
+ "description": "A project id.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
+ }, |
+ "jobId": { |
+ "description": "The job to get messages for.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
+ }, |
+ "location": { |
+ "description": "The location which contains the job specified by job_id.", |
+ "location": "path", |
+ "required": true, |
+ "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" |
+ } |
+ }, |
+ "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics", |
+ "response": { |
+ "$ref": "JobMetrics" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform", |
+ "https://www.googleapis.com/auth/userinfo.email" |
+ ] |
} |
}, |
"resources": { |
- "workItems": { |
+ "messages": { |
"methods": { |
- "lease": { |
- "description": "Leases a dataflow WorkItem to run.", |
- "httpMethod": "POST", |
- "id": "dataflow.projects.locations.jobs.workItems.lease", |
+ "list": { |
+ "description": "Request the job status.", |
+ "httpMethod": "GET", |
+ "id": "dataflow.projects.locations.jobs.messages.list", |
"parameterOrder": [ |
"projectId", |
"location", |
"jobId" |
], |
"parameters": { |
- "location": { |
- "description": "The location which contains the WorkItem's job.", |
+ "projectId": { |
+ "description": "A project id.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "projectId": { |
- "description": "Identifies the project this worker belongs to.", |
+ "jobId": { |
+ "description": "The job to get messages about.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "jobId": { |
- "description": "Identifies the workflow job this worker belongs to.", |
+ "location": { |
+ "description": "The location which contains the job specified by job_id.", |
"location": "path", |
"required": true, |
"type": "string" |
+ }, |
+ "endTime": { |
+ "description": "Return only messages with timestamps < end_time. The default is now\n(i.e. return up to the latest messages available).", |
+ "format": "google-datetime", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "pageToken": { |
+ "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" |
+ }, |
+ "startTime": { |
+ "description": "If specified, return only messages with timestamps >= start_time.\nThe default is the job creation time (i.e. beginning of messages).", |
+ "format": "google-datetime", |
+ "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}/workItems:lease", |
- "request": { |
- "$ref": "LeaseWorkItemRequest" |
- }, |
+ "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages", |
"response": { |
- "$ref": "LeaseWorkItemResponse" |
+ "$ref": "ListJobMessagesResponse" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform", |
"https://www.googleapis.com/auth/userinfo.email" |
] |
- }, |
- "reportStatus": { |
- "description": "Reports the status of dataflow WorkItems leased by a worker.", |
+ } |
+ } |
+ }, |
+ "workItems": { |
+ "methods": { |
+ "lease": { |
+ "description": "Leases a dataflow WorkItem to run.", |
"httpMethod": "POST", |
- "id": "dataflow.projects.locations.jobs.workItems.reportStatus", |
+ "id": "dataflow.projects.locations.jobs.workItems.lease", |
"parameterOrder": [ |
"projectId", |
"location", |
@@ -452,13 +492,13 @@ |
], |
"parameters": { |
"projectId": { |
- "description": "The project which owns the WorkItem's job.", |
+ "description": "Identifies the project this worker belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
"jobId": { |
- "description": "The job which the WorkItem is part of.", |
+ "description": "Identifies the workflow job this worker belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
@@ -470,90 +510,53 @@ |
"type": "string" |
} |
}, |
- "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus", |
+ "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease", |
"request": { |
- "$ref": "ReportWorkItemStatusRequest" |
+ "$ref": "LeaseWorkItemRequest" |
}, |
"response": { |
- "$ref": "ReportWorkItemStatusResponse" |
+ "$ref": "LeaseWorkItemResponse" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform", |
"https://www.googleapis.com/auth/userinfo.email" |
] |
- } |
- } |
- }, |
- "messages": { |
- "methods": { |
- "list": { |
- "description": "Request the job status.", |
- "httpMethod": "GET", |
- "id": "dataflow.projects.locations.jobs.messages.list", |
+ }, |
+ "reportStatus": { |
+ "description": "Reports the status of dataflow WorkItems leased by a worker.", |
+ "httpMethod": "POST", |
+ "id": "dataflow.projects.locations.jobs.workItems.reportStatus", |
"parameterOrder": [ |
"projectId", |
"location", |
"jobId" |
], |
"parameters": { |
- "jobId": { |
- "description": "The job to get messages about.", |
+ "location": { |
+ "description": "The location which contains the WorkItem's job.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
"projectId": { |
- "description": "A project id.", |
+ "description": "The project which owns the WorkItem's job.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "endTime": { |
- "description": "Return only messages with timestamps < end_time. The default is now\n(i.e. return up to the latest messages available).", |
- "format": "google-datetime", |
- "location": "query", |
- "type": "string" |
- }, |
- "location": { |
- "description": "The location which contains the job specified by job_id.", |
+ "jobId": { |
+ "description": "The job which the WorkItem is part of.", |
"location": "path", |
"required": true, |
"type": "string" |
- }, |
- "startTime": { |
- "description": "If specified, return only messages with timestamps >= start_time.\nThe default is the job creation time (i.e. beginning of messages).", |
- "format": "google-datetime", |
- "location": "query", |
- "type": "string" |
- }, |
- "pageToken": { |
- "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", |
+ "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus", |
+ "request": { |
+ "$ref": "ReportWorkItemStatusRequest" |
+ }, |
"response": { |
- "$ref": "ListJobMessagesResponse" |
+ "$ref": "ReportWorkItemStatusResponse" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform", |
@@ -568,6 +571,43 @@ |
}, |
"templates": { |
"methods": { |
+ "get": { |
+ "description": "Get the template associated with a template.", |
+ "httpMethod": "GET", |
+ "id": "dataflow.projects.templates.get", |
+ "parameterOrder": [ |
+ "projectId" |
+ ], |
+ "parameters": { |
+ "projectId": { |
+ "description": "Required. The ID of the Cloud Platform project that the job belongs to.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
+ }, |
+ "view": { |
+ "description": "The view to retrieve. Defaults to METADATA_ONLY.", |
+ "enum": [ |
+ "METADATA_ONLY" |
+ ], |
+ "location": "query", |
+ "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:get", |
+ "response": { |
+ "$ref": "GetTemplateResponse" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform", |
+ "https://www.googleapis.com/auth/userinfo.email" |
+ ] |
+ }, |
"create": { |
"description": "Creates a Cloud Dataflow job from a template.", |
"httpMethod": "POST", |
@@ -594,6 +634,43 @@ |
"https://www.googleapis.com/auth/cloud-platform", |
"https://www.googleapis.com/auth/userinfo.email" |
] |
+ }, |
+ "launch": { |
+ "description": "Launch a template.", |
+ "httpMethod": "POST", |
+ "id": "dataflow.projects.templates.launch", |
+ "parameterOrder": [ |
+ "projectId" |
+ ], |
+ "parameters": { |
+ "dryRun": { |
+ "description": "Whether or not the job should actually be executed after\nvalidating parameters. Defaults to false. Validation errors do\nnot cause the HTTP request to fail if true.", |
+ "location": "query", |
+ "type": "boolean" |
+ }, |
+ "projectId": { |
+ "description": "Required. The ID of the Cloud Platform project that the job belongs to.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
+ }, |
+ "gcsPath": { |
+ "description": "Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.", |
+ "location": "query", |
+ "type": "string" |
+ } |
+ }, |
+ "path": "v1b3/projects/{projectId}/templates:launch", |
+ "request": { |
+ "$ref": "LaunchTemplateParameters" |
+ }, |
+ "response": { |
+ "$ref": "LaunchTemplateResponse" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform", |
+ "https://www.googleapis.com/auth/userinfo.email" |
+ ] |
} |
} |
}, |
@@ -608,6 +685,17 @@ |
"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" |
+ }, |
"projectId": { |
"description": "A project id.", |
"location": "path", |
@@ -619,17 +707,6 @@ |
"location": "path", |
"required": true, |
"type": "string" |
- }, |
- "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" |
} |
}, |
"path": "v1b3/projects/{projectId}/jobs/{jobId}/metrics", |
@@ -650,6 +727,11 @@ |
"jobId" |
], |
"parameters": { |
+ "location": { |
+ "description": "The location that contains this job.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
"projectId": { |
"description": "The ID of the Cloud Platform project that the job belongs to.", |
"location": "path", |
@@ -667,15 +749,11 @@ |
"enum": [ |
"JOB_VIEW_UNKNOWN", |
"JOB_VIEW_SUMMARY", |
- "JOB_VIEW_ALL" |
+ "JOB_VIEW_ALL", |
+ "JOB_VIEW_DESCRIPTION" |
], |
"location": "query", |
"type": "string" |
- }, |
- "location": { |
- "description": "The location that contains this job.", |
- "location": "query", |
- "type": "string" |
} |
}, |
"path": "v1b3/projects/{projectId}/jobs/{jobId}", |
@@ -695,12 +773,6 @@ |
"projectId" |
], |
"parameters": { |
- "projectId": { |
- "description": "The project which owns the jobs.", |
- "location": "path", |
- "required": true, |
- "type": "string" |
- }, |
"filter": { |
"description": "The kind of filter to use.", |
"enum": [ |
@@ -733,10 +805,17 @@ |
"enum": [ |
"JOB_VIEW_UNKNOWN", |
"JOB_VIEW_SUMMARY", |
- "JOB_VIEW_ALL" |
+ "JOB_VIEW_ALL", |
+ "JOB_VIEW_DESCRIPTION" |
], |
"location": "query", |
"type": "string" |
+ }, |
+ "projectId": { |
+ "description": "The project which owns the jobs.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
} |
}, |
"path": "v1b3/projects/{projectId}/jobs", |
@@ -757,11 +836,6 @@ |
"jobId" |
], |
"parameters": { |
- "location": { |
- "description": "The location that contains this job.", |
- "location": "query", |
- "type": "string" |
- }, |
"projectId": { |
"description": "The ID of the Cloud Platform project that the job belongs to.", |
"location": "path", |
@@ -773,6 +847,11 @@ |
"location": "path", |
"required": true, |
"type": "string" |
+ }, |
+ "location": { |
+ "description": "The location that contains this job.", |
+ "location": "query", |
+ "type": "string" |
} |
}, |
"path": "v1b3/projects/{projectId}/jobs/{jobId}", |
@@ -816,7 +895,8 @@ |
"enum": [ |
"JOB_VIEW_UNKNOWN", |
"JOB_VIEW_SUMMARY", |
- "JOB_VIEW_ALL" |
+ "JOB_VIEW_ALL", |
+ "JOB_VIEW_DESCRIPTION" |
], |
"location": "query", |
"type": "string" |
@@ -836,6 +916,82 @@ |
} |
}, |
"resources": { |
+ "messages": { |
+ "methods": { |
+ "list": { |
+ "description": "Request the job status.", |
+ "httpMethod": "GET", |
+ "id": "dataflow.projects.jobs.messages.list", |
+ "parameterOrder": [ |
+ "projectId", |
+ "jobId" |
+ ], |
+ "parameters": { |
+ "startTime": { |
+ "description": "If specified, return only messages with timestamps >= start_time.\nThe default is the job creation time (i.e. beginning of messages).", |
+ "format": "google-datetime", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "pageToken": { |
+ "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" |
+ }, |
+ "jobId": { |
+ "description": "The job to get messages about.", |
+ "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" |
+ }, |
+ "endTime": { |
+ "description": "Return only messages with timestamps < end_time. The default is now\n(i.e. return up to the latest messages available).", |
+ "format": "google-datetime", |
+ "location": "query", |
+ "type": "string" |
+ } |
+ }, |
+ "path": "v1b3/projects/{projectId}/jobs/{jobId}/messages", |
+ "response": { |
+ "$ref": "ListJobMessagesResponse" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform", |
+ "https://www.googleapis.com/auth/userinfo.email" |
+ ] |
+ } |
+ } |
+ }, |
"debug": { |
"methods": { |
"getConfig": { |
@@ -910,42 +1066,8 @@ |
}, |
"workItems": { |
"methods": { |
- "reportStatus": { |
- "description": "Reports the status of dataflow WorkItems leased by a worker.", |
- "httpMethod": "POST", |
- "id": "dataflow.projects.jobs.workItems.reportStatus", |
- "parameterOrder": [ |
- "projectId", |
- "jobId" |
- ], |
- "parameters": { |
- "projectId": { |
- "description": "The project which owns the WorkItem's job.", |
- "location": "path", |
- "required": true, |
- "type": "string" |
- }, |
- "jobId": { |
- "description": "The job which the WorkItem is part of.", |
- "location": "path", |
- "required": true, |
- "type": "string" |
- } |
- }, |
- "path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:reportStatus", |
- "request": { |
- "$ref": "ReportWorkItemStatusRequest" |
- }, |
- "response": { |
- "$ref": "ReportWorkItemStatusResponse" |
- }, |
- "scopes": [ |
- "https://www.googleapis.com/auth/cloud-platform", |
- "https://www.googleapis.com/auth/userinfo.email" |
- ] |
- }, |
- "lease": { |
- "description": "Leases a dataflow WorkItem to run.", |
+ "lease": { |
+ "description": "Leases a dataflow WorkItem to run.", |
"httpMethod": "POST", |
"id": "dataflow.projects.jobs.workItems.lease", |
"parameterOrder": [ |
@@ -977,77 +1099,35 @@ |
"https://www.googleapis.com/auth/cloud-platform", |
"https://www.googleapis.com/auth/userinfo.email" |
] |
- } |
- } |
- }, |
- "messages": { |
- "methods": { |
- "list": { |
- "description": "Request the job status.", |
- "httpMethod": "GET", |
- "id": "dataflow.projects.jobs.messages.list", |
+ }, |
+ "reportStatus": { |
+ "description": "Reports the status of dataflow WorkItems leased by a worker.", |
+ "httpMethod": "POST", |
+ "id": "dataflow.projects.jobs.workItems.reportStatus", |
"parameterOrder": [ |
"projectId", |
"jobId" |
], |
"parameters": { |
- "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" |
- }, |
- "jobId": { |
- "description": "The job to get messages about.", |
+ "projectId": { |
+ "description": "The project which owns the WorkItem's job.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "projectId": { |
- "description": "A project id.", |
+ "jobId": { |
+ "description": "The job which the WorkItem is part of.", |
"location": "path", |
"required": true, |
"type": "string" |
- }, |
- "location": { |
- "description": "The location which contains the job specified by job_id.", |
- "location": "query", |
- "type": "string" |
- }, |
- "endTime": { |
- "description": "Return only messages with timestamps < end_time. The default is now\n(i.e. return up to the latest messages available).", |
- "format": "google-datetime", |
- "location": "query", |
- "type": "string" |
- }, |
- "startTime": { |
- "description": "If specified, return only messages with timestamps >= start_time.\nThe default is the job creation time (i.e. beginning of messages).", |
- "format": "google-datetime", |
- "location": "query", |
- "type": "string" |
- }, |
- "pageToken": { |
- "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" |
} |
}, |
- "path": "v1b3/projects/{projectId}/jobs/{jobId}/messages", |
+ "path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:reportStatus", |
+ "request": { |
+ "$ref": "ReportWorkItemStatusRequest" |
+ }, |
"response": { |
- "$ref": "ListJobMessagesResponse" |
+ "$ref": "ReportWorkItemStatusResponse" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform", |
@@ -1061,161 +1141,20 @@ |
} |
} |
}, |
- "revision": "20170210", |
+ "revision": "20170303", |
"rootUrl": "https://dataflow.googleapis.com/", |
"schemas": { |
- "WorkItemStatus": { |
- "description": "Conveys a worker's progress through the work described by a WorkItem.", |
- "id": "WorkItemStatus", |
- "properties": { |
- "counterUpdates": { |
- "description": "Worker output counters for this WorkItem.", |
- "items": { |
- "$ref": "CounterUpdate" |
- }, |
- "type": "array" |
- }, |
- "workItemId": { |
- "description": "Identifies the WorkItem.", |
- "type": "string" |
- }, |
- "metricUpdates": { |
- "description": "DEPRECATED in favor of counter_updates.", |
- "items": { |
- "$ref": "MetricUpdate" |
- }, |
- "type": "array" |
- }, |
- "errors": { |
- "description": "Specifies errors which occurred during processing. If errors are\nprovided, and completed = true, then the WorkItem is considered\nto have failed.", |
- "items": { |
- "$ref": "Status" |
- }, |
- "type": "array" |
- }, |
- "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." |
- } |
- }, |
- "type": "object" |
- }, |
- "WorkItemServiceState": { |
- "description": "The Dataflow service's idea of the current state of a WorkItem\nbeing processed by a worker.", |
- "id": "WorkItemServiceState", |
- "properties": { |
- "leaseExpireTime": { |
- "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." |
- }, |
- "splitRequest": { |
- "$ref": "ApproximateSplitRequest", |
- "description": "The progress point in the WorkItem where the Dataflow service\nsuggests that the worker truncate the task." |
- }, |
- "reportStatusInterval": { |
- "description": "New recommended reporting interval.", |
- "format": "google-duration", |
- "type": "string" |
- }, |
- "suggestedStopPosition": { |
- "$ref": "Position", |
- "description": "Obsolete, always empty." |
- }, |
- "harnessData": { |
- "additionalProperties": { |
- "description": "Properties of the object.", |
- "type": "any" |
- }, |
- "description": "Other data returned by the service, specific to the particular\nworker harness.", |
- "type": "object" |
- } |
- }, |
- "type": "object" |
- }, |
- "MetricStructuredName": { |
- "description": "Identifies a metric, by describing the source which generated the\nmetric.", |
- "id": "MetricStructuredName", |
- "properties": { |
- "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" |
- }, |
- "name": { |
- "description": "Worker-defined metric name.", |
- "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" |
- }, |
"SeqMapTaskOutputInfo": { |
"description": "Information about an output of a SeqMapTask.", |
"id": "SeqMapTaskOutputInfo", |
"properties": { |
- "tag": { |
- "description": "The id of the TupleTag the user code will tag the output value by.", |
- "type": "string" |
- }, |
"sink": { |
"$ref": "Sink", |
"description": "The sink to write the output value to." |
+ }, |
+ "tag": { |
+ "description": "The id of the TupleTag the user code will tag the output value by.", |
+ "type": "string" |
} |
}, |
"type": "object" |
@@ -1313,6 +1252,21 @@ |
"description": "Describes a particular function to invoke.", |
"id": "SeqMapTask", |
"properties": { |
+ "inputs": { |
+ "description": "Information about each of the inputs.", |
+ "items": { |
+ "$ref": "SideInputInfo" |
+ }, |
+ "type": "array" |
+ }, |
+ "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.", |
@@ -1331,21 +1285,6 @@ |
"$ref": "SeqMapTaskOutputInfo" |
}, |
"type": "array" |
- }, |
- "inputs": { |
- "description": "Information about each of the inputs.", |
- "items": { |
- "$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" |
} |
}, |
"type": "object" |
@@ -1354,6 +1293,10 @@ |
"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.", |
@@ -1361,10 +1304,6 @@ |
}, |
"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" |
@@ -1436,14 +1375,6 @@ |
"description": "An output of an instruction.", |
"id": "InstructionOutput", |
"properties": { |
- "name": { |
- "description": "The user-provided name of this output.", |
- "type": "string" |
- }, |
- "originalName": { |
- "description": "System-defined name for this output in the original workflow graph.\nOutputs that do not contribute to an original instruction do not set this.", |
- "type": "string" |
- }, |
"systemName": { |
"description": "System-defined name of this output.\nUnique across the workflow.", |
"type": "string" |
@@ -1463,6 +1394,14 @@ |
}, |
"description": "The codec to use to encode data being written via this output.", |
"type": "object" |
+ }, |
+ "name": { |
+ "description": "The user-provided name of this output.", |
+ "type": "string" |
+ }, |
+ "originalName": { |
+ "description": "System-defined name for this output in the original workflow graph.\nOutputs that do not contribute to an original instruction do not set this.", |
+ "type": "string" |
} |
}, |
"type": "object" |
@@ -1512,6 +1451,13 @@ |
"description": "Response to a request to list Cloud Dataflow jobs. This may be a partial\nresponse, depending on the page size in the ListJobsRequest.", |
"id": "ListJobsResponse", |
"properties": { |
+ "jobs": { |
+ "description": "A subset of the requested job information.", |
+ "items": { |
+ "$ref": "Job" |
+ }, |
+ "type": "array" |
+ }, |
"nextPageToken": { |
"description": "Set if there may be more results than fit in this response.", |
"type": "string" |
@@ -1522,13 +1468,6 @@ |
"$ref": "FailedLocation" |
}, |
"type": "array" |
- }, |
- "jobs": { |
- "description": "A subset of the requested job information.", |
- "items": { |
- "$ref": "Job" |
- }, |
- "type": "array" |
} |
}, |
"type": "object" |
@@ -1537,43 +1476,43 @@ |
"description": "All configuration data for a particular Computation.", |
"id": "ComputationTopology", |
"properties": { |
- "userStageName": { |
- "description": "The user stage name.", |
+ "systemStageName": { |
+ "description": "The system stage name.", |
"type": "string" |
}, |
- "outputs": { |
- "description": "The outputs from the computation.", |
+ "inputs": { |
+ "description": "The inputs to the computation.", |
"items": { |
"$ref": "StreamLocation" |
}, |
"type": "array" |
}, |
- "stateFamilies": { |
- "description": "The state family values.", |
+ "computationId": { |
+ "description": "The ID of the computation.", |
+ "type": "string" |
+ }, |
+ "keyRanges": { |
+ "description": "The key ranges processed by the computation.", |
"items": { |
- "$ref": "StateFamilyConfig" |
+ "$ref": "KeyRangeLocation" |
}, |
"type": "array" |
}, |
- "systemStageName": { |
- "description": "The system stage name.", |
- "type": "string" |
- }, |
- "computationId": { |
- "description": "The ID of the computation.", |
+ "userStageName": { |
+ "description": "The user stage name.", |
"type": "string" |
}, |
- "inputs": { |
- "description": "The inputs to the computation.", |
+ "outputs": { |
+ "description": "The outputs from the computation.", |
"items": { |
"$ref": "StreamLocation" |
}, |
"type": "array" |
}, |
- "keyRanges": { |
- "description": "The key ranges processed by the computation.", |
+ "stateFamilies": { |
+ "description": "The state family values.", |
"items": { |
- "$ref": "KeyRangeLocation" |
+ "$ref": "StateFamilyConfig" |
}, |
"type": "array" |
} |
@@ -1584,6 +1523,15 @@ |
"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" |
+ }, |
+ "zone": { |
+ "description": "The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)\nfor launching worker instances to run your pipeline.", |
+ "type": "string" |
+ }, |
"serviceAccountEmail": { |
"description": "The email address of the service account to run the job as.", |
"type": "string" |
@@ -1595,14 +1543,20 @@ |
"bypassTempDirValidation": { |
"description": "Whether to bypass the safety checks for the job's temporary directory.\nUse with caution.", |
"type": "boolean" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "StreamingSideInputLocation": { |
+ "description": "Identifies the location of a streaming side input.", |
+ "id": "StreamingSideInputLocation", |
+ "properties": { |
+ "stateFamily": { |
+ "description": "Identifies the state family where this side input is stored.", |
+ "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" |
- }, |
- "zone": { |
- "description": "The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)\nfor launching worker instances to run your pipeline.", |
+ "tag": { |
+ "description": "Identifies the particular side input within the streaming Dataflow job.", |
"type": "string" |
} |
}, |
@@ -1619,66 +1573,67 @@ |
}, |
"type": "object" |
}, |
- "StreamingSideInputLocation": { |
- "description": "Identifies the location of a streaming side input.", |
- "id": "StreamingSideInputLocation", |
+ "LaunchTemplateResponse": { |
+ "description": "Response to the request to launch a template.", |
+ "id": "LaunchTemplateResponse", |
"properties": { |
- "stateFamily": { |
- "description": "Identifies the state family where this side input is stored.", |
- "type": "string" |
+ "status": { |
+ "$ref": "Status", |
+ "description": "The status of the launch template request. Any problems with the request\nwill be indicated in the error_details." |
}, |
- "tag": { |
- "description": "Identifies the particular side input within the streaming Dataflow job.", |
- "type": "string" |
+ "job": { |
+ "$ref": "Job", |
+ "description": "The job that was launched, if the request was not a dry run and\nthe job was successfully launched." |
} |
}, |
"type": "object" |
}, |
- "Job": { |
- "description": "Defines a job to be run by the Cloud Dataflow service.", |
- "id": "Job", |
+ "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": { |
- "requestedState": { |
- "description": "The job's requested state.\n\n`UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and\n`JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may\nalso be used to directly set a job's requested state to\n`JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the\njob if it has not already reached a terminal state.", |
+ "derivationMode": { |
+ "description": "What source to base the produced source on (if any).", |
"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" |
+ "SOURCE_DERIVATION_MODE_UNKNOWN", |
+ "SOURCE_DERIVATION_MODE_INDEPENDENT", |
+ "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT", |
+ "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT" |
], |
"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`." |
+ "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" |
}, |
- "tempFiles": { |
- "description": "A set of files the system should be aware of that are used\nfor temporary storage. These temporary files will be\nremoved on job completion.\nNo duplicates are allowed.\nNo file patterns are supported.\n\nThe supported files are:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}", |
- "items": { |
- "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" |
+ "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": { |
+ "primary": { |
+ "$ref": "DerivedSource", |
+ "description": "Primary part (continued to be processed by worker).\nSpecified relative to the previously-current source.\nBecomes current." |
}, |
+ "residual": { |
+ "$ref": "DerivedSource", |
+ "description": "Residual part (returned to the pool of work).\nSpecified relative to the previously-current source." |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "Job": { |
+ "description": "Defines a job to be run by the Cloud Dataflow service.", |
+ "id": "Job", |
+ "properties": { |
"steps": { |
"description": "The top-level steps that constitute the entire job.", |
"items": { |
@@ -1692,7 +1647,7 @@ |
}, |
"executionInfo": { |
"$ref": "JobExecutionInfo", |
- "description": "Information about how the Cloud Dataflow service will run the job." |
+ "description": "Deprecated." |
}, |
"id": { |
"description": "The unique ID of this job.\n\nThis field is set by the Cloud Dataflow service when the Job is\ncreated, and is immutable for the life of the job.", |
@@ -1740,15 +1695,6 @@ |
"description": "The map of transform name prefixes of the job to be replaced to the\ncorresponding name prefixes of the new job.", |
"type": "object" |
}, |
- "createTime": { |
- "description": "The timestamp when the job was initially created. Immutable and set by the\nCloud Dataflow service.", |
- "format": "google-datetime", |
- "type": "string" |
- }, |
- "environment": { |
- "$ref": "Environment", |
- "description": "The environment for the job." |
- }, |
"labels": { |
"additionalProperties": { |
"type": "string" |
@@ -1756,6 +1702,15 @@ |
"description": "User-defined labels for this job.\n\nThe labels map can contain no more than 64 entries. Entries of the labels\nmap are UTF8 strings that comply with the following restrictions:\n\n* Keys must conform to regexp: \\p{Ll}\\p{Lo}{0,62}\n* Values must conform to regexp: [\\p{Ll}\\p{Lo}\\p{N}_-]{0,63}\n* Both keys and values are additionally constrained to be <= 128 bytes in\nsize.", |
"type": "object" |
}, |
+ "environment": { |
+ "$ref": "Environment", |
+ "description": "The environment for the job." |
+ }, |
+ "createTime": { |
+ "description": "The timestamp when the job was initially created. Immutable and set by the\nCloud Dataflow service.", |
+ "format": "google-datetime", |
+ "type": "string" |
+ }, |
"type": { |
"description": "The type of Cloud Dataflow job.", |
"enum": [ |
@@ -1774,51 +1729,54 @@ |
"description": "The ID of the Cloud Platform project that the job belongs to.", |
"type": "string" |
}, |
+ "pipelineDescription": { |
+ "$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." |
+ }, |
"replaceJobId": { |
"description": "If this job is an update of an existing job, this field is the job ID\nof the job it replaced.\n\nWhen sending a `CreateJobRequest`, you can update a job by specifying it\nhere. The job named here is stopped, and its intermediate state is\ntransferred to 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": { |
- "source": { |
- "$ref": "Source", |
- "description": "Specification of the source." |
+ "type": "string" |
}, |
- "derivationMode": { |
- "description": "What source to base the produced source on (if any).", |
+ "requestedState": { |
+ "description": "The job's requested state.\n\n`UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and\n`JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may\nalso be used to directly set a job's requested state to\n`JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the\njob if it has not already reached a terminal state.", |
"enum": [ |
- "SOURCE_DERIVATION_MODE_UNKNOWN", |
- "SOURCE_DERIVATION_MODE_INDEPENDENT", |
- "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT", |
- "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT" |
+ "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" |
], |
"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." |
+ "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`." |
], |
"type": "string" |
+ }, |
+ "tempFiles": { |
+ "description": "A set of files the system should be aware of that are used\nfor temporary storage. These temporary files will be\nremoved on job completion.\nNo duplicates are allowed.\nNo file patterns are supported.\n\nThe supported files are:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}", |
+ "items": { |
+ "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" |
} |
}, |
"type": "object" |
@@ -1838,12 +1796,6 @@ |
}, |
"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", |
@@ -1870,20 +1822,10 @@ |
}, |
"type": "object" |
}, |
- "ConcatPosition": { |
- "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": { |
- "position": { |
- "$ref": "Position", |
- "description": "Position within the inner source." |
- }, |
- "index": { |
- "description": "Index of the inner source.", |
- "format": "int32", |
- "type": "integer" |
- } |
- }, |
+ "SendDebugCaptureResponse": { |
+ "description": "Response to a send capture request.\nnothing", |
+ "id": "SendDebugCaptureResponse", |
+ "properties": {}, |
"type": "object" |
}, |
"WriteInstruction": { |
@@ -1901,6 +1843,22 @@ |
}, |
"type": "object" |
}, |
+ "ConcatPosition": { |
+ "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": { |
+ "position": { |
+ "$ref": "Position", |
+ "description": "Position within the inner source." |
+ }, |
+ "index": { |
+ "description": "Index of the inner source.", |
+ "format": "int32", |
+ "type": "integer" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"CounterStructuredNameAndMetadata": { |
"description": "A single message which encapsulates structured name and metadata for a given\ncounter.", |
"id": "CounterStructuredNameAndMetadata", |
@@ -1960,6 +1918,75 @@ |
}, |
"type": "object" |
}, |
+ "ExecutionStageSummary": { |
+ "description": "Description of the composing transforms, names/ids, and input/outputs of a\nstage of execution. Some composing transforms and sources may have been\ngenerated by the Dataflow service during execution planning.", |
+ "id": "ExecutionStageSummary", |
+ "properties": { |
+ "outputSource": { |
+ "description": "Output sources for this stage.", |
+ "items": { |
+ "$ref": "StageSource" |
+ }, |
+ "type": "array" |
+ }, |
+ "name": { |
+ "description": "Dataflow service generated name for this stage.", |
+ "type": "string" |
+ }, |
+ "inputSource": { |
+ "description": "Input sources for this stage.", |
+ "items": { |
+ "$ref": "StageSource" |
+ }, |
+ "type": "array" |
+ }, |
+ "id": { |
+ "description": "Dataflow service generated id for this stage.", |
+ "type": "string" |
+ }, |
+ "componentTransform": { |
+ "description": "Transforms that comprise this execution stage.", |
+ "items": { |
+ "$ref": "ComponentTransform" |
+ }, |
+ "type": "array" |
+ }, |
+ "componentSource": { |
+ "description": "Collections produced and consumed by component transforms of this stage.", |
+ "items": { |
+ "$ref": "ComponentSource" |
+ }, |
+ "type": "array" |
+ }, |
+ "kind": { |
+ "description": "Type of tranform this stage is executing.", |
+ "enum": [ |
+ "UNKNOWN_KIND", |
+ "PAR_DO_KIND", |
+ "GROUP_BY_KEY_KIND", |
+ "FLATTEN_KIND", |
+ "READ_KIND", |
+ "WRITE_KIND", |
+ "CONSTANT_KIND", |
+ "SINGLETON_KIND", |
+ "SHUFFLE_KIND" |
+ ], |
+ "enumDescriptions": [ |
+ "Unrecognized transform type.", |
+ "ParDo transform.", |
+ "Group By Key transform.", |
+ "Flatten transform.", |
+ "Read transform.", |
+ "Write transform.", |
+ "Constructs from a constant value, such as with Create.of.", |
+ "Creates a Singleton view of a collection.", |
+ "Opening or closing a shuffle session, often as part of a GroupByKey." |
+ ], |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"SendWorkerMessagesRequest": { |
"description": "A request for sending worker messages to the service.", |
"id": "SendWorkerMessagesRequest", |
@@ -2005,11 +2032,6 @@ |
"description": "Modeled after information exposed by /proc/stat.", |
"id": "CPUTime", |
"properties": { |
- "totalMs": { |
- "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", |
@@ -2019,6 +2041,11 @@ |
"description": "Timestamp of the measurement.", |
"format": "google-datetime", |
"type": "string" |
+ }, |
+ "totalMs": { |
+ "description": "Total active CPU time across all cores (ie., non-idle) in milliseconds\nsince start-up.", |
+ "format": "uint64", |
+ "type": "string" |
} |
}, |
"type": "object" |
@@ -2027,6 +2054,26 @@ |
"description": "Describes the environment in which a Dataflow Job runs.", |
"id": "Environment", |
"properties": { |
+ "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": "A description of the process that generated the request.", |
+ "type": "object" |
+ }, |
+ "sdkPipelineOptions": { |
+ "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.", |
+ "type": "object" |
+ }, |
"clusterManagerApiService": { |
"description": "The type of cluster manager API to use. If unknown or\nunspecified, the service will attempt to choose a reasonable\ndefault. This should be in the form of the API service name,\ne.g. \"compute.googleapis.com\".", |
"type": "string" |
@@ -2053,14 +2100,6 @@ |
}, |
"type": "array" |
}, |
- "internalExperiments": { |
- "additionalProperties": { |
- "description": "Properties of the object. Contains field @type with type URL.", |
- "type": "any" |
- }, |
- "description": "Experimental settings.", |
- "type": "object" |
- }, |
"version": { |
"additionalProperties": { |
"description": "Properties of the object.", |
@@ -2069,24 +2108,12 @@ |
"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" |
- }, |
- "userAgent": { |
- "additionalProperties": { |
- "description": "Properties of the object.", |
- "type": "any" |
- }, |
- "description": "A description of the process that generated the request.", |
- "type": "object" |
- }, |
- "sdkPipelineOptions": { |
+ "internalExperiments": { |
"additionalProperties": { |
- "description": "Properties of the object.", |
+ "description": "Properties of the object. Contains field @type with type URL.", |
"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": "Experimental settings.", |
"type": "object" |
} |
}, |
@@ -2096,13 +2123,6 @@ |
"description": "A task which describes what action should be performed for the specified\nstreaming computation ranges.", |
"id": "StreamingComputationTask", |
"properties": { |
- "dataDisks": { |
- "description": "Describes the set of data disks this task should apply to.", |
- "items": { |
- "$ref": "MountedDataDisk" |
- }, |
- "type": "array" |
- }, |
"taskType": { |
"description": "A type of streaming computation task.", |
"enum": [ |
@@ -2123,6 +2143,13 @@ |
"$ref": "StreamingComputationRanges" |
}, |
"type": "array" |
+ }, |
+ "dataDisks": { |
+ "description": "Describes the set of data disks this task should apply to.", |
+ "items": { |
+ "$ref": "MountedDataDisk" |
+ }, |
+ "type": "array" |
} |
}, |
"type": "object" |
@@ -2131,6 +2158,10 @@ |
"description": "Request to send encoded debug information.", |
"id": "SendDebugCaptureRequest", |
"properties": { |
+ "data": { |
+ "description": "The encoded debug information.", |
+ "type": "string" |
+ }, |
"componentId": { |
"description": "The internal component id for which debug information is sent.", |
"type": "string" |
@@ -2138,10 +2169,6 @@ |
"workerId": { |
"description": "The worker id, i.e., VM hostname.", |
"type": "string" |
- }, |
- "data": { |
- "description": "The encoded debug information.", |
- "type": "string" |
} |
}, |
"type": "object" |
@@ -2157,10 +2184,33 @@ |
}, |
"type": "object" |
}, |
+ "ComponentTransform": { |
+ "description": "Description of a transform executed as part of an execution stage.", |
+ "id": "ComponentTransform", |
+ "properties": { |
+ "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" |
+ }, |
+ "originalTransform": { |
+ "description": "User name for the original user transform with which this transform is\nmost closely associated.", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"StreamingSetupTask": { |
"description": "A task which initializes part of a streaming Dataflow job.", |
"id": "StreamingSetupTask", |
"properties": { |
+ "streamingComputationTopology": { |
+ "$ref": "TopologyConfig", |
+ "description": "The global topology of the streaming Dataflow job." |
+ }, |
"workerHarnessPort": { |
"description": "The TCP port used by the worker to communicate with the Dataflow\nworker harness.", |
"format": "int32", |
@@ -2174,10 +2224,6 @@ |
"description": "The TCP port on which the worker should listen for messages from\nother streaming computation workers.", |
"format": "int32", |
"type": "integer" |
- }, |
- "streamingComputationTopology": { |
- "$ref": "TopologyConfig", |
- "description": "The global topology of the streaming Dataflow job." |
} |
}, |
"type": "object" |
@@ -2194,14 +2240,14 @@ |
"description": "If set, contains a pubsub label from which to extract record ids.\nIf left empty, record deduplication will be strictly best effort.", |
"type": "string" |
}, |
- "topic": { |
- "description": "A pubsub topic, in the form of\n\"pubsub.googleapis.com/topics/<project-id>/<topic-name>\"", |
- "type": "string" |
- }, |
"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" |
}, |
+ "topic": { |
+ "description": "A pubsub topic, in the form of\n\"pubsub.googleapis.com/topics/<project-id>/<topic-name>\"", |
+ "type": "string" |
+ }, |
"subscription": { |
"description": "A pubsub subscription, in the form of\n\"pubsub.googleapis.com/subscriptions/<project-id>/<subscription-name>\"", |
"type": "string" |
@@ -2221,6 +2267,15 @@ |
"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": { |
+ "vmIsHealthy": { |
+ "description": "Whether the VM is healthy.", |
+ "type": "boolean" |
+ }, |
+ "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", |
+ "type": "string" |
+ }, |
"pods": { |
"description": "The pods running on the worker. See:\nhttp://kubernetes.io/v1.1/docs/api-reference/v1/definitions.html#_v1_pod\n\nThis field is used by the worker to send the status of the indvidual\ncontainers running on each worker.", |
"items": { |
@@ -2236,15 +2291,6 @@ |
"description": "The time the VM was booted.", |
"format": "google-datetime", |
"type": "string" |
- }, |
- "vmIsHealthy": { |
- "description": "Whether the VM is healthy.", |
- "type": "boolean" |
- }, |
- "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", |
- "type": "string" |
} |
}, |
"type": "object" |
@@ -2289,6 +2335,36 @@ |
}, |
"type": "object" |
}, |
+ "ParameterMetadata": { |
+ "description": "Metadata for a specific parameter.", |
+ "id": "ParameterMetadata", |
+ "properties": { |
+ "label": { |
+ "description": "Required. The label to display for the parameter.", |
+ "type": "string" |
+ }, |
+ "helpText": { |
+ "description": "Required. The help text to display for the parameter.", |
+ "type": "string" |
+ }, |
+ "isOptional": { |
+ "description": "Optional. Whether the parameter is optional. Defaults to false.", |
+ "type": "boolean" |
+ }, |
+ "name": { |
+ "description": "Required. The name of the parameter.", |
+ "type": "string" |
+ }, |
+ "regexes": { |
+ "description": "Optional. Regexes that the parameter must match.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"MultiOutputInfo": { |
"description": "Information about an output of a multi-output DoFn.", |
"id": "MultiOutputInfo", |
@@ -2363,34 +2439,6 @@ |
"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." |
- }, |
- "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" |
- }, |
"taskGroup": { |
"description": "The UNIX group ID on the worker VM to use for tasks launched by\ntaskrunner; e.g. \"wheel\".", |
"type": "string" |
@@ -2403,10 +2451,6 @@ |
"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": { |
@@ -2414,33 +2458,65 @@ |
}, |
"type": "array" |
}, |
- "streamingWorkerMainClass": { |
- "description": "The streaming worker main class name.", |
+ "dataflowApiVersion": { |
+ "description": "The API version of endpoint, e.g. \"v1b3\"", |
"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.", |
+ "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.", |
"type": "string" |
}, |
"languageHint": { |
"description": "The suggested backend language.", |
"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}", |
+ "commandlinesFileName": { |
+ "description": "The file to store preprocessing commands in.", |
"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" |
+ }, |
+ "parallelWorkerSettings": { |
+ "$ref": "WorkerSettings", |
+ "description": "The settings to pass to the parallel worker harness." |
+ }, |
+ "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" |
} |
}, |
"type": "object" |
@@ -2449,6 +2525,11 @@ |
"description": "Position defines a position within a collection of data. The value\ncan be either the end position, a key (used with ordered\ncollections), a byte offset, or a record index.", |
"id": "Position", |
"properties": { |
+ "recordIndex": { |
+ "description": "Position is a record index.", |
+ "format": "int64", |
+ "type": "string" |
+ }, |
"shufflePosition": { |
"description": "CloudPosition is a base64 encoded BatchShufflePosition (with FIXED\nsharding).", |
"type": "string" |
@@ -2469,11 +2550,6 @@ |
"key": { |
"description": "Position is a string key, ordered lexicographically.", |
"type": "string" |
- }, |
- "recordIndex": { |
- "description": "Position is a record index.", |
- "format": "int64", |
- "type": "string" |
} |
}, |
"type": "object" |
@@ -2499,6 +2575,21 @@ |
"description": "A source that records can be read and decoded from.", |
"id": "Source", |
"properties": { |
+ "metadata": { |
+ "$ref": "SourceMetadata", |
+ "description": "Optionally, metadata for this source can be supplied right away,\navoiding a SourceGetMetadataOperation roundtrip\n(see SourceOperationRequest).\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated." |
+ }, |
+ "baseSpecs": { |
+ "description": "While splitting, sources may specify the produced bundles\nas differences against another source, in order to save backend-side\nmemory and allow bigger jobs. For details, see SourceSplitRequest.\nTo support this use case, the full set of parameters of the source\nis logically obtained by taking the latest explicitly specified value\nof each parameter in the order:\nbase_specs (later items win), spec (overrides anything in base_specs).", |
+ "items": { |
+ "additionalProperties": { |
+ "description": "Properties of the object.", |
+ "type": "any" |
+ }, |
+ "type": "object" |
+ }, |
+ "type": "array" |
+ }, |
"codec": { |
"additionalProperties": { |
"description": "Properties of the object.", |
@@ -2518,21 +2609,6 @@ |
}, |
"description": "The source to read from, plus its parameters.", |
"type": "object" |
- }, |
- "metadata": { |
- "$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" |
@@ -2541,18 +2617,76 @@ |
"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" |
+ }, |
+ "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.", |
+ "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" |
+ }, |
+ "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" |
@@ -2597,10 +2731,6 @@ |
"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": [ |
@@ -2617,63 +2747,9 @@ |
], |
"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.", |
- "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.", |
+ "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" |
@@ -2682,13 +2758,13 @@ |
"description": "A work item that represents the different operations that can be\nperformed on a user-defined Source specification.", |
"id": "SourceOperationRequest", |
"properties": { |
- "split": { |
- "$ref": "SourceSplitRequest", |
- "description": "Information about a request to split a source." |
- }, |
"getMetadata": { |
"$ref": "SourceGetMetadataRequest", |
"description": "Information about a request to get metadata about a source." |
+ }, |
+ "split": { |
+ "$ref": "SourceSplitRequest", |
+ "description": "Information about a request to split a source." |
} |
}, |
"type": "object" |
@@ -2697,19 +2773,14 @@ |
"description": "WorkItem represents basic information about a WorkItem to be executed\nin the cloud.", |
"id": "WorkItem", |
"properties": { |
- "initialReportIndex": { |
- "description": "The initial index to use when reporting the status of the WorkItem.", |
- "format": "int64", |
- "type": "string" |
+ "shellTask": { |
+ "$ref": "ShellTask", |
+ "description": "Additional information for ShellTask WorkItems." |
}, |
"streamingComputationTask": { |
"$ref": "StreamingComputationTask", |
"description": "Additional information for StreamingComputationTask WorkItems." |
}, |
- "shellTask": { |
- "$ref": "ShellTask", |
- "description": "Additional information for ShellTask WorkItems." |
- }, |
"jobId": { |
"description": "Identifies the workflow job this WorkItem belongs to.", |
"type": "string" |
@@ -2742,11 +2813,6 @@ |
"description": "Identifies the cloud project this WorkItem belongs to.", |
"type": "string" |
}, |
- "reportStatusInterval": { |
- "description": "Recommended reporting interval.", |
- "format": "google-duration", |
- "type": "string" |
- }, |
"sourceOperationTask": { |
"$ref": "SourceOperationRequest", |
"description": "Additional information for source operation WorkItems." |
@@ -2755,6 +2821,11 @@ |
"$ref": "StreamingSetupTask", |
"description": "Additional information for StreamingSetupTask WorkItems." |
}, |
+ "reportStatusInterval": { |
+ "description": "Recommended reporting interval.", |
+ "format": "google-duration", |
+ "type": "string" |
+ }, |
"streamingConfigTask": { |
"$ref": "StreamingConfigTask", |
"description": "Additional information for StreamingConfigTask WorkItems." |
@@ -2763,6 +2834,27 @@ |
"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" |
+ }, |
+ "ReportedParallelism": { |
+ "description": "Represents the level of parallelism in a WorkItem's input,\nreported by the worker.", |
+ "id": "ReportedParallelism", |
+ "properties": { |
+ "value": { |
+ "description": "Specifies the level of parallelism in case it is finite.", |
+ "format": "double", |
+ "type": "number" |
+ }, |
+ "isInfinite": { |
+ "description": "Specifies whether the parallelism is infinite. If true, \"value\" is\nignored.\nInfinite parallelism means the service will assume that the work item\ncan always be split into more non-empty work items by dynamic splitting.\nThis is a work-around for lack of support for infinity by the current\nJSON-based Java RPC stack.", |
+ "type": "boolean" |
} |
}, |
"type": "object" |
@@ -2781,38 +2873,10 @@ |
}, |
"type": "object" |
}, |
- "ReportedParallelism": { |
- "description": "Represents the level of parallelism in a WorkItem's input,\nreported by the worker.", |
- "id": "ReportedParallelism", |
- "properties": { |
- "isInfinite": { |
- "description": "Specifies whether the parallelism is infinite. If true, \"value\" is\nignored.\nInfinite parallelism means the service will assume that the work item\ncan always be split into more non-empty work items by dynamic splitting.\nThis is a work-around for lack of support for infinity by the current\nJSON-based Java RPC stack.", |
- "type": "boolean" |
- }, |
- "value": { |
- "description": "Specifies the level of parallelism in case it is finite.", |
- "format": "double", |
- "type": "number" |
- } |
- }, |
- "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" |
- }, |
- "description": "Maps user stage names to stable computation names.", |
- "type": "object" |
- }, |
"computations": { |
"description": "The computations associated with a streaming Dataflow job.", |
"items": { |
@@ -2831,6 +2895,18 @@ |
"description": "Version number for persistent state.", |
"format": "int32", |
"type": "integer" |
+ }, |
+ "forwardingKeyBits": { |
+ "description": "The size (in bits) of keys that will be assigned to source messages.", |
+ "format": "int32", |
+ "type": "integer" |
+ }, |
+ "userStageToComputationNameMap": { |
+ "additionalProperties": { |
+ "type": "string" |
+ }, |
+ "description": "Maps user stage names to stable computation names.", |
+ "type": "object" |
} |
}, |
"type": "object" |
@@ -2867,6 +2943,18 @@ |
"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}", |
+ "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/\"", |
+ "type": "string" |
+ }, |
+ "reportingEnabled": { |
+ "description": "Whether to send work progress updates to the service.", |
+ "type": "boolean" |
+ }, |
"servicePath": { |
"description": "The Cloud Dataflow service path relative to the root URL, for example,\n\"dataflow/v1b3/projects\".", |
"type": "string" |
@@ -2878,18 +2966,17 @@ |
"workerId": { |
"description": "The ID of the worker running this pipeline.", |
"type": "string" |
- }, |
- "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" |
- }, |
- "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": "object" |
+ }, |
+ "StreamingStageLocation": { |
+ "description": "Identifies the location of a streaming computation stage, for\nstage-to-stage communication.", |
+ "id": "StreamingStageLocation", |
+ "properties": { |
+ "streamId": { |
+ "description": "Identifies the particular stream within the streaming Dataflow\njob.", |
"type": "string" |
- }, |
- "reportingEnabled": { |
- "description": "Whether to send work progress updates to the service.", |
- "type": "boolean" |
} |
}, |
"type": "object" |
@@ -2912,29 +2999,18 @@ |
}, |
"type": "object" |
}, |
- "StreamingStageLocation": { |
- "description": "Identifies the location of a streaming computation stage, for\nstage-to-stage communication.", |
- "id": "StreamingStageLocation", |
- "properties": { |
- "streamId": { |
- "description": "Identifies the particular stream within the streaming Dataflow\njob.", |
- "type": "string" |
- } |
- }, |
- "type": "object" |
- }, |
"ApproximateSplitRequest": { |
"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": { |
- "$ref": "Position", |
- "description": "A Position at which to split the work item." |
} |
}, |
"type": "object" |
@@ -3017,6 +3093,68 @@ |
}, |
"type": "object" |
}, |
+ "TransformSummary": { |
+ "description": "Description of the type, names/ids, and input/outputs for a transform.", |
+ "id": "TransformSummary", |
+ "properties": { |
+ "name": { |
+ "description": "User provided name for this transform instance.", |
+ "type": "string" |
+ }, |
+ "id": { |
+ "description": "SDK generated id of this transform instance.", |
+ "type": "string" |
+ }, |
+ "displayData": { |
+ "description": "Transform-specific display data.", |
+ "items": { |
+ "$ref": "DisplayData" |
+ }, |
+ "type": "array" |
+ }, |
+ "outputCollectionName": { |
+ "description": "User names for all collection outputs to this transform.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ }, |
+ "kind": { |
+ "description": "Type of transform.", |
+ "enum": [ |
+ "UNKNOWN_KIND", |
+ "PAR_DO_KIND", |
+ "GROUP_BY_KEY_KIND", |
+ "FLATTEN_KIND", |
+ "READ_KIND", |
+ "WRITE_KIND", |
+ "CONSTANT_KIND", |
+ "SINGLETON_KIND", |
+ "SHUFFLE_KIND" |
+ ], |
+ "enumDescriptions": [ |
+ "Unrecognized transform type.", |
+ "ParDo transform.", |
+ "Group By Key transform.", |
+ "Flatten transform.", |
+ "Read transform.", |
+ "Write transform.", |
+ "Constructs from a constant value, such as with Create.of.", |
+ "Creates a Singleton view of a collection.", |
+ "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" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"StreamingComputationConfig": { |
"description": "Configuration information for a single streaming computation.", |
"id": "StreamingComputationConfig", |
@@ -3066,6 +3204,28 @@ |
}, |
"type": "object" |
}, |
+ "LaunchTemplateParameters": { |
+ "description": "Parameters to provide to the template being launched.", |
+ "id": "LaunchTemplateParameters", |
+ "properties": { |
+ "environment": { |
+ "$ref": "RuntimeEnvironment", |
+ "description": "The runtime environment for the job." |
+ }, |
+ "parameters": { |
+ "additionalProperties": { |
+ "type": "string" |
+ }, |
+ "description": "The runtime parameters to pass to the job.", |
+ "type": "object" |
+ }, |
+ "jobName": { |
+ "description": "Required. The job name to use for the created job.", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"FlattenInstruction": { |
"description": "An instruction that copies its inputs (zero or more) to its (single) output.", |
"id": "FlattenInstruction", |
@@ -3104,10 +3264,6 @@ |
"description": "If this instruction includes a combining function this is the name of the\nintermediate store between the GBK and the CombineValues.", |
"type": "string" |
}, |
- "originalCombineValuesStepName": { |
- "description": "If this instruction includes a combining function, this is the name of the\nCombineValues instruction lifted into this instruction.", |
- "type": "string" |
- }, |
"sideInputs": { |
"description": "Zero or more side inputs.", |
"items": { |
@@ -3115,6 +3271,10 @@ |
}, |
"type": "array" |
}, |
+ "originalCombineValuesStepName": { |
+ "description": "If this instruction includes a combining function, this is the name of the\nCombineValues instruction lifted into this instruction.", |
+ "type": "string" |
+ }, |
"input": { |
"$ref": "InstructionInput", |
"description": "Describes the input to the partial group-by-key instruction." |
@@ -3139,6 +3299,30 @@ |
}, |
"type": "object" |
}, |
+ "StageSource": { |
+ "description": "Description of an input or output of an execution stage.", |
+ "id": "StageSource", |
+ "properties": { |
+ "originalTransformOrCollection": { |
+ "description": "User name for the original user transform or collection with which this\nsource is most closely associated.", |
+ "type": "string" |
+ }, |
+ "name": { |
+ "description": "Dataflow service generated name for this source.", |
+ "type": "string" |
+ }, |
+ "sizeBytes": { |
+ "description": "Size of the source, if measurable.", |
+ "format": "int64", |
+ "type": "string" |
+ }, |
+ "userName": { |
+ "description": "Human-readable name for this source; may be user or system generated.", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"StringList": { |
"description": "A metric value representing a list of strings.", |
"id": "StringList", |
@@ -3153,10 +3337,100 @@ |
}, |
"type": "object" |
}, |
+ "DisplayData": { |
+ "description": "Data provided with a pipeline or transform to provide descriptive info.", |
+ "id": "DisplayData", |
+ "properties": { |
+ "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" |
+ }, |
+ "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" |
+ }, |
+ "floatValue": { |
+ "description": "Contains value if the data is of float type.", |
+ "format": "float", |
+ "type": "number" |
+ }, |
+ "key": { |
+ "description": "The key identifying the display data.\nThis is intended to be used as a label for the display data\nwhen viewed in a dax monitoring system.", |
+ "type": "string" |
+ }, |
+ "shortStrValue": { |
+ "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" |
+ }, |
+ "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" |
+ }, |
+ "strValue": { |
+ "description": "Contains value if the data is of string type.", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "GetDebugConfigRequest": { |
+ "description": "Request to get updated debug configuration for component.", |
+ "id": "GetDebugConfigRequest", |
+ "properties": { |
+ "workerId": { |
+ "description": "The worker id, i.e., VM hostname.", |
+ "type": "string" |
+ }, |
+ "componentId": { |
+ "description": "The internal component id for which debug configuration is\nrequested.", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"LeaseWorkItemRequest": { |
"description": "Request to lease WorkItems.", |
"id": "LeaseWorkItemRequest", |
"properties": { |
+ "currentWorkerTime": { |
+ "description": "The current timestamp at the worker.", |
+ "format": "google-datetime", |
+ "type": "string" |
+ }, |
+ "location": { |
+ "description": "The location which contains the WorkItem's job.", |
+ "type": "string" |
+ }, |
+ "workItemTypes": { |
+ "description": "Filter for WorkItem type.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ }, |
"workerCapabilities": { |
"description": "Worker capabilities. WorkItems might be limited to workers with specific\ncapabilities.", |
"items": { |
@@ -3172,37 +3446,21 @@ |
"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" |
}, |
- "GetDebugConfigRequest": { |
- "description": "Request to get updated debug configuration for component.", |
- "id": "GetDebugConfigRequest", |
+ "GetTemplateResponse": { |
+ "description": "The response to a GetTemplate request.", |
+ "id": "GetTemplateResponse", |
"properties": { |
- "componentId": { |
- "description": "The internal component id for which debug configuration is\nrequested.", |
- "type": "string" |
+ "status": { |
+ "$ref": "Status", |
+ "description": "The status of the get template request. Any problems with the\nrequest will be indicated in the error_details." |
}, |
- "workerId": { |
- "description": "The worker id, i.e., VM hostname.", |
- "type": "string" |
+ "metadata": { |
+ "$ref": "TemplateMetadata", |
+ "description": "The template metadata describing the template name, available\nparameters, etc." |
} |
}, |
"type": "object" |
@@ -3238,33 +3496,47 @@ |
"description": "A task that carries configuration information for streaming computations.", |
"id": "StreamingConfigTask", |
"properties": { |
- "userStepToStateFamilyNameMap": { |
- "additionalProperties": { |
- "type": "string" |
- }, |
- "description": "Map from user step names to state families.", |
- "type": "object" |
- }, |
"streamingComputationConfigs": { |
"description": "Set of computation configuration information.", |
"items": { |
"$ref": "StreamingComputationConfig" |
}, |
"type": "array" |
+ }, |
+ "userStepToStateFamilyNameMap": { |
+ "additionalProperties": { |
+ "type": "string" |
+ }, |
+ "description": "Map from user step names to state families.", |
+ "type": "object" |
} |
}, |
"type": "object" |
}, |
- "JobExecutionInfo": { |
- "description": "Additional information about how a Cloud Dataflow job will be executed that\nisn't contained in the submitted job.", |
- "id": "JobExecutionInfo", |
+ "PipelineDescription": { |
+ "description": "A descriptive representation of submitted pipeline as well as the executed\nform. This data is provided by the Dataflow service for ease of visualizing\nthe pipeline and interpretting Dataflow provided metrics.", |
+ "id": "PipelineDescription", |
"properties": { |
- "stages": { |
- "additionalProperties": { |
- "$ref": "JobExecutionStageInfo" |
+ "originalPipelineTransform": { |
+ "description": "Description of each transform in the pipeline and collections between them.", |
+ "items": { |
+ "$ref": "TransformSummary" |
}, |
- "description": "A mapping from each stage to the information about that stage.", |
- "type": "object" |
+ "type": "array" |
+ }, |
+ "displayData": { |
+ "description": "Pipeline level display data.", |
+ "items": { |
+ "$ref": "DisplayData" |
+ }, |
+ "type": "array" |
+ }, |
+ "executionPipelineStage": { |
+ "description": "Description of each stage of execution of the pipeline.", |
+ "items": { |
+ "$ref": "ExecutionStageSummary" |
+ }, |
+ "type": "array" |
} |
}, |
"type": "object" |
@@ -3286,7 +3558,21 @@ |
"description": "Properties of the object.", |
"type": "any" |
}, |
- "description": "Named properties associated with the step. Each kind of\npredefined step has its own required set of properties.", |
+ "description": "Named properties associated with the step. Each kind of\npredefined step has its own required set of properties.\nMust be provided on Create. Only retrieved with JOB_VIEW_ALL.", |
+ "type": "object" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "JobExecutionInfo": { |
+ "description": "Additional information about how a Cloud Dataflow job will be executed that\nisn't contained in the submitted job.", |
+ "id": "JobExecutionInfo", |
+ "properties": { |
+ "stages": { |
+ "additionalProperties": { |
+ "$ref": "JobExecutionStageInfo" |
+ }, |
+ "description": "A mapping from each stage to the information about that stage.", |
"type": "object" |
} |
}, |
@@ -3323,24 +3609,6 @@ |
}, |
"type": "object" |
}, |
- "ListJobMessagesResponse": { |
- "description": "Response to a request to list job messages.", |
- "id": "ListJobMessagesResponse", |
- "properties": { |
- "jobMessages": { |
- "description": "Messages in ascending timestamp order.", |
- "items": { |
- "$ref": "JobMessage" |
- }, |
- "type": "array" |
- }, |
- "nextPageToken": { |
- "description": "The token to obtain the next page of results if there are more.", |
- "type": "string" |
- } |
- }, |
- "type": "object" |
- }, |
"CounterMetadata": { |
"description": "CounterMetadata includes all static non-name non-value counter attributes.", |
"id": "CounterMetadata", |
@@ -3406,14 +3674,28 @@ |
}, |
"type": "object" |
}, |
+ "ListJobMessagesResponse": { |
+ "description": "Response to a request to list job messages.", |
+ "id": "ListJobMessagesResponse", |
+ "properties": { |
+ "jobMessages": { |
+ "description": "Messages in ascending timestamp order.", |
+ "items": { |
+ "$ref": "JobMessage" |
+ }, |
+ "type": "array" |
+ }, |
+ "nextPageToken": { |
+ "description": "The token to obtain the next page of results if there are more.", |
+ "type": "string" |
+ } |
+ }, |
+ "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." |
@@ -3426,6 +3708,10 @@ |
"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." |
} |
}, |
"type": "object" |
@@ -3504,18 +3790,6 @@ |
"description": "Describes a particular operation comprising a MapTask.", |
"id": "ParallelInstruction", |
"properties": { |
- "name": { |
- "description": "User-provided name of this operation.", |
- "type": "string" |
- }, |
- "parDo": { |
- "$ref": "ParDoInstruction", |
- "description": "Additional information for ParDo instructions." |
- }, |
- "read": { |
- "$ref": "ReadInstruction", |
- "description": "Additional information for Read instructions." |
- }, |
"flatten": { |
"$ref": "FlattenInstruction", |
"description": "Additional information for Flatten instructions." |
@@ -3542,6 +3816,18 @@ |
"$ref": "InstructionOutput" |
}, |
"type": "array" |
+ }, |
+ "name": { |
+ "description": "User-provided name of this operation.", |
+ "type": "string" |
+ }, |
+ "parDo": { |
+ "$ref": "ParDoInstruction", |
+ "description": "Additional information for ParDo instructions." |
+ }, |
+ "read": { |
+ "$ref": "ReadInstruction", |
+ "description": "Additional information for Read instructions." |
} |
}, |
"type": "object" |
@@ -3618,54 +3904,32 @@ |
}, |
"type": "object" |
}, |
- "MetricUpdate": { |
- "description": "Describes the state of a metric.", |
- "id": "MetricUpdate", |
+ "CounterStructuredName": { |
+ "description": "Identifies a counter within a per-job namespace. Counters whose structured\nnames are the same get merged into a single value for the job.", |
+ "id": "CounterStructuredName", |
"properties": { |
- "meanSum": { |
- "description": "Worker-computed aggregate value for the \"Mean\" aggregation kind.\nThis holds the sum of the aggregated values and is used in combination\nwith mean_count below to obtain the actual mean aggregate value.\nThe only possible value types are Long and Double.", |
- "type": "any" |
- }, |
- "updateTime": { |
- "description": "Timestamp associated with the metric value. Optional when workers are\nreporting work progress; it will be filled in responses from the\nmetrics API.", |
- "format": "google-datetime", |
+ "componentStepName": { |
+ "description": "Name of the optimized step being executed by the workers.", |
"type": "string" |
}, |
- "name": { |
- "$ref": "MetricStructuredName", |
- "description": "Name of the metric." |
- }, |
- "set": { |
- "description": "Worker-computed aggregate value for the \"Set\" aggregation kind. The only\npossible value type is a list of Values whose type can be Long, Double,\nor String, according to the metric's type. All Values in the list must\nbe of the same type.", |
- "type": "any" |
- }, |
- "internal": { |
- "description": "Worker-computed aggregate value for internal use by the Dataflow\nservice.", |
- "type": "any" |
- }, |
- "cumulative": { |
- "description": "True if this metric is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this metric is reported\nas a delta that is not associated with any WorkItem.", |
- "type": "boolean" |
- }, |
- "kind": { |
- "description": "Metric aggregation kind. The possible metric aggregation kinds are\n\"Sum\", \"Max\", \"Min\", \"Mean\", \"Set\", \"And\", and \"Or\".\nThe specified aggregation kind is case-insensitive.\n\nIf omitted, this is not an aggregated value but instead\na single metric sample value.", |
+ "portion": { |
+ "description": "Portion of this counter, either key or value.", |
+ "enum": [ |
+ "ALL", |
+ "KEY", |
+ "VALUE" |
+ ], |
+ "enumDescriptions": [ |
+ "Counter portion has not been set.", |
+ "Counter reports a key.", |
+ "Counter reports a 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" |
+ "originalStepName": { |
+ "description": "System generated name of the original step in the user's graph, before\noptimization.", |
+ "type": "string" |
}, |
- "meanCount": { |
- "description": "Worker-computed aggregate value for the \"Mean\" aggregation kind.\nThis holds the count of the aggregated values and is used in combination\nwith mean_sum above to obtain the actual mean aggregate value.\nThe only possible value type is Long.", |
- "type": "any" |
- } |
- }, |
- "type": "object" |
- }, |
- "CounterStructuredName": { |
- "description": "Identifies a counter within a per-job namespace. Counters whose structured\nnames are the same get merged into a single value for the job.", |
- "id": "CounterStructuredName", |
- "properties": { |
"workerId": { |
"description": "ID of a particular worker.", |
"type": "string" |
@@ -3686,35 +3950,57 @@ |
], |
"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" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "MetricUpdate": { |
+ "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\", and \"Or\".\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" |
}, |
- "executionStepName": { |
- "description": "Name of the stage. An execution step contains multiple component steps.", |
+ "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" |
+ }, |
+ "meanCount": { |
+ "description": "Worker-computed aggregate value for the \"Mean\" aggregation kind.\nThis holds the count of the aggregated values and is used in combination\nwith mean_sum above to obtain the actual mean aggregate value.\nThe only possible value type is Long.", |
+ "type": "any" |
+ }, |
+ "meanSum": { |
+ "description": "Worker-computed aggregate value for the \"Mean\" aggregation kind.\nThis holds the sum of the aggregated values and is used in combination\nwith mean_count below to obtain the actual mean aggregate value.\nThe only possible value types are Long and Double.", |
+ "type": "any" |
+ }, |
+ "updateTime": { |
+ "description": "Timestamp associated with the metric value. Optional when workers are\nreporting work progress; it will be filled in responses from the\nmetrics API.", |
+ "format": "google-datetime", |
"type": "string" |
}, |
- "componentStepName": { |
- "description": "Name of the optimized step being executed by the workers.", |
- "type": "string" |
+ "name": { |
+ "$ref": "MetricStructuredName", |
+ "description": "Name of the metric." |
+ }, |
+ "set": { |
+ "description": "Worker-computed aggregate value for the \"Set\" aggregation kind. The only\npossible value type is a list of Values whose type can be Long, Double,\nor String, according to the metric's type. All Values in the list must\nbe of the same type.", |
+ "type": "any" |
}, |
- "portion": { |
- "description": "Portion of this counter, either key or value.", |
- "enum": [ |
- "ALL", |
- "KEY", |
- "VALUE" |
- ], |
- "enumDescriptions": [ |
- "Counter portion has not been set.", |
- "Counter reports a key.", |
- "Counter reports a value." |
- ], |
- "type": "string" |
+ "cumulative": { |
+ "description": "True if this metric is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this metric is reported\nas a delta that is not associated with any WorkItem.", |
+ "type": "boolean" |
}, |
- "originalStepName": { |
- "description": "System generated name of the original step in the user's graph, before\noptimization.", |
- "type": "string" |
+ "internal": { |
+ "description": "Worker-computed aggregate value for internal use by the Dataflow\nservice.", |
+ "type": "any" |
} |
}, |
"type": "object" |
@@ -3723,6 +4009,10 @@ |
"description": "Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest.", |
"id": "ApproximateProgress", |
"properties": { |
+ "position": { |
+ "$ref": "Position", |
+ "description": "Obsolete." |
+ }, |
"percentComplete": { |
"description": "Obsolete.", |
"format": "float", |
@@ -3732,10 +4022,6 @@ |
"description": "Obsolete.", |
"format": "google-duration", |
"type": "string" |
- }, |
- "position": { |
- "$ref": "Position", |
- "description": "Obsolete." |
} |
}, |
"type": "object" |
@@ -3755,6 +4041,32 @@ |
}, |
"type": "object" |
}, |
+ "TemplateMetadata": { |
+ "description": "Metadata describing a template.", |
+ "id": "TemplateMetadata", |
+ "properties": { |
+ "name": { |
+ "description": "Required. The name of the template.", |
+ "type": "string" |
+ }, |
+ "parameters": { |
+ "description": "The parameters for the template.", |
+ "items": { |
+ "$ref": "ParameterMetadata" |
+ }, |
+ "type": "array" |
+ }, |
+ "description": { |
+ "description": "Optional. A description of the template.", |
+ "type": "string" |
+ }, |
+ "bypassTempDirValidation": { |
+ "description": "If true, will bypass the validation that the temp directory is\nwritable. This should only be used with templates for pipelines\nthat are guaranteed not to need to write to the temp directory,\nwhich is subject to change based on the optimizer.", |
+ "type": "boolean" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"WorkerMessage": { |
"description": "WorkerMessage provides information to the backend about a worker.", |
"id": "WorkerMessage", |
@@ -3824,19 +4136,6 @@ |
"description": "An update to a Counter sent from a worker.", |
"id": "CounterUpdate", |
"properties": { |
- "shortId": { |
- "description": "The service-generated short identifier for this counter.\nThe short_id -> (name, metadata) mapping is constant for the lifetime of\na job.", |
- "format": "int64", |
- "type": "string" |
- }, |
- "floatingPointList": { |
- "$ref": "FloatingPointList", |
- "description": "List of floating point numbers, for Set." |
- }, |
- "integer": { |
- "$ref": "SplitInt64", |
- "description": "Integer value for Sum, Max, Min." |
- }, |
"structuredNameAndMetadata": { |
"$ref": "CounterStructuredNameAndMetadata", |
"description": "Counter structured name and metadata." |
@@ -3854,14 +4153,14 @@ |
"$ref": "IntegerMean", |
"description": "Integer mean aggregation value for Mean." |
}, |
- "cumulative": { |
- "description": "True if this counter is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this counter is reported\nas a delta.", |
- "type": "boolean" |
- }, |
"internal": { |
"description": "Value for internally-defined counters used by the Dataflow service.", |
"type": "any" |
}, |
+ "cumulative": { |
+ "description": "True if this counter is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this counter is reported\nas a delta.", |
+ "type": "boolean" |
+ }, |
"floatingPointMean": { |
"$ref": "FloatingPointMean", |
"description": "Floating point mean aggregation value for Mean." |
@@ -3881,6 +4180,19 @@ |
"distribution": { |
"$ref": "DistributionUpdate", |
"description": "Distribution data" |
+ }, |
+ "shortId": { |
+ "description": "The service-generated short identifier for this counter.\nThe short_id -> (name, metadata) mapping is constant for the lifetime of\na job.", |
+ "format": "int64", |
+ "type": "string" |
+ }, |
+ "floatingPointList": { |
+ "$ref": "FloatingPointList", |
+ "description": "List of floating point numbers, for Set." |
+ }, |
+ "integer": { |
+ "$ref": "SplitInt64", |
+ "description": "Integer value for Sum, Max, Min." |
} |
}, |
"type": "object" |
@@ -3933,10 +4245,26 @@ |
}, |
"type": "object" |
}, |
+ "WorkerHealthReportResponse": { |
+ "description": "WorkerHealthReportResponse contains information returned to the worker\nin response to a health ping.", |
+ "id": "WorkerHealthReportResponse", |
+ "properties": { |
+ "reportInterval": { |
+ "description": "A positive value indicates the worker should change its reporting interval\nto the specified value.\n\nThe default value of zero means no change in report rate is requested by\nthe server.", |
+ "format": "google-duration", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"SourceFork": { |
"description": "DEPRECATED in favor of DynamicSourceSplit.", |
"id": "SourceFork", |
"properties": { |
+ "residual": { |
+ "$ref": "SourceSplitShard", |
+ "description": "DEPRECATED" |
+ }, |
"residualSource": { |
"$ref": "DerivedSource", |
"description": "DEPRECATED" |
@@ -3948,22 +4276,166 @@ |
"primarySource": { |
"$ref": "DerivedSource", |
"description": "DEPRECATED" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "WorkItemStatus": { |
+ "description": "Conveys a worker's progress through the work described by a WorkItem.", |
+ "id": "WorkItemStatus", |
+ "properties": { |
+ "sourceFork": { |
+ "$ref": "SourceFork", |
+ "description": "DEPRECATED in favor of dynamic_source_split." |
}, |
- "residual": { |
- "$ref": "SourceSplitShard", |
- "description": "DEPRECATED" |
+ "counterUpdates": { |
+ "description": "Worker output counters for this WorkItem.", |
+ "items": { |
+ "$ref": "CounterUpdate" |
+ }, |
+ "type": "array" |
+ }, |
+ "workItemId": { |
+ "description": "Identifies the WorkItem.", |
+ "type": "string" |
+ }, |
+ "metricUpdates": { |
+ "description": "DEPRECATED in favor of counter_updates.", |
+ "items": { |
+ "$ref": "MetricUpdate" |
+ }, |
+ "type": "array" |
+ }, |
+ "errors": { |
+ "description": "Specifies errors which occurred during processing. If errors are\nprovided, and completed = true, then the WorkItem is considered\nto have failed.", |
+ "items": { |
+ "$ref": "Status" |
+ }, |
+ "type": "array" |
+ }, |
+ "dynamicSourceSplit": { |
+ "$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." |
} |
}, |
"type": "object" |
}, |
- "WorkerHealthReportResponse": { |
- "description": "WorkerHealthReportResponse contains information returned to the worker\nin response to a health ping.", |
- "id": "WorkerHealthReportResponse", |
+ "ComponentSource": { |
+ "description": "Description of an interstitial value between transforms in an execution\nstage.", |
+ "id": "ComponentSource", |
"properties": { |
- "reportInterval": { |
- "description": "A positive value indicates the worker should change its reporting interval\nto the specified value.\n\nThe default value of zero means no change in report rate is requested by\nthe server.", |
+ "originalTransformOrCollection": { |
+ "description": "User name for the original user transform or collection with which this\nsource is most closely associated.", |
+ "type": "string" |
+ }, |
+ "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" |
+ }, |
+ "WorkItemServiceState": { |
+ "description": "The Dataflow service's idea of the current state of a WorkItem\nbeing processed by a worker.", |
+ "id": "WorkItemServiceState", |
+ "properties": { |
+ "suggestedStopPosition": { |
+ "$ref": "Position", |
+ "description": "Obsolete, always empty." |
+ }, |
+ "reportStatusInterval": { |
+ "description": "New recommended reporting interval.", |
"format": "google-duration", |
"type": "string" |
+ }, |
+ "harnessData": { |
+ "additionalProperties": { |
+ "description": "Properties of the object.", |
+ "type": "any" |
+ }, |
+ "description": "Other data returned by the service, specific to the particular\nworker harness.", |
+ "type": "object" |
+ }, |
+ "leaseExpireTime": { |
+ "description": "Time at which the current lease will expire.", |
+ "format": "google-datetime", |
+ "type": "string" |
+ }, |
+ "metricShortId": { |
+ "description": "The short ids that workers should use in subsequent metric updates.\nWorkers should strive to use short ids whenever possible, but it is ok\nto request the short_id again if a worker lost track of it\n(e.g. if the worker is recovering from a crash).\nNOTE: it is possible that the response may have short ids for a subset\nof the metrics.", |
+ "items": { |
+ "$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": { |
+ "$ref": "ApproximateProgress", |
+ "description": "DEPRECATED in favor of split_request." |
+ }, |
+ "splitRequest": { |
+ "$ref": "ApproximateSplitRequest", |
+ "description": "The progress point in the WorkItem where the Dataflow service\nsuggests that the worker truncate the task." |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "MetricStructuredName": { |
+ "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" |
+ }, |
+ "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" |
+ }, |
+ "name": { |
+ "description": "Worker-defined metric name.", |
+ "type": "string" |
} |
}, |
"type": "object" |