| Index: discovery/googleapis_beta/dataflow__v1b3.json
|
| diff --git a/discovery/googleapis_beta/dataflow__v1b3.json b/discovery/googleapis_beta/dataflow__v1b3.json
|
| index e61d9ca8e89ce9fde6b76df3cc699ee555be0e06..25b26c77f6cb169f9717849392070af269826d2e 100644
|
| --- a/discovery/googleapis_beta/dataflow__v1b3.json
|
| +++ b/discovery/googleapis_beta/dataflow__v1b3.json
|
| @@ -2,17 +2,17 @@
|
| "auth": {
|
| "oauth2": {
|
| "scopes": {
|
| - "https://www.googleapis.com/auth/compute.readonly": {
|
| - "description": "View your Google Compute Engine resources"
|
| - },
|
| - "https://www.googleapis.com/auth/compute": {
|
| - "description": "View and manage your Google Compute Engine resources"
|
| - },
|
| "https://www.googleapis.com/auth/cloud-platform": {
|
| "description": "View and manage your data across Google Cloud Platform services"
|
| },
|
| "https://www.googleapis.com/auth/userinfo.email": {
|
| "description": "View your email address"
|
| + },
|
| + "https://www.googleapis.com/auth/compute.readonly": {
|
| + "description": "View your Google Compute Engine resources"
|
| + },
|
| + "https://www.googleapis.com/auth/compute": {
|
| + "description": "View and manage your Google Compute Engine resources"
|
| }
|
| }
|
| }
|
| @@ -33,16 +33,53 @@
|
| "ownerDomain": "google.com",
|
| "ownerName": "Google",
|
| "parameters": {
|
| - "oauth_token": {
|
| - "description": "OAuth 2.0 token for the current user.",
|
| + "alt": {
|
| + "default": "json",
|
| + "description": "Data format for response.",
|
| + "enum": [
|
| + "json",
|
| + "media",
|
| + "proto"
|
| + ],
|
| + "enumDescriptions": [
|
| + "Responses with Content-Type of application/json",
|
| + "Media download with context-dependent Content-Type",
|
| + "Responses with Content-Type of application/x-protobuf"
|
| + ],
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "key": {
|
| + "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.",
|
| "location": "query",
|
| "type": "string"
|
| },
|
| + "access_token": {
|
| + "description": "OAuth access token.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "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",
|
| @@ -81,43 +118,6 @@
|
| "description": "JSONP",
|
| "location": "query",
|
| "type": "string"
|
| - },
|
| - "alt": {
|
| - "default": "json",
|
| - "description": "Data format for response.",
|
| - "enum": [
|
| - "json",
|
| - "media",
|
| - "proto"
|
| - ],
|
| - "enumDescriptions": [
|
| - "Responses with Content-Type of application/json",
|
| - "Media download with context-dependent Content-Type",
|
| - "Responses with Content-Type of application/x-protobuf"
|
| - ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "key": {
|
| - "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "access_token": {
|
| - "description": "OAuth access token.",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "quotaUser": {
|
| - "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "pp": {
|
| - "default": "true",
|
| - "description": "Pretty-print response.",
|
| - "location": "query",
|
| - "type": "boolean"
|
| }
|
| },
|
| "protocol": "rest",
|
| @@ -197,10 +197,10 @@
|
| "resources": {
|
| "templates": {
|
| "methods": {
|
| - "launch": {
|
| - "description": "Launch a template.",
|
| - "httpMethod": "POST",
|
| - "id": "dataflow.projects.locations.templates.launch",
|
| + "get": {
|
| + "description": "Get the template associated with a template.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.locations.templates.get",
|
| "parameterOrder": [
|
| "projectId",
|
| "location"
|
| @@ -212,10 +212,13 @@
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "validateOnly": {
|
| - "description": "If true, the request is validated but not actually executed.\nDefaults to false.",
|
| + "view": {
|
| + "description": "The view to retrieve. Defaults to METADATA_ONLY.",
|
| + "enum": [
|
| + "METADATA_ONLY"
|
| + ],
|
| "location": "query",
|
| - "type": "boolean"
|
| + "type": "string"
|
| },
|
| "projectId": {
|
| "description": "Required. The ID of the Cloud Platform project that the job belongs to.",
|
| @@ -224,17 +227,14 @@
|
| "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://'.",
|
| + "description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
|
| "location": "query",
|
| "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/locations/{location}/templates:launch",
|
| - "request": {
|
| - "$ref": "LaunchTemplateParameters"
|
| - },
|
| + "path": "v1b3/projects/{projectId}/locations/{location}/templates:get",
|
| "response": {
|
| - "$ref": "LaunchTemplateResponse"
|
| + "$ref": "GetTemplateResponse"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -243,10 +243,10 @@
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| },
|
| - "get": {
|
| - "description": "Get the template associated with a template.",
|
| - "httpMethod": "GET",
|
| - "id": "dataflow.projects.locations.templates.get",
|
| + "create": {
|
| + "description": "Creates a Cloud Dataflow job from a template.",
|
| + "httpMethod": "POST",
|
| + "id": "dataflow.projects.locations.templates.create",
|
| "parameterOrder": [
|
| "projectId",
|
| "location"
|
| @@ -258,29 +258,19 @@
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "view": {
|
| - "description": "The view to retrieve. Defaults to METADATA_ONLY.",
|
| - "enum": [
|
| - "METADATA_ONLY"
|
| - ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| "projectId": {
|
| "description": "Required. The ID of the Cloud Platform project that the job belongs to.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| - },
|
| - "gcsPath": {
|
| - "description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
|
| - "location": "query",
|
| - "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/locations/{location}/templates:get",
|
| + "path": "v1b3/projects/{projectId}/locations/{location}/templates",
|
| + "request": {
|
| + "$ref": "CreateJobFromTemplateRequest"
|
| + },
|
| "response": {
|
| - "$ref": "GetTemplateResponse"
|
| + "$ref": "Job"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -289,10 +279,10 @@
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| },
|
| - "create": {
|
| - "description": "Creates a Cloud Dataflow job from a template.",
|
| + "launch": {
|
| + "description": "Launch a template.",
|
| "httpMethod": "POST",
|
| - "id": "dataflow.projects.locations.templates.create",
|
| + "id": "dataflow.projects.locations.templates.launch",
|
| "parameterOrder": [
|
| "projectId",
|
| "location"
|
| @@ -304,19 +294,29 @@
|
| "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"
|
| + },
|
| "location": {
|
| "description": "The location to which to direct the request.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| + },
|
| + "validateOnly": {
|
| + "description": "If true, the request is validated but not actually executed.\nDefaults to false.",
|
| + "location": "query",
|
| + "type": "boolean"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/locations/{location}/templates",
|
| + "path": "v1b3/projects/{projectId}/locations/{location}/templates:launch",
|
| "request": {
|
| - "$ref": "CreateJobFromTemplateRequest"
|
| + "$ref": "LaunchTemplateParameters"
|
| },
|
| "response": {
|
| - "$ref": "Job"
|
| + "$ref": "LaunchTemplateResponse"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -339,18 +339,6 @@
|
| "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"
|
| - },
|
| "jobId": {
|
| "description": "The job to get messages for.",
|
| "location": "path",
|
| @@ -362,6 +350,18 @@
|
| "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",
|
| @@ -376,7 +376,7 @@
|
| ]
|
| },
|
| "list": {
|
| - "description": "List the jobs of a project.",
|
| + "description": "List the jobs of a project in a given region.",
|
| "httpMethod": "GET",
|
| "id": "dataflow.projects.locations.jobs.list",
|
| "parameterOrder": [
|
| @@ -601,25 +601,6 @@
|
| "jobId"
|
| ],
|
| "parameters": {
|
| - "pageSize": {
|
| - "description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results.",
|
| - "format": "int32",
|
| - "location": "query",
|
| - "type": "integer"
|
| - },
|
| - "minimumImportance": {
|
| - "description": "Filter to only get messages with importance >= level",
|
| - "enum": [
|
| - "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
|
| - "JOB_MESSAGE_DEBUG",
|
| - "JOB_MESSAGE_DETAILED",
|
| - "JOB_MESSAGE_BASIC",
|
| - "JOB_MESSAGE_WARNING",
|
| - "JOB_MESSAGE_ERROR"
|
| - ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| "projectId": {
|
| "description": "A project id.",
|
| "location": "path",
|
| @@ -632,18 +613,18 @@
|
| "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.",
|
| "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"
|
| + },
|
| "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",
|
| @@ -654,6 +635,25 @@
|
| "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",
|
| @@ -681,12 +681,6 @@
|
| "jobId"
|
| ],
|
| "parameters": {
|
| - "location": {
|
| - "description": "The location which contains the WorkItem's job.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| "jobId": {
|
| "description": "The job which the WorkItem is part of.",
|
| "location": "path",
|
| @@ -698,6 +692,12 @@
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| + },
|
| + "location": {
|
| + "description": "The location which contains the WorkItem's job.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| }
|
| },
|
| "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus",
|
| @@ -771,20 +771,20 @@
|
| "jobId"
|
| ],
|
| "parameters": {
|
| - "jobId": {
|
| - "description": "The job id.",
|
| + "location": {
|
| + "description": "The location which contains the job specified by job_id.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "projectId": {
|
| - "description": "The project id.",
|
| + "jobId": {
|
| + "description": "The job id.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "location": {
|
| - "description": "The location which contains the job specified by job_id.",
|
| + "projectId": {
|
| + "description": "The project id.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| @@ -976,42 +976,88 @@
|
| },
|
| "jobs": {
|
| "methods": {
|
| - "getMetrics": {
|
| - "description": "Request the job status.",
|
| + "get": {
|
| + "description": "Gets the state of the specified Cloud Dataflow job.",
|
| "httpMethod": "GET",
|
| - "id": "dataflow.projects.jobs.getMetrics",
|
| + "id": "dataflow.projects.jobs.get",
|
| "parameterOrder": [
|
| "projectId",
|
| "jobId"
|
| ],
|
| "parameters": {
|
| - "startTime": {
|
| - "description": "Return only metric data that has changed since this time.\nDefault is to return all information about all metrics for the job.",
|
| - "format": "google-datetime",
|
| + "location": {
|
| + "description": "The location that contains this job.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "view": {
|
| + "description": "The level of information requested in response.",
|
| + "enum": [
|
| + "JOB_VIEW_UNKNOWN",
|
| + "JOB_VIEW_SUMMARY",
|
| + "JOB_VIEW_ALL",
|
| + "JOB_VIEW_DESCRIPTION"
|
| + ],
|
| "location": "query",
|
| "type": "string"
|
| },
|
| "jobId": {
|
| - "description": "The job to get messages for.",
|
| + "description": "The job ID.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| "projectId": {
|
| - "description": "A project id.",
|
| + "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}",
|
| + "response": {
|
| + "$ref": "Job"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/compute",
|
| + "https://www.googleapis.com/auth/compute.readonly",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + },
|
| + "update": {
|
| + "description": "Updates the state of an existing Cloud Dataflow job.",
|
| + "httpMethod": "PUT",
|
| + "id": "dataflow.projects.jobs.update",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "jobId"
|
| + ],
|
| + "parameters": {
|
| + "jobId": {
|
| + "description": "The job ID.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "projectId": {
|
| + "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| "location": {
|
| - "description": "The location which contains the job specified by job_id.",
|
| + "description": "The location that contains this job.",
|
| "location": "query",
|
| "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/metrics",
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}",
|
| + "request": {
|
| + "$ref": "Job"
|
| + },
|
| "response": {
|
| - "$ref": "JobMetrics"
|
| + "$ref": "Job"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -1020,14 +1066,35 @@
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| },
|
| - "list": {
|
| - "description": "List the jobs of a project.",
|
| + "aggregated": {
|
| + "description": "List the jobs of a project across all regions.",
|
| "httpMethod": "GET",
|
| - "id": "dataflow.projects.jobs.list",
|
| + "id": "dataflow.projects.jobs.aggregated",
|
| "parameterOrder": [
|
| "projectId"
|
| ],
|
| "parameters": {
|
| + "filter": {
|
| + "description": "The kind of filter to use.",
|
| + "enum": [
|
| + "UNKNOWN",
|
| + "ALL",
|
| + "TERMINATED",
|
| + "ACTIVE"
|
| + ],
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "location": {
|
| + "description": "The location that contains this job.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "pageToken": {
|
| + "description": "Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| "pageSize": {
|
| "description": "If there are many jobs, limit response to at most this many.\nThe actual number of jobs returned will be the lesser of max_responses\nand an unspecified server-defined limit.",
|
| "format": "int32",
|
| @@ -1050,30 +1117,9 @@
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| - },
|
| - "filter": {
|
| - "description": "The kind of filter to use.",
|
| - "enum": [
|
| - "UNKNOWN",
|
| - "ALL",
|
| - "TERMINATED",
|
| - "ACTIVE"
|
| - ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location that contains this job.",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "pageToken": {
|
| - "description": "Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
|
| - "location": "query",
|
| - "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/jobs",
|
| + "path": "v1b3/projects/{projectId}/jobs:aggregated",
|
| "response": {
|
| "$ref": "ListJobsResponse"
|
| },
|
| @@ -1084,17 +1130,16 @@
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| },
|
| - "get": {
|
| - "description": "Gets the state of the specified Cloud Dataflow job.",
|
| + "list": {
|
| + "description": "List the jobs of a project in a given region.",
|
| "httpMethod": "GET",
|
| - "id": "dataflow.projects.jobs.get",
|
| + "id": "dataflow.projects.jobs.list",
|
| "parameterOrder": [
|
| - "projectId",
|
| - "jobId"
|
| + "projectId"
|
| ],
|
| "parameters": {
|
| "view": {
|
| - "description": "The level of information requested in response.",
|
| + "description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
|
| "enum": [
|
| "JOB_VIEW_UNKNOWN",
|
| "JOB_VIEW_SUMMARY",
|
| @@ -1104,27 +1149,43 @@
|
| "location": "query",
|
| "type": "string"
|
| },
|
| - "jobId": {
|
| - "description": "The job ID.",
|
| + "projectId": {
|
| + "description": "The project which owns the jobs.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "projectId": {
|
| - "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| - "location": "path",
|
| - "required": true,
|
| + "filter": {
|
| + "description": "The kind of filter to use.",
|
| + "enum": [
|
| + "UNKNOWN",
|
| + "ALL",
|
| + "TERMINATED",
|
| + "ACTIVE"
|
| + ],
|
| + "location": "query",
|
| "type": "string"
|
| },
|
| "location": {
|
| "description": "The location that contains this job.",
|
| "location": "query",
|
| "type": "string"
|
| + },
|
| + "pageToken": {
|
| + "description": "Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "pageSize": {
|
| + "description": "If there are many jobs, limit response to at most this many.\nThe actual number of jobs returned will be the lesser of max_responses\nand an unspecified server-defined limit.",
|
| + "format": "int32",
|
| + "location": "query",
|
| + "type": "integer"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}",
|
| + "path": "v1b3/projects/{projectId}/jobs",
|
| "response": {
|
| - "$ref": "Job"
|
| + "$ref": "ListJobsResponse"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -1133,13 +1194,12 @@
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| },
|
| - "update": {
|
| - "description": "Updates the state of an existing Cloud Dataflow job.",
|
| - "httpMethod": "PUT",
|
| - "id": "dataflow.projects.jobs.update",
|
| + "create": {
|
| + "description": "Creates a Cloud Dataflow job.",
|
| + "httpMethod": "POST",
|
| + "id": "dataflow.projects.jobs.create",
|
| "parameterOrder": [
|
| - "projectId",
|
| - "jobId"
|
| + "projectId"
|
| ],
|
| "parameters": {
|
| "location": {
|
| @@ -1147,10 +1207,20 @@
|
| "location": "query",
|
| "type": "string"
|
| },
|
| - "jobId": {
|
| - "description": "The job ID.",
|
| - "location": "path",
|
| - "required": true,
|
| + "replaceJobId": {
|
| + "description": "Deprecated. This field is now in the Job message.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "view": {
|
| + "description": "The level of information requested in response.",
|
| + "enum": [
|
| + "JOB_VIEW_UNKNOWN",
|
| + "JOB_VIEW_SUMMARY",
|
| + "JOB_VIEW_ALL",
|
| + "JOB_VIEW_DESCRIPTION"
|
| + ],
|
| + "location": "query",
|
| "type": "string"
|
| },
|
| "projectId": {
|
| @@ -1160,7 +1230,7 @@
|
| "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}",
|
| + "path": "v1b3/projects/{projectId}/jobs",
|
| "request": {
|
| "$ref": "Job"
|
| },
|
| @@ -1174,48 +1244,42 @@
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| },
|
| - "create": {
|
| - "description": "Creates a Cloud Dataflow job.",
|
| - "httpMethod": "POST",
|
| - "id": "dataflow.projects.jobs.create",
|
| + "getMetrics": {
|
| + "description": "Request the job status.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.jobs.getMetrics",
|
| "parameterOrder": [
|
| - "projectId"
|
| + "projectId",
|
| + "jobId"
|
| ],
|
| "parameters": {
|
| - "replaceJobId": {
|
| - "description": "Deprecated. This field is now in the Job message.",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "view": {
|
| - "description": "The level of information requested in response.",
|
| - "enum": [
|
| - "JOB_VIEW_UNKNOWN",
|
| - "JOB_VIEW_SUMMARY",
|
| - "JOB_VIEW_ALL",
|
| - "JOB_VIEW_DESCRIPTION"
|
| - ],
|
| - "location": "query",
|
| + "jobId": {
|
| + "description": "The job to get messages for.",
|
| + "location": "path",
|
| + "required": true,
|
| "type": "string"
|
| },
|
| "projectId": {
|
| - "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| + "description": "A project id.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| "location": {
|
| - "description": "The location that contains this job.",
|
| + "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",
|
| - "request": {
|
| - "$ref": "Job"
|
| - },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/metrics",
|
| "response": {
|
| - "$ref": "Job"
|
| + "$ref": "JobMetrics"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -1226,36 +1290,74 @@
|
| }
|
| },
|
| "resources": {
|
| - "workItems": {
|
| + "messages": {
|
| "methods": {
|
| - "lease": {
|
| - "description": "Leases a dataflow WorkItem to run.",
|
| - "httpMethod": "POST",
|
| - "id": "dataflow.projects.jobs.workItems.lease",
|
| + "list": {
|
| + "description": "Request the job status.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.jobs.messages.list",
|
| "parameterOrder": [
|
| "projectId",
|
| "jobId"
|
| ],
|
| "parameters": {
|
| - "jobId": {
|
| - "description": "Identifies the workflow job this worker belongs to.",
|
| + "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"
|
| + },
|
| + "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"
|
| + },
|
| + "minimumImportance": {
|
| + "description": "Filter to only get messages with importance >= level",
|
| + "enum": [
|
| + "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
|
| + "JOB_MESSAGE_DEBUG",
|
| + "JOB_MESSAGE_DETAILED",
|
| + "JOB_MESSAGE_BASIC",
|
| + "JOB_MESSAGE_WARNING",
|
| + "JOB_MESSAGE_ERROR"
|
| + ],
|
| + "location": "query",
|
| + "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:lease",
|
| - "request": {
|
| - "$ref": "LeaseWorkItemRequest"
|
| - },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/messages",
|
| "response": {
|
| - "$ref": "LeaseWorkItemResponse"
|
| + "$ref": "ListJobMessagesResponse"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -1263,7 +1365,11 @@
|
| "https://www.googleapis.com/auth/compute.readonly",
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| - },
|
| + }
|
| + }
|
| + },
|
| + "workItems": {
|
| + "methods": {
|
| "reportStatus": {
|
| "description": "Reports the status of dataflow WorkItems leased by a worker.",
|
| "httpMethod": "POST",
|
| @@ -1299,39 +1405,35 @@
|
| "https://www.googleapis.com/auth/compute.readonly",
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| - }
|
| - }
|
| - },
|
| - "debug": {
|
| - "methods": {
|
| - "sendCapture": {
|
| - "description": "Send encoded debug capture data for component.",
|
| + },
|
| + "lease": {
|
| + "description": "Leases a dataflow WorkItem to run.",
|
| "httpMethod": "POST",
|
| - "id": "dataflow.projects.jobs.debug.sendCapture",
|
| + "id": "dataflow.projects.jobs.workItems.lease",
|
| "parameterOrder": [
|
| "projectId",
|
| "jobId"
|
| ],
|
| "parameters": {
|
| "jobId": {
|
| - "description": "The job id.",
|
| + "description": "Identifies the workflow job this worker belongs to.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| "projectId": {
|
| - "description": "The project id.",
|
| + "description": "Identifies the project this worker belongs to.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/sendCapture",
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:lease",
|
| "request": {
|
| - "$ref": "SendDebugCaptureRequest"
|
| + "$ref": "LeaseWorkItemRequest"
|
| },
|
| "response": {
|
| - "$ref": "SendDebugCaptureResponse"
|
| + "$ref": "LeaseWorkItemResponse"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -1339,11 +1441,15 @@
|
| "https://www.googleapis.com/auth/compute.readonly",
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| - },
|
| - "getConfig": {
|
| - "description": "Get encoded debug configuration for component. Not cacheable.",
|
| + }
|
| + }
|
| + },
|
| + "debug": {
|
| + "methods": {
|
| + "sendCapture": {
|
| + "description": "Send encoded debug capture data for component.",
|
| "httpMethod": "POST",
|
| - "id": "dataflow.projects.jobs.debug.getConfig",
|
| + "id": "dataflow.projects.jobs.debug.sendCapture",
|
| "parameterOrder": [
|
| "projectId",
|
| "jobId"
|
| @@ -1362,12 +1468,12 @@
|
| "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/getConfig",
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/sendCapture",
|
| "request": {
|
| - "$ref": "GetDebugConfigRequest"
|
| + "$ref": "SendDebugCaptureRequest"
|
| },
|
| "response": {
|
| - "$ref": "GetDebugConfigResponse"
|
| + "$ref": "SendDebugCaptureResponse"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -1375,77 +1481,35 @@
|
| "https://www.googleapis.com/auth/compute.readonly",
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| - }
|
| - }
|
| - },
|
| - "messages": {
|
| - "methods": {
|
| - "list": {
|
| - "description": "Request the job status.",
|
| - "httpMethod": "GET",
|
| - "id": "dataflow.projects.jobs.messages.list",
|
| + },
|
| + "getConfig": {
|
| + "description": "Get encoded debug configuration for component. Not cacheable.",
|
| + "httpMethod": "POST",
|
| + "id": "dataflow.projects.jobs.debug.getConfig",
|
| "parameterOrder": [
|
| "projectId",
|
| "jobId"
|
| ],
|
| "parameters": {
|
| - "pageSize": {
|
| - "description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results.",
|
| - "format": "int32",
|
| - "location": "query",
|
| - "type": "integer"
|
| - },
|
| - "minimumImportance": {
|
| - "description": "Filter to only get messages with importance >= level",
|
| - "enum": [
|
| - "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
|
| - "JOB_MESSAGE_DEBUG",
|
| - "JOB_MESSAGE_DETAILED",
|
| - "JOB_MESSAGE_BASIC",
|
| - "JOB_MESSAGE_WARNING",
|
| - "JOB_MESSAGE_ERROR"
|
| - ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "projectId": {
|
| - "description": "A project id.",
|
| + "jobId": {
|
| + "description": "The job id.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "jobId": {
|
| - "description": "The job to get messages about.",
|
| + "projectId": {
|
| + "description": "The 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"
|
| - },
|
| - "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"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/messages",
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/getConfig",
|
| + "request": {
|
| + "$ref": "GetDebugConfigRequest"
|
| + },
|
| "response": {
|
| - "$ref": "ListJobMessagesResponse"
|
| + "$ref": "GetDebugConfigResponse"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -1461,1072 +1525,1124 @@
|
| }
|
| }
|
| },
|
| - "revision": "20170718",
|
| + "revision": "20170809",
|
| "rootUrl": "https://dataflow.googleapis.com/",
|
| "schemas": {
|
| - "WorkItemStatus": {
|
| - "description": "Conveys a worker's progress through the work described by a WorkItem.",
|
| - "id": "WorkItemStatus",
|
| + "ParallelInstruction": {
|
| + "description": "Describes a particular operation comprising a MapTask.",
|
| + "id": "ParallelInstruction",
|
| "properties": {
|
| - "workItemId": {
|
| - "description": "Identifies the WorkItem.",
|
| - "type": "string"
|
| - },
|
| - "errors": {
|
| - "description": "Specifies errors which occurred during processing. If errors are\nprovided, and completed = true, then the WorkItem is considered\nto have failed.",
|
| - "items": {
|
| - "$ref": "Status"
|
| - },
|
| - "type": "array"
|
| + "partialGroupByKey": {
|
| + "$ref": "PartialGroupByKeyInstruction",
|
| + "description": "Additional information for PartialGroupByKey instructions."
|
| },
|
| - "metricUpdates": {
|
| - "description": "DEPRECATED in favor of counter_updates.",
|
| + "outputs": {
|
| + "description": "Describes the outputs of the instruction.",
|
| "items": {
|
| - "$ref": "MetricUpdate"
|
| + "$ref": "InstructionOutput"
|
| },
|
| "type": "array"
|
| },
|
| - "dynamicSourceSplit": {
|
| - "$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",
|
| + "name": {
|
| + "description": "User-provided name of this operation.",
|
| "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"
|
| + "read": {
|
| + "$ref": "ReadInstruction",
|
| + "description": "Additional information for Read instructions."
|
| },
|
| - "stopPosition": {
|
| - "$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."
|
| + "parDo": {
|
| + "$ref": "ParDoInstruction",
|
| + "description": "Additional information for ParDo instructions."
|
| },
|
| - "completed": {
|
| - "description": "True if the WorkItem was completed (successfully or unsuccessfully).",
|
| - "type": "boolean"
|
| + "originalName": {
|
| + "description": "System-defined name for the operation in the original workflow graph.",
|
| + "type": "string"
|
| },
|
| - "reportedProgress": {
|
| - "$ref": "ApproximateReportedProgress",
|
| - "description": "The worker's progress through this WorkItem."
|
| + "flatten": {
|
| + "$ref": "FlattenInstruction",
|
| + "description": "Additional information for Flatten instructions."
|
| },
|
| - "sourceFork": {
|
| - "$ref": "SourceFork",
|
| - "description": "DEPRECATED in favor of dynamic_source_split."
|
| + "write": {
|
| + "$ref": "WriteInstruction",
|
| + "description": "Additional information for Write instructions."
|
| },
|
| - "counterUpdates": {
|
| - "description": "Worker output counters for this WorkItem.",
|
| - "items": {
|
| - "$ref": "CounterUpdate"
|
| - },
|
| - "type": "array"
|
| + "systemName": {
|
| + "description": "System-defined name of this operation.\nUnique across the workflow.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ComponentSource": {
|
| - "description": "Description of an interstitial value between transforms in an execution\nstage.",
|
| - "id": "ComponentSource",
|
| + "KeyRangeDataDiskAssignment": {
|
| + "description": "Data disk assignment information for a specific key-range of a sharded\ncomputation.\nCurrently we only support UTF-8 character splits to simplify encoding into\nJSON.",
|
| + "id": "KeyRangeDataDiskAssignment",
|
| "properties": {
|
| - "originalTransformOrCollection": {
|
| - "description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
|
| + "end": {
|
| + "description": "The end (exclusive) of the key range.",
|
| + "type": "string"
|
| + },
|
| + "dataDisk": {
|
| + "description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
|
| "type": "string"
|
| },
|
| + "start": {
|
| + "description": "The start (inclusive) of the key range.",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "Package": {
|
| + "description": "The packages that must be installed in order for a worker to run the\nsteps of the Cloud Dataflow job that will be assigned to its worker\npool.\n\nThis is the mechanism by which the Cloud Dataflow SDK causes code to\nbe loaded onto the workers. For example, the Cloud Dataflow Java SDK\nmight use this to install jars containing the user's code and all of the\nvarious dependencies (libraries, data files, etc.) required in order\nfor that code to run.",
|
| + "id": "Package",
|
| + "properties": {
|
| "name": {
|
| - "description": "Dataflow service generated name for this source.",
|
| + "description": "The name of the package.",
|
| "type": "string"
|
| },
|
| - "userName": {
|
| - "description": "Human-readable name for this transform; may be user or system generated.",
|
| + "location": {
|
| + "description": "The resource to read the package from. The supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}\n bucket.storage.googleapis.com/",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkItemServiceState": {
|
| - "description": "The Dataflow service's idea of the current state of a WorkItem\nbeing processed by a worker.",
|
| - "id": "WorkItemServiceState",
|
| + "ParDoInstruction": {
|
| + "description": "An instruction that does a ParDo operation.\nTakes one main input and zero or more side inputs, and produces\nzero or more outputs.\nRuns user code.",
|
| + "id": "ParDoInstruction",
|
| "properties": {
|
| - "splitRequest": {
|
| - "$ref": "ApproximateSplitRequest",
|
| - "description": "The progress point in the WorkItem where the Dataflow service\nsuggests that the worker truncate the task."
|
| + "input": {
|
| + "$ref": "InstructionInput",
|
| + "description": "The input."
|
| },
|
| - "suggestedStopPosition": {
|
| - "$ref": "Position",
|
| - "description": "Obsolete, always empty."
|
| + "numOutputs": {
|
| + "description": "The number of outputs.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| },
|
| - "reportStatusInterval": {
|
| - "description": "New recommended reporting interval.",
|
| - "format": "google-duration",
|
| - "type": "string"
|
| + "sideInputs": {
|
| + "description": "Zero or more side inputs.",
|
| + "items": {
|
| + "$ref": "SideInputInfo"
|
| + },
|
| + "type": "array"
|
| },
|
| - "harnessData": {
|
| + "multiOutputInfos": {
|
| + "description": "Information about each of the outputs, if user_fn is a MultiDoFn.",
|
| + "items": {
|
| + "$ref": "MultiOutputInfo"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "userFn": {
|
| "additionalProperties": {
|
| "description": "Properties of the object.",
|
| "type": "any"
|
| },
|
| - "description": "Other data returned by the service, specific to the particular\nworker harness.",
|
| + "description": "The user function to invoke.",
|
| "type": "object"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "CounterStructuredName": {
|
| + "description": "Identifies a counter within a per-job namespace. Counters whose structured\nnames are the same get merged into a single value for the job.",
|
| + "id": "CounterStructuredName",
|
| + "properties": {
|
| + "componentStepName": {
|
| + "description": "Name of the optimized step being executed by the workers.",
|
| + "type": "string"
|
| },
|
| - "leaseExpireTime": {
|
| - "description": "Time at which the current lease will expire.",
|
| - "format": "google-datetime",
|
| + "portion": {
|
| + "description": "Portion of this counter, either key or value.",
|
| + "enum": [
|
| + "ALL",
|
| + "KEY",
|
| + "VALUE"
|
| + ],
|
| + "enumDescriptions": [
|
| + "Counter portion has not been set.",
|
| + "Counter reports a key.",
|
| + "Counter reports a value."
|
| + ],
|
| "type": "string"
|
| },
|
| - "metricShortId": {
|
| - "description": "The short ids that workers should use in subsequent metric updates.\nWorkers should strive to use short ids whenever possible, but it is ok\nto request the short_id again if a worker lost track of it\n(e.g. if the worker is recovering from a crash).\nNOTE: it is possible that the response may have short ids for a subset\nof the metrics.",
|
| - "items": {
|
| - "$ref": "MetricShortId"
|
| - },
|
| - "type": "array"
|
| + "originalStepName": {
|
| + "description": "System generated name of the original step in the user's graph, before\noptimization.",
|
| + "type": "string"
|
| },
|
| - "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",
|
| + "workerId": {
|
| + "description": "ID of a particular worker.",
|
| "type": "string"
|
| },
|
| - "suggestedStopPoint": {
|
| - "$ref": "ApproximateProgress",
|
| - "description": "DEPRECATED in favor of split_request."
|
| + "originNamespace": {
|
| + "description": "A string containing a more specific namespace of the counter's origin.",
|
| + "type": "string"
|
| + },
|
| + "origin": {
|
| + "description": "One of the standard Origins defined above.",
|
| + "enum": [
|
| + "SYSTEM",
|
| + "USER"
|
| + ],
|
| + "enumDescriptions": [
|
| + "Counter was created by the Dataflow system.",
|
| + "Counter was created by the user."
|
| + ],
|
| + "type": "string"
|
| + },
|
| + "name": {
|
| + "description": "Counter name. Not necessarily globally-unique, but unique within the\ncontext of the other fields.\nRequired.",
|
| + "type": "string"
|
| + },
|
| + "executionStepName": {
|
| + "description": "Name of the stage. An execution step contains multiple component steps.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "MetricStructuredName": {
|
| - "description": "Identifies a metric, by describing the source which generated the\nmetric.",
|
| - "id": "MetricStructuredName",
|
| + "MetricUpdate": {
|
| + "description": "Describes the state of a metric.",
|
| + "id": "MetricUpdate",
|
| "properties": {
|
| "name": {
|
| - "description": "Worker-defined metric name.",
|
| - "type": "string"
|
| + "$ref": "MetricStructuredName",
|
| + "description": "Name of the metric."
|
| },
|
| - "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.",
|
| + "distribution": {
|
| + "description": "A struct value describing properties of a distribution of numeric values.",
|
| + "type": "any"
|
| + },
|
| + "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"
|
| + },
|
| + "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"
|
| + },
|
| + "internal": {
|
| + "description": "Worker-computed aggregate value for internal use by the Dataflow\nservice.",
|
| + "type": "any"
|
| + },
|
| + "kind": {
|
| + "description": "Metric aggregation kind. The possible metric aggregation kinds are\n\"Sum\", \"Max\", \"Min\", \"Mean\", \"Set\", \"And\", \"Or\", and \"Distribution\".\nThe specified aggregation kind is case-insensitive.\n\nIf omitted, this is not an aggregated value but instead\na single metric sample value.",
|
| "type": "string"
|
| },
|
| - "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"
|
| + "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"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SeqMapTaskOutputInfo": {
|
| - "description": "Information about an output of a SeqMapTask.",
|
| - "id": "SeqMapTaskOutputInfo",
|
| + "ApproximateProgress": {
|
| + "description": "Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest.",
|
| + "id": "ApproximateProgress",
|
| "properties": {
|
| - "tag": {
|
| - "description": "The id of the TupleTag the user code will tag the output value by.",
|
| - "type": "string"
|
| + "position": {
|
| + "$ref": "Position",
|
| + "description": "Obsolete."
|
| },
|
| - "sink": {
|
| - "$ref": "Sink",
|
| - "description": "The sink to write the output value to."
|
| + "percentComplete": {
|
| + "description": "Obsolete.",
|
| + "format": "float",
|
| + "type": "number"
|
| + },
|
| + "remainingTime": {
|
| + "description": "Obsolete.",
|
| + "format": "google-duration",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "JobExecutionStageInfo": {
|
| - "description": "Contains information about how a particular\ngoogle.dataflow.v1beta3.Step will be executed.",
|
| - "id": "JobExecutionStageInfo",
|
| + "WorkerMessageResponse": {
|
| + "description": "A worker_message response allows the server to pass information to the\nsender.",
|
| + "id": "WorkerMessageResponse",
|
| "properties": {
|
| - "stepName": {
|
| - "description": "The steps associated with the execution stage.\nNote that stages may have several steps, and that a given step\nmight be run by more than one stage.",
|
| - "items": {
|
| - "type": "string"
|
| - },
|
| - "type": "array"
|
| + "workerMetricsResponse": {
|
| + "$ref": "ResourceUtilizationReportResponse",
|
| + "description": "Service's response to reporting worker metrics (currently empty)."
|
| + },
|
| + "workerHealthReportResponse": {
|
| + "$ref": "WorkerHealthReportResponse",
|
| + "description": "The service's response to a worker's health report."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "KeyRangeLocation": {
|
| - "description": "Location information for a specific key-range of a sharded computation.\nCurrently we only support UTF-8 character splits to simplify encoding into\nJSON.",
|
| - "id": "KeyRangeLocation",
|
| + "TemplateMetadata": {
|
| + "description": "Metadata describing a template.",
|
| + "id": "TemplateMetadata",
|
| "properties": {
|
| - "dataDisk": {
|
| - "description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
|
| - "type": "string"
|
| - },
|
| - "start": {
|
| - "description": "The start (inclusive) of the key range.",
|
| - "type": "string"
|
| - },
|
| - "end": {
|
| - "description": "The end (exclusive) of the key range.",
|
| - "type": "string"
|
| + "parameters": {
|
| + "description": "The parameters for the template.",
|
| + "items": {
|
| + "$ref": "ParameterMetadata"
|
| + },
|
| + "type": "array"
|
| },
|
| - "deprecatedPersistentDirectory": {
|
| - "description": "DEPRECATED. The location of the persistent state for this range, as a\npersistent directory in the worker local filesystem.",
|
| + "name": {
|
| + "description": "Required. The name of the template.",
|
| "type": "string"
|
| },
|
| - "deliveryEndpoint": {
|
| - "description": "The physical location of this range assignment to be used for\nstreaming computation cross-worker message delivery.",
|
| + "description": {
|
| + "description": "Optional. A description of the template.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceGetMetadataRequest": {
|
| - "description": "A request to compute the SourceMetadata of a Source.",
|
| - "id": "SourceGetMetadataRequest",
|
| - "properties": {
|
| - "source": {
|
| - "$ref": "Source",
|
| - "description": "Specification of the source whose metadata should be computed."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "SeqMapTask": {
|
| - "description": "Describes a particular function to invoke.",
|
| - "id": "SeqMapTask",
|
| + "WorkerMessage": {
|
| + "description": "WorkerMessage provides information to the backend about a worker.",
|
| + "id": "WorkerMessage",
|
| "properties": {
|
| - "name": {
|
| - "description": "The user-provided name of the SeqDo operation.",
|
| + "time": {
|
| + "description": "The timestamp of the worker_message.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| - "outputInfos": {
|
| - "description": "Information about each of the outputs.",
|
| - "items": {
|
| - "$ref": "SeqMapTaskOutputInfo"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "inputs": {
|
| - "description": "Information about each of the inputs.",
|
| - "items": {
|
| - "$ref": "SideInputInfo"
|
| - },
|
| - "type": "array"
|
| + "workerHealthReport": {
|
| + "$ref": "WorkerHealthReport",
|
| + "description": "The health of a worker."
|
| },
|
| - "stageName": {
|
| - "description": "System-defined name of the stage containing the SeqDo operation.\nUnique across the workflow.",
|
| - "type": "string"
|
| + "workerMetrics": {
|
| + "$ref": "ResourceUtilizationReport",
|
| + "description": "Resource metrics reported by workers."
|
| },
|
| - "systemName": {
|
| - "description": "System-defined name of the SeqDo operation.\nUnique across the workflow.",
|
| - "type": "string"
|
| + "workerMessageCode": {
|
| + "$ref": "WorkerMessageCode",
|
| + "description": "A worker message code."
|
| },
|
| - "userFn": {
|
| + "labels": {
|
| "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| + "type": "string"
|
| },
|
| - "description": "The user function to invoke.",
|
| + "description": "Labels are used to group WorkerMessages.\nFor example, a worker_message about a particular container\nmight have the labels:\n{ \"JOB_ID\": \"2015-04-22\",\n \"WORKER_ID\": \"wordcount-vm-2015…\"\n \"CONTAINER_TYPE\": \"worker\",\n \"CONTAINER_ID\": \"ac1234def\"}\nLabel tags typically correspond to Label enum values. However, for ease\nof development other strings can be used as tags. LABEL_UNSPECIFIED should\nnot be used here.",
|
| "type": "object"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "NameAndKind": {
|
| - "description": "Basic metadata about a counter.",
|
| - "id": "NameAndKind",
|
| + "JobMetrics": {
|
| + "description": "JobMetrics contains a collection of metrics descibing the detailed progress\nof a Dataflow job. Metrics correspond to user-defined and system-defined\nmetrics in the job.\n\nThis resource captures only the most recent values of each metric;\ntime-series data can be queried for them (under the same metric names)\nfrom Cloud Monitoring.",
|
| + "id": "JobMetrics",
|
| "properties": {
|
| - "name": {
|
| - "description": "Name of the counter.",
|
| - "type": "string"
|
| + "metrics": {
|
| + "description": "All metrics for this job.",
|
| + "items": {
|
| + "$ref": "MetricUpdate"
|
| + },
|
| + "type": "array"
|
| },
|
| - "kind": {
|
| - "description": "Counter aggregation kind.",
|
| - "enum": [
|
| - "INVALID",
|
| - "SUM",
|
| - "MAX",
|
| - "MIN",
|
| - "MEAN",
|
| - "OR",
|
| - "AND",
|
| - "SET",
|
| - "DISTRIBUTION"
|
| - ],
|
| - "enumDescriptions": [
|
| - "Counter aggregation kind was not set.",
|
| - "Aggregated value is the sum of all contributed values.",
|
| - "Aggregated value is the max of all contributed values.",
|
| - "Aggregated value is the min of all contributed values.",
|
| - "Aggregated value is the mean of all contributed values.",
|
| - "Aggregated value represents the logical 'or' of all contributed values.",
|
| - "Aggregated value represents the logical 'and' of all contributed values.",
|
| - "Aggregated value is a set of unique contributed values.",
|
| - "Aggregated value captures statistics about a distribution."
|
| - ],
|
| + "metricTime": {
|
| + "description": "Timestamp as of which metric values are current.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerMessageCode": {
|
| - "description": "A message code is used to report status and error messages to the service.\nThe message codes are intended to be machine readable. The service will\ntake care of translating these into user understandable messages if\nnecessary.\n\nExample use cases:\n 1. Worker processes reporting successful startup.\n 2. Worker processes reporting specific errors (e.g. package staging\n failure).",
|
| - "id": "WorkerMessageCode",
|
| + "FloatingPointList": {
|
| + "description": "A metric value representing a list of floating point numbers.",
|
| + "id": "FloatingPointList",
|
| "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.",
|
| - "type": "any"
|
| + "elements": {
|
| + "description": "Elements of the list.",
|
| + "items": {
|
| + "format": "double",
|
| + "type": "number"
|
| },
|
| - "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"
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "CustomSourceLocation": {
|
| - "description": "Identifies the location of a custom souce.",
|
| - "id": "CustomSourceLocation",
|
| + "CounterUpdate": {
|
| + "description": "An update to a Counter sent from a worker.",
|
| + "id": "CounterUpdate",
|
| "properties": {
|
| - "stateful": {
|
| - "description": "Whether this source is stateful.",
|
| + "nameAndKind": {
|
| + "$ref": "NameAndKind",
|
| + "description": "Counter name and aggregation type."
|
| + },
|
| + "stringList": {
|
| + "$ref": "StringList",
|
| + "description": "List of strings, for Set."
|
| + },
|
| + "distribution": {
|
| + "$ref": "DistributionUpdate",
|
| + "description": "Distribution data"
|
| + },
|
| + "shortId": {
|
| + "description": "The service-generated short identifier for this counter.\nThe short_id -> (name, metadata) mapping is constant for the lifetime of\na job.",
|
| + "format": "int64",
|
| + "type": "string"
|
| + },
|
| + "floatingPointList": {
|
| + "$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."
|
| + },
|
| + "integerList": {
|
| + "$ref": "IntegerList",
|
| + "description": "List of integers, for Set."
|
| + },
|
| + "floatingPoint": {
|
| + "description": "Floating point value for Sum, Max, Min.",
|
| + "format": "double",
|
| + "type": "number"
|
| + },
|
| + "integerMean": {
|
| + "$ref": "IntegerMean",
|
| + "description": "Integer mean aggregation value for Mean."
|
| + },
|
| + "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": {
|
| + "$ref": "FloatingPointMean",
|
| + "description": "Floating point mean aggregation value for Mean."
|
| + },
|
| + "boolean": {
|
| + "description": "Boolean value for And, Or.",
|
| "type": "boolean"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "MapTask": {
|
| - "description": "MapTask consists of an ordered set of instructions, each of which\ndescribes one particular low-level operation for the worker to\nperform in order to accomplish the MapTask's WorkItem.\n\nEach instruction must appear in the list before any instructions which\ndepends on its output.",
|
| - "id": "MapTask",
|
| + "SourceMetadata": {
|
| + "description": "Metadata about a Source useful for automatically optimizing\nand tuning the pipeline, etc.",
|
| + "id": "SourceMetadata",
|
| "properties": {
|
| - "stageName": {
|
| - "description": "System-defined name of the stage containing this MapTask.\nUnique across the workflow.",
|
| + "estimatedSizeBytes": {
|
| + "description": "An estimate of the total size (in bytes) of the data that would be\nread from this source. This estimate is in terms of external storage\nsize, before any decompression or other processing done by the reader.",
|
| + "format": "int64",
|
| "type": "string"
|
| },
|
| - "systemName": {
|
| - "description": "System-defined name of this MapTask.\nUnique across the workflow.",
|
| - "type": "string"
|
| + "infinite": {
|
| + "description": "Specifies that the size of this source is known to be infinite\n(this is a streaming source).",
|
| + "type": "boolean"
|
| },
|
| - "instructions": {
|
| - "description": "The instructions in the MapTask.",
|
| - "items": {
|
| - "$ref": "ParallelInstruction"
|
| - },
|
| - "type": "array"
|
| + "producesSortedKeys": {
|
| + "description": "Whether this source is known to produce key/value pairs with\nthe (encoded) keys in lexicographically sorted order.",
|
| + "type": "boolean"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "FloatingPointMean": {
|
| - "description": "A representation of a floating point mean metric contribution.",
|
| - "id": "FloatingPointMean",
|
| + "DistributionUpdate": {
|
| + "description": "A metric value representing a distribution.",
|
| + "id": "DistributionUpdate",
|
| "properties": {
|
| - "sum": {
|
| - "description": "The sum of all values being aggregated.",
|
| + "max": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The maximum value present in the distribution."
|
| + },
|
| + "logBuckets": {
|
| + "description": "(Optional) Logarithmic histogram of values.\nEach log may be in no more than one bucket. Order does not matter.",
|
| + "items": {
|
| + "$ref": "LogBucket"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "count": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The count of the number of elements present in the distribution."
|
| + },
|
| + "min": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The minimum value present in the distribution."
|
| + },
|
| + "sumOfSquares": {
|
| + "description": "Use a double since the sum of squares is likely to overflow int64.",
|
| "format": "double",
|
| "type": "number"
|
| },
|
| - "count": {
|
| + "sum": {
|
| "$ref": "SplitInt64",
|
| - "description": "The number of values being aggregated."
|
| + "description": "Use an int64 since we'd prefer the added precision. If overflow is a common\nproblem we can detect it and use an additional int64 or a double."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ReportWorkItemStatusResponse": {
|
| - "description": "Response from a request to report the status of WorkItems.",
|
| - "id": "ReportWorkItemStatusResponse",
|
| + "SourceFork": {
|
| + "description": "DEPRECATED in favor of DynamicSourceSplit.",
|
| + "id": "SourceFork",
|
| "properties": {
|
| - "workItemServiceStates": {
|
| - "description": "A set of messages indicating the service-side state for each\nWorkItem whose status was reported, in the same order as the\nWorkItemStatus messages in the ReportWorkItemStatusRequest which\nresulting in this response.",
|
| - "items": {
|
| - "$ref": "WorkItemServiceState"
|
| - },
|
| - "type": "array"
|
| - }
|
| + "residual": {
|
| + "$ref": "SourceSplitShard",
|
| + "description": "DEPRECATED"
|
| + },
|
| + "residualSource": {
|
| + "$ref": "DerivedSource",
|
| + "description": "DEPRECATED"
|
| + },
|
| + "primary": {
|
| + "$ref": "SourceSplitShard",
|
| + "description": "DEPRECATED"
|
| + },
|
| + "primarySource": {
|
| + "$ref": "DerivedSource",
|
| + "description": "DEPRECATED"
|
| + }
|
| },
|
| "type": "object"
|
| },
|
| - "InstructionOutput": {
|
| - "description": "An output of an instruction.",
|
| - "id": "InstructionOutput",
|
| + "WorkerHealthReportResponse": {
|
| + "description": "WorkerHealthReportResponse contains information returned to the worker\nin response to a health ping.",
|
| + "id": "WorkerHealthReportResponse",
|
| "properties": {
|
| - "codec": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| + "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"
|
| + },
|
| + "WorkItemStatus": {
|
| + "description": "Conveys a worker's progress through the work described by a WorkItem.",
|
| + "id": "WorkItemStatus",
|
| + "properties": {
|
| + "sourceFork": {
|
| + "$ref": "SourceFork",
|
| + "description": "DEPRECATED in favor of dynamic_source_split."
|
| + },
|
| + "counterUpdates": {
|
| + "description": "Worker output counters for this WorkItem.",
|
| + "items": {
|
| + "$ref": "CounterUpdate"
|
| },
|
| - "description": "The codec to use to encode data being written via this output.",
|
| - "type": "object"
|
| + "type": "array"
|
| },
|
| - "name": {
|
| - "description": "The user-provided name of this output.",
|
| + "workItemId": {
|
| + "description": "Identifies the WorkItem.",
|
| "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.",
|
| + "errors": {
|
| + "description": "Specifies errors which occurred during processing. If errors are\nprovided, and completed = true, then the WorkItem is considered\nto have failed.",
|
| + "items": {
|
| + "$ref": "Status"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "metricUpdates": {
|
| + "description": "DEPRECATED in favor of counter_updates.",
|
| + "items": {
|
| + "$ref": "MetricUpdate"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "dynamicSourceSplit": {
|
| + "$ref": "DynamicSourceSplit",
|
| + "description": "See documentation of stop_position."
|
| + },
|
| + "sourceOperationResponse": {
|
| + "$ref": "SourceOperationResponse",
|
| + "description": "If the work item represented a SourceOperationRequest, and the work\nis completed, contains the result of the operation."
|
| + },
|
| + "progress": {
|
| + "$ref": "ApproximateProgress",
|
| + "description": "DEPRECATED in favor of reported_progress."
|
| + },
|
| + "requestedLeaseDuration": {
|
| + "description": "Amount of time the worker requests for its lease.",
|
| + "format": "google-duration",
|
| "type": "string"
|
| },
|
| - "systemName": {
|
| - "description": "System-defined name of this output.\nUnique across the workflow.",
|
| + "reportIndex": {
|
| + "description": "The report index. When a WorkItem is leased, the lease will\ncontain an initial report index. When a WorkItem's status is\nreported to the system, the report should be sent with\nthat report index, and the response will contain the index the\nworker should use for the next report. Reports received with\nunexpected index values will be rejected by the service.\n\nIn order to preserve idempotency, the worker should not alter the\ncontents of a report, even if the worker must submit the same\nreport multiple times before getting back a response. The worker\nshould not submit a subsequent report until the response for the\nprevious report had been received from the service.",
|
| + "format": "int64",
|
| "type": "string"
|
| },
|
| - "onlyCountKeyBytes": {
|
| - "description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the key size.",
|
| - "type": "boolean"
|
| + "stopPosition": {
|
| + "$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."
|
| },
|
| - "onlyCountValueBytes": {
|
| - "description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the value size.",
|
| + "completed": {
|
| + "description": "True if the WorkItem was completed (successfully or unsuccessfully).",
|
| "type": "boolean"
|
| + },
|
| + "reportedProgress": {
|
| + "$ref": "ApproximateReportedProgress",
|
| + "description": "The worker's progress through this WorkItem."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "CreateJobFromTemplateRequest": {
|
| - "description": "A request to create a Cloud Dataflow job from a template.",
|
| - "id": "CreateJobFromTemplateRequest",
|
| + "ComponentSource": {
|
| + "description": "Description of an interstitial value between transforms in an execution\nstage.",
|
| + "id": "ComponentSource",
|
| "properties": {
|
| - "gcsPath": {
|
| - "description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
|
| + "name": {
|
| + "description": "Dataflow service generated name for this source.",
|
| "type": "string"
|
| },
|
| - "environment": {
|
| - "$ref": "RuntimeEnvironment",
|
| - "description": "The runtime environment for the job."
|
| - },
|
| - "location": {
|
| - "description": "The location to which to direct the request.",
|
| + "userName": {
|
| + "description": "Human-readable name for this transform; may be user or system generated.",
|
| "type": "string"
|
| },
|
| - "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.",
|
| + "originalTransformOrCollection": {
|
| + "description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "IntegerMean": {
|
| - "description": "A representation of an integer mean metric contribution.",
|
| - "id": "IntegerMean",
|
| + "WorkItemServiceState": {
|
| + "description": "The Dataflow service's idea of the current state of a WorkItem\nbeing processed by a worker.",
|
| + "id": "WorkItemServiceState",
|
| "properties": {
|
| - "sum": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The sum of all values being aggregated."
|
| + "suggestedStopPoint": {
|
| + "$ref": "ApproximateProgress",
|
| + "description": "DEPRECATED in favor of split_request."
|
| },
|
| - "count": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The number of values being aggregated."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "ListJobsResponse": {
|
| - "description": "Response to a request to list Cloud Dataflow jobs. This may be a partial\nresponse, depending on the page size in the ListJobsRequest.",
|
| - "id": "ListJobsResponse",
|
| - "properties": {
|
| - "jobs": {
|
| - "description": "A subset of the requested job information.",
|
| - "items": {
|
| - "$ref": "Job"
|
| + "splitRequest": {
|
| + "$ref": "ApproximateSplitRequest",
|
| + "description": "The progress point in the WorkItem where the Dataflow service\nsuggests that the worker truncate the task."
|
| + },
|
| + "suggestedStopPosition": {
|
| + "$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"
|
| },
|
| - "type": "array"
|
| + "description": "Other data returned by the service, specific to the particular\nworker harness.",
|
| + "type": "object"
|
| },
|
| - "failedLocation": {
|
| - "description": "Zero or more messages describing locations that failed to respond.",
|
| + "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": {
|
| - "$ref": "FailedLocation"
|
| + "$ref": "MetricShortId"
|
| },
|
| "type": "array"
|
| },
|
| - "nextPageToken": {
|
| - "description": "Set if there may be more results than fit in this response.",
|
| + "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"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ComputationTopology": {
|
| - "description": "All configuration data for a particular Computation.",
|
| - "id": "ComputationTopology",
|
| + "MetricStructuredName": {
|
| + "description": "Identifies a metric, by describing the source which generated the\nmetric.",
|
| + "id": "MetricStructuredName",
|
| "properties": {
|
| - "outputs": {
|
| - "description": "The outputs from the computation.",
|
| - "items": {
|
| - "$ref": "StreamLocation"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "stateFamilies": {
|
| - "description": "The state family values.",
|
| - "items": {
|
| - "$ref": "StateFamilyConfig"
|
| + "context": {
|
| + "additionalProperties": {
|
| + "type": "string"
|
| },
|
| - "type": "array"
|
| + "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"
|
| },
|
| - "systemStageName": {
|
| - "description": "The system stage name.",
|
| + "name": {
|
| + "description": "Worker-defined metric name.",
|
| "type": "string"
|
| },
|
| - "computationId": {
|
| - "description": "The ID of the computation.",
|
| + "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"
|
| - },
|
| - "inputs": {
|
| - "description": "The inputs to the computation.",
|
| - "items": {
|
| - "$ref": "StreamLocation"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "keyRanges": {
|
| - "description": "The key ranges processed by the computation.",
|
| - "items": {
|
| - "$ref": "KeyRangeLocation"
|
| - },
|
| - "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "RuntimeEnvironment": {
|
| - "description": "The environment values to set at runtime.",
|
| - "id": "RuntimeEnvironment",
|
| + "SeqMapTaskOutputInfo": {
|
| + "description": "Information about an output of a SeqMapTask.",
|
| + "id": "SeqMapTaskOutputInfo",
|
| "properties": {
|
| - "serviceAccountEmail": {
|
| - "description": "The email address of the service account to run the job as.",
|
| - "type": "string"
|
| - },
|
| - "tempLocation": {
|
| - "description": "The Cloud Storage path to use for temporary files.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
|
| + "tag": {
|
| + "description": "The id of the TupleTag the user code will tag the output value by.",
|
| "type": "string"
|
| },
|
| - "bypassTempDirValidation": {
|
| - "description": "Whether to bypass the safety checks for the job's temporary directory.\nUse with caution.",
|
| - "type": "boolean"
|
| - },
|
| - "machineType": {
|
| - "description": "The machine type to use for the job. Defaults to the value from the\ntemplate if not specified.",
|
| - "type": "string"
|
| - },
|
| - "zone": {
|
| - "description": "The Compute Engine [availability\nzone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)\nfor launching worker instances to run your pipeline.",
|
| - "type": "string"
|
| - },
|
| - "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"
|
| + "sink": {
|
| + "$ref": "Sink",
|
| + "description": "The sink to write the output value to."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamingSideInputLocation": {
|
| - "description": "Identifies the location of a streaming side input.",
|
| - "id": "StreamingSideInputLocation",
|
| + "JobExecutionStageInfo": {
|
| + "description": "Contains information about how a particular\ngoogle.dataflow.v1beta3.Step will be executed.",
|
| + "id": "JobExecutionStageInfo",
|
| "properties": {
|
| - "tag": {
|
| - "description": "Identifies the particular side input within the streaming Dataflow job.",
|
| - "type": "string"
|
| - },
|
| - "stateFamily": {
|
| - "description": "Identifies the state family where this side input is stored.",
|
| - "type": "string"
|
| + "stepName": {
|
| + "description": "The steps associated with the execution stage.\nNote that stages may have several steps, and that a given step\nmight be run by more than one stage.",
|
| + "items": {
|
| + "type": "string"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "MountedDataDisk": {
|
| - "description": "Describes mounted data disk.",
|
| - "id": "MountedDataDisk",
|
| + "KeyRangeLocation": {
|
| + "description": "Location information for a specific key-range of a sharded computation.\nCurrently we only support UTF-8 character splits to simplify encoding into\nJSON.",
|
| + "id": "KeyRangeLocation",
|
| "properties": {
|
| + "deprecatedPersistentDirectory": {
|
| + "description": "DEPRECATED. The location of the persistent state for this range, as a\npersistent directory in the worker local filesystem.",
|
| + "type": "string"
|
| + },
|
| + "deliveryEndpoint": {
|
| + "description": "The physical location of this range assignment to be used for\nstreaming computation cross-worker message delivery.",
|
| + "type": "string"
|
| + },
|
| "dataDisk": {
|
| - "description": "The name of the data disk.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
|
| + "description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
|
| + "type": "string"
|
| + },
|
| + "start": {
|
| + "description": "The start (inclusive) of the key range.",
|
| + "type": "string"
|
| + },
|
| + "end": {
|
| + "description": "The end (exclusive) of the key range.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "LaunchTemplateResponse": {
|
| - "description": "Response to the request to launch a template.",
|
| - "id": "LaunchTemplateResponse",
|
| + "SourceGetMetadataRequest": {
|
| + "description": "A request to compute the SourceMetadata of a Source.",
|
| + "id": "SourceGetMetadataRequest",
|
| "properties": {
|
| - "job": {
|
| - "$ref": "Job",
|
| - "description": "The job that was launched, if the request was not a dry run and\nthe job was successfully launched."
|
| + "source": {
|
| + "$ref": "Source",
|
| + "description": "Specification of the source whose metadata should be computed."
|
| }
|
| },
|
| "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",
|
| + "NameAndKind": {
|
| + "description": "Basic metadata about a counter.",
|
| + "id": "NameAndKind",
|
| "properties": {
|
| - "derivationMode": {
|
| - "description": "What source to base the produced source on (if any).",
|
| + "name": {
|
| + "description": "Name of the counter.",
|
| + "type": "string"
|
| + },
|
| + "kind": {
|
| + "description": "Counter aggregation kind.",
|
| "enum": [
|
| - "SOURCE_DERIVATION_MODE_UNKNOWN",
|
| - "SOURCE_DERIVATION_MODE_INDEPENDENT",
|
| - "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
|
| - "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
|
| + "INVALID",
|
| + "SUM",
|
| + "MAX",
|
| + "MIN",
|
| + "MEAN",
|
| + "OR",
|
| + "AND",
|
| + "SET",
|
| + "DISTRIBUTION"
|
| ],
|
| "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."
|
| + "Counter aggregation kind was not set.",
|
| + "Aggregated value is the sum of all contributed values.",
|
| + "Aggregated value is the max of all contributed values.",
|
| + "Aggregated value is the min of all contributed values.",
|
| + "Aggregated value is the mean of all contributed values.",
|
| + "Aggregated value represents the logical 'or' of all contributed values.",
|
| + "Aggregated value represents the logical 'and' of all contributed values.",
|
| + "Aggregated value is a set of unique contributed values.",
|
| + "Aggregated value captures statistics about a distribution."
|
| ],
|
| "type": "string"
|
| - },
|
| - "source": {
|
| - "$ref": "Source",
|
| - "description": "Specification of the source."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "DynamicSourceSplit": {
|
| - "description": "When a task splits using WorkItemStatus.dynamic_source_split, this\nmessage describes the two parts of the split relative to the\ndescription of the current task's input.",
|
| - "id": "DynamicSourceSplit",
|
| - "properties": {
|
| - "residual": {
|
| - "$ref": "DerivedSource",
|
| - "description": "Residual part (returned to the pool of work).\nSpecified relative to the previously-current source."
|
| - },
|
| - "primary": {
|
| - "$ref": "DerivedSource",
|
| - "description": "Primary part (continued to be processed by worker).\nSpecified relative to the previously-current source.\nBecomes current."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Job": {
|
| - "description": "Defines a job to be run by the Cloud Dataflow service.",
|
| - "id": "Job",
|
| + "SeqMapTask": {
|
| + "description": "Describes a particular function to invoke.",
|
| + "id": "SeqMapTask",
|
| "properties": {
|
| - "clientRequestId": {
|
| - "description": "The client's unique identifier of the job, re-used across retried attempts.\nIf this field is set, the service will ensure its uniqueness.\nThe request to create a job will fail if the service has knowledge of a\npreviously submitted job with the same client's ID and job name.\nThe caller may use this field to ensure idempotence of job\ncreation across retried attempts to create a job.\nBy default, the field is empty and, in that case, the service ignores it.",
|
| - "type": "string"
|
| + "userFn": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "The user function to invoke.",
|
| + "type": "object"
|
| },
|
| "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])?`",
|
| + "description": "The user-provided name of the SeqDo operation.",
|
| "type": "string"
|
| },
|
| - "steps": {
|
| - "description": "The top-level steps that constitute the entire job.",
|
| + "outputInfos": {
|
| + "description": "Information about each of the outputs.",
|
| "items": {
|
| - "$ref": "Step"
|
| + "$ref": "SeqMapTaskOutputInfo"
|
| },
|
| "type": "array"
|
| },
|
| - "replacedByJobId": {
|
| - "description": "If another job is an update of this job (and thus, this job is in\n`JOB_STATE_UPDATED`), this field contains the ID of that job.",
|
| - "type": "string"
|
| - },
|
| - "executionInfo": {
|
| - "$ref": "JobExecutionInfo",
|
| - "description": "Deprecated."
|
| - },
|
| - "id": {
|
| - "description": "The unique ID of this job.\n\nThis field is set by the Cloud Dataflow service when the Job is\ncreated, and is immutable for the life of the job.",
|
| - "type": "string"
|
| + "inputs": {
|
| + "description": "Information about each of the inputs.",
|
| + "items": {
|
| + "$ref": "SideInputInfo"
|
| + },
|
| + "type": "array"
|
| },
|
| - "currentState": {
|
| - "description": "The current state of the job.\n\nJobs are created in the `JOB_STATE_STOPPED` state unless otherwise\nspecified.\n\nA job in the `JOB_STATE_RUNNING` state may asynchronously enter a\nterminal state. After a job has reached a terminal state, no\nfurther state updates may be made.\n\nThis field may be mutated by the Cloud Dataflow service;\ncallers cannot mutate it.",
|
| - "enum": [
|
| - "JOB_STATE_UNKNOWN",
|
| - "JOB_STATE_STOPPED",
|
| - "JOB_STATE_RUNNING",
|
| - "JOB_STATE_DONE",
|
| - "JOB_STATE_FAILED",
|
| - "JOB_STATE_CANCELLED",
|
| - "JOB_STATE_UPDATED",
|
| - "JOB_STATE_DRAINING",
|
| - "JOB_STATE_DRAINED",
|
| - "JOB_STATE_PENDING",
|
| - "JOB_STATE_CANCELLING"
|
| - ],
|
| - "enumDescriptions": [
|
| - "The job's run state isn't specified.",
|
| - "`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
|
| - "`JOB_STATE_RUNNING` indicates that the job is currently running.",
|
| - "`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
|
| - "`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
|
| - "`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
|
| - "`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
|
| - "`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
|
| - "`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
|
| - "'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
|
| - "'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
|
| - ],
|
| + "stageName": {
|
| + "description": "System-defined name of the stage containing the SeqDo operation.\nUnique across the workflow.",
|
| "type": "string"
|
| },
|
| - "location": {
|
| - "description": "The location that contains this job.",
|
| + "systemName": {
|
| + "description": "System-defined name of the SeqDo operation.\nUnique across the workflow.",
|
| "type": "string"
|
| - },
|
| - "currentStateTime": {
|
| - "description": "The timestamp associated with the current state.",
|
| - "format": "google-datetime",
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "WorkerMessageCode": {
|
| + "description": "A message code is used to report status and error messages to the service.\nThe message codes are intended to be machine readable. The service will\ntake care of translating these into user understandable messages if\nnecessary.\n\nExample use cases:\n 1. Worker processes reporting successful startup.\n 2. Worker processes reporting specific errors (e.g. package staging\n failure).",
|
| + "id": "WorkerMessageCode",
|
| + "properties": {
|
| + "code": {
|
| + "description": "The code is a string intended for consumption by a machine that identifies\nthe type of message being sent.\nExamples:\n 1. \"HARNESS_STARTED\" might be used to indicate the worker harness has\n started.\n 2. \"GCS_DOWNLOAD_ERROR\" might be used to indicate an error downloading\n a GCS file as part of the boot process of one of the worker containers.\n\nThis is a string and not an enum to make it easy to add new codes without\nwaiting for an API change.",
|
| "type": "string"
|
| },
|
| - "transformNameMapping": {
|
| - "additionalProperties": {
|
| - "type": "string"
|
| - },
|
| - "description": "The map of transform name prefixes of the job to be replaced to the\ncorresponding name prefixes of the new job.",
|
| - "type": "object"
|
| - },
|
| - "labels": {
|
| + "parameters": {
|
| "additionalProperties": {
|
| - "type": "string"
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| },
|
| - "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.",
|
| + "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"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "CustomSourceLocation": {
|
| + "description": "Identifies the location of a custom souce.",
|
| + "id": "CustomSourceLocation",
|
| + "properties": {
|
| + "stateful": {
|
| + "description": "Whether this source is stateful.",
|
| + "type": "boolean"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "MapTask": {
|
| + "description": "MapTask consists of an ordered set of instructions, each of which\ndescribes one particular low-level operation for the worker to\nperform in order to accomplish the MapTask's WorkItem.\n\nEach instruction must appear in the list before any instructions which\ndepends on its output.",
|
| + "id": "MapTask",
|
| + "properties": {
|
| + "stageName": {
|
| + "description": "System-defined name of the stage containing this MapTask.\nUnique across the workflow.",
|
| + "type": "string"
|
| },
|
| - "environment": {
|
| - "$ref": "Environment",
|
| - "description": "The environment for the job."
|
| - },
|
| - "createTime": {
|
| - "description": "The timestamp when the job was initially created. Immutable and set by the\nCloud Dataflow service.",
|
| - "format": "google-datetime",
|
| - "type": "string"
|
| - },
|
| - "stageStates": {
|
| - "description": "This field may be mutated by the Cloud Dataflow service;\ncallers cannot mutate it.",
|
| - "items": {
|
| - "$ref": "ExecutionStageState"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "projectId": {
|
| - "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| - "type": "string"
|
| - },
|
| - "type": {
|
| - "description": "The type of Cloud Dataflow job.",
|
| - "enum": [
|
| - "JOB_TYPE_UNKNOWN",
|
| - "JOB_TYPE_BATCH",
|
| - "JOB_TYPE_STREAMING"
|
| - ],
|
| - "enumDescriptions": [
|
| - "The type of the job is unspecified, or unknown.",
|
| - "A batch job with a well-defined end point: data is read, data is\nprocessed, data is written, and the job is done.",
|
| - "A continuously streaming job with no end: data is read,\nprocessed, and written continuously."
|
| - ],
|
| - "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"
|
| - },
|
| - "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": [
|
| - "JOB_STATE_UNKNOWN",
|
| - "JOB_STATE_STOPPED",
|
| - "JOB_STATE_RUNNING",
|
| - "JOB_STATE_DONE",
|
| - "JOB_STATE_FAILED",
|
| - "JOB_STATE_CANCELLED",
|
| - "JOB_STATE_UPDATED",
|
| - "JOB_STATE_DRAINING",
|
| - "JOB_STATE_DRAINED",
|
| - "JOB_STATE_PENDING",
|
| - "JOB_STATE_CANCELLING"
|
| - ],
|
| - "enumDescriptions": [
|
| - "The job's run state isn't specified.",
|
| - "`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
|
| - "`JOB_STATE_RUNNING` indicates that the job is currently running.",
|
| - "`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
|
| - "`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
|
| - "`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
|
| - "`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
|
| - "`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
|
| - "`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
|
| - "'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
|
| - "'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
|
| - ],
|
| + "systemName": {
|
| + "description": "System-defined name of this MapTask.\nUnique across the workflow.",
|
| "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}",
|
| + "instructions": {
|
| + "description": "The instructions in the MapTask.",
|
| "items": {
|
| - "type": "string"
|
| + "$ref": "ParallelInstruction"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceOperationResponse": {
|
| - "description": "The result of a SourceOperationRequest, specified in\nReportWorkItemStatusRequest.source_operation when the work item\nis completed.",
|
| - "id": "SourceOperationResponse",
|
| + "FloatingPointMean": {
|
| + "description": "A representation of a floating point mean metric contribution.",
|
| + "id": "FloatingPointMean",
|
| "properties": {
|
| - "split": {
|
| - "$ref": "SourceSplitResponse",
|
| - "description": "A response to a request to split a source."
|
| + "count": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The number of values being aggregated."
|
| },
|
| - "getMetadata": {
|
| - "$ref": "SourceGetMetadataResponse",
|
| - "description": "A response to a request to get metadata about a source."
|
| + "sum": {
|
| + "description": "The sum of all values being aggregated.",
|
| + "format": "double",
|
| + "type": "number"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SideInputInfo": {
|
| - "description": "Information about a side input of a DoFn or an input of a SeqDoFn.",
|
| - "id": "SideInputInfo",
|
| + "ReportWorkItemStatusResponse": {
|
| + "description": "Response from a request to report the status of WorkItems.",
|
| + "id": "ReportWorkItemStatusResponse",
|
| "properties": {
|
| - "tag": {
|
| - "description": "The id of the tag the user code will access this side input by;\nthis should correspond to the tag of some MultiOutputInfo.",
|
| - "type": "string"
|
| - },
|
| - "kind": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "How to interpret the source element(s) as a side input value.",
|
| - "type": "object"
|
| - },
|
| - "sources": {
|
| - "description": "The source(s) to read element(s) from to get the value of this side input.\nIf more than one source, then the elements are taken from the\nsources, in the specified order if order matters.\nAt least one source is required.",
|
| + "workItemServiceStates": {
|
| + "description": "A set of messages indicating the service-side state for each\nWorkItem whose status was reported, in the same order as the\nWorkItemStatus messages in the ReportWorkItemStatusRequest which\nresulting in this response.",
|
| "items": {
|
| - "$ref": "Source"
|
| + "$ref": "WorkItemServiceState"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SendDebugCaptureResponse": {
|
| - "description": "Response to a send capture request.\nnothing",
|
| - "id": "SendDebugCaptureResponse",
|
| - "properties": {},
|
| - "type": "object"
|
| - },
|
| - "WriteInstruction": {
|
| - "description": "An instruction that writes records.\nTakes one input, produces no outputs.",
|
| - "id": "WriteInstruction",
|
| + "InstructionOutput": {
|
| + "description": "An output of an instruction.",
|
| + "id": "InstructionOutput",
|
| "properties": {
|
| - "input": {
|
| - "$ref": "InstructionInput",
|
| - "description": "The input."
|
| + "onlyCountValueBytes": {
|
| + "description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the value size.",
|
| + "type": "boolean"
|
| },
|
| - "sink": {
|
| - "$ref": "Sink",
|
| - "description": "The sink to write to."
|
| + "codec": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "The codec to use to encode data being written via this output.",
|
| + "type": "object"
|
| + },
|
| + "name": {
|
| + "description": "The user-provided name of this output.",
|
| + "type": "string"
|
| + },
|
| + "originalName": {
|
| + "description": "System-defined name for this output in the original workflow graph.\nOutputs that do not contribute to an original instruction do not set this.",
|
| + "type": "string"
|
| + },
|
| + "systemName": {
|
| + "description": "System-defined name of this output.\nUnique across the workflow.",
|
| + "type": "string"
|
| + },
|
| + "onlyCountKeyBytes": {
|
| + "description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the key size.",
|
| + "type": "boolean"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ConcatPosition": {
|
| - "description": "A position that encapsulates an inner position and an index for the inner\nposition. A ConcatPosition can be used by a reader of a source that\nencapsulates a set of other sources.",
|
| - "id": "ConcatPosition",
|
| + "CreateJobFromTemplateRequest": {
|
| + "description": "A request to create a Cloud Dataflow job from a template.",
|
| + "id": "CreateJobFromTemplateRequest",
|
| "properties": {
|
| - "position": {
|
| - "$ref": "Position",
|
| - "description": "Position within the inner source."
|
| + "jobName": {
|
| + "description": "Required. The job name to use for the created job.",
|
| + "type": "string"
|
| },
|
| - "index": {
|
| - "description": "Index of the inner source.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "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://`.",
|
| + "type": "string"
|
| + },
|
| + "environment": {
|
| + "$ref": "RuntimeEnvironment",
|
| + "description": "The runtime environment for the job."
|
| + },
|
| + "location": {
|
| + "description": "The location to which to direct the request.",
|
| + "type": "string"
|
| + },
|
| + "parameters": {
|
| + "additionalProperties": {
|
| + "type": "string"
|
| + },
|
| + "description": "The runtime parameters to pass to the job.",
|
| + "type": "object"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "CounterStructuredNameAndMetadata": {
|
| - "description": "A single message which encapsulates structured name and metadata for a given\ncounter.",
|
| - "id": "CounterStructuredNameAndMetadata",
|
| + "IntegerMean": {
|
| + "description": "A representation of an integer mean metric contribution.",
|
| + "id": "IntegerMean",
|
| "properties": {
|
| - "name": {
|
| - "$ref": "CounterStructuredName",
|
| - "description": "Structured name of the counter."
|
| + "count": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The number of values being aggregated."
|
| },
|
| - "metadata": {
|
| - "$ref": "CounterMetadata",
|
| - "description": "Metadata associated with a counter"
|
| + "sum": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The sum of all values being aggregated."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "AutoscalingSettings": {
|
| - "description": "Settings for WorkerPool autoscaling.",
|
| - "id": "AutoscalingSettings",
|
| + "ListJobsResponse": {
|
| + "description": "Response to a request to list Cloud Dataflow jobs. This may be a partial\nresponse, depending on the page size in the ListJobsRequest.",
|
| + "id": "ListJobsResponse",
|
| "properties": {
|
| - "algorithm": {
|
| - "description": "The algorithm to use for autoscaling.",
|
| - "enum": [
|
| - "AUTOSCALING_ALGORITHM_UNKNOWN",
|
| - "AUTOSCALING_ALGORITHM_NONE",
|
| - "AUTOSCALING_ALGORITHM_BASIC"
|
| - ],
|
| - "enumDescriptions": [
|
| - "The algorithm is unknown, or unspecified.",
|
| - "Disable autoscaling.",
|
| - "Increase worker count over time to reduce job execution time."
|
| - ],
|
| + "failedLocation": {
|
| + "description": "Zero or more messages describing locations that failed to respond.",
|
| + "items": {
|
| + "$ref": "FailedLocation"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "nextPageToken": {
|
| + "description": "Set if there may be more results than fit in this response.",
|
| "type": "string"
|
| },
|
| - "maxNumWorkers": {
|
| - "description": "The maximum number of workers to cap scaling at.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "jobs": {
|
| + "description": "A subset of the requested job information.",
|
| + "items": {
|
| + "$ref": "Job"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamingComputationRanges": {
|
| - "description": "Describes full or partial data disk assignment information of the computation\nranges.",
|
| - "id": "StreamingComputationRanges",
|
| + "ComputationTopology": {
|
| + "description": "All configuration data for a particular Computation.",
|
| + "id": "ComputationTopology",
|
| "properties": {
|
| - "computationId": {
|
| - "description": "The ID of the computation.",
|
| - "type": "string"
|
| - },
|
| - "rangeAssignments": {
|
| - "description": "Data disk assignments for ranges from this computation.",
|
| + "outputs": {
|
| + "description": "The outputs from the computation.",
|
| "items": {
|
| - "$ref": "KeyRangeDataDiskAssignment"
|
| + "$ref": "StreamLocation"
|
| },
|
| "type": "array"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "ExecutionStageSummary": {
|
| - "description": "Description of the composing transforms, names/ids, and input/outputs of a\nstage of execution. Some composing transforms and sources may have been\ngenerated by the Dataflow service during execution planning.",
|
| - "id": "ExecutionStageSummary",
|
| - "properties": {
|
| - "outputSource": {
|
| - "description": "Output sources for this stage.",
|
| + },
|
| + "stateFamilies": {
|
| + "description": "The state family values.",
|
| "items": {
|
| - "$ref": "StageSource"
|
| + "$ref": "StateFamilyConfig"
|
| },
|
| "type": "array"
|
| },
|
| - "name": {
|
| - "description": "Dataflow service generated name for this stage.",
|
| + "systemStageName": {
|
| + "description": "The system stage name.",
|
| "type": "string"
|
| },
|
| - "inputSource": {
|
| - "description": "Input sources for this stage.",
|
| - "items": {
|
| - "$ref": "StageSource"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "id": {
|
| - "description": "Dataflow service generated id for this stage.",
|
| + "computationId": {
|
| + "description": "The ID of the computation.",
|
| "type": "string"
|
| },
|
| - "componentTransform": {
|
| - "description": "Transforms that comprise this execution stage.",
|
| + "inputs": {
|
| + "description": "The inputs to the computation.",
|
| "items": {
|
| - "$ref": "ComponentTransform"
|
| + "$ref": "StreamLocation"
|
| },
|
| "type": "array"
|
| },
|
| - "componentSource": {
|
| - "description": "Collections produced and consumed by component transforms of this stage.",
|
| + "keyRanges": {
|
| + "description": "The key ranges processed by the computation.",
|
| "items": {
|
| - "$ref": "ComponentSource"
|
| + "$ref": "KeyRangeLocation"
|
| },
|
| "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"
|
| },
|
| - "LogBucket": {
|
| - "description": "Bucket of values for Distribution's logarithmic histogram.",
|
| - "id": "LogBucket",
|
| + "RuntimeEnvironment": {
|
| + "description": "The environment values to set at runtime.",
|
| + "id": "RuntimeEnvironment",
|
| "properties": {
|
| - "count": {
|
| - "description": "Number of values in this bucket.",
|
| - "format": "int64",
|
| + "machineType": {
|
| + "description": "The machine type to use for the job. Defaults to the value from the\ntemplate if not specified.",
|
| "type": "string"
|
| },
|
| - "log": {
|
| - "description": "floor(log2(value)); defined to be zero for nonpositive values.\n log(-1) = 0\n log(0) = 0\n log(1) = 0\n log(2) = 1\n log(3) = 1\n log(4) = 2\n log(5) = 2",
|
| + "zone": {
|
| + "description": "The Compute Engine [availability\nzone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)\nfor launching worker instances to run your pipeline.",
|
| + "type": "string"
|
| + },
|
| + "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"
|
| + },
|
| + "serviceAccountEmail": {
|
| + "description": "The email address of the service account to run the job as.",
|
| + "type": "string"
|
| + },
|
| + "tempLocation": {
|
| + "description": "The Cloud Storage path to use for temporary files.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
|
| + "type": "string"
|
| + },
|
| + "bypassTempDirValidation": {
|
| + "description": "Whether to bypass the safety checks for the job's temporary directory.\nUse with caution.",
|
| + "type": "boolean"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SendWorkerMessagesRequest": {
|
| - "description": "A request for sending worker messages to the service.",
|
| - "id": "SendWorkerMessagesRequest",
|
| + "StreamingSideInputLocation": {
|
| + "description": "Identifies the location of a streaming side input.",
|
| + "id": "StreamingSideInputLocation",
|
| "properties": {
|
| - "workerMessages": {
|
| - "description": "The WorkerMessages to send.",
|
| - "items": {
|
| - "$ref": "WorkerMessage"
|
| - },
|
| - "type": "array"
|
| + "tag": {
|
| + "description": "Identifies the particular side input within the streaming Dataflow job.",
|
| + "type": "string"
|
| },
|
| - "location": {
|
| - "description": "The location which contains the job",
|
| + "stateFamily": {
|
| + "description": "Identifies the state family where this side input is stored.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceSplitShard": {
|
| - "description": "DEPRECATED in favor of DerivedSource.",
|
| - "id": "SourceSplitShard",
|
| + "MountedDataDisk": {
|
| + "description": "Describes mounted data disk.",
|
| + "id": "MountedDataDisk",
|
| + "properties": {
|
| + "dataDisk": {
|
| + "description": "The name of the data disk.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "LaunchTemplateResponse": {
|
| + "description": "Response to the request to launch a template.",
|
| + "id": "LaunchTemplateResponse",
|
| + "properties": {
|
| + "job": {
|
| + "$ref": "Job",
|
| + "description": "The job that was launched, if the request was not a dry run and\nthe job was successfully launched."
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "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": {
|
| "$ref": "Source",
|
| - "description": "DEPRECATED"
|
| + "description": "Specification of the source."
|
| },
|
| "derivationMode": {
|
| - "description": "DEPRECATED",
|
| + "description": "What source to base the produced source on (if any).",
|
| "enum": [
|
| "SOURCE_DERIVATION_MODE_UNKNOWN",
|
| "SOURCE_DERIVATION_MODE_INDEPENDENT",
|
| @@ -2544,2412 +2660,2360 @@
|
| },
|
| "type": "object"
|
| },
|
| - "CPUTime": {
|
| - "description": "Modeled after information exposed by /proc/stat.",
|
| - "id": "CPUTime",
|
| + "DynamicSourceSplit": {
|
| + "description": "When a task splits using WorkItemStatus.dynamic_source_split, this\nmessage describes the two parts of the split relative to the\ndescription of the current task's input.",
|
| + "id": "DynamicSourceSplit",
|
| "properties": {
|
| - "timestamp": {
|
| - "description": "Timestamp of the measurement.",
|
| - "format": "google-datetime",
|
| - "type": "string"
|
| - },
|
| - "totalMs": {
|
| - "description": "Total active CPU time across all cores (ie., non-idle) in milliseconds\nsince start-up.",
|
| - "format": "uint64",
|
| - "type": "string"
|
| + "residual": {
|
| + "$ref": "DerivedSource",
|
| + "description": "Residual part (returned to the pool of work).\nSpecified relative to the previously-current source."
|
| },
|
| - "rate": {
|
| - "description": "Average CPU utilization rate (% non-idle cpu / second) since previous\nsample.",
|
| - "format": "double",
|
| - "type": "number"
|
| + "primary": {
|
| + "$ref": "DerivedSource",
|
| + "description": "Primary part (continued to be processed by worker).\nSpecified relative to the previously-current source.\nBecomes current."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Environment": {
|
| - "description": "Describes the environment in which a Dataflow Job runs.",
|
| - "id": "Environment",
|
| + "Job": {
|
| + "description": "Defines a job to be run by the Cloud Dataflow service.",
|
| + "id": "Job",
|
| "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"
|
| - },
|
| - "tempStoragePrefix": {
|
| - "description": "The prefix of the resources the system should use for temporary\nstorage. The system will append the suffix \"/temp-{JOBNAME} to\nthis resource prefix, where {JOBNAME} is the value of the\njob_name field. The resulting bucket and object prefix is used\nas the prefix of the resources used to store temporary data\nneeded during the job execution. NOTE: This will override the\nvalue in taskrunner_settings.\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
|
| + "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"
|
| },
|
| - "workerPools": {
|
| - "description": "The worker pools. At least one \"harness\" worker pool must be\nspecified in order for the job to have workers.",
|
| + "steps": {
|
| + "description": "The top-level steps that constitute the entire job.",
|
| "items": {
|
| - "$ref": "WorkerPool"
|
| + "$ref": "Step"
|
| },
|
| "type": "array"
|
| },
|
| - "dataset": {
|
| - "description": "The dataset for the current project where various workflow\nrelated tables are stored.\n\nThe supported resource type is:\n\nGoogle BigQuery:\n bigquery.googleapis.com/{dataset}",
|
| + "replacedByJobId": {
|
| + "description": "If another job is an update of this job (and thus, this job is in\n`JOB_STATE_UPDATED`), this field contains the ID of that job.",
|
| "type": "string"
|
| },
|
| - "experiments": {
|
| - "description": "The list of experiments to enable.",
|
| - "items": {
|
| - "type": "string"
|
| - },
|
| - "type": "array"
|
| + "id": {
|
| + "description": "The unique ID of this job.\n\nThis field is set by the Cloud Dataflow service when the Job is\ncreated, and is immutable for the life of the job.",
|
| + "type": "string"
|
| },
|
| - "internalExperiments": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object. Contains field @type with type URL.",
|
| - "type": "any"
|
| - },
|
| - "description": "Experimental settings.",
|
| - "type": "object"
|
| + "executionInfo": {
|
| + "$ref": "JobExecutionInfo",
|
| + "description": "Deprecated."
|
| },
|
| - "version": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| + "currentState": {
|
| + "description": "The current state of the job.\n\nJobs are created in the `JOB_STATE_STOPPED` state unless otherwise\nspecified.\n\nA job in the `JOB_STATE_RUNNING` state may asynchronously enter a\nterminal state. After a job has reached a terminal state, no\nfurther state updates may be made.\n\nThis field may be mutated by the Cloud Dataflow service;\ncallers cannot mutate it.",
|
| + "enum": [
|
| + "JOB_STATE_UNKNOWN",
|
| + "JOB_STATE_STOPPED",
|
| + "JOB_STATE_RUNNING",
|
| + "JOB_STATE_DONE",
|
| + "JOB_STATE_FAILED",
|
| + "JOB_STATE_CANCELLED",
|
| + "JOB_STATE_UPDATED",
|
| + "JOB_STATE_DRAINING",
|
| + "JOB_STATE_DRAINED",
|
| + "JOB_STATE_PENDING",
|
| + "JOB_STATE_CANCELLING"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The job's run state isn't specified.",
|
| + "`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
|
| + "`JOB_STATE_RUNNING` indicates that the job is currently running.",
|
| + "`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
|
| + "`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
|
| + "`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
|
| + "`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
|
| + "`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
|
| + "`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
|
| + "'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
|
| + "'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
|
| + ],
|
| + "type": "string"
|
| + },
|
| + "location": {
|
| + "description": "The location that contains this job.",
|
| + "type": "string"
|
| + },
|
| + "currentStateTime": {
|
| + "description": "The timestamp associated with the current state.",
|
| + "format": "google-datetime",
|
| + "type": "string"
|
| + },
|
| + "transformNameMapping": {
|
| + "additionalProperties": {
|
| + "type": "string"
|
| },
|
| - "description": "A structure describing which components and their versions of the service\nare required in order to run the job.",
|
| + "description": "The map of transform name prefixes of the job to be replaced to the\ncorresponding name prefixes of the new job.",
|
| "type": "object"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "StreamingComputationTask": {
|
| - "description": "A task which describes what action should be performed for the specified\nstreaming computation ranges.",
|
| - "id": "StreamingComputationTask",
|
| - "properties": {
|
| - "computationRanges": {
|
| - "description": "Contains ranges of a streaming computation this task should apply to.",
|
| - "items": {
|
| - "$ref": "StreamingComputationRanges"
|
| + },
|
| + "labels": {
|
| + "additionalProperties": {
|
| + "type": "string"
|
| },
|
| - "type": "array"
|
| + "description": "User-defined labels for this job.\n\nThe labels map can contain no more than 64 entries. Entries of the labels\nmap are UTF8 strings that comply with the following restrictions:\n\n* Keys must conform to regexp: \\p{Ll}\\p{Lo}{0,62}\n* Values must conform to regexp: [\\p{Ll}\\p{Lo}\\p{N}_-]{0,63}\n* Both keys and values are additionally constrained to be <= 128 bytes in\nsize.",
|
| + "type": "object"
|
| },
|
| - "dataDisks": {
|
| - "description": "Describes the set of data disks this task should apply to.",
|
| + "environment": {
|
| + "$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"
|
| + },
|
| + "stageStates": {
|
| + "description": "This field may be mutated by the Cloud Dataflow service;\ncallers cannot mutate it.",
|
| "items": {
|
| - "$ref": "MountedDataDisk"
|
| + "$ref": "ExecutionStageState"
|
| },
|
| "type": "array"
|
| },
|
| - "taskType": {
|
| - "description": "A type of streaming computation task.",
|
| + "type": {
|
| + "description": "The type of Cloud Dataflow job.",
|
| "enum": [
|
| - "STREAMING_COMPUTATION_TASK_UNKNOWN",
|
| - "STREAMING_COMPUTATION_TASK_STOP",
|
| - "STREAMING_COMPUTATION_TASK_START"
|
| + "JOB_TYPE_UNKNOWN",
|
| + "JOB_TYPE_BATCH",
|
| + "JOB_TYPE_STREAMING"
|
| ],
|
| "enumDescriptions": [
|
| - "The streaming computation task is unknown, or unspecified.",
|
| - "Stop processing specified streaming computation range(s).",
|
| - "Start processing specified streaming computation range(s)."
|
| + "The type of the job is unspecified, or unknown.",
|
| + "A batch job with a well-defined end point: data is read, data is\nprocessed, data is written, and the job is done.",
|
| + "A continuously streaming job with no end: data is read,\nprocessed, and written continuously."
|
| ],
|
| "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "SendDebugCaptureRequest": {
|
| - "description": "Request to send encoded debug information.",
|
| - "id": "SendDebugCaptureRequest",
|
| - "properties": {
|
| - "componentId": {
|
| - "description": "The internal component id for which debug information is sent.",
|
| + },
|
| + "projectId": {
|
| + "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| "type": "string"
|
| },
|
| - "workerId": {
|
| - "description": "The worker id, i.e., VM hostname.",
|
| + "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"
|
| },
|
| - "location": {
|
| - "description": "The location which contains the job specified by job_id.",
|
| + "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": [
|
| + "JOB_STATE_UNKNOWN",
|
| + "JOB_STATE_STOPPED",
|
| + "JOB_STATE_RUNNING",
|
| + "JOB_STATE_DONE",
|
| + "JOB_STATE_FAILED",
|
| + "JOB_STATE_CANCELLED",
|
| + "JOB_STATE_UPDATED",
|
| + "JOB_STATE_DRAINING",
|
| + "JOB_STATE_DRAINED",
|
| + "JOB_STATE_PENDING",
|
| + "JOB_STATE_CANCELLING"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The job's run state isn't specified.",
|
| + "`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
|
| + "`JOB_STATE_RUNNING` indicates that the job is currently running.",
|
| + "`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
|
| + "`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
|
| + "`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
|
| + "`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
|
| + "`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
|
| + "`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
|
| + "'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
|
| + "'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
|
| + ],
|
| "type": "string"
|
| },
|
| - "data": {
|
| - "description": "The encoded debug information.",
|
| + "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"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "GetDebugConfigResponse": {
|
| - "description": "Response to a get debug configuration request.",
|
| - "id": "GetDebugConfigResponse",
|
| + "SourceOperationResponse": {
|
| + "description": "The result of a SourceOperationRequest, specified in\nReportWorkItemStatusRequest.source_operation when the work item\nis completed.",
|
| + "id": "SourceOperationResponse",
|
| "properties": {
|
| - "config": {
|
| - "description": "The encoded debug configuration for the requested component.",
|
| - "type": "string"
|
| + "getMetadata": {
|
| + "$ref": "SourceGetMetadataResponse",
|
| + "description": "A response to a request to get metadata about a source."
|
| + },
|
| + "split": {
|
| + "$ref": "SourceSplitResponse",
|
| + "description": "A response to a request to split a source."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ComponentTransform": {
|
| - "description": "Description of a transform executed as part of an execution stage.",
|
| - "id": "ComponentTransform",
|
| + "SideInputInfo": {
|
| + "description": "Information about a side input of a DoFn or an input of a SeqDoFn.",
|
| + "id": "SideInputInfo",
|
| "properties": {
|
| - "originalTransform": {
|
| - "description": "User name for the original user transform with which this transform is\nmost closely associated.",
|
| + "tag": {
|
| + "description": "The id of the tag the user code will access this side input by;\nthis should correspond to the tag of some MultiOutputInfo.",
|
| "type": "string"
|
| },
|
| - "name": {
|
| - "description": "Dataflow service generated name for this source.",
|
| - "type": "string"
|
| + "kind": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "How to interpret the source element(s) as a side input value.",
|
| + "type": "object"
|
| },
|
| - "userName": {
|
| - "description": "Human-readable name for this transform; may be user or system generated.",
|
| - "type": "string"
|
| + "sources": {
|
| + "description": "The source(s) to read element(s) from to get the value of this side input.\nIf more than one source, then the elements are taken from the\nsources, in the specified order if order matters.\nAt least one source is required.",
|
| + "items": {
|
| + "$ref": "Source"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamingSetupTask": {
|
| - "description": "A task which initializes part of a streaming Dataflow job.",
|
| - "id": "StreamingSetupTask",
|
| + "SendDebugCaptureResponse": {
|
| + "description": "Response to a send capture request.\nnothing",
|
| + "id": "SendDebugCaptureResponse",
|
| + "properties": {},
|
| + "type": "object"
|
| + },
|
| + "WriteInstruction": {
|
| + "description": "An instruction that writes records.\nTakes one input, produces no outputs.",
|
| + "id": "WriteInstruction",
|
| "properties": {
|
| - "receiveWorkPort": {
|
| - "description": "The TCP port on which the worker should listen for messages from\nother streaming computation workers.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - },
|
| - "streamingComputationTopology": {
|
| - "$ref": "TopologyConfig",
|
| - "description": "The global topology of the streaming Dataflow job."
|
| + "input": {
|
| + "$ref": "InstructionInput",
|
| + "description": "The input."
|
| },
|
| - "drain": {
|
| - "description": "The user has requested drain.",
|
| - "type": "boolean"
|
| + "sink": {
|
| + "$ref": "Sink",
|
| + "description": "The sink to write to."
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "ConcatPosition": {
|
| + "description": "A position that encapsulates an inner position and an index for the inner\nposition. A ConcatPosition can be used by a reader of a source that\nencapsulates a set of other sources.",
|
| + "id": "ConcatPosition",
|
| + "properties": {
|
| + "position": {
|
| + "$ref": "Position",
|
| + "description": "Position within the inner source."
|
| },
|
| - "workerHarnessPort": {
|
| - "description": "The TCP port used by the worker to communicate with the Dataflow\nworker harness.",
|
| + "index": {
|
| + "description": "Index of the inner source.",
|
| "format": "int32",
|
| "type": "integer"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "PubsubLocation": {
|
| - "description": "Identifies a pubsub location to use for transferring data into or\nout of a streaming Dataflow job.",
|
| - "id": "PubsubLocation",
|
| + "CounterStructuredNameAndMetadata": {
|
| + "description": "A single message which encapsulates structured name and metadata for a given\ncounter.",
|
| + "id": "CounterStructuredNameAndMetadata",
|
| "properties": {
|
| - "subscription": {
|
| - "description": "A pubsub subscription, in the form of\n\"pubsub.googleapis.com/subscriptions/<project-id>/<subscription-name>\"",
|
| - "type": "string"
|
| - },
|
| - "dropLateData": {
|
| - "description": "Indicates whether the pipeline allows late-arriving data.",
|
| - "type": "boolean"
|
| - },
|
| - "trackingSubscription": {
|
| - "description": "If set, specifies the pubsub subscription that will be used for tracking\ncustom time timestamps for watermark estimation.",
|
| - "type": "string"
|
| - },
|
| - "withAttributes": {
|
| - "description": "If true, then the client has requested to get pubsub attributes.",
|
| - "type": "boolean"
|
| - },
|
| - "idLabel": {
|
| - "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"
|
| + "metadata": {
|
| + "$ref": "CounterMetadata",
|
| + "description": "Metadata associated with a counter"
|
| },
|
| - "topic": {
|
| - "description": "A pubsub topic, in the form of\n\"pubsub.googleapis.com/topics/<project-id>/<topic-name>\"",
|
| + "name": {
|
| + "$ref": "CounterStructuredName",
|
| + "description": "Structured name of the counter."
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "AutoscalingSettings": {
|
| + "description": "Settings for WorkerPool autoscaling.",
|
| + "id": "AutoscalingSettings",
|
| + "properties": {
|
| + "algorithm": {
|
| + "description": "The algorithm to use for autoscaling.",
|
| + "enum": [
|
| + "AUTOSCALING_ALGORITHM_UNKNOWN",
|
| + "AUTOSCALING_ALGORITHM_NONE",
|
| + "AUTOSCALING_ALGORITHM_BASIC"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The algorithm is unknown, or unspecified.",
|
| + "Disable autoscaling.",
|
| + "Increase worker count over time to reduce job execution time."
|
| + ],
|
| "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"
|
| + "maxNumWorkers": {
|
| + "description": "The maximum number of workers to cap scaling at.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerHealthReport": {
|
| - "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",
|
| + "StreamingComputationRanges": {
|
| + "description": "Describes full or partial data disk assignment information of the computation\nranges.",
|
| + "id": "StreamingComputationRanges",
|
| "properties": {
|
| - "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",
|
| + "computationId": {
|
| + "description": "The ID of the computation.",
|
| "type": "string"
|
| },
|
| - "vmIsHealthy": {
|
| - "description": "Whether the VM is healthy.",
|
| - "type": "boolean"
|
| - },
|
| - "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.",
|
| + "rangeAssignments": {
|
| + "description": "Data disk assignments for ranges from this computation.",
|
| "items": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "type": "object"
|
| + "$ref": "KeyRangeDataDiskAssignment"
|
| },
|
| "type": "array"
|
| - },
|
| - "vmStartupTime": {
|
| - "description": "The time the VM was booted.",
|
| - "format": "google-datetime",
|
| - "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "JobMessage": {
|
| - "description": "A particular message pertaining to a Dataflow job.",
|
| - "id": "JobMessage",
|
| + "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": {
|
| - "messageImportance": {
|
| - "description": "Importance level of the message.",
|
| - "enum": [
|
| - "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
|
| - "JOB_MESSAGE_DEBUG",
|
| - "JOB_MESSAGE_DETAILED",
|
| - "JOB_MESSAGE_BASIC",
|
| - "JOB_MESSAGE_WARNING",
|
| - "JOB_MESSAGE_ERROR"
|
| - ],
|
| - "enumDescriptions": [
|
| - "The message importance isn't specified, or is unknown.",
|
| - "The message is at the 'debug' level: typically only useful for\nsoftware engineers working on the code the job is running.\nTypically, Dataflow pipeline runners do not display log messages\nat this level by default.",
|
| - "The message is at the 'detailed' level: somewhat verbose, but\npotentially useful to users. Typically, Dataflow pipeline\nrunners do not display log messages at this level by default.\nThese messages are displayed by default in the Dataflow\nmonitoring UI.",
|
| - "The message is at the 'basic' level: useful for keeping\ntrack of the execution of a Dataflow pipeline. Typically,\nDataflow pipeline runners display log messages at this level by\ndefault, and these messages are displayed by default in the\nDataflow monitoring UI.",
|
| - "The message is at the 'warning' level: indicating a condition\npertaining to a job which may require human intervention.\nTypically, Dataflow pipeline runners display log messages at this\nlevel by default, and these messages are displayed by default in\nthe Dataflow monitoring UI.",
|
| - "The message is at the 'error' level: indicating a condition\npreventing a job from succeeding. Typically, Dataflow pipeline\nrunners display log messages at this level by default, and these\nmessages are displayed by default in the Dataflow monitoring UI."
|
| - ],
|
| - "type": "string"
|
| - },
|
| - "messageText": {
|
| - "description": "The text of the message.",
|
| + "name": {
|
| + "description": "Dataflow service generated name for this stage.",
|
| "type": "string"
|
| },
|
| - "time": {
|
| - "description": "The timestamp of the message.",
|
| - "format": "google-datetime",
|
| - "type": "string"
|
| + "inputSource": {
|
| + "description": "Input sources for this stage.",
|
| + "items": {
|
| + "$ref": "StageSource"
|
| + },
|
| + "type": "array"
|
| },
|
| "id": {
|
| - "description": "Deprecated.",
|
| + "description": "Dataflow service generated id for this stage.",
|
| "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "ParameterMetadata": {
|
| - "description": "Metadata for a specific parameter.",
|
| - "id": "ParameterMetadata",
|
| - "properties": {
|
| - "regexes": {
|
| - "description": "Optional. Regexes that the parameter must match.",
|
| + },
|
| + "componentTransform": {
|
| + "description": "Transforms that comprise this execution stage.",
|
| "items": {
|
| - "type": "string"
|
| + "$ref": "ComponentTransform"
|
| },
|
| "type": "array"
|
| },
|
| - "label": {
|
| - "description": "Required. The label to display for the parameter.",
|
| - "type": "string"
|
| + "componentSource": {
|
| + "description": "Collections produced and consumed by component transforms of this stage.",
|
| + "items": {
|
| + "$ref": "ComponentSource"
|
| + },
|
| + "type": "array"
|
| },
|
| - "helpText": {
|
| - "description": "Required. The help text to display for the parameter.",
|
| + "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"
|
| },
|
| - "isOptional": {
|
| - "description": "Optional. Whether the parameter is optional. Defaults to false.",
|
| - "type": "boolean"
|
| - },
|
| - "name": {
|
| - "description": "Required. The name of the parameter.",
|
| - "type": "string"
|
| + "outputSource": {
|
| + "description": "Output sources for this stage.",
|
| + "items": {
|
| + "$ref": "StageSource"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "MultiOutputInfo": {
|
| - "description": "Information about an output of a multi-output DoFn.",
|
| - "id": "MultiOutputInfo",
|
| + "LogBucket": {
|
| + "description": "Bucket of values for Distribution's logarithmic histogram.",
|
| + "id": "LogBucket",
|
| "properties": {
|
| - "tag": {
|
| - "description": "The id of the tag the user code will emit to this output by; this\nshould correspond to the tag of some SideInputInfo.",
|
| + "log": {
|
| + "description": "floor(log2(value)); defined to be zero for nonpositive values.\n log(-1) = 0\n log(0) = 0\n log(1) = 0\n log(2) = 1\n log(3) = 1\n log(4) = 2\n log(5) = 2",
|
| + "format": "int32",
|
| + "type": "integer"
|
| + },
|
| + "count": {
|
| + "description": "Number of values in this bucket.",
|
| + "format": "int64",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceSplitRequest": {
|
| - "description": "Represents the operation to split a high-level Source specification\ninto bundles (parts for parallel processing).\n\nAt a high level, splitting of a source into bundles happens as follows:\nSourceSplitRequest is applied to the source. If it returns\nSOURCE_SPLIT_OUTCOME_USE_CURRENT, no further splitting happens and the source\nis used \"as is\". Otherwise, splitting is applied recursively to each\nproduced DerivedSource.\n\nAs an optimization, for any Source, if its does_not_need_splitting is\ntrue, the framework assumes that splitting this source would return\nSOURCE_SPLIT_OUTCOME_USE_CURRENT, and doesn't initiate a SourceSplitRequest.\nThis applies both to the initial source being split and to bundles\nproduced from it.",
|
| - "id": "SourceSplitRequest",
|
| + "SendWorkerMessagesRequest": {
|
| + "description": "A request for sending worker messages to the service.",
|
| + "id": "SendWorkerMessagesRequest",
|
| "properties": {
|
| - "options": {
|
| - "$ref": "SourceSplitOptions",
|
| - "description": "Hints for tuning the splitting process."
|
| + "workerMessages": {
|
| + "description": "The WorkerMessages to send.",
|
| + "items": {
|
| + "$ref": "WorkerMessage"
|
| + },
|
| + "type": "array"
|
| },
|
| - "source": {
|
| - "$ref": "Source",
|
| - "description": "Specification of the source to be split."
|
| + "location": {
|
| + "description": "The location which contains the job",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceGetMetadataResponse": {
|
| - "description": "The result of a SourceGetMetadataOperation.",
|
| - "id": "SourceGetMetadataResponse",
|
| + "SourceSplitShard": {
|
| + "description": "DEPRECATED in favor of DerivedSource.",
|
| + "id": "SourceSplitShard",
|
| "properties": {
|
| - "metadata": {
|
| - "$ref": "SourceMetadata",
|
| - "description": "The computed metadata."
|
| + "derivationMode": {
|
| + "description": "DEPRECATED",
|
| + "enum": [
|
| + "SOURCE_DERIVATION_MODE_UNKNOWN",
|
| + "SOURCE_DERIVATION_MODE_INDEPENDENT",
|
| + "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
|
| + "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The source derivation is unknown, or unspecified.",
|
| + "Produce a completely independent Source with no base.",
|
| + "Produce a Source based on the Source being split.",
|
| + "Produce a Source based on the base of the Source being split."
|
| + ],
|
| + "type": "string"
|
| + },
|
| + "source": {
|
| + "$ref": "Source",
|
| + "description": "DEPRECATED"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "AutoscalingEvent": {
|
| - "description": "A structured message reporting an autoscaling decision made by the Dataflow\nservice.",
|
| - "id": "AutoscalingEvent",
|
| + "CPUTime": {
|
| + "description": "Modeled after information exposed by /proc/stat.",
|
| + "id": "CPUTime",
|
| "properties": {
|
| - "time": {
|
| - "description": "The time this event was emitted to indicate a new target or current\nnum_workers value.",
|
| - "format": "google-datetime",
|
| - "type": "string"
|
| - },
|
| - "description": {
|
| - "$ref": "StructuredMessage",
|
| - "description": "A message describing why the system decided to adjust the current\nnumber of workers, why it failed, or why the system decided to\nnot make any changes to the number of workers."
|
| - },
|
| - "eventType": {
|
| - "description": "The type of autoscaling event to report.",
|
| - "enum": [
|
| - "TYPE_UNKNOWN",
|
| - "TARGET_NUM_WORKERS_CHANGED",
|
| - "CURRENT_NUM_WORKERS_CHANGED",
|
| - "ACTUATION_FAILURE",
|
| - "NO_CHANGE"
|
| - ],
|
| - "enumDescriptions": [
|
| - "Default type for the enum. Value should never be returned.",
|
| - "The TARGET_NUM_WORKERS_CHANGED type should be used when the target\nworker pool size has changed at the start of an actuation. An event\nshould always be specified as TARGET_NUM_WORKERS_CHANGED if it reflects\na change in the target_num_workers.",
|
| - "The CURRENT_NUM_WORKERS_CHANGED type should be used when actual worker\npool size has been changed, but the target_num_workers has not changed.",
|
| - "The ACTUATION_FAILURE type should be used when we want to report\nan error to the user indicating why the current number of workers\nin the pool could not be changed.\nDisplayed in the current status and history widgets.",
|
| - "Used when we want to report to the user a reason why we are\nnot currently adjusting the number of workers.\nShould specify both target_num_workers, current_num_workers and a\ndecision_message."
|
| - ],
|
| - "type": "string"
|
| - },
|
| - "targetNumWorkers": {
|
| - "description": "The target number of workers the worker pool wants to resize to use.",
|
| - "format": "int64",
|
| - "type": "string"
|
| - },
|
| - "currentNumWorkers": {
|
| - "description": "The current number of workers the job has.",
|
| - "format": "int64",
|
| + "totalMs": {
|
| + "description": "Total active CPU time across all cores (ie., non-idle) in milliseconds\nsince start-up.",
|
| + "format": "uint64",
|
| "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "MetricShortId": {
|
| - "description": "The metric short id is returned to the user alongside an offset into\nReportWorkItemStatusRequest",
|
| - "id": "MetricShortId",
|
| - "properties": {
|
| - "metricIndex": {
|
| - "description": "The index of the corresponding metric in\nthe ReportWorkItemStatusRequest. Required.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| },
|
| - "shortId": {
|
| - "description": "The service-generated short identifier for the metric.",
|
| - "format": "int64",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "ShellTask": {
|
| - "description": "A task which consists of a shell command for the worker to execute.",
|
| - "id": "ShellTask",
|
| - "properties": {
|
| - "exitCode": {
|
| - "description": "Exit code for the task.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "rate": {
|
| + "description": "Average CPU utilization rate (% non-idle cpu / second) since previous\nsample.",
|
| + "format": "double",
|
| + "type": "number"
|
| },
|
| - "command": {
|
| - "description": "The shell command to run.",
|
| + "timestamp": {
|
| + "description": "Timestamp of the measurement.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "TaskRunnerSettings": {
|
| - "description": "Taskrunner configuration settings.",
|
| - "id": "TaskRunnerSettings",
|
| + "Environment": {
|
| + "description": "Describes the environment in which a Dataflow Job runs.",
|
| + "id": "Environment",
|
| "properties": {
|
| - "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"
|
| + "userAgent": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "A description of the process that generated the request.",
|
| + "type": "object"
|
| },
|
| - "alsologtostderr": {
|
| - "description": "Whether to also send taskrunner log info to stderr.",
|
| - "type": "boolean"
|
| + "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"
|
| },
|
| - "taskGroup": {
|
| - "description": "The UNIX group ID on the worker VM to use for tasks launched by\ntaskrunner; e.g. \"wheel\".",
|
| + "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"
|
| },
|
| - "harnessCommand": {
|
| - "description": "The command to launch the worker harness.",
|
| + "tempStoragePrefix": {
|
| + "description": "The prefix of the resources the system should use for temporary\nstorage. The system will append the suffix \"/temp-{JOBNAME} to\nthis resource prefix, where {JOBNAME} is the value of the\njob_name field. The resulting bucket and object prefix is used\nas the prefix of the resources used to store temporary data\nneeded during the job execution. NOTE: This will override the\nvalue in taskrunner_settings.\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
|
| "type": "string"
|
| },
|
| - "logDir": {
|
| - "description": "The directory on the VM to store logs.",
|
| - "type": "string"
|
| + "workerPools": {
|
| + "description": "The worker pools. At least one \"harness\" worker pool must be\nspecified in order for the job to have workers.",
|
| + "items": {
|
| + "$ref": "WorkerPool"
|
| + },
|
| + "type": "array"
|
| },
|
| - "dataflowApiVersion": {
|
| - "description": "The API version of endpoint, e.g. \"v1b3\"",
|
| + "dataset": {
|
| + "description": "The dataset for the current project where various workflow\nrelated tables are stored.\n\nThe supported resource type is:\n\nGoogle BigQuery:\n bigquery.googleapis.com/{dataset}",
|
| "type": "string"
|
| },
|
| - "oauthScopes": {
|
| - "description": "The OAuth2 scopes to be requested by the taskrunner in order to\naccess the Cloud Dataflow API.",
|
| + "experiments": {
|
| + "description": "The list of experiments to enable.",
|
| "items": {
|
| "type": "string"
|
| },
|
| "type": "array"
|
| },
|
| - "streamingWorkerMainClass": {
|
| - "description": "The streaming worker main class name.",
|
| - "type": "string"
|
| - },
|
| - "logUploadLocation": {
|
| - "description": "Indicates where to put logs. If this is not specified, the logs\nwill not be uploaded.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
|
| - "type": "string"
|
| - },
|
| - "workflowFileName": {
|
| - "description": "The file to store the workflow in.",
|
| - "type": "string"
|
| - },
|
| - "commandlinesFileName": {
|
| - "description": "The file to store preprocessing commands in.",
|
| - "type": "string"
|
| - },
|
| - "languageHint": {
|
| - "description": "The suggested backend language.",
|
| - "type": "string"
|
| + "version": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "A structure describing which components and their versions of the service\nare required in order to run the job.",
|
| + "type": "object"
|
| },
|
| - "baseTaskDir": {
|
| - "description": "The location on the worker for task-specific subdirectories.",
|
| - "type": "string"
|
| + "internalExperiments": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object. Contains field @type with type URL.",
|
| + "type": "any"
|
| + },
|
| + "description": "Experimental settings.",
|
| + "type": "object"
|
| },
|
| - "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}",
|
| + "serviceAccountEmail": {
|
| + "description": "Identity to run virtual machines as. Defaults to the default account.",
|
| "type": "string"
|
| - },
|
| - "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": "object"
|
| + },
|
| + "StreamingComputationTask": {
|
| + "description": "A task which describes what action should be performed for the specified\nstreaming computation ranges.",
|
| + "id": "StreamingComputationTask",
|
| + "properties": {
|
| + "taskType": {
|
| + "description": "A type of streaming computation task.",
|
| + "enum": [
|
| + "STREAMING_COMPUTATION_TASK_UNKNOWN",
|
| + "STREAMING_COMPUTATION_TASK_STOP",
|
| + "STREAMING_COMPUTATION_TASK_START"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The streaming computation task is unknown, or unspecified.",
|
| + "Stop processing specified streaming computation range(s).",
|
| + "Start processing specified streaming computation range(s)."
|
| + ],
|
| "type": "string"
|
| },
|
| - "logToSerialconsole": {
|
| - "description": "Whether to send taskrunner log info to Google Compute Engine VM serial\nconsole.",
|
| - "type": "boolean"
|
| + "computationRanges": {
|
| + "description": "Contains ranges of a streaming computation this task should apply to.",
|
| + "items": {
|
| + "$ref": "StreamingComputationRanges"
|
| + },
|
| + "type": "array"
|
| },
|
| - "continueOnException": {
|
| - "description": "Whether to continue taskrunner if an exception is hit.",
|
| - "type": "boolean"
|
| + "dataDisks": {
|
| + "description": "Describes the set of data disks this task should apply to.",
|
| + "items": {
|
| + "$ref": "MountedDataDisk"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Position": {
|
| - "description": "Position defines a position within a collection of data. The value\ncan be either the end position, a key (used with ordered\ncollections), a byte offset, or a record index.",
|
| - "id": "Position",
|
| + "SendDebugCaptureRequest": {
|
| + "description": "Request to send encoded debug information.",
|
| + "id": "SendDebugCaptureRequest",
|
| "properties": {
|
| - "recordIndex": {
|
| - "description": "Position is a record index.",
|
| - "format": "int64",
|
| + "componentId": {
|
| + "description": "The internal component id for which debug information is sent.",
|
| "type": "string"
|
| },
|
| - "shufflePosition": {
|
| - "description": "CloudPosition is a base64 encoded BatchShufflePosition (with FIXED\nsharding).",
|
| + "workerId": {
|
| + "description": "The worker id, i.e., VM hostname.",
|
| "type": "string"
|
| },
|
| - "concatPosition": {
|
| - "$ref": "ConcatPosition",
|
| - "description": "CloudPosition is a concat position."
|
| - },
|
| - "byteOffset": {
|
| - "description": "Position is a byte offset.",
|
| - "format": "int64",
|
| + "location": {
|
| + "description": "The location which contains the job specified by job_id.",
|
| "type": "string"
|
| },
|
| - "end": {
|
| - "description": "Position is past all other positions. Also useful for the end\nposition of an unbounded range.",
|
| - "type": "boolean"
|
| - },
|
| - "key": {
|
| - "description": "Position is a string key, ordered lexicographically.",
|
| + "data": {
|
| + "description": "The encoded debug information.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SplitInt64": {
|
| - "description": "A representation of an int64, n, that is immune to precision loss when\nencoded in JSON.",
|
| - "id": "SplitInt64",
|
| + "GetDebugConfigResponse": {
|
| + "description": "Response to a get debug configuration request.",
|
| + "id": "GetDebugConfigResponse",
|
| "properties": {
|
| - "lowBits": {
|
| - "description": "The low order bits: n & 0xffffffff.",
|
| - "format": "uint32",
|
| - "type": "integer"
|
| - },
|
| - "highBits": {
|
| - "description": "The high order bits, including the sign: n >> 32.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "config": {
|
| + "description": "The encoded debug configuration for the requested component.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Source": {
|
| - "description": "A source that records can be read and decoded from.",
|
| - "id": "Source",
|
| + "ComponentTransform": {
|
| + "description": "Description of a transform executed as part of an execution stage.",
|
| + "id": "ComponentTransform",
|
| "properties": {
|
| - "metadata": {
|
| - "$ref": "SourceMetadata",
|
| - "description": "Optionally, metadata for this source can be supplied right away,\navoiding a SourceGetMetadataOperation roundtrip\n(see SourceOperationRequest).\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated."
|
| - },
|
| - "baseSpecs": {
|
| - "description": "While splitting, sources may specify the produced bundles\nas differences against another source, in order to save backend-side\nmemory and allow bigger jobs. For details, see SourceSplitRequest.\nTo support this use case, the full set of parameters of the source\nis logically obtained by taking the latest explicitly specified value\nof each parameter in the order:\nbase_specs (later items win), spec (overrides anything in base_specs).",
|
| - "items": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "type": "object"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "doesNotNeedSplitting": {
|
| - "description": "Setting this value to true hints to the framework that the source\ndoesn't need splitting, and using SourceSplitRequest on it would\nyield SOURCE_SPLIT_OUTCOME_USE_CURRENT.\n\nE.g. a file splitter may set this to true when splitting a single file\ninto a set of byte ranges of appropriate size, and set this\nto false when splitting a filepattern into individual files.\nHowever, for efficiency, a file splitter may decide to produce\nfile subranges directly from the filepattern to avoid a splitting\nround-trip.\n\nSee SourceSplitRequest for an overview of the splitting process.\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated.",
|
| - "type": "boolean"
|
| + "originalTransform": {
|
| + "description": "User name for the original user transform with which this transform is\nmost closely associated.",
|
| + "type": "string"
|
| },
|
| - "codec": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The codec to use to decode data read from the source.",
|
| - "type": "object"
|
| + "name": {
|
| + "description": "Dataflow service generated name for this source.",
|
| + "type": "string"
|
| },
|
| - "spec": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The source to read from, plus its parameters.",
|
| - "type": "object"
|
| + "userName": {
|
| + "description": "Human-readable name for this transform; may be user or system generated.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerPool": {
|
| - "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",
|
| + "StreamingSetupTask": {
|
| + "description": "A task which initializes part of a streaming Dataflow job.",
|
| + "id": "StreamingSetupTask",
|
| "properties": {
|
| - "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).",
|
| + "drain": {
|
| + "description": "The user has requested drain.",
|
| + "type": "boolean"
|
| + },
|
| + "workerHarnessPort": {
|
| + "description": "The TCP port used by the worker to communicate with the Dataflow\nworker harness.",
|
| "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.",
|
| + "receiveWorkPort": {
|
| + "description": "The TCP port on which the worker should listen for messages from\nother streaming computation workers.",
|
| "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.",
|
| + "streamingComputationTopology": {
|
| + "$ref": "TopologyConfig",
|
| + "description": "The global topology of the streaming Dataflow job."
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "PubsubLocation": {
|
| + "description": "Identifies a pubsub location to use for transferring data into or\nout of a streaming Dataflow job.",
|
| + "id": "PubsubLocation",
|
| + "properties": {
|
| + "trackingSubscription": {
|
| + "description": "If set, specifies the pubsub subscription that will be used for tracking\ncustom time timestamps for watermark estimation.",
|
| "type": "string"
|
| },
|
| - "packages": {
|
| - "description": "Packages to be installed on workers.",
|
| - "items": {
|
| - "$ref": "Package"
|
| - },
|
| - "type": "array"
|
| + "withAttributes": {
|
| + "description": "If true, then the client has requested to get pubsub attributes.",
|
| + "type": "boolean"
|
| },
|
| - "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."
|
| - ],
|
| + "idLabel": {
|
| + "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"
|
| },
|
| - "onHostMaintenance": {
|
| - "description": "The action to take on host maintenance, as defined by the Google\nCompute Engine API.",
|
| + "topic": {
|
| + "description": "A pubsub topic, in the form of\n\"pubsub.googleapis.com/topics/<project-id>/<topic-name>\"",
|
| "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.",
|
| + "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"
|
| },
|
| - "machineType": {
|
| - "description": "Machine type (e.g. \"n1-standard-1\"). If empty or unspecified, the\nservice will attempt to choose a reasonable default.",
|
| + "subscription": {
|
| + "description": "A pubsub subscription, in the form of\n\"pubsub.googleapis.com/subscriptions/<project-id>/<subscription-name>\"",
|
| "type": "string"
|
| },
|
| - "diskType": {
|
| - "description": "Type of root disk for VMs. If empty or unspecified, the service will\nattempt to choose a reasonable default.",
|
| + "dropLateData": {
|
| + "description": "Indicates whether the pipeline allows late-arriving data.",
|
| + "type": "boolean"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "WorkerHealthReport": {
|
| + "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": {
|
| + "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"
|
| },
|
| - "kind": {
|
| - "description": "The kind of the worker pool; currently only `harness` and `shuffle`\nare supported.",
|
| - "type": "string"
|
| + "vmIsHealthy": {
|
| + "description": "Whether the VM is healthy.",
|
| + "type": "boolean"
|
| },
|
| - "dataDisks": {
|
| - "description": "Data disks that are used by a VM in this workflow.",
|
| + "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": {
|
| - "$ref": "Disk"
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "type": "object"
|
| },
|
| "type": "array"
|
| },
|
| - "subnetwork": {
|
| - "description": "Subnetwork to which VMs will be assigned, if desired. Expected to be of\nthe form \"regions/REGION/subnetworks/SUBNETWORK\".",
|
| + "vmStartupTime": {
|
| + "description": "The time the VM was booted.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| - },
|
| - "ipConfiguration": {
|
| - "description": "Configuration for VM IPs.",
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "JobMessage": {
|
| + "description": "A particular message pertaining to a Dataflow job.",
|
| + "id": "JobMessage",
|
| + "properties": {
|
| + "messageImportance": {
|
| + "description": "Importance level of the message.",
|
| "enum": [
|
| - "WORKER_IP_UNSPECIFIED",
|
| - "WORKER_IP_PUBLIC",
|
| - "WORKER_IP_PRIVATE"
|
| + "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
|
| + "JOB_MESSAGE_DEBUG",
|
| + "JOB_MESSAGE_DETAILED",
|
| + "JOB_MESSAGE_BASIC",
|
| + "JOB_MESSAGE_WARNING",
|
| + "JOB_MESSAGE_ERROR"
|
| ],
|
| "enumDescriptions": [
|
| - "The configuration is unknown, or unspecified.",
|
| - "Workers should have public IP addresses.",
|
| - "Workers should have private IP addresses."
|
| + "The message importance isn't specified, or is unknown.",
|
| + "The message is at the 'debug' level: typically only useful for\nsoftware engineers working on the code the job is running.\nTypically, Dataflow pipeline runners do not display log messages\nat this level by default.",
|
| + "The message is at the 'detailed' level: somewhat verbose, but\npotentially useful to users. Typically, Dataflow pipeline\nrunners do not display log messages at this level by default.\nThese messages are displayed by default in the Dataflow\nmonitoring UI.",
|
| + "The message is at the 'basic' level: useful for keeping\ntrack of the execution of a Dataflow pipeline. Typically,\nDataflow pipeline runners display log messages at this level by\ndefault, and these messages are displayed by default in the\nDataflow monitoring UI.",
|
| + "The message is at the 'warning' level: indicating a condition\npertaining to a job which may require human intervention.\nTypically, Dataflow pipeline runners display log messages at this\nlevel by default, and these messages are displayed by default in\nthe Dataflow monitoring UI.",
|
| + "The message is at the 'error' level: indicating a condition\npreventing a job from succeeding. Typically, Dataflow pipeline\nrunners display log messages at this level by default, and these\nmessages are displayed by default in the Dataflow monitoring UI."
|
| ],
|
| "type": "string"
|
| },
|
| - "autoscalingSettings": {
|
| - "$ref": "AutoscalingSettings",
|
| - "description": "Settings for autoscaling of this WorkerPool."
|
| - },
|
| - "taskrunnerSettings": {
|
| - "$ref": "TaskRunnerSettings",
|
| - "description": "Settings passed through to Google Compute Engine workers when\nusing the standard Dataflow task runner. Users should ignore\nthis field."
|
| - },
|
| - "metadata": {
|
| - "additionalProperties": {
|
| - "type": "string"
|
| - },
|
| - "description": "Metadata to set on the Google Compute Engine VMs.",
|
| - "type": "object"
|
| + "messageText": {
|
| + "description": "The text of the message.",
|
| + "type": "string"
|
| },
|
| - "defaultPackageSet": {
|
| - "description": "The default package set to install. This allows the service to\nselect a default set of packages which are useful to worker\nharnesses written in a particular language.",
|
| - "enum": [
|
| - "DEFAULT_PACKAGE_SET_UNKNOWN",
|
| - "DEFAULT_PACKAGE_SET_NONE",
|
| - "DEFAULT_PACKAGE_SET_JAVA",
|
| - "DEFAULT_PACKAGE_SET_PYTHON"
|
| - ],
|
| - "enumDescriptions": [
|
| - "The default set of packages to stage is unknown, or unspecified.",
|
| - "Indicates that no packages should be staged at the worker unless\nexplicitly specified by the job.",
|
| - "Stage packages typically useful to workers written in Java.",
|
| - "Stage pacakges typically useful to workers written in Python."
|
| - ],
|
| + "time": {
|
| + "description": "The timestamp of the message.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| - "network": {
|
| - "description": "Network to which VMs will be assigned. If empty or unspecified,\nthe service will use the network \"default\".",
|
| + "id": {
|
| + "description": "Deprecated.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceOperationRequest": {
|
| - "description": "A work item that represents the different operations that can be\nperformed on a user-defined Source specification.",
|
| - "id": "SourceOperationRequest",
|
| + "ParameterMetadata": {
|
| + "description": "Metadata for a specific parameter.",
|
| + "id": "ParameterMetadata",
|
| "properties": {
|
| - "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"
|
| - },
|
| - "StructuredMessage": {
|
| - "description": "A rich message format, including a human readable string, a key for\nidentifying the message, and structured data associated with the message for\nprogrammatic consumption.",
|
| - "id": "StructuredMessage",
|
| - "properties": {
|
| - "messageKey": {
|
| - "description": "Idenfier for this message type. Used by external systems to\ninternationalize or personalize message.",
|
| + "helpText": {
|
| + "description": "Required. The help text to display for the parameter.",
|
| "type": "string"
|
| },
|
| - "messageText": {
|
| - "description": "Human-readable version of message.",
|
| + "isOptional": {
|
| + "description": "Optional. Whether the parameter is optional. Defaults to false.",
|
| + "type": "boolean"
|
| + },
|
| + "name": {
|
| + "description": "Required. The name of the parameter.",
|
| "type": "string"
|
| },
|
| - "parameters": {
|
| - "description": "The structured data associated with this message.",
|
| + "regexes": {
|
| + "description": "Optional. Regexes that the parameter must match.",
|
| "items": {
|
| - "$ref": "Parameter"
|
| + "type": "string"
|
| },
|
| "type": "array"
|
| + },
|
| + "label": {
|
| + "description": "Required. The label to display for the parameter.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkItem": {
|
| - "description": "WorkItem represents basic information about a WorkItem to be executed\nin the cloud.",
|
| - "id": "WorkItem",
|
| + "MultiOutputInfo": {
|
| + "description": "Information about an output of a multi-output DoFn.",
|
| + "id": "MultiOutputInfo",
|
| "properties": {
|
| - "initialReportIndex": {
|
| - "description": "The initial index to use when reporting the status of the WorkItem.",
|
| - "format": "int64",
|
| - "type": "string"
|
| - },
|
| - "streamingComputationTask": {
|
| - "$ref": "StreamingComputationTask",
|
| - "description": "Additional information for StreamingComputationTask WorkItems."
|
| - },
|
| - "shellTask": {
|
| - "$ref": "ShellTask",
|
| - "description": "Additional information for ShellTask WorkItems."
|
| - },
|
| - "jobId": {
|
| - "description": "Identifies the workflow job this WorkItem belongs to.",
|
| - "type": "string"
|
| - },
|
| - "id": {
|
| - "description": "Identifies this WorkItem.",
|
| - "format": "int64",
|
| - "type": "string"
|
| - },
|
| - "configuration": {
|
| - "description": "Work item-specific configuration as an opaque blob.",
|
| - "type": "string"
|
| - },
|
| - "mapTask": {
|
| - "$ref": "MapTask",
|
| - "description": "Additional information for MapTask WorkItems."
|
| - },
|
| - "seqMapTask": {
|
| - "$ref": "SeqMapTask",
|
| - "description": "Additional information for SeqMapTask WorkItems."
|
| - },
|
| - "packages": {
|
| - "description": "Any required packages that need to be fetched in order to execute\nthis WorkItem.",
|
| - "items": {
|
| - "$ref": "Package"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "projectId": {
|
| - "description": "Identifies the cloud project this WorkItem belongs to.",
|
| - "type": "string"
|
| - },
|
| - "streamingSetupTask": {
|
| - "$ref": "StreamingSetupTask",
|
| - "description": "Additional information for StreamingSetupTask WorkItems."
|
| - },
|
| - "reportStatusInterval": {
|
| - "description": "Recommended reporting interval.",
|
| - "format": "google-duration",
|
| - "type": "string"
|
| - },
|
| - "sourceOperationTask": {
|
| - "$ref": "SourceOperationRequest",
|
| - "description": "Additional information for source operation WorkItems."
|
| - },
|
| - "streamingConfigTask": {
|
| - "$ref": "StreamingConfigTask",
|
| - "description": "Additional information for StreamingConfigTask WorkItems."
|
| - },
|
| - "leaseExpireTime": {
|
| - "description": "Time when the lease on this Work will expire.",
|
| - "format": "google-datetime",
|
| + "tag": {
|
| + "description": "The id of the tag the user code will emit to this output by; this\nshould correspond to the tag of some SideInputInfo.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ResourceUtilizationReport": {
|
| - "description": "Worker metrics exported from workers. This contains resource utilization\nmetrics accumulated from a variety of sources. For more information, see\ngo/df-resource-signals.",
|
| - "id": "ResourceUtilizationReport",
|
| + "SourceSplitRequest": {
|
| + "description": "Represents the operation to split a high-level Source specification\ninto bundles (parts for parallel processing).\n\nAt a high level, splitting of a source into bundles happens as follows:\nSourceSplitRequest is applied to the source. If it returns\nSOURCE_SPLIT_OUTCOME_USE_CURRENT, no further splitting happens and the source\nis used \"as is\". Otherwise, splitting is applied recursively to each\nproduced DerivedSource.\n\nAs an optimization, for any Source, if its does_not_need_splitting is\ntrue, the framework assumes that splitting this source would return\nSOURCE_SPLIT_OUTCOME_USE_CURRENT, and doesn't initiate a SourceSplitRequest.\nThis applies both to the initial source being split and to bundles\nproduced from it.",
|
| + "id": "SourceSplitRequest",
|
| "properties": {
|
| - "cpuTime": {
|
| - "description": "CPU utilization samples.",
|
| - "items": {
|
| - "$ref": "CPUTime"
|
| - },
|
| - "type": "array"
|
| + "options": {
|
| + "$ref": "SourceSplitOptions",
|
| + "description": "Hints for tuning the splitting process."
|
| + },
|
| + "source": {
|
| + "$ref": "Source",
|
| + "description": "Specification of the source to be split."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ReportedParallelism": {
|
| - "description": "Represents the level of parallelism in a WorkItem's input,\nreported by the worker.",
|
| - "id": "ReportedParallelism",
|
| + "SourceGetMetadataResponse": {
|
| + "description": "The result of a SourceGetMetadataOperation.",
|
| + "id": "SourceGetMetadataResponse",
|
| "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"
|
| + "metadata": {
|
| + "$ref": "SourceMetadata",
|
| + "description": "The computed metadata."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "TopologyConfig": {
|
| - "description": "Global topology of the streaming Dataflow job, including all\ncomputations and their sharded locations.",
|
| - "id": "TopologyConfig",
|
| + "ShellTask": {
|
| + "description": "A task which consists of a shell command for the worker to execute.",
|
| + "id": "ShellTask",
|
| "properties": {
|
| - "userStageToComputationNameMap": {
|
| - "additionalProperties": {
|
| - "type": "string"
|
| - },
|
| - "description": "Maps user stage names to stable computation names.",
|
| - "type": "object"
|
| - },
|
| - "computations": {
|
| - "description": "The computations associated with a streaming Dataflow job.",
|
| - "items": {
|
| - "$ref": "ComputationTopology"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "persistentStateVersion": {
|
| - "description": "Version number for persistent state.",
|
| + "exitCode": {
|
| + "description": "Exit code for the task.",
|
| "format": "int32",
|
| "type": "integer"
|
| },
|
| - "dataDiskAssignments": {
|
| - "description": "The disks assigned to a streaming Dataflow job.",
|
| - "items": {
|
| - "$ref": "DataDiskAssignment"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "forwardingKeyBits": {
|
| - "description": "The size (in bits) of keys that will be assigned to source messages.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "command": {
|
| + "description": "The shell command to run.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceSplitOptions": {
|
| - "description": "Hints for splitting a Source into bundles (parts for parallel\nprocessing) using SourceSplitRequest.",
|
| - "id": "SourceSplitOptions",
|
| + "MetricShortId": {
|
| + "description": "The metric short id is returned to the user alongside an offset into\nReportWorkItemStatusRequest",
|
| + "id": "MetricShortId",
|
| "properties": {
|
| - "desiredBundleSizeBytes": {
|
| - "description": "The source should be split into a set of bundles where the estimated size\nof each is approximately this many bytes.",
|
| - "format": "int64",
|
| - "type": "string"
|
| + "metricIndex": {
|
| + "description": "The index of the corresponding metric in\nthe ReportWorkItemStatusRequest. Required.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| },
|
| - "desiredShardSizeBytes": {
|
| - "description": "DEPRECATED in favor of desired_bundle_size_bytes.",
|
| + "shortId": {
|
| + "description": "The service-generated short identifier for the metric.",
|
| "format": "int64",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ReadInstruction": {
|
| - "description": "An instruction that reads records.\nTakes no inputs, produces one output.",
|
| - "id": "ReadInstruction",
|
| - "properties": {
|
| - "source": {
|
| - "$ref": "Source",
|
| - "description": "The source to read from."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "WorkerSettings": {
|
| - "description": "Provides data to pass through to the worker harness.",
|
| - "id": "WorkerSettings",
|
| + "AutoscalingEvent": {
|
| + "description": "A structured message reporting an autoscaling decision made by the Dataflow\nservice.",
|
| + "id": "AutoscalingEvent",
|
| "properties": {
|
| - "workerId": {
|
| - "description": "The ID of the worker running this pipeline.",
|
| + "eventType": {
|
| + "description": "The type of autoscaling event to report.",
|
| + "enum": [
|
| + "TYPE_UNKNOWN",
|
| + "TARGET_NUM_WORKERS_CHANGED",
|
| + "CURRENT_NUM_WORKERS_CHANGED",
|
| + "ACTUATION_FAILURE",
|
| + "NO_CHANGE"
|
| + ],
|
| + "enumDescriptions": [
|
| + "Default type for the enum. Value should never be returned.",
|
| + "The TARGET_NUM_WORKERS_CHANGED type should be used when the target\nworker pool size has changed at the start of an actuation. An event\nshould always be specified as TARGET_NUM_WORKERS_CHANGED if it reflects\na change in the target_num_workers.",
|
| + "The CURRENT_NUM_WORKERS_CHANGED type should be used when actual worker\npool size has been changed, but the target_num_workers has not changed.",
|
| + "The ACTUATION_FAILURE type should be used when we want to report\nan error to the user indicating why the current number of workers\nin the pool could not be changed.\nDisplayed in the current status and history widgets.",
|
| + "Used when we want to report to the user a reason why we are\nnot currently adjusting the number of workers.\nShould specify both target_num_workers, current_num_workers and a\ndecision_message."
|
| + ],
|
| "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}",
|
| + "targetNumWorkers": {
|
| + "description": "The target number of workers the worker pool wants to resize to use.",
|
| + "format": "int64",
|
| "type": "string"
|
| },
|
| - "reportingEnabled": {
|
| - "description": "Whether to send work progress updates to the service.",
|
| - "type": "boolean"
|
| - },
|
| - "baseUrl": {
|
| - "description": "The base URL for accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
|
| + "currentNumWorkers": {
|
| + "description": "The current number of workers the job has.",
|
| + "format": "int64",
|
| "type": "string"
|
| },
|
| - "servicePath": {
|
| - "description": "The Cloud Dataflow service path relative to the root URL, for example,\n\"dataflow/v1b3/projects\".",
|
| + "time": {
|
| + "description": "The time this event was emitted to indicate a new target or current\nnum_workers value.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| - "shuffleServicePath": {
|
| - "description": "The Shuffle service path relative to the root URL, for example,\n\"shuffle/v1beta1\".",
|
| - "type": "string"
|
| + "description": {
|
| + "$ref": "StructuredMessage",
|
| + "description": "A message describing why the system decided to adjust the current\nnumber of workers, why it failed, or why the system decided to\nnot make any changes to the number of workers."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamingStageLocation": {
|
| - "description": "Identifies the location of a streaming computation stage, for\nstage-to-stage communication.",
|
| - "id": "StreamingStageLocation",
|
| + "TaskRunnerSettings": {
|
| + "description": "Taskrunner configuration settings.",
|
| + "id": "TaskRunnerSettings",
|
| "properties": {
|
| - "streamId": {
|
| - "description": "Identifies the particular stream within the streaming Dataflow\njob.",
|
| + "vmId": {
|
| + "description": "The ID string of the VM.",
|
| "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "DataDiskAssignment": {
|
| - "description": "Data disk assignment for a given VM instance.",
|
| - "id": "DataDiskAssignment",
|
| - "properties": {
|
| - "dataDisks": {
|
| - "description": "Mounted data disks. The order is important a data disk's 0-based index in\nthis list defines which persistent directory the disk is mounted to, for\nexample the list of { \"myproject-1014-104817-4c2-harness-0-disk-0\" },\n{ \"myproject-1014-104817-4c2-harness-0-disk-1\" }.",
|
| + },
|
| + "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"
|
| + },
|
| + "harnessCommand": {
|
| + "description": "The command to launch the worker harness.",
|
| + "type": "string"
|
| + },
|
| + "logDir": {
|
| + "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": {
|
| "type": "string"
|
| },
|
| "type": "array"
|
| },
|
| - "vmInstance": {
|
| - "description": "VM instance name the data disks mounted to, for example\n\"myproject-1014-104817-4c2-harness-0\".",
|
| + "streamingWorkerMainClass": {
|
| + "description": "The streaming worker main class name.",
|
| + "type": "string"
|
| + },
|
| + "logUploadLocation": {
|
| + "description": "Indicates where to put logs. If this is not specified, the logs\nwill not be uploaded.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
|
| + "type": "string"
|
| + },
|
| + "workflowFileName": {
|
| + "description": "The file to store the workflow in.",
|
| + "type": "string"
|
| + },
|
| + "languageHint": {
|
| + "description": "The suggested backend language.",
|
| + "type": "string"
|
| + },
|
| + "commandlinesFileName": {
|
| + "description": "The file to store preprocessing commands in.",
|
| + "type": "string"
|
| + },
|
| + "tempStoragePrefix": {
|
| + "description": "The prefix of the resources the taskrunner should use for\ntemporary storage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
|
| + "type": "string"
|
| + },
|
| + "baseTaskDir": {
|
| + "description": "The location on the worker for task-specific subdirectories.",
|
| + "type": "string"
|
| + },
|
| + "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."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ApproximateSplitRequest": {
|
| - "description": "A suggestion by the service to the worker to dynamically split the WorkItem.",
|
| - "id": "ApproximateSplitRequest",
|
| + "Position": {
|
| + "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": {
|
| - "position": {
|
| - "$ref": "Position",
|
| - "description": "A Position at which to split the work item."
|
| + "shufflePosition": {
|
| + "description": "CloudPosition is a base64 encoded BatchShufflePosition (with FIXED\nsharding).",
|
| + "type": "string"
|
| },
|
| - "fractionConsumed": {
|
| - "description": "A fraction at which to split the work item, from 0.0 (beginning of the\ninput) to 1.0 (end of the input).",
|
| - "format": "double",
|
| - "type": "number"
|
| + "byteOffset": {
|
| + "description": "Position is a byte offset.",
|
| + "format": "int64",
|
| + "type": "string"
|
| + },
|
| + "concatPosition": {
|
| + "$ref": "ConcatPosition",
|
| + "description": "CloudPosition is a concat position."
|
| + },
|
| + "end": {
|
| + "description": "Position is past all other positions. Also useful for the end\nposition of an unbounded range.",
|
| + "type": "boolean"
|
| + },
|
| + "key": {
|
| + "description": "Position is a string key, ordered lexicographically.",
|
| + "type": "string"
|
| + },
|
| + "recordIndex": {
|
| + "description": "Position is a record index.",
|
| + "format": "int64",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Status": {
|
| - "description": "The `Status` type defines a logical error model that is suitable for different\nprogramming environments, including REST APIs and RPC APIs. It is used by\n[gRPC](https://github.com/grpc). The error model is designed to be:\n\n- Simple to use and understand for most users\n- Flexible enough to meet unexpected needs\n\n# Overview\n\nThe `Status` message contains three pieces of data: error code, error message,\nand error details. The error code should be an enum value of\ngoogle.rpc.Code, but it may accept additional error codes if needed. The\nerror message should be a developer-facing English message that helps\ndevelopers *understand* and *resolve* the error. If a localized user-facing\nerror message is needed, put the localized message in the error details or\nlocalize it in the client. The optional error details may contain arbitrary\ninformation about the error. There is a predefined set of error detail types\nin the package `google.rpc` that can be used for common error conditions.\n\n# Language mapping\n\nThe `Status` message is the logical representation of the error model, but it\nis not necessarily the actual wire format. When the `Status` message is\nexposed in different client libraries and different wire protocols, it can be\nmapped differently. For example, it will likely be mapped to some exceptions\nin Java, but more likely mapped to some error codes in C.\n\n# Other uses\n\nThe error model and the `Status` message can be used in a variety of\nenvironments, either with or without APIs, to provide a\nconsistent developer experience across different environments.\n\nExample uses of this error model include:\n\n- Partial errors. If a service needs to return partial errors to the client,\n it may embed the `Status` in the normal response to indicate the partial\n errors.\n\n- Workflow errors. A typical workflow has multiple steps. Each step may\n have a `Status` message for error reporting.\n\n- Batch operations. If a client uses batch request and batch response, the\n `Status` message should be used directly inside batch response, one for\n each error sub-response.\n\n- Asynchronous operations. If an API call embeds asynchronous operation\n results in its response, the status of those operations should be\n represented directly using the `Status` message.\n\n- Logging. If some API errors are stored in logs, the message `Status` could\n be used directly after any stripping needed for security/privacy reasons.",
|
| - "id": "Status",
|
| + "Source": {
|
| + "description": "A source that records can be read and decoded from.",
|
| + "id": "Source",
|
| "properties": {
|
| - "details": {
|
| - "description": "A list of messages that carry the error details. There is a common set of\nmessage types for APIs to use.",
|
| + "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. Contains field @type with type URL.",
|
| + "description": "Properties of the object.",
|
| "type": "any"
|
| },
|
| "type": "object"
|
| },
|
| "type": "array"
|
| },
|
| - "code": {
|
| - "description": "The status code, which should be an enum value of google.rpc.Code.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "doesNotNeedSplitting": {
|
| + "description": "Setting this value to true hints to the framework that the source\ndoesn't need splitting, and using SourceSplitRequest on it would\nyield SOURCE_SPLIT_OUTCOME_USE_CURRENT.\n\nE.g. a file splitter may set this to true when splitting a single file\ninto a set of byte ranges of appropriate size, and set this\nto false when splitting a filepattern into individual files.\nHowever, for efficiency, a file splitter may decide to produce\nfile subranges directly from the filepattern to avoid a splitting\nround-trip.\n\nSee SourceSplitRequest for an overview of the splitting process.\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated.",
|
| + "type": "boolean"
|
| },
|
| - "message": {
|
| - "description": "A developer-facing error message, which should be in English. Any\nuser-facing error message should be localized and sent in the\ngoogle.rpc.Status.details field, or localized by the client.",
|
| - "type": "string"
|
| + "codec": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "The codec to use to decode data read from the source.",
|
| + "type": "object"
|
| + },
|
| + "spec": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "The source to read from, plus its parameters.",
|
| + "type": "object"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ExecutionStageState": {
|
| - "description": "A message describing the state of a particular execution stage.",
|
| - "id": "ExecutionStageState",
|
| + "SplitInt64": {
|
| + "description": "A representation of an int64, n, that is immune to precision loss when\nencoded in JSON.",
|
| + "id": "SplitInt64",
|
| "properties": {
|
| - "executionStageName": {
|
| - "description": "The name of the execution stage.",
|
| - "type": "string"
|
| - },
|
| - "currentStateTime": {
|
| - "description": "The time at which the stage transitioned to this state.",
|
| - "format": "google-datetime",
|
| - "type": "string"
|
| + "lowBits": {
|
| + "description": "The low order bits: n & 0xffffffff.",
|
| + "format": "uint32",
|
| + "type": "integer"
|
| },
|
| - "executionStageState": {
|
| - "description": "Executions stage states allow the same set of values as JobState.",
|
| - "enum": [
|
| - "JOB_STATE_UNKNOWN",
|
| - "JOB_STATE_STOPPED",
|
| - "JOB_STATE_RUNNING",
|
| - "JOB_STATE_DONE",
|
| - "JOB_STATE_FAILED",
|
| - "JOB_STATE_CANCELLED",
|
| - "JOB_STATE_UPDATED",
|
| - "JOB_STATE_DRAINING",
|
| - "JOB_STATE_DRAINED",
|
| - "JOB_STATE_PENDING",
|
| - "JOB_STATE_CANCELLING"
|
| - ],
|
| - "enumDescriptions": [
|
| - "The job's run state isn't specified.",
|
| - "`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
|
| - "`JOB_STATE_RUNNING` indicates that the job is currently running.",
|
| - "`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
|
| - "`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
|
| - "`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
|
| - "`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
|
| - "`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
|
| - "`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
|
| - "'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
|
| - "'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
|
| - ],
|
| - "type": "string"
|
| + "highBits": {
|
| + "description": "The high order bits, including the sign: n >> 32.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamLocation": {
|
| - "description": "Describes a stream of data, either as input to be processed or as\noutput of a streaming Dataflow job.",
|
| - "id": "StreamLocation",
|
| + "WorkerPool": {
|
| + "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": {
|
| - "customSourceLocation": {
|
| - "$ref": "CustomSourceLocation",
|
| - "description": "The stream is a custom source."
|
| + "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"
|
| },
|
| - "sideInputLocation": {
|
| - "$ref": "StreamingSideInputLocation",
|
| - "description": "The stream is a streaming side input."
|
| + "onHostMaintenance": {
|
| + "description": "The action to take on host maintenance, as defined by the Google\nCompute Engine API.",
|
| + "type": "string"
|
| },
|
| - "pubsubLocation": {
|
| - "$ref": "PubsubLocation",
|
| - "description": "The stream is a pubsub stream."
|
| - },
|
| - "streamingStageLocation": {
|
| - "$ref": "StreamingStageLocation",
|
| - "description": "The stream is part of another computation within the current\nstreaming Dataflow job."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "SendWorkerMessagesResponse": {
|
| - "description": "The response to the worker messages.",
|
| - "id": "SendWorkerMessagesResponse",
|
| - "properties": {
|
| - "workerMessageResponses": {
|
| - "description": "The servers response to the worker messages.",
|
| - "items": {
|
| - "$ref": "WorkerMessageResponse"
|
| - },
|
| - "type": "array"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "LeaseWorkItemResponse": {
|
| - "description": "Response to a request to lease WorkItems.",
|
| - "id": "LeaseWorkItemResponse",
|
| - "properties": {
|
| - "workItems": {
|
| - "description": "A list of the leased WorkItems.",
|
| - "items": {
|
| - "$ref": "WorkItem"
|
| - },
|
| - "type": "array"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "TransformSummary": {
|
| - "description": "Description of the type, names/ids, and input/outputs for a transform.",
|
| - "id": "TransformSummary",
|
| - "properties": {
|
| - "inputCollectionName": {
|
| - "description": "User names for all collection inputs to this transform.",
|
| - "items": {
|
| - "type": "string"
|
| + "poolArgs": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object. Contains field @type with type URL.",
|
| + "type": "any"
|
| },
|
| - "type": "array"
|
| + "description": "Extra arguments for this worker pool.",
|
| + "type": "object"
|
| },
|
| - "name": {
|
| - "description": "User provided name for this transform instance.",
|
| + "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"
|
| },
|
| - "id": {
|
| - "description": "SDK generated id of this transform instance.",
|
| + "diskType": {
|
| + "description": "Type of root disk for VMs. If empty or unspecified, the service will\nattempt to choose a reasonable default.",
|
| "type": "string"
|
| },
|
| - "displayData": {
|
| - "description": "Transform-specific display data.",
|
| + "machineType": {
|
| + "description": "Machine type (e.g. \"n1-standard-1\"). If empty or unspecified, the\nservice will attempt to choose a reasonable default.",
|
| + "type": "string"
|
| + },
|
| + "kind": {
|
| + "description": "The kind of the worker pool; currently only `harness` and `shuffle`\nare supported.",
|
| + "type": "string"
|
| + },
|
| + "dataDisks": {
|
| + "description": "Data disks that are used by a VM in this workflow.",
|
| "items": {
|
| - "$ref": "DisplayData"
|
| + "$ref": "Disk"
|
| },
|
| "type": "array"
|
| },
|
| - "outputCollectionName": {
|
| - "description": "User names for all collection outputs to this transform.",
|
| - "items": {
|
| + "subnetwork": {
|
| + "description": "Subnetwork to which VMs will be assigned, if desired. Expected to be of\nthe form \"regions/REGION/subnetworks/SUBNETWORK\".",
|
| + "type": "string"
|
| + },
|
| + "ipConfiguration": {
|
| + "description": "Configuration for VM IPs.",
|
| + "enum": [
|
| + "WORKER_IP_UNSPECIFIED",
|
| + "WORKER_IP_PUBLIC",
|
| + "WORKER_IP_PRIVATE"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The configuration is unknown, or unspecified.",
|
| + "Workers should have public IP addresses.",
|
| + "Workers should have private IP addresses."
|
| + ],
|
| + "type": "string"
|
| + },
|
| + "autoscalingSettings": {
|
| + "$ref": "AutoscalingSettings",
|
| + "description": "Settings for autoscaling of this WorkerPool."
|
| + },
|
| + "taskrunnerSettings": {
|
| + "$ref": "TaskRunnerSettings",
|
| + "description": "Settings passed through to Google Compute Engine workers when\nusing the standard Dataflow task runner. Users should ignore\nthis field."
|
| + },
|
| + "metadata": {
|
| + "additionalProperties": {
|
| "type": "string"
|
| },
|
| - "type": "array"
|
| + "description": "Metadata to set on the Google Compute Engine VMs.",
|
| + "type": "object"
|
| },
|
| - "kind": {
|
| - "description": "Type of transform.",
|
| + "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": [
|
| - "UNKNOWN_KIND",
|
| - "PAR_DO_KIND",
|
| - "GROUP_BY_KEY_KIND",
|
| - "FLATTEN_KIND",
|
| - "READ_KIND",
|
| - "WRITE_KIND",
|
| - "CONSTANT_KIND",
|
| - "SINGLETON_KIND",
|
| - "SHUFFLE_KIND"
|
| + "DEFAULT_PACKAGE_SET_UNKNOWN",
|
| + "DEFAULT_PACKAGE_SET_NONE",
|
| + "DEFAULT_PACKAGE_SET_JAVA",
|
| + "DEFAULT_PACKAGE_SET_PYTHON"
|
| ],
|
| "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."
|
| + "The default set of packages to stage is unknown, or unspecified.",
|
| + "Indicates that no packages should be staged at the worker unless\nexplicitly specified by the job.",
|
| + "Stage packages typically useful to workers written in Java.",
|
| + "Stage pacakges typically useful to workers written in Python."
|
| ],
|
| "type": "string"
|
| + },
|
| + "network": {
|
| + "description": "Network to which VMs will be assigned. If empty or unspecified,\nthe service will use the network \"default\".",
|
| + "type": "string"
|
| + },
|
| + "zone": {
|
| + "description": "Zone to run the worker pools in. If empty or unspecified, the service\nwill attempt to choose a reasonable default.",
|
| + "type": "string"
|
| + },
|
| + "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"
|
| + },
|
| + "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"
|
| + },
|
| + "diskSourceImage": {
|
| + "description": "Fully qualified source image for disks.",
|
| + "type": "string"
|
| + },
|
| + "packages": {
|
| + "description": "Packages to be installed on workers.",
|
| + "items": {
|
| + "$ref": "Package"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamingComputationConfig": {
|
| - "description": "Configuration information for a single streaming computation.",
|
| - "id": "StreamingComputationConfig",
|
| + "SourceOperationRequest": {
|
| + "description": "A work item that represents the different operations that can be\nperformed on a user-defined Source specification.",
|
| + "id": "SourceOperationRequest",
|
| "properties": {
|
| - "stageName": {
|
| - "description": "Stage name of this computation.",
|
| + "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."
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "WorkItem": {
|
| + "description": "WorkItem represents basic information about a WorkItem to be executed\nin the cloud.",
|
| + "id": "WorkItem",
|
| + "properties": {
|
| + "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"
|
| },
|
| - "systemName": {
|
| - "description": "System defined name for this computation.",
|
| + "id": {
|
| + "description": "Identifies this WorkItem.",
|
| + "format": "int64",
|
| "type": "string"
|
| },
|
| - "instructions": {
|
| - "description": "Instructions that comprise the computation.",
|
| + "configuration": {
|
| + "description": "Work item-specific configuration as an opaque blob.",
|
| + "type": "string"
|
| + },
|
| + "mapTask": {
|
| + "$ref": "MapTask",
|
| + "description": "Additional information for MapTask WorkItems."
|
| + },
|
| + "seqMapTask": {
|
| + "$ref": "SeqMapTask",
|
| + "description": "Additional information for SeqMapTask WorkItems."
|
| + },
|
| + "packages": {
|
| + "description": "Any required packages that need to be fetched in order to execute\nthis WorkItem.",
|
| "items": {
|
| - "$ref": "ParallelInstruction"
|
| + "$ref": "Package"
|
| },
|
| "type": "array"
|
| },
|
| - "computationId": {
|
| - "description": "Unique identifier for this computation.",
|
| + "projectId": {
|
| + "description": "Identifies the cloud project this WorkItem belongs to.",
|
| + "type": "string"
|
| + },
|
| + "sourceOperationTask": {
|
| + "$ref": "SourceOperationRequest",
|
| + "description": "Additional information for source operation WorkItems."
|
| + },
|
| + "reportStatusInterval": {
|
| + "description": "Recommended reporting interval.",
|
| + "format": "google-duration",
|
| + "type": "string"
|
| + },
|
| + "streamingSetupTask": {
|
| + "$ref": "StreamingSetupTask",
|
| + "description": "Additional information for StreamingSetupTask WorkItems."
|
| + },
|
| + "streamingConfigTask": {
|
| + "$ref": "StreamingConfigTask",
|
| + "description": "Additional information for StreamingConfigTask WorkItems."
|
| + },
|
| + "leaseExpireTime": {
|
| + "description": "Time when the lease on this Work will expire.",
|
| + "format": "google-datetime",
|
| + "type": "string"
|
| + },
|
| + "initialReportIndex": {
|
| + "description": "The initial index to use when reporting the status of the WorkItem.",
|
| + "format": "int64",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Sink": {
|
| - "description": "A sink that records can be encoded and written to.",
|
| - "id": "Sink",
|
| + "StructuredMessage": {
|
| + "description": "A rich message format, including a human readable string, a key for\nidentifying the message, and structured data associated with the message for\nprogrammatic consumption.",
|
| + "id": "StructuredMessage",
|
| "properties": {
|
| - "codec": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The codec to use to encode data written to the sink.",
|
| - "type": "object"
|
| + "messageKey": {
|
| + "description": "Idenfier for this message type. Used by external systems to\ninternationalize or personalize message.",
|
| + "type": "string"
|
| },
|
| - "spec": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| + "messageText": {
|
| + "description": "Human-readable version of message.",
|
| + "type": "string"
|
| + },
|
| + "parameters": {
|
| + "description": "The structured data associated with this message.",
|
| + "items": {
|
| + "$ref": "Parameter"
|
| },
|
| - "description": "The sink to write to, plus its parameters.",
|
| - "type": "object"
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "LaunchTemplateParameters": {
|
| - "description": "Parameters to provide to the template being launched.",
|
| - "id": "LaunchTemplateParameters",
|
| + "ReportedParallelism": {
|
| + "description": "Represents the level of parallelism in a WorkItem's input,\nreported by the worker.",
|
| + "id": "ReportedParallelism",
|
| "properties": {
|
| - "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"
|
| + "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"
|
| },
|
| - "environment": {
|
| - "$ref": "RuntimeEnvironment",
|
| - "description": "The runtime environment for the job."
|
| + "value": {
|
| + "description": "Specifies the level of parallelism in case it is finite.",
|
| + "format": "double",
|
| + "type": "number"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "FlattenInstruction": {
|
| - "description": "An instruction that copies its inputs (zero or more) to its (single) output.",
|
| - "id": "FlattenInstruction",
|
| + "ResourceUtilizationReport": {
|
| + "description": "Worker metrics exported from workers. This contains resource utilization\nmetrics accumulated from a variety of sources. For more information, see\ngo/df-resource-signals.",
|
| + "id": "ResourceUtilizationReport",
|
| "properties": {
|
| - "inputs": {
|
| - "description": "Describes the inputs to the flatten instruction.",
|
| + "cpuTime": {
|
| + "description": "CPU utilization samples.",
|
| "items": {
|
| - "$ref": "InstructionInput"
|
| + "$ref": "CPUTime"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "PartialGroupByKeyInstruction": {
|
| - "description": "An instruction that does a partial group-by-key.\nOne input and one output.",
|
| - "id": "PartialGroupByKeyInstruction",
|
| + "TopologyConfig": {
|
| + "description": "Global topology of the streaming Dataflow job, including all\ncomputations and their sharded locations.",
|
| + "id": "TopologyConfig",
|
| "properties": {
|
| - "inputElementCodec": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The codec to use for interpreting an element in the input PTable.",
|
| - "type": "object"
|
| - },
|
| - "valueCombiningFn": {
|
| + "userStageToComputationNameMap": {
|
| "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| + "type": "string"
|
| },
|
| - "description": "The value combining function to invoke.",
|
| + "description": "Maps user stage names to stable computation names.",
|
| "type": "object"
|
| },
|
| - "originalCombineValuesInputStoreName": {
|
| - "description": "If this instruction includes a combining function this is the name of the\nintermediate store between the GBK and the CombineValues.",
|
| - "type": "string"
|
| - },
|
| - "originalCombineValuesStepName": {
|
| - "description": "If this instruction includes a combining function, this is the name of the\nCombineValues instruction lifted into this instruction.",
|
| - "type": "string"
|
| - },
|
| - "sideInputs": {
|
| - "description": "Zero or more side inputs.",
|
| + "computations": {
|
| + "description": "The computations associated with a streaming Dataflow job.",
|
| "items": {
|
| - "$ref": "SideInputInfo"
|
| + "$ref": "ComputationTopology"
|
| },
|
| "type": "array"
|
| },
|
| - "input": {
|
| - "$ref": "InstructionInput",
|
| - "description": "Describes the input to the partial group-by-key instruction."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "InstructionInput": {
|
| - "description": "An input of an instruction, as a reference to an output of a\nproducer instruction.",
|
| - "id": "InstructionInput",
|
| - "properties": {
|
| - "producerInstructionIndex": {
|
| - "description": "The index (origin zero) of the parallel instruction that produces\nthe output to be consumed by this input. This index is relative\nto the list of instructions in this input's instruction's\ncontaining MapTask.",
|
| + "persistentStateVersion": {
|
| + "description": "Version number for persistent state.",
|
| "format": "int32",
|
| "type": "integer"
|
| },
|
| - "outputNum": {
|
| - "description": "The output index (origin zero) within the producer.",
|
| + "dataDiskAssignments": {
|
| + "description": "The disks assigned to a streaming Dataflow job.",
|
| + "items": {
|
| + "$ref": "DataDiskAssignment"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "forwardingKeyBits": {
|
| + "description": "The size (in bits) of keys that will be assigned to source messages.",
|
| "format": "int32",
|
| "type": "integer"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StageSource": {
|
| - "description": "Description of an input or output of an execution stage.",
|
| - "id": "StageSource",
|
| + "SourceSplitOptions": {
|
| + "description": "Hints for splitting a Source into bundles (parts for parallel\nprocessing) using SourceSplitRequest.",
|
| + "id": "SourceSplitOptions",
|
| "properties": {
|
| - "userName": {
|
| - "description": "Human-readable name for this source; may be user or system generated.",
|
| - "type": "string"
|
| - },
|
| - "originalTransformOrCollection": {
|
| - "description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
|
| - "type": "string"
|
| - },
|
| - "sizeBytes": {
|
| - "description": "Size of the source, if measurable.",
|
| + "desiredBundleSizeBytes": {
|
| + "description": "The source should be split into a set of bundles where the estimated size\nof each is approximately this many bytes.",
|
| "format": "int64",
|
| "type": "string"
|
| },
|
| - "name": {
|
| - "description": "Dataflow service generated name for this source.",
|
| + "desiredShardSizeBytes": {
|
| + "description": "DEPRECATED in favor of desired_bundle_size_bytes.",
|
| + "format": "int64",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StringList": {
|
| - "description": "A metric value representing a list of strings.",
|
| - "id": "StringList",
|
| + "ReadInstruction": {
|
| + "description": "An instruction that reads records.\nTakes no inputs, produces one output.",
|
| + "id": "ReadInstruction",
|
| "properties": {
|
| - "elements": {
|
| - "description": "Elements of the list.",
|
| - "items": {
|
| - "type": "string"
|
| - },
|
| - "type": "array"
|
| + "source": {
|
| + "$ref": "Source",
|
| + "description": "The source to read from."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "DisplayData": {
|
| - "description": "Data provided with a pipeline or transform to provide descriptive info.",
|
| - "id": "DisplayData",
|
| + "WorkerSettings": {
|
| + "description": "Provides data to pass through to the worker harness.",
|
| + "id": "WorkerSettings",
|
| "properties": {
|
| - "strValue": {
|
| - "description": "Contains value if the data is of string type.",
|
| - "type": "string"
|
| - },
|
| - "int64Value": {
|
| - "description": "Contains value if the data is of int64 type.",
|
| - "format": "int64",
|
| - "type": "string"
|
| - },
|
| - "durationValue": {
|
| - "description": "Contains value if the data is of duration type.",
|
| - "format": "google-duration",
|
| - "type": "string"
|
| - },
|
| - "namespace": {
|
| - "description": "The namespace for the key. This is usually a class name or programming\nlanguage namespace (i.e. python module) which defines the display data.\nThis allows a dax monitoring system to specially handle the data\nand perform custom rendering.",
|
| - "type": "string"
|
| - },
|
| - "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.",
|
| + "servicePath": {
|
| + "description": "The Cloud Dataflow service path relative to the root URL, for example,\n\"dataflow/v1b3/projects\".",
|
| "type": "string"
|
| },
|
| - "label": {
|
| - "description": "An optional label to display in a dax UI for the element.",
|
| + "shuffleServicePath": {
|
| + "description": "The Shuffle service path relative to the root URL, for example,\n\"shuffle/v1beta1\".",
|
| "type": "string"
|
| },
|
| - "url": {
|
| - "description": "An optional full URL.",
|
| + "workerId": {
|
| + "description": "The ID of the worker running this pipeline.",
|
| "type": "string"
|
| },
|
| - "timestampValue": {
|
| - "description": "Contains value if the data is of timestamp type.",
|
| - "format": "google-datetime",
|
| + "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"
|
| },
|
| - "javaClassValue": {
|
| - "description": "Contains value if the data is of java class type.",
|
| + "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"
|
| },
|
| - "boolValue": {
|
| - "description": "Contains value if the data is of a boolean type.",
|
| + "reportingEnabled": {
|
| + "description": "Whether to send work progress updates to the service.",
|
| "type": "boolean"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "GetDebugConfigRequest": {
|
| - "description": "Request to get updated debug configuration for component.",
|
| - "id": "GetDebugConfigRequest",
|
| + "StreamingStageLocation": {
|
| + "description": "Identifies the location of a streaming computation stage, for\nstage-to-stage communication.",
|
| + "id": "StreamingStageLocation",
|
| "properties": {
|
| - "workerId": {
|
| - "description": "The worker id, i.e., VM hostname.",
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location which contains the job specified by job_id.",
|
| - "type": "string"
|
| - },
|
| - "componentId": {
|
| - "description": "The internal component id for which debug configuration is\nrequested.",
|
| + "streamId": {
|
| + "description": "Identifies the particular stream within the streaming Dataflow\njob.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "LeaseWorkItemRequest": {
|
| - "description": "Request to lease WorkItems.",
|
| - "id": "LeaseWorkItemRequest",
|
| + "DataDiskAssignment": {
|
| + "description": "Data disk assignment for a given VM instance.",
|
| + "id": "DataDiskAssignment",
|
| "properties": {
|
| - "workerCapabilities": {
|
| - "description": "Worker capabilities. WorkItems might be limited to workers with specific\ncapabilities.",
|
| + "vmInstance": {
|
| + "description": "VM instance name the data disks mounted to, for example\n\"myproject-1014-104817-4c2-harness-0\".",
|
| + "type": "string"
|
| + },
|
| + "dataDisks": {
|
| + "description": "Mounted data disks. The order is important a data disk's 0-based index in\nthis list defines which persistent directory the disk is mounted to, for\nexample the list of { \"myproject-1014-104817-4c2-harness-0-disk-0\" },\n{ \"myproject-1014-104817-4c2-harness-0-disk-1\" }.",
|
| "items": {
|
| "type": "string"
|
| },
|
| "type": "array"
|
| + }
|
| + },
|
| + "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."
|
| },
|
| - "workerId": {
|
| - "description": "Identifies the worker leasing work -- typically the ID of the\nvirtual machine running the worker.",
|
| - "type": "string"
|
| - },
|
| - "requestedLeaseDuration": {
|
| - "description": "The initial lease period.",
|
| - "format": "google-duration",
|
| - "type": "string"
|
| + "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"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "Status": {
|
| + "description": "The `Status` type defines a logical error model that is suitable for different\nprogramming environments, including REST APIs and RPC APIs. It is used by\n[gRPC](https://github.com/grpc). The error model is designed to be:\n\n- Simple to use and understand for most users\n- Flexible enough to meet unexpected needs\n\n# Overview\n\nThe `Status` message contains three pieces of data: error code, error message,\nand error details. The error code should be an enum value of\ngoogle.rpc.Code, but it may accept additional error codes if needed. The\nerror message should be a developer-facing English message that helps\ndevelopers *understand* and *resolve* the error. If a localized user-facing\nerror message is needed, put the localized message in the error details or\nlocalize it in the client. The optional error details may contain arbitrary\ninformation about the error. There is a predefined set of error detail types\nin the package `google.rpc` that can be used for common error conditions.\n\n# Language mapping\n\nThe `Status` message is the logical representation of the error model, but it\nis not necessarily the actual wire format. When the `Status` message is\nexposed in different client libraries and different wire protocols, it can be\nmapped differently. For example, it will likely be mapped to some exceptions\nin Java, but more likely mapped to some error codes in C.\n\n# Other uses\n\nThe error model and the `Status` message can be used in a variety of\nenvironments, either with or without APIs, to provide a\nconsistent developer experience across different environments.\n\nExample uses of this error model include:\n\n- Partial errors. If a service needs to return partial errors to the client,\n it may embed the `Status` in the normal response to indicate the partial\n errors.\n\n- Workflow errors. A typical workflow has multiple steps. Each step may\n have a `Status` message for error reporting.\n\n- Batch operations. If a client uses batch request and batch response, the\n `Status` message should be used directly inside batch response, one for\n each error sub-response.\n\n- Asynchronous operations. If an API call embeds asynchronous operation\n results in its response, the status of those operations should be\n represented directly using the `Status` message.\n\n- Logging. If some API errors are stored in logs, the message `Status` could\n be used directly after any stripping needed for security/privacy reasons.",
|
| + "id": "Status",
|
| + "properties": {
|
| + "code": {
|
| + "description": "The status code, which should be an enum value of google.rpc.Code.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| },
|
| - "currentWorkerTime": {
|
| - "description": "The current timestamp at the worker.",
|
| - "format": "google-datetime",
|
| + "message": {
|
| + "description": "A developer-facing error message, which should be in English. Any\nuser-facing error message should be localized and sent in the\ngoogle.rpc.Status.details field, or localized by the client.",
|
| "type": "string"
|
| },
|
| - "workItemTypes": {
|
| - "description": "Filter for WorkItem type.",
|
| + "details": {
|
| + "description": "A list of messages that carry the error details. There is a common set of\nmessage types for APIs to use.",
|
| "items": {
|
| - "type": "string"
|
| + "additionalProperties": {
|
| + "description": "Properties of the object. Contains field @type with type URL.",
|
| + "type": "any"
|
| + },
|
| + "type": "object"
|
| },
|
| "type": "array"
|
| - },
|
| - "location": {
|
| - "description": "The location which contains the WorkItem's job.",
|
| - "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "GetTemplateResponse": {
|
| - "description": "The response to a GetTemplate request.",
|
| - "id": "GetTemplateResponse",
|
| + "ExecutionStageState": {
|
| + "description": "A message describing the state of a particular execution stage.",
|
| + "id": "ExecutionStageState",
|
| "properties": {
|
| - "status": {
|
| - "$ref": "Status",
|
| - "description": "The status of the get template request. Any problems with the\nrequest will be indicated in the error_details."
|
| + "executionStageState": {
|
| + "description": "Executions stage states allow the same set of values as JobState.",
|
| + "enum": [
|
| + "JOB_STATE_UNKNOWN",
|
| + "JOB_STATE_STOPPED",
|
| + "JOB_STATE_RUNNING",
|
| + "JOB_STATE_DONE",
|
| + "JOB_STATE_FAILED",
|
| + "JOB_STATE_CANCELLED",
|
| + "JOB_STATE_UPDATED",
|
| + "JOB_STATE_DRAINING",
|
| + "JOB_STATE_DRAINED",
|
| + "JOB_STATE_PENDING",
|
| + "JOB_STATE_CANCELLING"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The job's run state isn't specified.",
|
| + "`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
|
| + "`JOB_STATE_RUNNING` indicates that the job is currently running.",
|
| + "`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
|
| + "`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
|
| + "`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
|
| + "`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
|
| + "`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
|
| + "`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
|
| + "'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
|
| + "'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
|
| + ],
|
| + "type": "string"
|
| },
|
| - "metadata": {
|
| - "$ref": "TemplateMetadata",
|
| - "description": "The template metadata describing the template name, available\nparameters, etc."
|
| + "executionStageName": {
|
| + "description": "The name of the execution stage.",
|
| + "type": "string"
|
| + },
|
| + "currentStateTime": {
|
| + "description": "The time at which the stage transitioned to this state.",
|
| + "format": "google-datetime",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Parameter": {
|
| - "description": "Structured data associated with this message.",
|
| - "id": "Parameter",
|
| + "StreamLocation": {
|
| + "description": "Describes a stream of data, either as input to be processed or as\noutput of a streaming Dataflow job.",
|
| + "id": "StreamLocation",
|
| "properties": {
|
| - "key": {
|
| - "description": "Key or name for this parameter.",
|
| - "type": "string"
|
| + "customSourceLocation": {
|
| + "$ref": "CustomSourceLocation",
|
| + "description": "The stream is a custom source."
|
| },
|
| - "value": {
|
| - "description": "Value for this parameter.",
|
| - "type": "any"
|
| + "sideInputLocation": {
|
| + "$ref": "StreamingSideInputLocation",
|
| + "description": "The stream is a streaming side input."
|
| + },
|
| + "pubsubLocation": {
|
| + "$ref": "PubsubLocation",
|
| + "description": "The stream is a pubsub stream."
|
| + },
|
| + "streamingStageLocation": {
|
| + "$ref": "StreamingStageLocation",
|
| + "description": "The stream is part of another computation within the current\nstreaming Dataflow job."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ReportWorkItemStatusRequest": {
|
| - "description": "Request to report the status of WorkItems.",
|
| - "id": "ReportWorkItemStatusRequest",
|
| + "SendWorkerMessagesResponse": {
|
| + "description": "The response to the worker messages.",
|
| + "id": "SendWorkerMessagesResponse",
|
| "properties": {
|
| - "workItemStatuses": {
|
| - "description": "The order is unimportant, except that the order of the\nWorkItemServiceState messages in the ReportWorkItemStatusResponse\ncorresponds to the order of WorkItemStatus messages here.",
|
| + "workerMessageResponses": {
|
| + "description": "The servers response to the worker messages.",
|
| "items": {
|
| - "$ref": "WorkItemStatus"
|
| + "$ref": "WorkerMessageResponse"
|
| },
|
| "type": "array"
|
| - },
|
| - "currentWorkerTime": {
|
| - "description": "The current timestamp at the worker.",
|
| - "format": "google-datetime",
|
| - "type": "string"
|
| - },
|
| - "workerId": {
|
| - "description": "The ID of the worker reporting the WorkItem status. If this\ndoes not match the ID of the worker which the Dataflow service\nbelieves currently has the lease on the WorkItem, the report\nwill be dropped (with an error response).",
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location which contains the WorkItem's job.",
|
| - "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamingConfigTask": {
|
| - "description": "A task that carries configuration information for streaming computations.",
|
| - "id": "StreamingConfigTask",
|
| + "StreamingComputationConfig": {
|
| + "description": "Configuration information for a single streaming computation.",
|
| + "id": "StreamingComputationConfig",
|
| "properties": {
|
| - "windmillServiceEndpoint": {
|
| - "description": "If present, the worker must use this endpoint to communicate with Windmill\nService dispatchers, otherwise the worker must continue to use whatever\nendpoint it had been using.",
|
| + "computationId": {
|
| + "description": "Unique identifier for this computation.",
|
| "type": "string"
|
| },
|
| - "userStepToStateFamilyNameMap": {
|
| - "additionalProperties": {
|
| - "type": "string"
|
| - },
|
| - "description": "Map from user step names to state families.",
|
| - "type": "object"
|
| + "stageName": {
|
| + "description": "Stage name of this computation.",
|
| + "type": "string"
|
| },
|
| - "windmillServicePort": {
|
| - "description": "If present, the worker must use this port to communicate with Windmill\nService dispatchers. Only applicable when windmill_service_endpoint is\nspecified.",
|
| - "format": "int64",
|
| + "systemName": {
|
| + "description": "System defined name for this computation.",
|
| "type": "string"
|
| },
|
| - "streamingComputationConfigs": {
|
| - "description": "Set of computation configuration information.",
|
| + "instructions": {
|
| + "description": "Instructions that comprise the computation.",
|
| "items": {
|
| - "$ref": "StreamingComputationConfig"
|
| + "$ref": "ParallelInstruction"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "PipelineDescription": {
|
| - "description": "A descriptive representation of submitted pipeline as well as the executed\nform. This data is provided by the Dataflow service for ease of visualizing\nthe pipeline and interpretting Dataflow provided metrics.",
|
| - "id": "PipelineDescription",
|
| + "TransformSummary": {
|
| + "description": "Description of the type, names/ids, and input/outputs for a transform.",
|
| + "id": "TransformSummary",
|
| "properties": {
|
| - "executionPipelineStage": {
|
| - "description": "Description of each stage of execution of the pipeline.",
|
| + "inputCollectionName": {
|
| + "description": "User names for all collection inputs to this transform.",
|
| "items": {
|
| - "$ref": "ExecutionStageSummary"
|
| + "type": "string"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "name": {
|
| + "description": "User provided name for this transform instance.",
|
| + "type": "string"
|
| + },
|
| + "id": {
|
| + "description": "SDK generated id of this transform instance.",
|
| + "type": "string"
|
| + },
|
| + "outputCollectionName": {
|
| + "description": "User names for all collection outputs to this transform.",
|
| + "items": {
|
| + "type": "string"
|
| },
|
| "type": "array"
|
| },
|
| - "originalPipelineTransform": {
|
| - "description": "Description of each transform in the pipeline and collections between them.",
|
| + "displayData": {
|
| + "description": "Transform-specific display data.",
|
| "items": {
|
| - "$ref": "TransformSummary"
|
| + "$ref": "DisplayData"
|
| },
|
| "type": "array"
|
| },
|
| - "displayData": {
|
| - "description": "Pipeline level display data.",
|
| + "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"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "LeaseWorkItemResponse": {
|
| + "description": "Response to a request to lease WorkItems.",
|
| + "id": "LeaseWorkItemResponse",
|
| + "properties": {
|
| + "workItems": {
|
| + "description": "A list of the leased WorkItems.",
|
| "items": {
|
| - "$ref": "DisplayData"
|
| + "$ref": "WorkItem"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "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",
|
| + "LaunchTemplateParameters": {
|
| + "description": "Parameters to provide to the template being launched.",
|
| + "id": "LaunchTemplateParameters",
|
| "properties": {
|
| - "stages": {
|
| + "parameters": {
|
| "additionalProperties": {
|
| - "$ref": "JobExecutionStageInfo"
|
| + "type": "string"
|
| },
|
| - "description": "A mapping from each stage to the information about that stage.",
|
| + "description": "The runtime parameters to pass to the job.",
|
| "type": "object"
|
| + },
|
| + "jobName": {
|
| + "description": "Required. The job name to use for the created job.",
|
| + "type": "string"
|
| + },
|
| + "environment": {
|
| + "$ref": "RuntimeEnvironment",
|
| + "description": "The runtime environment for the job."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Step": {
|
| - "description": "Defines a particular step within a Cloud Dataflow job.\n\nA job consists of multiple steps, each of which performs some\nspecific operation as part of the overall job. Data is typically\npassed from one step to another as part of the job.\n\nHere's an example of a sequence of steps which together implement a\nMap-Reduce job:\n\n * Read a collection of data from some source, parsing the\n collection's elements.\n\n * Validate the elements.\n\n * Apply a user-defined function to map each element to some value\n and extract an element-specific key value.\n\n * Group elements with the same key into a single element with\n that key, transforming a multiply-keyed collection into a\n uniquely-keyed collection.\n\n * Write the elements out to some data sink.\n\nNote that the Cloud Dataflow service may be used to run many different\ntypes of jobs, not just Map-Reduce.",
|
| - "id": "Step",
|
| + "Sink": {
|
| + "description": "A sink that records can be encoded and written to.",
|
| + "id": "Sink",
|
| "properties": {
|
| - "name": {
|
| - "description": "The name that identifies the step. This must be unique for each\nstep with respect to all other steps in the Cloud Dataflow job.",
|
| - "type": "string"
|
| - },
|
| - "kind": {
|
| - "description": "The kind of step in the Cloud Dataflow job.",
|
| - "type": "string"
|
| + "codec": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "The codec to use to encode data written to the sink.",
|
| + "type": "object"
|
| },
|
| - "properties": {
|
| + "spec": {
|
| "additionalProperties": {
|
| "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.\nMust be provided on Create. Only retrieved with JOB_VIEW_ALL.",
|
| + "description": "The sink to write to, plus its parameters.",
|
| "type": "object"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "FailedLocation": {
|
| - "description": "Indicates which location failed to respond to a request for data.",
|
| - "id": "FailedLocation",
|
| - "properties": {
|
| - "name": {
|
| - "description": "The name of the failed location.",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "Disk": {
|
| - "description": "Describes the data disk used by a workflow job.",
|
| - "id": "Disk",
|
| + "FlattenInstruction": {
|
| + "description": "An instruction that copies its inputs (zero or more) to its (single) output.",
|
| + "id": "FlattenInstruction",
|
| "properties": {
|
| - "diskType": {
|
| - "description": "Disk storage type, as defined by Google Compute Engine. This\nmust be a disk type appropriate to the project and zone in which\nthe workers will run. If unknown or unspecified, the service\nwill attempt to choose a reasonable default.\n\nFor example, the standard persistent disk type is a resource name\ntypically ending in \"pd-standard\". If SSD persistent disks are\navailable, the resource name typically ends with \"pd-ssd\". The\nactual valid values are defined the Google Compute Engine API,\nnot by the Cloud Dataflow API; consult the Google Compute Engine\ndocumentation for more information about determining the set of\navailable disk types for a particular project and zone.\n\nGoogle Compute Engine Disk types are local to a particular\nproject in a particular zone, and so the resource name will\ntypically look something like this:\n\ncompute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard",
|
| - "type": "string"
|
| - },
|
| - "sizeGb": {
|
| - "description": "Size of disk in GB. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - },
|
| - "mountPoint": {
|
| - "description": "Directory in a VM where disk is mounted.",
|
| - "type": "string"
|
| + "inputs": {
|
| + "description": "Describes the inputs to the flatten instruction.",
|
| + "items": {
|
| + "$ref": "InstructionInput"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ListJobMessagesResponse": {
|
| - "description": "Response to a request to list job messages.",
|
| - "id": "ListJobMessagesResponse",
|
| + "PartialGroupByKeyInstruction": {
|
| + "description": "An instruction that does a partial group-by-key.\nOne input and one output.",
|
| + "id": "PartialGroupByKeyInstruction",
|
| "properties": {
|
| - "jobMessages": {
|
| - "description": "Messages in ascending timestamp order.",
|
| + "sideInputs": {
|
| + "description": "Zero or more side inputs.",
|
| "items": {
|
| - "$ref": "JobMessage"
|
| + "$ref": "SideInputInfo"
|
| },
|
| "type": "array"
|
| },
|
| - "nextPageToken": {
|
| - "description": "The token to obtain the next page of results if there are more.",
|
| + "originalCombineValuesStepName": {
|
| + "description": "If this instruction includes a combining function, this is the name of the\nCombineValues instruction lifted into this instruction.",
|
| "type": "string"
|
| },
|
| - "autoscalingEvents": {
|
| - "description": "Autoscaling events in ascending timestamp order.",
|
| - "items": {
|
| - "$ref": "AutoscalingEvent"
|
| - },
|
| - "type": "array"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "CounterMetadata": {
|
| - "description": "CounterMetadata includes all static non-name non-value counter attributes.",
|
| - "id": "CounterMetadata",
|
| - "properties": {
|
| - "otherUnits": {
|
| - "description": "A string referring to the unit type.",
|
| - "type": "string"
|
| + "input": {
|
| + "$ref": "InstructionInput",
|
| + "description": "Describes the input to the partial group-by-key instruction."
|
| },
|
| - "description": {
|
| - "description": "Human-readable description of the counter semantics.",
|
| - "type": "string"
|
| + "valueCombiningFn": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "The value combining function to invoke.",
|
| + "type": "object"
|
| },
|
| - "kind": {
|
| - "description": "Counter aggregation kind.",
|
| - "enum": [
|
| - "INVALID",
|
| - "SUM",
|
| - "MAX",
|
| - "MIN",
|
| - "MEAN",
|
| - "OR",
|
| - "AND",
|
| - "SET",
|
| - "DISTRIBUTION"
|
| - ],
|
| - "enumDescriptions": [
|
| - "Counter aggregation kind was not set.",
|
| - "Aggregated value is the sum of all contributed values.",
|
| - "Aggregated value is the max of all contributed values.",
|
| - "Aggregated value is the min of all contributed values.",
|
| - "Aggregated value is the mean of all contributed values.",
|
| - "Aggregated value represents the logical 'or' of all contributed values.",
|
| - "Aggregated value represents the logical 'and' of all contributed values.",
|
| - "Aggregated value is a set of unique contributed values.",
|
| - "Aggregated value captures statistics about a distribution."
|
| - ],
|
| - "type": "string"
|
| + "inputElementCodec": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "The codec to use for interpreting an element in the input PTable.",
|
| + "type": "object"
|
| },
|
| - "standardUnits": {
|
| - "description": "System defined Units, see above enum.",
|
| - "enum": [
|
| - "BYTES",
|
| - "BYTES_PER_SEC",
|
| - "MILLISECONDS",
|
| - "MICROSECONDS",
|
| - "NANOSECONDS",
|
| - "TIMESTAMP_MSEC",
|
| - "TIMESTAMP_USEC",
|
| - "TIMESTAMP_NSEC"
|
| - ],
|
| - "enumDescriptions": [
|
| - "Counter returns a value in bytes.",
|
| - "Counter returns a value in bytes per second.",
|
| - "Counter returns a value in milliseconds.",
|
| - "Counter returns a value in microseconds.",
|
| - "Counter returns a value in nanoseconds.",
|
| - "Counter returns a timestamp in milliseconds.",
|
| - "Counter returns a timestamp in microseconds.",
|
| - "Counter returns a timestamp in nanoseconds."
|
| - ],
|
| + "originalCombineValuesInputStoreName": {
|
| + "description": "If this instruction includes a combining function this is the name of the\nintermediate store between the GBK and the CombineValues.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ApproximateReportedProgress": {
|
| - "description": "A progress measurement of a WorkItem by a worker.",
|
| - "id": "ApproximateReportedProgress",
|
| + "StageSource": {
|
| + "description": "Description of an input or output of an execution stage.",
|
| + "id": "StageSource",
|
| "properties": {
|
| - "fractionConsumed": {
|
| - "description": "Completion as fraction of the input consumed, from 0.0 (beginning, nothing\nconsumed), to 1.0 (end of the input, entire input consumed).",
|
| - "format": "double",
|
| - "type": "number"
|
| - },
|
| - "consumedParallelism": {
|
| - "$ref": "ReportedParallelism",
|
| - "description": "Total amount of parallelism in the portion of input of this task that has\nalready been consumed and is no longer active. In the first two examples\nabove (see remaining_parallelism), the value should be 29 or 2\nrespectively. The sum of remaining_parallelism and consumed_parallelism\nshould equal the total amount of parallelism in this work item. If\nspecified, must be finite."
|
| + "sizeBytes": {
|
| + "description": "Size of the source, if measurable.",
|
| + "format": "int64",
|
| + "type": "string"
|
| },
|
| - "remainingParallelism": {
|
| - "$ref": "ReportedParallelism",
|
| - "description": "Total amount of parallelism in the input of this task that remains,\n(i.e. can be delegated to this task and any new tasks via dynamic\nsplitting). Always at least 1 for non-finished work items and 0 for\nfinished.\n\n\"Amount of parallelism\" refers to how many non-empty parts of the input\ncan be read in parallel. This does not necessarily equal number\nof records. An input that can be read in parallel down to the\nindividual records is called \"perfectly splittable\".\nAn example of non-perfectly parallelizable input is a block-compressed\nfile format where a block of records has to be read as a whole,\nbut different blocks can be read in parallel.\n\nExamples:\n* If we are processing record #30 (starting at 1) out of 50 in a perfectly\n splittable 50-record input, this value should be 21 (20 remaining + 1\n current).\n* If we are reading through block 3 in a block-compressed file consisting\n of 5 blocks, this value should be 3 (since blocks 4 and 5 can be\n processed in parallel by new tasks via dynamic splitting and the current\n task remains processing block 3).\n* If we are reading through the last block in a block-compressed file,\n or reading or processing the last record in a perfectly splittable\n input, this value should be 1, because apart from the current task, no\n additional remainder can be split off."
|
| + "name": {
|
| + "description": "Dataflow service generated name for this source.",
|
| + "type": "string"
|
| },
|
| - "position": {
|
| - "$ref": "Position",
|
| - "description": "A Position within the work to represent a progress."
|
| + "userName": {
|
| + "description": "Human-readable name for this source; may be user or system generated.",
|
| + "type": "string"
|
| + },
|
| + "originalTransformOrCollection": {
|
| + "description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StateFamilyConfig": {
|
| - "description": "State family configuration.",
|
| - "id": "StateFamilyConfig",
|
| + "InstructionInput": {
|
| + "description": "An input of an instruction, as a reference to an output of a\nproducer instruction.",
|
| + "id": "InstructionInput",
|
| "properties": {
|
| - "isRead": {
|
| - "description": "If true, this family corresponds to a read operation.",
|
| - "type": "boolean"
|
| + "producerInstructionIndex": {
|
| + "description": "The index (origin zero) of the parallel instruction that produces\nthe output to be consumed by this input. This index is relative\nto the list of instructions in this input's instruction's\ncontaining MapTask.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| },
|
| - "stateFamily": {
|
| - "description": "The state family value.",
|
| - "type": "string"
|
| + "outputNum": {
|
| + "description": "The output index (origin zero) within the producer.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "IntegerList": {
|
| - "description": "A metric value representing a list of integers.",
|
| - "id": "IntegerList",
|
| + "StringList": {
|
| + "description": "A metric value representing a list of strings.",
|
| + "id": "StringList",
|
| "properties": {
|
| "elements": {
|
| "description": "Elements of the list.",
|
| "items": {
|
| - "$ref": "SplitInt64"
|
| + "type": "string"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ResourceUtilizationReportResponse": {
|
| - "description": "Service-side response to WorkerMessage reporting resource utilization.",
|
| - "id": "ResourceUtilizationReportResponse",
|
| - "properties": {},
|
| - "type": "object"
|
| - },
|
| - "SourceSplitResponse": {
|
| - "description": "The response to a SourceSplitRequest.",
|
| - "id": "SourceSplitResponse",
|
| + "DisplayData": {
|
| + "description": "Data provided with a pipeline or transform to provide descriptive info.",
|
| + "id": "DisplayData",
|
| "properties": {
|
| - "shards": {
|
| - "description": "DEPRECATED in favor of bundles.",
|
| - "items": {
|
| - "$ref": "SourceSplitShard"
|
| - },
|
| - "type": "array"
|
| + "strValue": {
|
| + "description": "Contains value if the data is of string type.",
|
| + "type": "string"
|
| },
|
| - "outcome": {
|
| - "description": "Indicates whether splitting happened and produced a list of bundles.\nIf this is USE_CURRENT_SOURCE_AS_IS, the current source should\nbe processed \"as is\" without splitting. \"bundles\" is ignored in this case.\nIf this is SPLITTING_HAPPENED, then \"bundles\" contains a list of\nbundles into which the source was split.",
|
| - "enum": [
|
| - "SOURCE_SPLIT_OUTCOME_UNKNOWN",
|
| - "SOURCE_SPLIT_OUTCOME_USE_CURRENT",
|
| - "SOURCE_SPLIT_OUTCOME_SPLITTING_HAPPENED"
|
| - ],
|
| - "enumDescriptions": [
|
| - "The source split outcome is unknown, or unspecified.",
|
| - "The current source should be processed \"as is\" without splitting.",
|
| - "Splitting produced a list of bundles."
|
| - ],
|
| + "durationValue": {
|
| + "description": "Contains value if the data is of duration type.",
|
| + "format": "google-duration",
|
| "type": "string"
|
| },
|
| - "bundles": {
|
| - "description": "If outcome is SPLITTING_HAPPENED, then this is a list of bundles\ninto which the source was split. Otherwise this field is ignored.\nThis list can be empty, which means the source represents an empty input.",
|
| - "items": {
|
| - "$ref": "DerivedSource"
|
| - },
|
| - "type": "array"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "ParallelInstruction": {
|
| - "description": "Describes a particular operation comprising a MapTask.",
|
| - "id": "ParallelInstruction",
|
| - "properties": {
|
| - "name": {
|
| - "description": "User-provided name of this operation.",
|
| + "int64Value": {
|
| + "description": "Contains value if the data is of int64 type.",
|
| + "format": "int64",
|
| "type": "string"
|
| },
|
| - "read": {
|
| - "$ref": "ReadInstruction",
|
| - "description": "Additional information for Read instructions."
|
| + "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"
|
| },
|
| - "parDo": {
|
| - "$ref": "ParDoInstruction",
|
| - "description": "Additional information for ParDo instructions."
|
| + "floatValue": {
|
| + "description": "Contains value if the data is of float type.",
|
| + "format": "float",
|
| + "type": "number"
|
| },
|
| - "originalName": {
|
| - "description": "System-defined name for the operation in the original workflow graph.",
|
| + "key": {
|
| + "description": "The key identifying the display data.\nThis is intended to be used as a label for the display data\nwhen viewed in a dax monitoring system.",
|
| "type": "string"
|
| },
|
| - "flatten": {
|
| - "$ref": "FlattenInstruction",
|
| - "description": "Additional information for Flatten instructions."
|
| - },
|
| - "write": {
|
| - "$ref": "WriteInstruction",
|
| - "description": "Additional information for Write instructions."
|
| + "shortStrValue": {
|
| + "description": "A possible additional shorter value to display.\nFor example a java_class_name_value of com.mypackage.MyDoFn\nwill be stored with MyDoFn as the short_str_value and\ncom.mypackage.MyDoFn as the java_class_name value.\nshort_str_value can be displayed and java_class_name_value\nwill be displayed as a tooltip.",
|
| + "type": "string"
|
| },
|
| - "systemName": {
|
| - "description": "System-defined name of this operation.\nUnique across the workflow.",
|
| + "url": {
|
| + "description": "An optional full URL.",
|
| "type": "string"
|
| },
|
| - "partialGroupByKey": {
|
| - "$ref": "PartialGroupByKeyInstruction",
|
| - "description": "Additional information for PartialGroupByKey instructions."
|
| + "label": {
|
| + "description": "An optional label to display in a dax UI for the element.",
|
| + "type": "string"
|
| },
|
| - "outputs": {
|
| - "description": "Describes the outputs of the instruction.",
|
| - "items": {
|
| - "$ref": "InstructionOutput"
|
| - },
|
| - "type": "array"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "Package": {
|
| - "description": "The packages that must be installed in order for a worker to run the\nsteps of the Cloud Dataflow job that will be assigned to its worker\npool.\n\nThis is the mechanism by which the Cloud Dataflow SDK causes code to\nbe loaded onto the workers. For example, the Cloud Dataflow Java SDK\nmight use this to install jars containing the user's code and all of the\nvarious dependencies (libraries, data files, etc.) required in order\nfor that code to run.",
|
| - "id": "Package",
|
| - "properties": {
|
| - "name": {
|
| - "description": "The name of the package.",
|
| + "timestampValue": {
|
| + "description": "Contains value if the data is of timestamp type.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| - "location": {
|
| - "description": "The resource to read the package from. The supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}\n bucket.storage.googleapis.com/",
|
| + "boolValue": {
|
| + "description": "Contains value if the data is of a boolean type.",
|
| + "type": "boolean"
|
| + },
|
| + "javaClassValue": {
|
| + "description": "Contains value if the data is of java class type.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "KeyRangeDataDiskAssignment": {
|
| - "description": "Data disk assignment information for a specific key-range of a sharded\ncomputation.\nCurrently we only support UTF-8 character splits to simplify encoding into\nJSON.",
|
| - "id": "KeyRangeDataDiskAssignment",
|
| + "GetDebugConfigRequest": {
|
| + "description": "Request to get updated debug configuration for component.",
|
| + "id": "GetDebugConfigRequest",
|
| "properties": {
|
| - "end": {
|
| - "description": "The end (exclusive) of the key range.",
|
| + "location": {
|
| + "description": "The location which contains the job specified by job_id.",
|
| "type": "string"
|
| },
|
| - "dataDisk": {
|
| - "description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
|
| + "componentId": {
|
| + "description": "The internal component id for which debug configuration is\nrequested.",
|
| "type": "string"
|
| },
|
| - "start": {
|
| - "description": "The start (inclusive) of the key range.",
|
| + "workerId": {
|
| + "description": "The worker id, i.e., VM hostname.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ParDoInstruction": {
|
| - "description": "An instruction that does a ParDo operation.\nTakes one main input and zero or more side inputs, and produces\nzero or more outputs.\nRuns user code.",
|
| - "id": "ParDoInstruction",
|
| + "LeaseWorkItemRequest": {
|
| + "description": "Request to lease WorkItems.",
|
| + "id": "LeaseWorkItemRequest",
|
| "properties": {
|
| - "sideInputs": {
|
| - "description": "Zero or more side inputs.",
|
| - "items": {
|
| - "$ref": "SideInputInfo"
|
| - },
|
| - "type": "array"
|
| + "currentWorkerTime": {
|
| + "description": "The current timestamp at the worker.",
|
| + "format": "google-datetime",
|
| + "type": "string"
|
| },
|
| - "multiOutputInfos": {
|
| - "description": "Information about each of the outputs, if user_fn is a MultiDoFn.",
|
| + "workItemTypes": {
|
| + "description": "Filter for WorkItem type.",
|
| "items": {
|
| - "$ref": "MultiOutputInfo"
|
| + "type": "string"
|
| },
|
| "type": "array"
|
| },
|
| - "userFn": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The user function to invoke.",
|
| - "type": "object"
|
| - },
|
| - "input": {
|
| - "$ref": "InstructionInput",
|
| - "description": "The input."
|
| - },
|
| - "numOutputs": {
|
| - "description": "The number of outputs.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - }
|
| - },
|
| - "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\", \"Or\", and \"Distribution\".\nThe specified aggregation kind is case-insensitive.\n\nIf omitted, this is not an aggregated value but instead\na single metric sample value.",
|
| + "location": {
|
| + "description": "The location which contains the WorkItem's job.",
|
| "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"
|
| - },
|
| - "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"
|
| + "workerCapabilities": {
|
| + "description": "Worker capabilities. WorkItems might be limited to workers with specific\ncapabilities.",
|
| + "items": {
|
| + "type": "string"
|
| + },
|
| + "type": "array"
|
| },
|
| - "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",
|
| + "workerId": {
|
| + "description": "Identifies the worker leasing work -- typically the ID of the\nvirtual machine running the worker.",
|
| "type": "string"
|
| },
|
| - "name": {
|
| - "$ref": "MetricStructuredName",
|
| - "description": "Name of the metric."
|
| - },
|
| - "distribution": {
|
| - "description": "A struct value describing properties of a distribution of numeric values.",
|
| - "type": "any"
|
| - },
|
| - "set": {
|
| - "description": "Worker-computed aggregate value for the \"Set\" aggregation kind. The only\npossible value type is a list of Values whose type can be Long, Double,\nor String, according to the metric's type. All Values in the list must\nbe of the same type.",
|
| - "type": "any"
|
| - },
|
| - "cumulative": {
|
| - "description": "True if this metric is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this metric is reported\nas a delta that is not associated with any WorkItem.",
|
| - "type": "boolean"
|
| + "requestedLeaseDuration": {
|
| + "description": "The initial lease period.",
|
| + "format": "google-duration",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "GetTemplateResponse": {
|
| + "description": "The response to a GetTemplate request.",
|
| + "id": "GetTemplateResponse",
|
| + "properties": {
|
| + "metadata": {
|
| + "$ref": "TemplateMetadata",
|
| + "description": "The template metadata describing the template name, available\nparameters, etc."
|
| },
|
| - "internal": {
|
| - "description": "Worker-computed aggregate value for internal use by the Dataflow\nservice.",
|
| - "type": "any"
|
| + "status": {
|
| + "$ref": "Status",
|
| + "description": "The status of the get template request. Any problems with the\nrequest will be indicated in the error_details."
|
| }
|
| },
|
| "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",
|
| + "Parameter": {
|
| + "description": "Structured data associated with this message.",
|
| + "id": "Parameter",
|
| "properties": {
|
| - "componentStepName": {
|
| - "description": "Name of the optimized step being executed by the workers.",
|
| - "type": "string"
|
| + "value": {
|
| + "description": "Value for this parameter.",
|
| + "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."
|
| - ],
|
| + "key": {
|
| + "description": "Key or name for this parameter.",
|
| "type": "string"
|
| - },
|
| - "originalStepName": {
|
| - "description": "System generated name of the original step in the user's graph, before\noptimization.",
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "ReportWorkItemStatusRequest": {
|
| + "description": "Request to report the status of WorkItems.",
|
| + "id": "ReportWorkItemStatusRequest",
|
| + "properties": {
|
| + "currentWorkerTime": {
|
| + "description": "The current timestamp at the worker.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| "workerId": {
|
| - "description": "ID of a particular worker.",
|
| - "type": "string"
|
| - },
|
| - "originNamespace": {
|
| - "description": "A string containing a more specific namespace of the counter's origin.",
|
| - "type": "string"
|
| - },
|
| - "origin": {
|
| - "description": "One of the standard Origins defined above.",
|
| - "enum": [
|
| - "SYSTEM",
|
| - "USER"
|
| - ],
|
| - "enumDescriptions": [
|
| - "Counter was created by the Dataflow system.",
|
| - "Counter was created by the user."
|
| - ],
|
| + "description": "The ID of the worker reporting the WorkItem status. If this\ndoes not match the ID of the worker which the Dataflow service\nbelieves currently has the lease on the WorkItem, the report\nwill be dropped (with an error response).",
|
| "type": "string"
|
| },
|
| - "name": {
|
| - "description": "Counter name. Not necessarily globally-unique, but unique within the\ncontext of the other fields.\nRequired.",
|
| + "location": {
|
| + "description": "The location which contains the WorkItem's job.",
|
| "type": "string"
|
| },
|
| - "executionStepName": {
|
| - "description": "Name of the stage. An execution step contains multiple component steps.",
|
| - "type": "string"
|
| + "workItemStatuses": {
|
| + "description": "The order is unimportant, except that the order of the\nWorkItemServiceState messages in the ReportWorkItemStatusResponse\ncorresponds to the order of WorkItemStatus messages here.",
|
| + "items": {
|
| + "$ref": "WorkItemStatus"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ApproximateProgress": {
|
| - "description": "Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest.",
|
| - "id": "ApproximateProgress",
|
| + "StreamingConfigTask": {
|
| + "description": "A task that carries configuration information for streaming computations.",
|
| + "id": "StreamingConfigTask",
|
| "properties": {
|
| - "remainingTime": {
|
| - "description": "Obsolete.",
|
| - "format": "google-duration",
|
| + "windmillServicePort": {
|
| + "description": "If present, the worker must use this port to communicate with Windmill\nService dispatchers. Only applicable when windmill_service_endpoint is\nspecified.",
|
| + "format": "int64",
|
| "type": "string"
|
| },
|
| - "position": {
|
| - "$ref": "Position",
|
| - "description": "Obsolete."
|
| + "streamingComputationConfigs": {
|
| + "description": "Set of computation configuration information.",
|
| + "items": {
|
| + "$ref": "StreamingComputationConfig"
|
| + },
|
| + "type": "array"
|
| },
|
| - "percentComplete": {
|
| - "description": "Obsolete.",
|
| - "format": "float",
|
| - "type": "number"
|
| + "windmillServiceEndpoint": {
|
| + "description": "If present, the worker must use this endpoint to communicate with Windmill\nService dispatchers, otherwise the worker must continue to use whatever\nendpoint it had been using.",
|
| + "type": "string"
|
| + },
|
| + "userStepToStateFamilyNameMap": {
|
| + "additionalProperties": {
|
| + "type": "string"
|
| + },
|
| + "description": "Map from user step names to state families.",
|
| + "type": "object"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerMessageResponse": {
|
| - "description": "A worker_message response allows the server to pass information to the\nsender.",
|
| - "id": "WorkerMessageResponse",
|
| + "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": {
|
| - "workerMetricsResponse": {
|
| - "$ref": "ResourceUtilizationReportResponse",
|
| - "description": "Service's response to reporting worker metrics (currently empty)."
|
| + "displayData": {
|
| + "description": "Pipeline level display data.",
|
| + "items": {
|
| + "$ref": "DisplayData"
|
| + },
|
| + "type": "array"
|
| },
|
| - "workerHealthReportResponse": {
|
| - "$ref": "WorkerHealthReportResponse",
|
| - "description": "The service's response to a worker's health report."
|
| + "executionPipelineStage": {
|
| + "description": "Description of each stage of execution of the pipeline.",
|
| + "items": {
|
| + "$ref": "ExecutionStageSummary"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "originalPipelineTransform": {
|
| + "description": "Description of each transform in the pipeline and collections between them.",
|
| + "items": {
|
| + "$ref": "TransformSummary"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "TemplateMetadata": {
|
| - "description": "Metadata describing a template.",
|
| - "id": "TemplateMetadata",
|
| + "Step": {
|
| + "description": "Defines a particular step within a Cloud Dataflow job.\n\nA job consists of multiple steps, each of which performs some\nspecific operation as part of the overall job. Data is typically\npassed from one step to another as part of the job.\n\nHere's an example of a sequence of steps which together implement a\nMap-Reduce job:\n\n * Read a collection of data from some source, parsing the\n collection's elements.\n\n * Validate the elements.\n\n * Apply a user-defined function to map each element to some value\n and extract an element-specific key value.\n\n * Group elements with the same key into a single element with\n that key, transforming a multiply-keyed collection into a\n uniquely-keyed collection.\n\n * Write the elements out to some data sink.\n\nNote that the Cloud Dataflow service may be used to run many different\ntypes of jobs, not just Map-Reduce.",
|
| + "id": "Step",
|
| "properties": {
|
| - "parameters": {
|
| - "description": "The parameters for the template.",
|
| - "items": {
|
| - "$ref": "ParameterMetadata"
|
| + "properties": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| },
|
| - "type": "array"
|
| + "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"
|
| },
|
| "name": {
|
| - "description": "Required. The name of the template.",
|
| + "description": "The name that identifies the step. This must be unique for each\nstep with respect to all other steps in the Cloud Dataflow job.",
|
| "type": "string"
|
| },
|
| - "description": {
|
| - "description": "Optional. A description of the template.",
|
| + "kind": {
|
| + "description": "The kind of step in the Cloud Dataflow job.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerMessage": {
|
| - "description": "WorkerMessage provides information to the backend about a worker.",
|
| - "id": "WorkerMessage",
|
| + "JobExecutionInfo": {
|
| + "description": "Additional information about how a Cloud Dataflow job will be executed that\nisn't contained in the submitted job.",
|
| + "id": "JobExecutionInfo",
|
| "properties": {
|
| - "labels": {
|
| + "stages": {
|
| "additionalProperties": {
|
| - "type": "string"
|
| + "$ref": "JobExecutionStageInfo"
|
| },
|
| - "description": "Labels are used to group WorkerMessages.\nFor example, a worker_message about a particular container\nmight have the labels:\n{ \"JOB_ID\": \"2015-04-22\",\n \"WORKER_ID\": \"wordcount-vm-2015…\"\n \"CONTAINER_TYPE\": \"worker\",\n \"CONTAINER_ID\": \"ac1234def\"}\nLabel tags typically correspond to Label enum values. However, for ease\nof development other strings can be used as tags. LABEL_UNSPECIFIED should\nnot be used here.",
|
| + "description": "A mapping from each stage to the information about that stage.",
|
| "type": "object"
|
| - },
|
| - "time": {
|
| - "description": "The timestamp of the worker_message.",
|
| - "format": "google-datetime",
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "FailedLocation": {
|
| + "description": "Indicates which location failed to respond to a request for data.",
|
| + "id": "FailedLocation",
|
| + "properties": {
|
| + "name": {
|
| + "description": "The name of the failed location.",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "Disk": {
|
| + "description": "Describes the data disk used by a workflow job.",
|
| + "id": "Disk",
|
| + "properties": {
|
| + "diskType": {
|
| + "description": "Disk storage type, as defined by Google Compute Engine. This\nmust be a disk type appropriate to the project and zone in which\nthe workers will run. If unknown or unspecified, the service\nwill attempt to choose a reasonable default.\n\nFor example, the standard persistent disk type is a resource name\ntypically ending in \"pd-standard\". If SSD persistent disks are\navailable, the resource name typically ends with \"pd-ssd\". The\nactual valid values are defined the Google Compute Engine API,\nnot by the Cloud Dataflow API; consult the Google Compute Engine\ndocumentation for more information about determining the set of\navailable disk types for a particular project and zone.\n\nGoogle Compute Engine Disk types are local to a particular\nproject in a particular zone, and so the resource name will\ntypically look something like this:\n\ncompute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard",
|
| "type": "string"
|
| },
|
| - "workerHealthReport": {
|
| - "$ref": "WorkerHealthReport",
|
| - "description": "The health of a worker."
|
| - },
|
| - "workerMetrics": {
|
| - "$ref": "ResourceUtilizationReport",
|
| - "description": "Resource metrics reported by workers."
|
| + "sizeGb": {
|
| + "description": "Size of disk in GB. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| },
|
| - "workerMessageCode": {
|
| - "$ref": "WorkerMessageCode",
|
| - "description": "A worker message code."
|
| + "mountPoint": {
|
| + "description": "Directory in a VM where disk is mounted.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "JobMetrics": {
|
| - "description": "JobMetrics contains a collection of metrics descibing the detailed progress\nof a Dataflow job. Metrics correspond to user-defined and system-defined\nmetrics in the job.\n\nThis resource captures only the most recent values of each metric;\ntime-series data can be queried for them (under the same metric names)\nfrom Cloud Monitoring.",
|
| - "id": "JobMetrics",
|
| + "ListJobMessagesResponse": {
|
| + "description": "Response to a request to list job messages.",
|
| + "id": "ListJobMessagesResponse",
|
| "properties": {
|
| - "metrics": {
|
| - "description": "All metrics for this job.",
|
| + "jobMessages": {
|
| + "description": "Messages in ascending timestamp order.",
|
| + "items": {
|
| + "$ref": "JobMessage"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "nextPageToken": {
|
| + "description": "The token to obtain the next page of results if there are more.",
|
| + "type": "string"
|
| + },
|
| + "autoscalingEvents": {
|
| + "description": "Autoscaling events in ascending timestamp order.",
|
| "items": {
|
| - "$ref": "MetricUpdate"
|
| + "$ref": "AutoscalingEvent"
|
| },
|
| "type": "array"
|
| - },
|
| - "metricTime": {
|
| - "description": "Timestamp as of which metric values are current.",
|
| - "format": "google-datetime",
|
| - "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "FloatingPointList": {
|
| - "description": "A metric value representing a list of floating point numbers.",
|
| - "id": "FloatingPointList",
|
| + "CounterMetadata": {
|
| + "description": "CounterMetadata includes all static non-name non-value counter attributes.",
|
| + "id": "CounterMetadata",
|
| "properties": {
|
| - "elements": {
|
| - "description": "Elements of the list.",
|
| - "items": {
|
| - "format": "double",
|
| - "type": "number"
|
| - },
|
| - "type": "array"
|
| + "otherUnits": {
|
| + "description": "A string referring to the unit type.",
|
| + "type": "string"
|
| + },
|
| + "description": {
|
| + "description": "Human-readable description of the counter semantics.",
|
| + "type": "string"
|
| + },
|
| + "kind": {
|
| + "description": "Counter aggregation kind.",
|
| + "enum": [
|
| + "INVALID",
|
| + "SUM",
|
| + "MAX",
|
| + "MIN",
|
| + "MEAN",
|
| + "OR",
|
| + "AND",
|
| + "SET",
|
| + "DISTRIBUTION"
|
| + ],
|
| + "enumDescriptions": [
|
| + "Counter aggregation kind was not set.",
|
| + "Aggregated value is the sum of all contributed values.",
|
| + "Aggregated value is the max of all contributed values.",
|
| + "Aggregated value is the min of all contributed values.",
|
| + "Aggregated value is the mean of all contributed values.",
|
| + "Aggregated value represents the logical 'or' of all contributed values.",
|
| + "Aggregated value represents the logical 'and' of all contributed values.",
|
| + "Aggregated value is a set of unique contributed values.",
|
| + "Aggregated value captures statistics about a distribution."
|
| + ],
|
| + "type": "string"
|
| + },
|
| + "standardUnits": {
|
| + "description": "System defined Units, see above enum.",
|
| + "enum": [
|
| + "BYTES",
|
| + "BYTES_PER_SEC",
|
| + "MILLISECONDS",
|
| + "MICROSECONDS",
|
| + "NANOSECONDS",
|
| + "TIMESTAMP_MSEC",
|
| + "TIMESTAMP_USEC",
|
| + "TIMESTAMP_NSEC"
|
| + ],
|
| + "enumDescriptions": [
|
| + "Counter returns a value in bytes.",
|
| + "Counter returns a value in bytes per second.",
|
| + "Counter returns a value in milliseconds.",
|
| + "Counter returns a value in microseconds.",
|
| + "Counter returns a value in nanoseconds.",
|
| + "Counter returns a timestamp in milliseconds.",
|
| + "Counter returns a timestamp in microseconds.",
|
| + "Counter returns a timestamp in nanoseconds."
|
| + ],
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "CounterUpdate": {
|
| - "description": "An update to a Counter sent from a worker.",
|
| - "id": "CounterUpdate",
|
| + "ApproximateReportedProgress": {
|
| + "description": "A progress measurement of a WorkItem by a worker.",
|
| + "id": "ApproximateReportedProgress",
|
| "properties": {
|
| - "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."
|
| - },
|
| - "integerList": {
|
| - "$ref": "IntegerList",
|
| - "description": "List of integers, for Set."
|
| - },
|
| - "integerMean": {
|
| - "$ref": "IntegerMean",
|
| - "description": "Integer mean aggregation value for Mean."
|
| + "position": {
|
| + "$ref": "Position",
|
| + "description": "A Position within the work to represent a progress."
|
| },
|
| - "floatingPoint": {
|
| - "description": "Floating point value for Sum, Max, Min.",
|
| + "fractionConsumed": {
|
| + "description": "Completion as fraction of the input consumed, from 0.0 (beginning, nothing\nconsumed), to 1.0 (end of the input, entire input consumed).",
|
| "format": "double",
|
| "type": "number"
|
| },
|
| - "internal": {
|
| - "description": "Value for internally-defined counters used by the Dataflow service.",
|
| - "type": "any"
|
| - },
|
| - "cumulative": {
|
| - "description": "True if this counter is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this counter is reported\nas a delta.",
|
| - "type": "boolean"
|
| - },
|
| - "floatingPointMean": {
|
| - "$ref": "FloatingPointMean",
|
| - "description": "Floating point mean aggregation value for Mean."
|
| - },
|
| - "boolean": {
|
| - "description": "Boolean value for And, Or.",
|
| - "type": "boolean"
|
| - },
|
| - "nameAndKind": {
|
| - "$ref": "NameAndKind",
|
| - "description": "Counter name and aggregation type."
|
| - },
|
| - "stringList": {
|
| - "$ref": "StringList",
|
| - "description": "List of strings, for Set."
|
| - },
|
| - "distribution": {
|
| - "$ref": "DistributionUpdate",
|
| - "description": "Distribution data"
|
| + "consumedParallelism": {
|
| + "$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."
|
| },
|
| - "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"
|
| + "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"
|
| },
|
| - "SourceMetadata": {
|
| - "description": "Metadata about a Source useful for automatically optimizing\nand tuning the pipeline, etc.",
|
| - "id": "SourceMetadata",
|
| + "StateFamilyConfig": {
|
| + "description": "State family configuration.",
|
| + "id": "StateFamilyConfig",
|
| "properties": {
|
| - "estimatedSizeBytes": {
|
| - "description": "An estimate of the total size (in bytes) of the data that would be\nread from this source. This estimate is in terms of external storage\nsize, before any decompression or other processing done by the reader.",
|
| - "format": "int64",
|
| + "stateFamily": {
|
| + "description": "The state family value.",
|
| "type": "string"
|
| },
|
| - "infinite": {
|
| - "description": "Specifies that the size of this source is known to be infinite\n(this is a streaming source).",
|
| - "type": "boolean"
|
| - },
|
| - "producesSortedKeys": {
|
| - "description": "Whether this source is known to produce key/value pairs with\nthe (encoded) keys in lexicographically sorted order.",
|
| + "isRead": {
|
| + "description": "If true, this family corresponds to a read operation.",
|
| "type": "boolean"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "DistributionUpdate": {
|
| - "description": "A metric value representing a distribution.",
|
| - "id": "DistributionUpdate",
|
| + "IntegerList": {
|
| + "description": "A metric value representing a list of integers.",
|
| + "id": "IntegerList",
|
| "properties": {
|
| - "sum": {
|
| - "$ref": "SplitInt64",
|
| - "description": "Use an int64 since we'd prefer the added precision. If overflow is a common\nproblem we can detect it and use an additional int64 or a double."
|
| - },
|
| - "max": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The maximum value present in the distribution."
|
| - },
|
| - "logBuckets": {
|
| - "description": "(Optional) Logarithmic histogram of values.\nEach log may be in no more than one bucket. Order does not matter.",
|
| + "elements": {
|
| + "description": "Elements of the list.",
|
| "items": {
|
| - "$ref": "LogBucket"
|
| + "$ref": "SplitInt64"
|
| },
|
| "type": "array"
|
| - },
|
| - "count": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The count of the number of elements present in the distribution."
|
| - },
|
| - "sumOfSquares": {
|
| - "description": "Use a double since the sum of squares is likely to overflow int64.",
|
| - "format": "double",
|
| - "type": "number"
|
| - },
|
| - "min": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The minimum value present in the distribution."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerHealthReportResponse": {
|
| - "description": "WorkerHealthReportResponse contains information returned to the worker\nin response to a health ping.",
|
| - "id": "WorkerHealthReportResponse",
|
| - "properties": {
|
| - "reportInterval": {
|
| - "description": "A positive value indicates the worker should change its reporting interval\nto the specified value.\n\nThe default value of zero means no change in report rate is requested by\nthe server.",
|
| - "format": "google-duration",
|
| - "type": "string"
|
| - }
|
| - },
|
| + "ResourceUtilizationReportResponse": {
|
| + "description": "Service-side response to WorkerMessage reporting resource utilization.",
|
| + "id": "ResourceUtilizationReportResponse",
|
| + "properties": {},
|
| "type": "object"
|
| },
|
| - "SourceFork": {
|
| - "description": "DEPRECATED in favor of DynamicSourceSplit.",
|
| - "id": "SourceFork",
|
| + "SourceSplitResponse": {
|
| + "description": "The response to a SourceSplitRequest.",
|
| + "id": "SourceSplitResponse",
|
| "properties": {
|
| - "residualSource": {
|
| - "$ref": "DerivedSource",
|
| - "description": "DEPRECATED"
|
| - },
|
| - "primary": {
|
| - "$ref": "SourceSplitShard",
|
| - "description": "DEPRECATED"
|
| + "shards": {
|
| + "description": "DEPRECATED in favor of bundles.",
|
| + "items": {
|
| + "$ref": "SourceSplitShard"
|
| + },
|
| + "type": "array"
|
| },
|
| - "primarySource": {
|
| - "$ref": "DerivedSource",
|
| - "description": "DEPRECATED"
|
| + "outcome": {
|
| + "description": "Indicates whether splitting happened and produced a list of bundles.\nIf this is USE_CURRENT_SOURCE_AS_IS, the current source should\nbe processed \"as is\" without splitting. \"bundles\" is ignored in this case.\nIf this is SPLITTING_HAPPENED, then \"bundles\" contains a list of\nbundles into which the source was split.",
|
| + "enum": [
|
| + "SOURCE_SPLIT_OUTCOME_UNKNOWN",
|
| + "SOURCE_SPLIT_OUTCOME_USE_CURRENT",
|
| + "SOURCE_SPLIT_OUTCOME_SPLITTING_HAPPENED"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The source split outcome is unknown, or unspecified.",
|
| + "The current source should be processed \"as is\" without splitting.",
|
| + "Splitting produced a list of bundles."
|
| + ],
|
| + "type": "string"
|
| },
|
| - "residual": {
|
| - "$ref": "SourceSplitShard",
|
| - "description": "DEPRECATED"
|
| + "bundles": {
|
| + "description": "If outcome is SPLITTING_HAPPENED, then this is a list of bundles\ninto which the source was split. Otherwise this field is ignored.\nThis list can be empty, which means the source represents an empty input.",
|
| + "items": {
|
| + "$ref": "DerivedSource"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
|
|
Chromium Code Reviews
Issue 3003493002:
Api-Roll 53: 2017-08-21 (Closed)
