| Index: discovery/googleapis_beta/dataflow__v1b3.json
|
| diff --git a/discovery/googleapis_beta/dataflow__v1b3.json b/discovery/googleapis_beta/dataflow__v1b3.json
|
| index aececd68dd2de8b9f117ec2649ae194537911a63..7393c174153f1eecb66fd2e0da059c7e4003baf1 100644
|
| --- a/discovery/googleapis_beta/dataflow__v1b3.json
|
| +++ b/discovery/googleapis_beta/dataflow__v1b3.json
|
| @@ -17,7 +17,6 @@
|
| "description": "Manages Google Cloud Dataflow projects on Google Cloud Platform.",
|
| "discoveryVersion": "v1",
|
| "documentationLink": "https://cloud.google.com/dataflow",
|
| - "etag": "\"tbys6C40o18GZwyMen5GMkdK-3s/8IKdD_GkxmHITZPPBvAy8YZADEQ\"",
|
| "icons": {
|
| "x16": "http://www.google.com/images/icons/product/search-16.gif",
|
| "x32": "http://www.google.com/images/icons/product/search-32.gif"
|
| @@ -28,52 +27,31 @@
|
| "ownerDomain": "google.com",
|
| "ownerName": "Google",
|
| "parameters": {
|
| - "access_token": {
|
| - "description": "OAuth access token.",
|
| + "quotaUser": {
|
| + "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.",
|
| "location": "query",
|
| "type": "string"
|
| },
|
| - "alt": {
|
| - "default": "json",
|
| - "description": "Data format for response.",
|
| - "enumDescriptions": [
|
| - "Responses with Content-Type of application/json",
|
| - "Media download with context-dependent Content-Type",
|
| - "Responses with Content-Type of application/x-protobuf"
|
| - ],
|
| + "pp": {
|
| + "default": "true",
|
| + "description": "Pretty-print response.",
|
| "location": "query",
|
| - "type": "string"
|
| + "type": "boolean"
|
| },
|
| "bearer_token": {
|
| "description": "OAuth bearer token.",
|
| "location": "query",
|
| "type": "string"
|
| },
|
| - "callback": {
|
| - "description": "JSONP",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "fields": {
|
| - "description": "Selector specifying which fields to include in a partial response.",
|
| - "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"
|
| - },
|
| "oauth_token": {
|
| "description": "OAuth 2.0 token for the current user.",
|
| "location": "query",
|
| "type": "string"
|
| },
|
| - "pp": {
|
| - "default": "true",
|
| - "description": "Pretty-print response.",
|
| + "upload_protocol": {
|
| + "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
|
| "location": "query",
|
| - "type": "boolean"
|
| + "type": "string"
|
| },
|
| "prettyPrint": {
|
| "default": "true",
|
| @@ -81,29 +59,59 @@
|
| "location": "query",
|
| "type": "boolean"
|
| },
|
| - "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.",
|
| + "uploadType": {
|
| + "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
|
| "location": "query",
|
| "type": "string"
|
| },
|
| - "upload_protocol": {
|
| - "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
|
| + "fields": {
|
| + "description": "Selector specifying which fields to include in a partial response.",
|
| "location": "query",
|
| "type": "string"
|
| },
|
| - "uploadType": {
|
| - "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
|
| + "callback": {
|
| + "description": "JSONP",
|
| "location": "query",
|
| "type": "string"
|
| },
|
| "$.xgafv": {
|
| "description": "V1 error format.",
|
| + "enum": [
|
| + "1",
|
| + "2"
|
| + ],
|
| "enumDescriptions": [
|
| "v1 error format",
|
| "v2 error format"
|
| ],
|
| "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"
|
| }
|
| },
|
| "protocol": "rest",
|
| @@ -139,499 +147,237 @@
|
| }
|
| },
|
| "resources": {
|
| - "jobs": {
|
| - "methods": {
|
| - "create": {
|
| - "description": "Creates a Cloud Dataflow job.",
|
| - "httpMethod": "POST",
|
| - "id": "dataflow.projects.jobs.create",
|
| - "parameterOrder": [
|
| - "projectId"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "view": {
|
| - "description": "The level of information requested in response.",
|
| - "enum": [
|
| - "JOB_VIEW_UNKNOWN",
|
| - "JOB_VIEW_SUMMARY",
|
| - "JOB_VIEW_ALL"
|
| + "locations": {
|
| + "resources": {
|
| + "jobs": {
|
| + "methods": {
|
| + "getMetrics": {
|
| + "description": "Request the job status.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.locations.jobs.getMetrics",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "location",
|
| + "jobId"
|
| ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "replaceJobId": {
|
| - "description": "Deprecated. This field is now in the Job message.",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location that contains this job.",
|
| - "location": "query",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/jobs",
|
| - "request": {
|
| - "$ref": "Job"
|
| - },
|
| - "response": {
|
| - "$ref": "Job"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - },
|
| - "get": {
|
| - "description": "Gets the state of the specified Cloud Dataflow job.",
|
| - "httpMethod": "GET",
|
| - "id": "dataflow.projects.jobs.get",
|
| - "parameterOrder": [
|
| - "projectId",
|
| - "jobId"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "jobId": {
|
| - "description": "The job ID.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| + "parameters": {
|
| + "location": {
|
| + "description": "The location which contains the job specified by job_id.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "startTime": {
|
| + "description": "Return only metric data that has changed since this time.\nDefault is to return all information about all metrics for the job.",
|
| + "format": "google-datetime",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "projectId": {
|
| + "description": "A project id.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "jobId": {
|
| + "description": "The job to get messages for.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics",
|
| + "response": {
|
| + "$ref": "JobMetrics"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| },
|
| - "view": {
|
| - "description": "The level of information requested in response.",
|
| - "enum": [
|
| - "JOB_VIEW_UNKNOWN",
|
| - "JOB_VIEW_SUMMARY",
|
| - "JOB_VIEW_ALL"
|
| + "get": {
|
| + "description": "Gets the state of the specified Cloud Dataflow job.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.locations.jobs.get",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "location",
|
| + "jobId"
|
| ],
|
| - "location": "query",
|
| - "type": "string"
|
| + "parameters": {
|
| + "location": {
|
| + "description": "The location that contains this job.",
|
| + "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"
|
| + },
|
| + "jobId": {
|
| + "description": "The job ID.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "view": {
|
| + "description": "The level of information requested in response.",
|
| + "enum": [
|
| + "JOB_VIEW_UNKNOWN",
|
| + "JOB_VIEW_SUMMARY",
|
| + "JOB_VIEW_ALL"
|
| + ],
|
| + "location": "query",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
|
| + "response": {
|
| + "$ref": "Job"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| },
|
| - "location": {
|
| - "description": "The location that contains this job.",
|
| - "location": "query",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}",
|
| - "response": {
|
| - "$ref": "Job"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "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": {
|
| - "projectId": {
|
| - "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "jobId": {
|
| - "description": "The job ID.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location that contains this job.",
|
| - "location": "query",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}",
|
| - "request": {
|
| - "$ref": "Job"
|
| - },
|
| - "response": {
|
| - "$ref": "Job"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - },
|
| - "list": {
|
| - "description": "List the jobs of a project.",
|
| - "httpMethod": "GET",
|
| - "id": "dataflow.projects.jobs.list",
|
| - "parameterOrder": [
|
| - "projectId"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "The project which owns the jobs.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "filter": {
|
| - "description": "The kind of filter to use.",
|
| - "enum": [
|
| - "UNKNOWN",
|
| - "ALL",
|
| - "TERMINATED",
|
| - "ACTIVE"
|
| - ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "view": {
|
| - "description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
|
| - "enum": [
|
| - "JOB_VIEW_UNKNOWN",
|
| - "JOB_VIEW_SUMMARY",
|
| - "JOB_VIEW_ALL"
|
| - ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "pageSize": {
|
| - "description": "If there are many jobs, limit response to at most this many. The actual number of jobs returned will be the lesser of max_responses and an unspecified server-defined limit.",
|
| - "format": "int32",
|
| - "location": "query",
|
| - "type": "integer"
|
| - },
|
| - "pageToken": {
|
| - "description": "Set this to the 'next_page_token' field of a previous response to request additional results in a long list.",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location that contains this job.",
|
| - "location": "query",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/jobs",
|
| - "response": {
|
| - "$ref": "ListJobsResponse"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - },
|
| - "getMetrics": {
|
| - "description": "Request the job status.",
|
| - "httpMethod": "GET",
|
| - "id": "dataflow.projects.jobs.getMetrics",
|
| - "parameterOrder": [
|
| - "projectId",
|
| - "jobId"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "A project id.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "jobId": {
|
| - "description": "The job to get messages for.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "startTime": {
|
| - "description": "Return only metric data that has changed since this time. Default is to return all information about all metrics for the job.",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location which contains the job specified by job_id.",
|
| - "location": "query",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/metrics",
|
| - "response": {
|
| - "$ref": "JobMetrics"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - }
|
| - },
|
| - "resources": {
|
| - "debug": {
|
| - "methods": {
|
| - "getConfig": {
|
| - "description": "Get encoded debug configuration for component. Not cacheable.",
|
| - "httpMethod": "POST",
|
| - "id": "dataflow.projects.jobs.debug.getConfig",
|
| + "list": {
|
| + "description": "List the jobs of a project.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.locations.jobs.list",
|
| "parameterOrder": [
|
| "projectId",
|
| - "jobId"
|
| + "location"
|
| ],
|
| "parameters": {
|
| "projectId": {
|
| - "description": "The project id.",
|
| + "description": "The project which owns the jobs.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "jobId": {
|
| - "description": "The job id.",
|
| + "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": "path",
|
| "required": true,
|
| "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"
|
| + },
|
| + "view": {
|
| + "description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
|
| + "enum": [
|
| + "JOB_VIEW_UNKNOWN",
|
| + "JOB_VIEW_SUMMARY",
|
| + "JOB_VIEW_ALL"
|
| + ],
|
| + "location": "query",
|
| + "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/getConfig",
|
| - "request": {
|
| - "$ref": "GetDebugConfigRequest"
|
| - },
|
| + "path": "v1b3/projects/{projectId}/locations/{location}/jobs",
|
| "response": {
|
| - "$ref": "GetDebugConfigResponse"
|
| + "$ref": "ListJobsResponse"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| },
|
| - "sendCapture": {
|
| - "description": "Send encoded debug capture data for component.",
|
| - "httpMethod": "POST",
|
| - "id": "dataflow.projects.jobs.debug.sendCapture",
|
| + "update": {
|
| + "description": "Updates the state of an existing Cloud Dataflow job.",
|
| + "httpMethod": "PUT",
|
| + "id": "dataflow.projects.locations.jobs.update",
|
| "parameterOrder": [
|
| "projectId",
|
| + "location",
|
| "jobId"
|
| ],
|
| "parameters": {
|
| + "location": {
|
| + "description": "The location that contains this job.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| "projectId": {
|
| - "description": "The project id.",
|
| + "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| "jobId": {
|
| - "description": "The job id.",
|
| + "description": "The job ID.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/sendCapture",
|
| + "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
|
| "request": {
|
| - "$ref": "SendDebugCaptureRequest"
|
| + "$ref": "Job"
|
| },
|
| "response": {
|
| - "$ref": "SendDebugCaptureResponse"
|
| + "$ref": "Job"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| - }
|
| - }
|
| - },
|
| - "messages": {
|
| - "methods": {
|
| - "list": {
|
| - "description": "Request the job status.",
|
| - "httpMethod": "GET",
|
| - "id": "dataflow.projects.jobs.messages.list",
|
| + },
|
| + "create": {
|
| + "description": "Creates a Cloud Dataflow job.",
|
| + "httpMethod": "POST",
|
| + "id": "dataflow.projects.locations.jobs.create",
|
| "parameterOrder": [
|
| "projectId",
|
| - "jobId"
|
| + "location"
|
| ],
|
| "parameters": {
|
| "projectId": {
|
| - "description": "A project id.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "jobId": {
|
| - "description": "The job to get messages about.",
|
| + "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "minimumImportance": {
|
| - "description": "Filter to only get messages with importance >= level",
|
| + "view": {
|
| + "description": "The level of information requested in response.",
|
| "enum": [
|
| - "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
|
| - "JOB_MESSAGE_DEBUG",
|
| - "JOB_MESSAGE_DETAILED",
|
| - "JOB_MESSAGE_BASIC",
|
| - "JOB_MESSAGE_WARNING",
|
| - "JOB_MESSAGE_ERROR"
|
| + "JOB_VIEW_UNKNOWN",
|
| + "JOB_VIEW_SUMMARY",
|
| + "JOB_VIEW_ALL"
|
| ],
|
| "location": "query",
|
| "type": "string"
|
| },
|
| - "pageSize": {
|
| - "description": "If specified, determines the maximum number of messages to return. If unspecified, the service may choose an appropriate default, or may return an arbitrarily large number of results.",
|
| - "format": "int32",
|
| - "location": "query",
|
| - "type": "integer"
|
| - },
|
| - "pageToken": {
|
| - "description": "If supplied, this should be the value of next_page_token returned by an earlier call. This will cause the next page of results to be returned.",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "startTime": {
|
| - "description": "If specified, return only messages with timestamps >= start_time. The default is the job creation time (i.e. beginning of messages).",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "endTime": {
|
| - "description": "Return only messages with timestamps < end_time. The default is now (i.e. return up to the latest messages available).",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location which contains the job specified by job_id.",
|
| - "location": "query",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/messages",
|
| - "response": {
|
| - "$ref": "ListJobMessagesResponse"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - }
|
| - }
|
| - },
|
| - "workItems": {
|
| - "methods": {
|
| - "reportStatus": {
|
| - "description": "Reports the status of dataflow WorkItems leased by a worker.",
|
| - "httpMethod": "POST",
|
| - "id": "dataflow.projects.jobs.workItems.reportStatus",
|
| - "parameterOrder": [
|
| - "projectId",
|
| - "jobId"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "The project which owns the WorkItem's job.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "jobId": {
|
| - "description": "The job which the WorkItem is part of.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:reportStatus",
|
| - "request": {
|
| - "$ref": "ReportWorkItemStatusRequest"
|
| - },
|
| - "response": {
|
| - "$ref": "ReportWorkItemStatusResponse"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - },
|
| - "lease": {
|
| - "description": "Leases a dataflow WorkItem to run.",
|
| - "httpMethod": "POST",
|
| - "id": "dataflow.projects.jobs.workItems.lease",
|
| - "parameterOrder": [
|
| - "projectId",
|
| - "jobId"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "Identifies the project this worker belongs to.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "jobId": {
|
| - "description": "Identifies the workflow job this worker belongs to.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:lease",
|
| - "request": {
|
| - "$ref": "LeaseWorkItemRequest"
|
| - },
|
| - "response": {
|
| - "$ref": "LeaseWorkItemResponse"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - }
|
| - }
|
| - }
|
| - }
|
| - },
|
| - "locations": {
|
| - "resources": {
|
| - "jobs": {
|
| - "methods": {
|
| - "create": {
|
| - "description": "Creates a Cloud Dataflow job.",
|
| - "httpMethod": "POST",
|
| - "id": "dataflow.projects.locations.jobs.create",
|
| - "parameterOrder": [
|
| - "projectId",
|
| - "location"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| "location": {
|
| "description": "The location that contains this job.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "view": {
|
| - "description": "The level of information requested in response.",
|
| - "enum": [
|
| - "JOB_VIEW_UNKNOWN",
|
| - "JOB_VIEW_SUMMARY",
|
| - "JOB_VIEW_ALL"
|
| - ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| "replaceJobId": {
|
| "description": "Deprecated. This field is now in the Job message.",
|
| "location": "query",
|
| @@ -649,282 +395,52 @@
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| - },
|
| - "get": {
|
| - "description": "Gets the state of the specified Cloud Dataflow job.",
|
| - "httpMethod": "GET",
|
| - "id": "dataflow.projects.locations.jobs.get",
|
| - "parameterOrder": [
|
| - "projectId",
|
| - "location",
|
| - "jobId"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location that contains this job.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "jobId": {
|
| - "description": "The job ID.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "view": {
|
| - "description": "The level of information requested in response.",
|
| - "enum": [
|
| - "JOB_VIEW_UNKNOWN",
|
| - "JOB_VIEW_SUMMARY",
|
| - "JOB_VIEW_ALL"
|
| + }
|
| + },
|
| + "resources": {
|
| + "workItems": {
|
| + "methods": {
|
| + "lease": {
|
| + "description": "Leases a dataflow WorkItem to run.",
|
| + "httpMethod": "POST",
|
| + "id": "dataflow.projects.locations.jobs.workItems.lease",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "location",
|
| + "jobId"
|
| ],
|
| - "location": "query",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
|
| - "response": {
|
| - "$ref": "Job"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - },
|
| - "update": {
|
| - "description": "Updates the state of an existing Cloud Dataflow job.",
|
| - "httpMethod": "PUT",
|
| - "id": "dataflow.projects.locations.jobs.update",
|
| - "parameterOrder": [
|
| - "projectId",
|
| - "location",
|
| - "jobId"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location that contains this job.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| + "parameters": {
|
| + "location": {
|
| + "description": "The location which contains the WorkItem's job.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "projectId": {
|
| + "description": "Identifies the project this worker belongs to.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "jobId": {
|
| + "description": "Identifies the workflow job this worker belongs to.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease",
|
| + "request": {
|
| + "$ref": "LeaseWorkItemRequest"
|
| + },
|
| + "response": {
|
| + "$ref": "LeaseWorkItemResponse"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| },
|
| - "jobId": {
|
| - "description": "The job ID.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
|
| - "request": {
|
| - "$ref": "Job"
|
| - },
|
| - "response": {
|
| - "$ref": "Job"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - },
|
| - "list": {
|
| - "description": "List the jobs of a project.",
|
| - "httpMethod": "GET",
|
| - "id": "dataflow.projects.locations.jobs.list",
|
| - "parameterOrder": [
|
| - "projectId",
|
| - "location"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "The project which owns the jobs.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location that contains this job.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "filter": {
|
| - "description": "The kind of filter to use.",
|
| - "enum": [
|
| - "UNKNOWN",
|
| - "ALL",
|
| - "TERMINATED",
|
| - "ACTIVE"
|
| - ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "view": {
|
| - "description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
|
| - "enum": [
|
| - "JOB_VIEW_UNKNOWN",
|
| - "JOB_VIEW_SUMMARY",
|
| - "JOB_VIEW_ALL"
|
| - ],
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "pageSize": {
|
| - "description": "If there are many jobs, limit response to at most this many. The actual number of jobs returned will be the lesser of max_responses and an unspecified server-defined limit.",
|
| - "format": "int32",
|
| - "location": "query",
|
| - "type": "integer"
|
| - },
|
| - "pageToken": {
|
| - "description": "Set this to the 'next_page_token' field of a previous response to request additional results in a long list.",
|
| - "location": "query",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/locations/{location}/jobs",
|
| - "response": {
|
| - "$ref": "ListJobsResponse"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - },
|
| - "getMetrics": {
|
| - "description": "Request the job status.",
|
| - "httpMethod": "GET",
|
| - "id": "dataflow.projects.locations.jobs.getMetrics",
|
| - "parameterOrder": [
|
| - "projectId",
|
| - "location",
|
| - "jobId"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "A project id.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location which contains the job specified by job_id.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "jobId": {
|
| - "description": "The job to get messages for.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "startTime": {
|
| - "description": "Return only metric data that has changed since this time. Default is to return all information about all metrics for the job.",
|
| - "location": "query",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics",
|
| - "response": {
|
| - "$ref": "JobMetrics"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - }
|
| - },
|
| - "resources": {
|
| - "messages": {
|
| - "methods": {
|
| - "list": {
|
| - "description": "Request the job status.",
|
| - "httpMethod": "GET",
|
| - "id": "dataflow.projects.locations.jobs.messages.list",
|
| - "parameterOrder": [
|
| - "projectId",
|
| - "location",
|
| - "jobId"
|
| - ],
|
| - "parameters": {
|
| - "projectId": {
|
| - "description": "A project id.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "location": {
|
| - "description": "The location which contains the job specified by job_id.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "jobId": {
|
| - "description": "The job to get messages about.",
|
| - "location": "path",
|
| - "required": true,
|
| - "type": "string"
|
| - },
|
| - "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"
|
| - },
|
| - "pageSize": {
|
| - "description": "If specified, determines the maximum number of messages to return. If unspecified, the service may choose an appropriate default, or may return an arbitrarily large number of results.",
|
| - "format": "int32",
|
| - "location": "query",
|
| - "type": "integer"
|
| - },
|
| - "pageToken": {
|
| - "description": "If supplied, this should be the value of next_page_token returned by an earlier call. This will cause the next page of results to be returned.",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "startTime": {
|
| - "description": "If specified, return only messages with timestamps >= start_time. The default is the job creation time (i.e. beginning of messages).",
|
| - "location": "query",
|
| - "type": "string"
|
| - },
|
| - "endTime": {
|
| - "description": "Return only messages with timestamps < end_time. The default is now (i.e. return up to the latest messages available).",
|
| - "location": "query",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages",
|
| - "response": {
|
| - "$ref": "ListJobMessagesResponse"
|
| - },
|
| - "scopes": [
|
| - "https://www.googleapis.com/auth/cloud-platform",
|
| - "https://www.googleapis.com/auth/userinfo.email"
|
| - ]
|
| - }
|
| - }
|
| - },
|
| - "workItems": {
|
| - "methods": {
|
| "reportStatus": {
|
| "description": "Reports the status of dataflow WorkItems leased by a worker.",
|
| "httpMethod": "POST",
|
| @@ -941,14 +457,14 @@
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "location": {
|
| - "description": "The location which contains the WorkItem's job.",
|
| + "jobId": {
|
| + "description": "The job which the WorkItem is part of.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "jobId": {
|
| - "description": "The job which the WorkItem is part of.",
|
| + "location": {
|
| + "description": "The location which contains the WorkItem's job.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| @@ -965,42 +481,79 @@
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| "https://www.googleapis.com/auth/userinfo.email"
|
| ]
|
| - },
|
| - "lease": {
|
| - "description": "Leases a dataflow WorkItem to run.",
|
| - "httpMethod": "POST",
|
| - "id": "dataflow.projects.locations.jobs.workItems.lease",
|
| + }
|
| + }
|
| + },
|
| + "messages": {
|
| + "methods": {
|
| + "list": {
|
| + "description": "Request the job status.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.locations.jobs.messages.list",
|
| "parameterOrder": [
|
| "projectId",
|
| "location",
|
| "jobId"
|
| ],
|
| "parameters": {
|
| - "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 WorkItem's job.",
|
| + "projectId": {
|
| + "description": "A project id.",
|
| "location": "path",
|
| "required": true,
|
| "type": "string"
|
| },
|
| - "jobId": {
|
| - "description": "Identifies the workflow job this worker belongs to.",
|
| + "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"
|
| + },
|
| + "startTime": {
|
| + "description": "If specified, return only messages with timestamps >= start_time.\nThe default is the job creation time (i.e. beginning of messages).",
|
| + "format": "google-datetime",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "pageToken": {
|
| + "description": "If supplied, this should be the value of next_page_token returned\nby an earlier call. This will cause the next page of results to\nbe returned.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "pageSize": {
|
| + "description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results.",
|
| + "format": "int32",
|
| + "location": "query",
|
| + "type": "integer"
|
| + },
|
| + "minimumImportance": {
|
| + "description": "Filter to only get messages with importance >= level",
|
| + "enum": [
|
| + "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
|
| + "JOB_MESSAGE_DEBUG",
|
| + "JOB_MESSAGE_DETAILED",
|
| + "JOB_MESSAGE_BASIC",
|
| + "JOB_MESSAGE_WARNING",
|
| + "JOB_MESSAGE_ERROR"
|
| + ],
|
| + "location": "query",
|
| + "type": "string"
|
| }
|
| },
|
| - "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease",
|
| - "request": {
|
| - "$ref": "LeaseWorkItemRequest"
|
| - },
|
| + "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages",
|
| "response": {
|
| - "$ref": "LeaseWorkItemResponse"
|
| + "$ref": "ListJobMessagesResponse"
|
| },
|
| "scopes": [
|
| "https://www.googleapis.com/auth/cloud-platform",
|
| @@ -1043,609 +596,922 @@
|
| ]
|
| }
|
| }
|
| - }
|
| - }
|
| - }
|
| - },
|
| - "revision": "20161004",
|
| - "rootUrl": "https://dataflow.googleapis.com/",
|
| - "schemas": {
|
| - "GetDebugConfigRequest": {
|
| - "description": "Request to get updated debug configuration for component.",
|
| - "id": "GetDebugConfigRequest",
|
| - "properties": {
|
| - "workerId": {
|
| - "description": "The worker id, i.e., VM hostname.",
|
| - "type": "string"
|
| - },
|
| - "componentId": {
|
| - "description": "The internal component id for which debug configuration is requested.",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "GetDebugConfigResponse": {
|
| - "description": "Response to a get debug configuration request.",
|
| - "id": "GetDebugConfigResponse",
|
| - "properties": {
|
| - "config": {
|
| - "description": "The encoded debug configuration for the requested component.",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "SendDebugCaptureRequest": {
|
| - "description": "Request to send encoded debug information.",
|
| - "id": "SendDebugCaptureRequest",
|
| - "properties": {
|
| - "workerId": {
|
| - "description": "The worker id, i.e., VM hostname.",
|
| - "type": "string"
|
| - },
|
| - "componentId": {
|
| - "description": "The internal component id for which debug information is sent.",
|
| - "type": "string"
|
| - },
|
| - "data": {
|
| - "description": "The encoded debug information.",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "SendDebugCaptureResponse": {
|
| - "description": "Response to a send capture request. nothing",
|
| - "id": "SendDebugCaptureResponse",
|
| - "type": "object"
|
| - },
|
| - "Job": {
|
| - "description": "Defines a job to be run by the Cloud Dataflow service.",
|
| - "id": "Job",
|
| - "properties": {
|
| - "id": {
|
| - "description": "The unique ID of this job. This field is set by the Cloud Dataflow service when the Job is created, and is immutable for the life of the job.",
|
| - "type": "string"
|
| - },
|
| - "projectId": {
|
| - "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| - "type": "string"
|
| - },
|
| - "name": {
|
| - "description": "The user-specified Cloud Dataflow job name. Only one Job with a given name may exist in a project at any given time. If a caller attempts to create a Job with the same name as an already-existing Job, the attempt returns the existing Job. The name must match the regular expression `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`",
|
| - "type": "string"
|
| - },
|
| - "type": {
|
| - "description": "The type of Cloud Dataflow job.",
|
| - "enum": [
|
| - "JOB_TYPE_UNKNOWN",
|
| - "JOB_TYPE_BATCH",
|
| - "JOB_TYPE_STREAMING"
|
| - ],
|
| - "type": "string"
|
| - },
|
| - "environment": {
|
| - "$ref": "Environment",
|
| - "description": "The environment for the job."
|
| },
|
| - "steps": {
|
| - "description": "The top-level steps that constitute the entire job.",
|
| + "jobs": {
|
| + "methods": {
|
| + "getMetrics": {
|
| + "description": "Request the job status.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.jobs.getMetrics",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "jobId"
|
| + ],
|
| + "parameters": {
|
| + "projectId": {
|
| + "description": "A project id.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "jobId": {
|
| + "description": "The job to get messages for.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "location": {
|
| + "description": "The location which contains the job specified by job_id.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "startTime": {
|
| + "description": "Return only metric data that has changed since this time.\nDefault is to return all information about all metrics for the job.",
|
| + "format": "google-datetime",
|
| + "location": "query",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/metrics",
|
| + "response": {
|
| + "$ref": "JobMetrics"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + },
|
| + "get": {
|
| + "description": "Gets the state of the specified Cloud Dataflow job.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.jobs.get",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "jobId"
|
| + ],
|
| + "parameters": {
|
| + "projectId": {
|
| + "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "jobId": {
|
| + "description": "The job ID.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "view": {
|
| + "description": "The level of information requested in response.",
|
| + "enum": [
|
| + "JOB_VIEW_UNKNOWN",
|
| + "JOB_VIEW_SUMMARY",
|
| + "JOB_VIEW_ALL"
|
| + ],
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "location": {
|
| + "description": "The location that contains this job.",
|
| + "location": "query",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}",
|
| + "response": {
|
| + "$ref": "Job"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + },
|
| + "list": {
|
| + "description": "List the jobs of a project.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.jobs.list",
|
| + "parameterOrder": [
|
| + "projectId"
|
| + ],
|
| + "parameters": {
|
| + "projectId": {
|
| + "description": "The project which owns the jobs.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "filter": {
|
| + "description": "The kind of filter to use.",
|
| + "enum": [
|
| + "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"
|
| + },
|
| + "view": {
|
| + "description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
|
| + "enum": [
|
| + "JOB_VIEW_UNKNOWN",
|
| + "JOB_VIEW_SUMMARY",
|
| + "JOB_VIEW_ALL"
|
| + ],
|
| + "location": "query",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs",
|
| + "response": {
|
| + "$ref": "ListJobsResponse"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + },
|
| + "update": {
|
| + "description": "Updates the state of an existing Cloud Dataflow job.",
|
| + "httpMethod": "PUT",
|
| + "id": "dataflow.projects.jobs.update",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "jobId"
|
| + ],
|
| + "parameters": {
|
| + "location": {
|
| + "description": "The location that contains this job.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "projectId": {
|
| + "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "jobId": {
|
| + "description": "The job ID.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}",
|
| + "request": {
|
| + "$ref": "Job"
|
| + },
|
| + "response": {
|
| + "$ref": "Job"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + },
|
| + "create": {
|
| + "description": "Creates a Cloud Dataflow job.",
|
| + "httpMethod": "POST",
|
| + "id": "dataflow.projects.jobs.create",
|
| + "parameterOrder": [
|
| + "projectId"
|
| + ],
|
| + "parameters": {
|
| + "location": {
|
| + "description": "The location that contains this job.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "replaceJobId": {
|
| + "description": "Deprecated. This field is now in the Job message.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "projectId": {
|
| + "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "view": {
|
| + "description": "The level of information requested in response.",
|
| + "enum": [
|
| + "JOB_VIEW_UNKNOWN",
|
| + "JOB_VIEW_SUMMARY",
|
| + "JOB_VIEW_ALL"
|
| + ],
|
| + "location": "query",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs",
|
| + "request": {
|
| + "$ref": "Job"
|
| + },
|
| + "response": {
|
| + "$ref": "Job"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + }
|
| + },
|
| + "resources": {
|
| + "debug": {
|
| + "methods": {
|
| + "getConfig": {
|
| + "description": "Get encoded debug configuration for component. Not cacheable.",
|
| + "httpMethod": "POST",
|
| + "id": "dataflow.projects.jobs.debug.getConfig",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "jobId"
|
| + ],
|
| + "parameters": {
|
| + "projectId": {
|
| + "description": "The project id.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "jobId": {
|
| + "description": "The job id.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/getConfig",
|
| + "request": {
|
| + "$ref": "GetDebugConfigRequest"
|
| + },
|
| + "response": {
|
| + "$ref": "GetDebugConfigResponse"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + },
|
| + "sendCapture": {
|
| + "description": "Send encoded debug capture data for component.",
|
| + "httpMethod": "POST",
|
| + "id": "dataflow.projects.jobs.debug.sendCapture",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "jobId"
|
| + ],
|
| + "parameters": {
|
| + "projectId": {
|
| + "description": "The project id.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "jobId": {
|
| + "description": "The job id.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/sendCapture",
|
| + "request": {
|
| + "$ref": "SendDebugCaptureRequest"
|
| + },
|
| + "response": {
|
| + "$ref": "SendDebugCaptureResponse"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + }
|
| + }
|
| + },
|
| + "workItems": {
|
| + "methods": {
|
| + "reportStatus": {
|
| + "description": "Reports the status of dataflow WorkItems leased by a worker.",
|
| + "httpMethod": "POST",
|
| + "id": "dataflow.projects.jobs.workItems.reportStatus",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "jobId"
|
| + ],
|
| + "parameters": {
|
| + "projectId": {
|
| + "description": "The project which owns the WorkItem's job.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "jobId": {
|
| + "description": "The job which the WorkItem is part of.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:reportStatus",
|
| + "request": {
|
| + "$ref": "ReportWorkItemStatusRequest"
|
| + },
|
| + "response": {
|
| + "$ref": "ReportWorkItemStatusResponse"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + },
|
| + "lease": {
|
| + "description": "Leases a dataflow WorkItem to run.",
|
| + "httpMethod": "POST",
|
| + "id": "dataflow.projects.jobs.workItems.lease",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "jobId"
|
| + ],
|
| + "parameters": {
|
| + "projectId": {
|
| + "description": "Identifies the project this worker belongs to.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "jobId": {
|
| + "description": "Identifies the workflow job this worker belongs to.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:lease",
|
| + "request": {
|
| + "$ref": "LeaseWorkItemRequest"
|
| + },
|
| + "response": {
|
| + "$ref": "LeaseWorkItemResponse"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + }
|
| + }
|
| + },
|
| + "messages": {
|
| + "methods": {
|
| + "list": {
|
| + "description": "Request the job status.",
|
| + "httpMethod": "GET",
|
| + "id": "dataflow.projects.jobs.messages.list",
|
| + "parameterOrder": [
|
| + "projectId",
|
| + "jobId"
|
| + ],
|
| + "parameters": {
|
| + "minimumImportance": {
|
| + "description": "Filter to only get messages with importance >= level",
|
| + "enum": [
|
| + "JOB_MESSAGE_IMPORTANCE_UNKNOWN",
|
| + "JOB_MESSAGE_DEBUG",
|
| + "JOB_MESSAGE_DETAILED",
|
| + "JOB_MESSAGE_BASIC",
|
| + "JOB_MESSAGE_WARNING",
|
| + "JOB_MESSAGE_ERROR"
|
| + ],
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "jobId": {
|
| + "description": "The job to get messages about.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "projectId": {
|
| + "description": "A project id.",
|
| + "location": "path",
|
| + "required": true,
|
| + "type": "string"
|
| + },
|
| + "location": {
|
| + "description": "The location which contains the job specified by job_id.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "endTime": {
|
| + "description": "Return only messages with timestamps < end_time. The default is now\n(i.e. return up to the latest messages available).",
|
| + "format": "google-datetime",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "startTime": {
|
| + "description": "If specified, return only messages with timestamps >= start_time.\nThe default is the job creation time (i.e. beginning of messages).",
|
| + "format": "google-datetime",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "pageToken": {
|
| + "description": "If supplied, this should be the value of next_page_token returned\nby an earlier call. This will cause the next page of results to\nbe returned.",
|
| + "location": "query",
|
| + "type": "string"
|
| + },
|
| + "pageSize": {
|
| + "description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results.",
|
| + "format": "int32",
|
| + "location": "query",
|
| + "type": "integer"
|
| + }
|
| + },
|
| + "path": "v1b3/projects/{projectId}/jobs/{jobId}/messages",
|
| + "response": {
|
| + "$ref": "ListJobMessagesResponse"
|
| + },
|
| + "scopes": [
|
| + "https://www.googleapis.com/auth/cloud-platform",
|
| + "https://www.googleapis.com/auth/userinfo.email"
|
| + ]
|
| + }
|
| + }
|
| + }
|
| + }
|
| + }
|
| + }
|
| + }
|
| + },
|
| + "revision": "20170210",
|
| + "rootUrl": "https://dataflow.googleapis.com/",
|
| + "schemas": {
|
| + "WorkItemStatus": {
|
| + "description": "Conveys a worker's progress through the work described by a WorkItem.",
|
| + "id": "WorkItemStatus",
|
| + "properties": {
|
| + "counterUpdates": {
|
| + "description": "Worker output counters for this WorkItem.",
|
| + "items": {
|
| + "$ref": "CounterUpdate"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "workItemId": {
|
| + "description": "Identifies the WorkItem.",
|
| + "type": "string"
|
| + },
|
| + "metricUpdates": {
|
| + "description": "DEPRECATED in favor of counter_updates.",
|
| "items": {
|
| - "$ref": "Step"
|
| + "$ref": "MetricUpdate"
|
| },
|
| "type": "array"
|
| },
|
| - "currentState": {
|
| - "description": "The current state of the job. Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise specified. A job in the `JOB_STATE_RUNNING` state may asynchronously enter a terminal state. After a job has reached a terminal state, no further state updates may be made. This field may be mutated by the Cloud Dataflow service; callers cannot mutate it.",
|
| - "enum": [
|
| - "JOB_STATE_UNKNOWN",
|
| - "JOB_STATE_STOPPED",
|
| - "JOB_STATE_RUNNING",
|
| - "JOB_STATE_DONE",
|
| - "JOB_STATE_FAILED",
|
| - "JOB_STATE_CANCELLED",
|
| - "JOB_STATE_UPDATED",
|
| - "JOB_STATE_DRAINING",
|
| - "JOB_STATE_DRAINED"
|
| - ],
|
| - "type": "string"
|
| - },
|
| - "currentStateTime": {
|
| - "description": "The timestamp associated with the current state.",
|
| - "type": "string"
|
| + "errors": {
|
| + "description": "Specifies errors which occurred during processing. If errors are\nprovided, and completed = true, then the WorkItem is considered\nto have failed.",
|
| + "items": {
|
| + "$ref": "Status"
|
| + },
|
| + "type": "array"
|
| },
|
| - "requestedState": {
|
| - "description": "The job's requested state. `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may also be used to directly set a job's requested state to `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the job 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"
|
| - ],
|
| - "type": "string"
|
| + "dynamicSourceSplit": {
|
| + "$ref": "DynamicSourceSplit",
|
| + "description": "See documentation of stop_position."
|
| },
|
| - "executionInfo": {
|
| - "$ref": "JobExecutionInfo",
|
| - "description": "Information about how the Cloud Dataflow service will run the job."
|
| + "sourceOperationResponse": {
|
| + "$ref": "SourceOperationResponse",
|
| + "description": "If the work item represented a SourceOperationRequest, and the work\nis completed, contains the result of the operation."
|
| },
|
| - "createTime": {
|
| - "description": "The timestamp when the job was initially created. Immutable and set by the Cloud Dataflow service.",
|
| - "type": "string"
|
| + "progress": {
|
| + "$ref": "ApproximateProgress",
|
| + "description": "DEPRECATED in favor of reported_progress."
|
| },
|
| - "replaceJobId": {
|
| - "description": "If this job is an update of an existing job, this field is the job ID of the job it replaced. When sending a `CreateJobRequest`, you can update a job by specifying it here. The job named here is stopped, and its intermediate state is transferred to this job.",
|
| + "requestedLeaseDuration": {
|
| + "description": "Amount of time the worker requests for its lease.",
|
| + "format": "google-duration",
|
| "type": "string"
|
| },
|
| - "transformNameMapping": {
|
| - "additionalProperties": {
|
| - "type": "string"
|
| - },
|
| - "description": "The map of transform name prefixes of the job to be replaced to the corresponding name prefixes of the new job.",
|
| - "type": "object"
|
| - },
|
| - "clientRequestId": {
|
| - "description": "The client's unique identifier of the job, re-used across retried attempts. If this field is set, the service will ensure its uniqueness. The request to create a job will fail if the service has knowledge of a previously submitted job with the same client's ID and job name. The caller may use this field to ensure idempotence of job creation across retried attempts to create a job. By default, the field is empty and, in that case, the service ignores it.",
|
| + "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"
|
| },
|
| - "replacedByJobId": {
|
| - "description": "If another job is an update of this job (and thus, this job is in `JOB_STATE_UPDATED`), this field contains the ID of that job.",
|
| - "type": "string"
|
| + "stopPosition": {
|
| + "$ref": "Position",
|
| + "description": "A worker may split an active map task in two parts, \"primary\" and\n\"residual\", continuing to process the primary part and returning the\nresidual part into the pool of available work.\nThis event is called a \"dynamic split\" and is critical to the dynamic\nwork rebalancing feature. The two obtained sub-tasks are called\n\"parts\" of the split.\nThe parts, if concatenated, must represent the same input as would\nbe read by the current task if the split did not happen.\nThe exact way in which the original task is decomposed into the two\nparts is specified either as a position demarcating them\n(stop_position), or explicitly as two DerivedSources, if this\ntask consumes a user-defined source type (dynamic_source_split).\n\nThe \"current\" task is adjusted as a result of the split: after a task\nwith range [A, B) sends a stop_position update at C, its range is\nconsidered to be [A, C), e.g.:\n* Progress should be interpreted relative to the new range, e.g.\n \"75% completed\" means \"75% of [A, C) completed\"\n* The worker should interpret proposed_stop_position relative to the\n new range, e.g. \"split at 68%\" should be interpreted as\n \"split at 68% of [A, C)\".\n* If the worker chooses to split again using stop_position, only\n stop_positions in [A, C) will be accepted.\n* Etc.\ndynamic_source_split has similar semantics: e.g., if a task with\nsource S splits using dynamic_source_split into {P, R}\n(where P and R must be together equivalent to S), then subsequent\nprogress and proposed_stop_position should be interpreted relative\nto P, and in a potential subsequent dynamic_source_split into {P', R'},\nP' and R' must be together equivalent to P, etc."
|
| },
|
| - "tempFiles": {
|
| - "description": "A set of files the system should be aware of that are used for temporary storage. These temporary files will be removed on job completion. No duplicates are allowed. No file patterns are supported. The supported files are: Google Cloud Storage: storage.googleapis.com/{bucket}/{object} bucket.storage.googleapis.com/{object}",
|
| - "items": {
|
| - "type": "string"
|
| - },
|
| - "type": "array"
|
| + "completed": {
|
| + "description": "True if the WorkItem was completed (successfully or unsuccessfully).",
|
| + "type": "boolean"
|
| },
|
| - "labels": {
|
| - "additionalProperties": {
|
| - "type": "string"
|
| - },
|
| - "description": "User-defined labels for this job. The labels map can contain no more than 64 entries. Entries of the labels map are UTF8 strings that comply with the following restrictions: * Keys must conform to regexp: \\p{Ll}\\p{Lo}{0,62} * Values must conform to regexp: [\\p{Ll}\\p{Lo}\\p{N}_-]{0,63} * Both keys and values are additionally constrained to be <= 128 bytes in size.",
|
| - "type": "object"
|
| + "reportedProgress": {
|
| + "$ref": "ApproximateReportedProgress",
|
| + "description": "The worker's progress through this WorkItem."
|
| },
|
| - "location": {
|
| - "description": "The location that contains this job.",
|
| - "type": "string"
|
| + "sourceFork": {
|
| + "$ref": "SourceFork",
|
| + "description": "DEPRECATED in favor of dynamic_source_split."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Environment": {
|
| - "description": "Describes the environment in which a Dataflow Job runs.",
|
| - "id": "Environment",
|
| + "WorkItemServiceState": {
|
| + "description": "The Dataflow service's idea of the current state of a WorkItem\nbeing processed by a worker.",
|
| + "id": "WorkItemServiceState",
|
| "properties": {
|
| - "tempStoragePrefix": {
|
| - "description": "The prefix of the resources the system should use for temporary storage. The system will append the suffix \"/temp-{JOBNAME} to this resource prefix, where {JOBNAME} is the value of the job_name field. The resulting bucket and object prefix is used as the prefix of the resources used to store temporary data needed during the job execution. NOTE: This will override the value in taskrunner_settings. The supported resource type is: Google Cloud Storage: storage.googleapis.com/{bucket}/{object} bucket.storage.googleapis.com/{object}",
|
| - "type": "string"
|
| - },
|
| - "clusterManagerApiService": {
|
| - "description": "The type of cluster manager API to use. If unknown or unspecified, the service will attempt to choose a reasonable default. This should be in the form of the API service name, e.g. \"compute.googleapis.com\".",
|
| + "leaseExpireTime": {
|
| + "description": "Time at which the current lease will expire.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| - "experiments": {
|
| - "description": "The list of experiments to enable.",
|
| + "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": {
|
| - "type": "string"
|
| + "$ref": "MetricShortId"
|
| },
|
| "type": "array"
|
| },
|
| - "workerPools": {
|
| - "description": "The worker pools. At least one \"harness\" worker pool must be specified in order for the job to have workers.",
|
| - "items": {
|
| - "$ref": "WorkerPool"
|
| - },
|
| - "type": "array"
|
| + "nextReportIndex": {
|
| + "description": "The index value to use for the next report sent by the worker.\nNote: If the report call fails for whatever reason, the worker should\nreuse this index for subsequent report attempts.",
|
| + "format": "int64",
|
| + "type": "string"
|
| },
|
| - "userAgent": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "A description of the process that generated the request.",
|
| - "type": "object"
|
| + "suggestedStopPoint": {
|
| + "$ref": "ApproximateProgress",
|
| + "description": "DEPRECATED in favor of split_request."
|
| },
|
| - "version": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "A structure describing which components and their versions of the service are required in order to run the job.",
|
| - "type": "object"
|
| + "splitRequest": {
|
| + "$ref": "ApproximateSplitRequest",
|
| + "description": "The progress point in the WorkItem where the Dataflow service\nsuggests that the worker truncate the task."
|
| },
|
| - "dataset": {
|
| - "description": "The dataset for the current project where various workflow related tables are stored. The supported resource type is: Google BigQuery: bigquery.googleapis.com/{dataset}",
|
| + "reportStatusInterval": {
|
| + "description": "New recommended reporting interval.",
|
| + "format": "google-duration",
|
| "type": "string"
|
| },
|
| - "sdkPipelineOptions": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The Cloud Dataflow SDK pipeline options specified by the user. These options are passed through the service and are used to recreate the SDK pipeline options on the worker in a language agnostic and platform independent way.",
|
| - "type": "object"
|
| + "suggestedStopPosition": {
|
| + "$ref": "Position",
|
| + "description": "Obsolete, always empty."
|
| },
|
| - "internalExperiments": {
|
| + "harnessData": {
|
| "additionalProperties": {
|
| - "description": "Properties of the object. Contains field @type with type URL.",
|
| + "description": "Properties of the object.",
|
| "type": "any"
|
| },
|
| - "description": "Experimental settings.",
|
| + "description": "Other data returned by the service, specific to the particular\nworker harness.",
|
| "type": "object"
|
| - },
|
| - "serviceAccountEmail": {
|
| - "description": "Identity to run virtual machines as. Defaults to the default account.",
|
| - "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerPool": {
|
| - "description": "Describes one particular pool of Cloud Dataflow workers to be instantiated by the Cloud Dataflow service in order to perform the computations required by a job. Note that a workflow job may use multiple pools, in order to match the various computational requirements of the various stages of the job.",
|
| - "id": "WorkerPool",
|
| + "MetricStructuredName": {
|
| + "description": "Identifies a metric, by describing the source which generated the\nmetric.",
|
| + "id": "MetricStructuredName",
|
| "properties": {
|
| - "kind": {
|
| - "description": "The kind of the worker pool; currently only `harness` and `shuffle` are supported.",
|
| - "type": "string"
|
| - },
|
| - "numWorkers": {
|
| - "description": "Number of Google Compute Engine workers in this pool needed to execute the job. If zero or unspecified, the service will attempt to choose a reasonable default.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - },
|
| - "packages": {
|
| - "description": "Packages to be installed on workers.",
|
| - "items": {
|
| - "$ref": "Package"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "defaultPackageSet": {
|
| - "description": "The default package set to install. This allows the service to select a default set of packages which are useful to worker harnesses written in a particular language.",
|
| - "enum": [
|
| - "DEFAULT_PACKAGE_SET_UNKNOWN",
|
| - "DEFAULT_PACKAGE_SET_NONE",
|
| - "DEFAULT_PACKAGE_SET_JAVA",
|
| - "DEFAULT_PACKAGE_SET_PYTHON"
|
| - ],
|
| - "type": "string"
|
| - },
|
| - "machineType": {
|
| - "description": "Machine type (e.g. \"n1-standard-1\"). If empty or unspecified, the service will attempt to choose a reasonable default.",
|
| - "type": "string"
|
| - },
|
| - "teardownPolicy": {
|
| - "description": "Sets the policy for determining when to turndown worker pool. Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and `TEARDOWN_NEVER`. `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn down. If the workers are not torn down by the service, they will continue to run and use Google Compute Engine VM resources in the user's project until they are explicitly terminated by the user. Because of this, Google recommends using the `TEARDOWN_ALWAYS` policy except for small, manually supervised test jobs. If unknown or unspecified, the service will attempt to choose a reasonable default.",
|
| - "enum": [
|
| - "TEARDOWN_POLICY_UNKNOWN",
|
| - "TEARDOWN_ALWAYS",
|
| - "TEARDOWN_ON_SUCCESS",
|
| - "TEARDOWN_NEVER"
|
| - ],
|
| - "type": "string"
|
| - },
|
| - "diskSizeGb": {
|
| - "description": "Size of root disk for VMs, in GB. If zero or unspecified, the service will attempt to choose a reasonable default.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - },
|
| - "diskType": {
|
| - "description": "Type of root disk for VMs. If empty or unspecified, the service will attempt to choose a reasonable default.",
|
| - "type": "string"
|
| - },
|
| - "diskSourceImage": {
|
| - "description": "Fully qualified source image for disks.",
|
| - "type": "string"
|
| - },
|
| - "zone": {
|
| - "description": "Zone to run the worker pools in. If empty or unspecified, the service will attempt to choose a reasonable default.",
|
| + "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"
|
| },
|
| - "taskrunnerSettings": {
|
| - "$ref": "TaskRunnerSettings",
|
| - "description": "Settings passed through to Google Compute Engine workers when using the standard Dataflow task runner. Users should ignore this field."
|
| - },
|
| - "onHostMaintenance": {
|
| - "description": "The action to take on host maintenance, as defined by the Google Compute Engine API.",
|
| + "name": {
|
| + "description": "Worker-defined metric name.",
|
| "type": "string"
|
| },
|
| - "dataDisks": {
|
| - "description": "Data disks that are used by a VM in this workflow.",
|
| - "items": {
|
| - "$ref": "Disk"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "metadata": {
|
| + "context": {
|
| "additionalProperties": {
|
| "type": "string"
|
| },
|
| - "description": "Metadata to set on the Google Compute Engine VMs.",
|
| + "description": "Zero or more labeled fields which identify the part of the job this\nmetric is associated with, such as the name of a step or collection.\n\nFor example, built-in counters associated with steps will have\ncontext['step'] = <step-name>. Counters associated with PCollections\nin the SDK will have context['pcollection'] = <pcollection-name>.",
|
| "type": "object"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "SeqMapTaskOutputInfo": {
|
| + "description": "Information about an output of a SeqMapTask.",
|
| + "id": "SeqMapTaskOutputInfo",
|
| + "properties": {
|
| + "tag": {
|
| + "description": "The id of the TupleTag the user code will tag the output value by.",
|
| + "type": "string"
|
| },
|
| - "autoscalingSettings": {
|
| - "$ref": "AutoscalingSettings",
|
| - "description": "Settings for autoscaling of this WorkerPool."
|
| - },
|
| - "poolArgs": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object. Contains field @type with type URL.",
|
| - "type": "any"
|
| + "sink": {
|
| + "$ref": "Sink",
|
| + "description": "The sink to write the output value to."
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "JobExecutionStageInfo": {
|
| + "description": "Contains information about how a particular\ngoogle.dataflow.v1beta3.Step will be executed.",
|
| + "id": "JobExecutionStageInfo",
|
| + "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"
|
| },
|
| - "description": "Extra arguments for this worker pool.",
|
| - "type": "object"
|
| - },
|
| - "network": {
|
| - "description": "Network to which VMs will be assigned. If empty or unspecified, the service will use the network \"default\".",
|
| + "type": "array"
|
| + }
|
| + },
|
| + "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",
|
| + "properties": {
|
| + "deliveryEndpoint": {
|
| + "description": "The physical location of this range assignment to be used for\nstreaming computation cross-worker message delivery.",
|
| "type": "string"
|
| },
|
| - "subnetwork": {
|
| - "description": "Subnetwork to which VMs will be assigned, if desired. Expected to be of the form \"regions/REGION/subnetworks/SUBNETWORK\".",
|
| + "start": {
|
| + "description": "The start (inclusive) of the key range.",
|
| "type": "string"
|
| },
|
| - "workerHarnessContainerImage": {
|
| - "description": "Required. Docker container image that executes the Cloud Dataflow worker harness, residing in Google Container Registry.",
|
| + "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"
|
| },
|
| - "numThreadsPerWorker": {
|
| - "description": "The number of threads per worker harness. If empty or unspecified, the service will choose a number of threads (according to the number of cores on the selected machine type for batch, or 1 by convention for streaming).",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "persistentDirectory": {
|
| + "description": "The location of the persistent state for this range, as a\npersistent directory in the worker local filesystem.",
|
| + "type": "string"
|
| },
|
| - "ipConfiguration": {
|
| - "description": "Configuration for VM IPs.",
|
| - "enum": [
|
| - "WORKER_IP_UNSPECIFIED",
|
| - "WORKER_IP_PUBLIC",
|
| - "WORKER_IP_PRIVATE"
|
| - ],
|
| + "end": {
|
| + "description": "The end (exclusive) of the key range.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Package": {
|
| - "description": "The packages that must be installed in order for a worker to run the steps of the Cloud Dataflow job that will be assigned to its worker pool. This is the mechanism by which the Cloud Dataflow SDK causes code to be loaded onto the workers. For example, the Cloud Dataflow Java SDK might use this to install jars containing the user's code and all of the various dependencies (libraries, data files, etc.) required in order for that code to run.",
|
| - "id": "Package",
|
| + "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"
|
| + },
|
| + "NameAndKind": {
|
| + "description": "Basic metadata about a counter.",
|
| + "id": "NameAndKind",
|
| "properties": {
|
| "name": {
|
| - "description": "The name of the package.",
|
| + "description": "Name of the counter.",
|
| "type": "string"
|
| },
|
| - "location": {
|
| - "description": "The resource to read the package from. The supported resource type is: Google Cloud Storage: storage.googleapis.com/{bucket} bucket.storage.googleapis.com/",
|
| + "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"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "TaskRunnerSettings": {
|
| - "description": "Taskrunner configuration settings.",
|
| - "id": "TaskRunnerSettings",
|
| + "SeqMapTask": {
|
| + "description": "Describes a particular function to invoke.",
|
| + "id": "SeqMapTask",
|
| "properties": {
|
| - "taskUser": {
|
| - "description": "The UNIX user ID on the worker VM to use for tasks launched by taskrunner; e.g. \"root\".",
|
| - "type": "string"
|
| + "userFn": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "The user function to invoke.",
|
| + "type": "object"
|
| },
|
| - "taskGroup": {
|
| - "description": "The UNIX group ID on the worker VM to use for tasks launched by taskrunner; e.g. \"wheel\".",
|
| + "name": {
|
| + "description": "The user-provided name of the SeqDo operation.",
|
| "type": "string"
|
| },
|
| - "oauthScopes": {
|
| - "description": "The OAuth2 scopes to be requested by the taskrunner in order to access the Cloud Dataflow API.",
|
| + "outputInfos": {
|
| + "description": "Information about each of the outputs.",
|
| "items": {
|
| - "type": "string"
|
| + "$ref": "SeqMapTaskOutputInfo"
|
| },
|
| "type": "array"
|
| },
|
| - "baseUrl": {
|
| - "description": "The base URL for the taskrunner to use when accessing Google Cloud APIs. When workers access Google Cloud APIs, they logically do so via relative URLs. If this field is specified, it supplies the base URL to use for resolving these relative URLs. The normative algorithm used is defined by RFC 1808, \"Relative Uniform Resource Locators\". If not specified, the default value is \"http://www.googleapis.com/\"",
|
| - "type": "string"
|
| - },
|
| - "dataflowApiVersion": {
|
| - "description": "The API version of endpoint, e.g. \"v1b3\"",
|
| - "type": "string"
|
| - },
|
| - "parallelWorkerSettings": {
|
| - "$ref": "WorkerSettings",
|
| - "description": "The settings to pass to the parallel worker harness."
|
| - },
|
| - "baseTaskDir": {
|
| - "description": "The location on the worker for task-specific subdirectories.",
|
| - "type": "string"
|
| - },
|
| - "continueOnException": {
|
| - "description": "Whether to continue taskrunner if an exception is hit.",
|
| - "type": "boolean"
|
| - },
|
| - "logToSerialconsole": {
|
| - "description": "Whether to send taskrunner log info to Google Compute Engine VM serial console.",
|
| - "type": "boolean"
|
| - },
|
| - "alsologtostderr": {
|
| - "description": "Whether to also send taskrunner log info to stderr.",
|
| - "type": "boolean"
|
| - },
|
| - "logUploadLocation": {
|
| - "description": "Indicates where to put logs. If this is not specified, the logs will not be uploaded. The supported resource type is: Google Cloud Storage: storage.googleapis.com/{bucket}/{object} bucket.storage.googleapis.com/{object}",
|
| - "type": "string"
|
| - },
|
| - "logDir": {
|
| - "description": "The directory on the VM to store logs.",
|
| - "type": "string"
|
| - },
|
| - "tempStoragePrefix": {
|
| - "description": "The prefix of the resources the taskrunner should use for temporary storage. The supported resource type is: Google Cloud Storage: storage.googleapis.com/{bucket}/{object} bucket.storage.googleapis.com/{object}",
|
| - "type": "string"
|
| - },
|
| - "harnessCommand": {
|
| - "description": "The command to launch the worker harness.",
|
| - "type": "string"
|
| - },
|
| - "workflowFileName": {
|
| - "description": "The file to store the workflow in.",
|
| - "type": "string"
|
| - },
|
| - "commandlinesFileName": {
|
| - "description": "The file to store preprocessing commands in.",
|
| - "type": "string"
|
| + "inputs": {
|
| + "description": "Information about each of the inputs.",
|
| + "items": {
|
| + "$ref": "SideInputInfo"
|
| + },
|
| + "type": "array"
|
| },
|
| - "vmId": {
|
| - "description": "The ID string of the VM.",
|
| + "stageName": {
|
| + "description": "System-defined name of the stage containing the SeqDo operation.\nUnique across the workflow.",
|
| "type": "string"
|
| },
|
| - "languageHint": {
|
| - "description": "The suggested backend language.",
|
| + "systemName": {
|
| + "description": "System-defined name of the SeqDo operation.\nUnique across the workflow.",
|
| "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",
|
| + "properties": {
|
| + "parameters": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "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"
|
| },
|
| - "streamingWorkerMainClass": {
|
| - "description": "The streaming worker main class name.",
|
| + "code": {
|
| + "description": "The code is a string intended for consumption by a machine that identifies\nthe type of message being sent.\nExamples:\n 1. \"HARNESS_STARTED\" might be used to indicate the worker harness has\n started.\n 2. \"GCS_DOWNLOAD_ERROR\" might be used to indicate an error downloading\n a GCS file as part of the boot process of one of the worker containers.\n\nThis is a string and not an enum to make it easy to add new codes without\nwaiting for an API change.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerSettings": {
|
| - "description": "Provides data to pass through to the worker harness.",
|
| - "id": "WorkerSettings",
|
| + "CustomSourceLocation": {
|
| + "description": "Identifies the location of a custom souce.",
|
| + "id": "CustomSourceLocation",
|
| "properties": {
|
| - "baseUrl": {
|
| - "description": "The base URL for accessing Google Cloud APIs. When workers access Google Cloud APIs, they logically do so via relative URLs. If this field is specified, it supplies the base URL to use for resolving these relative URLs. The normative algorithm used is defined by RFC 1808, \"Relative Uniform Resource Locators\". If not specified, the default value is \"http://www.googleapis.com/\"",
|
| - "type": "string"
|
| - },
|
| - "reportingEnabled": {
|
| - "description": "Whether to send work progress updates to the service.",
|
| + "stateful": {
|
| + "description": "Whether this source is stateful.",
|
| "type": "boolean"
|
| - },
|
| - "servicePath": {
|
| - "description": "The Cloud Dataflow service path relative to the root URL, for example, \"dataflow/v1b3/projects\".",
|
| - "type": "string"
|
| - },
|
| - "shuffleServicePath": {
|
| - "description": "The Shuffle service path relative to the root URL, for example, \"shuffle/v1beta1\".",
|
| + }
|
| + },
|
| + "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": {
|
| + "systemName": {
|
| + "description": "System-defined name of this MapTask.\nUnique across the workflow.",
|
| "type": "string"
|
| },
|
| - "workerId": {
|
| - "description": "The ID of the worker running this pipeline.",
|
| + "stageName": {
|
| + "description": "System-defined name of the stage containing this MapTask.\nUnique across the workflow.",
|
| "type": "string"
|
| },
|
| - "tempStoragePrefix": {
|
| - "description": "The prefix of the resources the system should use for temporary storage. The supported resource type is: Google Cloud Storage: storage.googleapis.com/{bucket}/{object} bucket.storage.googleapis.com/{object}",
|
| - "type": "string"
|
| + "instructions": {
|
| + "description": "The instructions in the MapTask.",
|
| + "items": {
|
| + "$ref": "ParallelInstruction"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Disk": {
|
| - "description": "Describes the data disk used by a workflow job.",
|
| - "id": "Disk",
|
| + "FloatingPointMean": {
|
| + "description": "A representation of a floating point mean metric contribution.",
|
| + "id": "FloatingPointMean",
|
| "properties": {
|
| - "sizeGb": {
|
| - "description": "Size of disk in GB. If zero or unspecified, the service will attempt to choose a reasonable default.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - },
|
| - "diskType": {
|
| - "description": "Disk storage type, as defined by Google Compute Engine. This must be a disk type appropriate to the project and zone in which the workers will run. If unknown or unspecified, the service will attempt to choose a reasonable default. For example, the standard persistent disk type is a resource name typically ending in \"pd-standard\". If SSD persistent disks are available, the resource name typically ends with \"pd-ssd\". The actual valid values are defined the Google Compute Engine API, not by the Cloud Dataflow API; consult the Google Compute Engine documentation for more information about determining the set of available disk types for a particular project and zone. Google Compute Engine Disk types are local to a particular project in a particular zone, and so the resource name will typically look something like this: compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard",
|
| - "type": "string"
|
| + "count": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The number of values being aggregated."
|
| },
|
| - "mountPoint": {
|
| - "description": "Directory in a VM where disk is mounted.",
|
| - "type": "string"
|
| + "sum": {
|
| + "description": "The sum of all values being aggregated.",
|
| + "format": "double",
|
| + "type": "number"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "AutoscalingSettings": {
|
| - "description": "Settings for WorkerPool autoscaling.",
|
| - "id": "AutoscalingSettings",
|
| + "ReportWorkItemStatusResponse": {
|
| + "description": "Response from a request to report the status of WorkItems.",
|
| + "id": "ReportWorkItemStatusResponse",
|
| "properties": {
|
| - "algorithm": {
|
| - "description": "The algorithm to use for autoscaling.",
|
| - "enum": [
|
| - "AUTOSCALING_ALGORITHM_UNKNOWN",
|
| - "AUTOSCALING_ALGORITHM_NONE",
|
| - "AUTOSCALING_ALGORITHM_BASIC"
|
| - ],
|
| - "type": "string"
|
| - },
|
| - "maxNumWorkers": {
|
| - "description": "The maximum number of workers to cap scaling at.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "workItemServiceStates": {
|
| + "description": "A set of messages indicating the service-side state for each\nWorkItem whose status was reported, in the same order as the\nWorkItemStatus messages in the ReportWorkItemStatusRequest which\nresulting in this response.",
|
| + "items": {
|
| + "$ref": "WorkItemServiceState"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Step": {
|
| - "description": "Defines a particular step within a Cloud Dataflow job. A job consists of multiple steps, each of which performs some specific operation as part of the overall job. Data is typically passed from one step to another as part of the job. Here's an example of a sequence of steps which together implement a Map-Reduce job: * Read a collection of data from some source, parsing the collection's elements. * Validate the elements. * Apply a user-defined function to map each element to some value and extract an element-specific key value. * Group elements with the same key into a single element with that key, transforming a multiply-keyed collection into a uniquely-keyed collection. * Write the elements out to some data sink. Note that the Cloud Dataflow service may be used to run many different types of jobs, not just Map-Reduce.",
|
| - "id": "Step",
|
| + "InstructionOutput": {
|
| + "description": "An output of an instruction.",
|
| + "id": "InstructionOutput",
|
| "properties": {
|
| - "kind": {
|
| - "description": "The kind of step in the Cloud Dataflow job.",
|
| + "name": {
|
| + "description": "The user-provided name of this output.",
|
| "type": "string"
|
| },
|
| - "name": {
|
| - "description": "The name that identifies the step. This must be unique for each step with respect to all other steps in the Cloud Dataflow job.",
|
| + "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"
|
| },
|
| - "properties": {
|
| + "onlyCountKeyBytes": {
|
| + "description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the key size.",
|
| + "type": "boolean"
|
| + },
|
| + "onlyCountValueBytes": {
|
| + "description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the value size.",
|
| + "type": "boolean"
|
| + },
|
| + "codec": {
|
| "additionalProperties": {
|
| "description": "Properties of the object.",
|
| "type": "any"
|
| },
|
| - "description": "Named properties associated with the step. Each kind of predefined step has its own required set of properties.",
|
| + "description": "The codec to use to encode data being written via this output.",
|
| "type": "object"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "JobExecutionInfo": {
|
| - "description": "Additional information about how a Cloud Dataflow job will be executed that isn't contained in the submitted job.",
|
| - "id": "JobExecutionInfo",
|
| + "CreateJobFromTemplateRequest": {
|
| + "description": "A request to create a Cloud Dataflow job from a template.",
|
| + "id": "CreateJobFromTemplateRequest",
|
| "properties": {
|
| - "stages": {
|
| + "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": {
|
| + "$ref": "RuntimeEnvironment",
|
| + "description": "The runtime environment for the job."
|
| + },
|
| + "parameters": {
|
| "additionalProperties": {
|
| - "$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"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "JobExecutionStageInfo": {
|
| - "description": "Contains information about how a particular google.dataflow.v1beta3.Step will be executed.",
|
| - "id": "JobExecutionStageInfo",
|
| + "IntegerMean": {
|
| + "description": "A representation of an integer mean metric contribution.",
|
| + "id": "IntegerMean",
|
| "properties": {
|
| - "stepName": {
|
| - "description": "The steps associated with the execution stage. Note that stages may have several steps, and that a given step might be run by more than one stage.",
|
| - "items": {
|
| - "type": "string"
|
| - },
|
| - "type": "array"
|
| + "sum": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The sum of all values being aggregated."
|
| + },
|
| + "count": {
|
| + "$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 response, depending on the page size in the ListJobsRequest.",
|
| + "description": "Response to a request to list Cloud Dataflow jobs. This may be a partial\nresponse, depending on the page size in the ListJobsRequest.",
|
| "id": "ListJobsResponse",
|
| "properties": {
|
| - "jobs": {
|
| - "description": "A subset of the requested job information.",
|
| - "items": {
|
| - "$ref": "Job"
|
| - },
|
| - "type": "array"
|
| - },
|
| "nextPageToken": {
|
| "description": "Set if there may be more results than fit in this response.",
|
| "type": "string"
|
| @@ -1656,422 +1522,387 @@
|
| "$ref": "FailedLocation"
|
| },
|
| "type": "array"
|
| + },
|
| + "jobs": {
|
| + "description": "A subset of the requested job information.",
|
| + "items": {
|
| + "$ref": "Job"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "FailedLocation": {
|
| - "description": "Indicates which location failed to respond to a request for data.",
|
| - "id": "FailedLocation",
|
| + "ComputationTopology": {
|
| + "description": "All configuration data for a particular Computation.",
|
| + "id": "ComputationTopology",
|
| "properties": {
|
| - "name": {
|
| - "description": "The name of the failed location.",
|
| + "userStageName": {
|
| + "description": "The user stage name.",
|
| "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "ListJobMessagesResponse": {
|
| - "description": "Response to a request to list job messages.",
|
| - "id": "ListJobMessagesResponse",
|
| - "properties": {
|
| - "jobMessages": {
|
| - "description": "Messages in ascending timestamp order.",
|
| + },
|
| + "outputs": {
|
| + "description": "The outputs from the computation.",
|
| "items": {
|
| - "$ref": "JobMessage"
|
| + "$ref": "StreamLocation"
|
| },
|
| "type": "array"
|
| },
|
| - "nextPageToken": {
|
| - "description": "The token to obtain the next page of results if there are more.",
|
| + "stateFamilies": {
|
| + "description": "The state family values.",
|
| + "items": {
|
| + "$ref": "StateFamilyConfig"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "systemStageName": {
|
| + "description": "The system stage name.",
|
| + "type": "string"
|
| + },
|
| + "computationId": {
|
| + "description": "The ID of the computation.",
|
| "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"
|
| },
|
| - "JobMessage": {
|
| - "description": "A particular message pertaining to a Dataflow job.",
|
| - "id": "JobMessage",
|
| + "RuntimeEnvironment": {
|
| + "description": "The environment values to set at runtime.",
|
| + "id": "RuntimeEnvironment",
|
| "properties": {
|
| - "id": {
|
| - "description": "Identifies the message. This is automatically generated by the service; the caller should treat it as an opaque string.",
|
| + "serviceAccountEmail": {
|
| + "description": "The email address of the service account to run the job as.",
|
| "type": "string"
|
| },
|
| - "time": {
|
| - "description": "The timestamp of the message.",
|
| + "tempLocation": {
|
| + "description": "The Cloud Storage path to use for temporary files.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
|
| "type": "string"
|
| },
|
| - "messageText": {
|
| - "description": "The text of the message.",
|
| - "type": "string"
|
| + "bypassTempDirValidation": {
|
| + "description": "Whether to bypass the safety checks for the job's temporary directory.\nUse with caution.",
|
| + "type": "boolean"
|
| },
|
| - "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"
|
| - ],
|
| + "maxWorkers": {
|
| + "description": "The maximum number of Google Compute Engine instances to be made\navailable to your pipeline during execution, from 1 to 1000.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| + },
|
| + "zone": {
|
| + "description": "The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)\nfor launching worker instances to run your pipeline.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "JobMetrics": {
|
| - "description": "JobMetrics contains a collection of metrics descibing the detailed progress of a Dataflow job. Metrics correspond to user-defined and system-defined metrics in the job. This resource captures only the most recent values of each metric; time-series data can be queried for them (under the same metric names) from Cloud Monitoring.",
|
| - "id": "JobMetrics",
|
| + "MountedDataDisk": {
|
| + "description": "Describes mounted data disk.",
|
| + "id": "MountedDataDisk",
|
| "properties": {
|
| - "metricTime": {
|
| - "description": "Timestamp as of which metric values are current.",
|
| + "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"
|
| - },
|
| - "metrics": {
|
| - "description": "All metrics for this job.",
|
| - "items": {
|
| - "$ref": "MetricUpdate"
|
| - },
|
| - "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "MetricUpdate": {
|
| - "description": "Describes the state of a metric.",
|
| - "id": "MetricUpdate",
|
| + "StreamingSideInputLocation": {
|
| + "description": "Identifies the location of a streaming side input.",
|
| + "id": "StreamingSideInputLocation",
|
| "properties": {
|
| - "name": {
|
| - "$ref": "MetricStructuredName",
|
| - "description": "Name of the metric."
|
| + "stateFamily": {
|
| + "description": "Identifies the state family where this side input is stored.",
|
| + "type": "string"
|
| },
|
| - "kind": {
|
| - "description": "Metric aggregation kind. The possible metric aggregation kinds are \"Sum\", \"Max\", \"Min\", \"Mean\", \"Set\", \"And\", and \"Or\". The specified aggregation kind is case-insensitive. If omitted, this is not an aggregated value but instead a single metric sample value.",
|
| + "tag": {
|
| + "description": "Identifies the particular side input within the streaming Dataflow job.",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "Job": {
|
| + "description": "Defines a job to be run by the Cloud Dataflow service.",
|
| + "id": "Job",
|
| + "properties": {
|
| + "requestedState": {
|
| + "description": "The job's requested state.\n\n`UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and\n`JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may\nalso be used to directly set a job's requested state to\n`JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the\njob if it has not already reached a terminal state.",
|
| + "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"
|
| + ],
|
| + "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`."
|
| + ],
|
| "type": "string"
|
| },
|
| - "cumulative": {
|
| - "description": "True if this metric is reported as the total cumulative aggregate value accumulated since the worker started working on this WorkItem. By default this is false, indicating that this metric is reported as a delta that is not associated with any WorkItem.",
|
| - "type": "boolean"
|
| + "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"
|
| },
|
| - "scalar": {
|
| - "description": "Worker-computed aggregate value for aggregation kinds \"Sum\", \"Max\", \"Min\", \"And\", and \"Or\". The possible value types are Long, Double, and Boolean.",
|
| - "type": "any"
|
| + "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"
|
| },
|
| - "meanSum": {
|
| - "description": "Worker-computed aggregate value for the \"Mean\" aggregation kind. This holds the sum of the aggregated values and is used in combination with mean_count below to obtain the actual mean aggregate value. The only possible value types are Long and Double.",
|
| - "type": "any"
|
| + "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"
|
| },
|
| - "meanCount": {
|
| - "description": "Worker-computed aggregate value for the \"Mean\" aggregation kind. This holds the count of the aggregated values and is used in combination with mean_sum above to obtain the actual mean aggregate value. The only possible value type is Long.",
|
| - "type": "any"
|
| + "steps": {
|
| + "description": "The top-level steps that constitute the entire job.",
|
| + "items": {
|
| + "$ref": "Step"
|
| + },
|
| + "type": "array"
|
| },
|
| - "set": {
|
| - "description": "Worker-computed aggregate value for the \"Set\" aggregation kind. The only possible value type is a list of Values whose type can be Long, Double, or String, according to the metric's type. All Values in the list must be of the same type.",
|
| - "type": "any"
|
| + "replacedByJobId": {
|
| + "description": "If another job is an update of this job (and thus, this job is in\n`JOB_STATE_UPDATED`), this field contains the ID of that job.",
|
| + "type": "string"
|
| },
|
| - "internal": {
|
| - "description": "Worker-computed aggregate value for internal use by the Dataflow service.",
|
| - "type": "any"
|
| + "executionInfo": {
|
| + "$ref": "JobExecutionInfo",
|
| + "description": "Information about how the Cloud Dataflow service will run the job."
|
| },
|
| - "updateTime": {
|
| - "description": "Timestamp associated with the metric value. Optional when workers are reporting work progress; it will be filled in responses from the metrics API.",
|
| + "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"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "MetricStructuredName": {
|
| - "description": "Identifies a metric, by describing the source which generated the metric.",
|
| - "id": "MetricStructuredName",
|
| - "properties": {
|
| - "origin": {
|
| - "description": "Origin (namespace) of metric name. May be blank for user-define metrics; will be \"dataflow\" for metrics defined by the Dataflow service or SDK.",
|
| + },
|
| + "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"
|
| + ],
|
| + "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`."
|
| + ],
|
| "type": "string"
|
| },
|
| - "name": {
|
| - "description": "Worker-defined metric name.",
|
| + "location": {
|
| + "description": "The location that contains this job.",
|
| "type": "string"
|
| },
|
| - "context": {
|
| + "currentStateTime": {
|
| + "description": "The timestamp associated with the current state.",
|
| + "format": "google-datetime",
|
| + "type": "string"
|
| + },
|
| + "transformNameMapping": {
|
| "additionalProperties": {
|
| "type": "string"
|
| },
|
| - "description": "Zero or more labeled fields which identify the part of the job this metric is associated with, such as the name of a step or collection. For example, built-in counters associated with steps will have context['step'] = . Counters associated with PCollections in the SDK will have context['pcollection'] =\n.",
|
| + "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"
|
| - },
|
| - "CreateJobFromTemplateRequest": {
|
| - "description": "A request to create a Cloud Dataflow job from a template.",
|
| - "id": "CreateJobFromTemplateRequest",
|
| - "properties": {
|
| - "jobName": {
|
| - "description": "Required. The job name to use for the created job.",
|
| - "type": "string"
|
| },
|
| - "gcsPath": {
|
| - "description": "Required. A Cloud Storage path to the template from which to create the job. Must be a valid Cloud Storage URL, beginning with `gs://`.",
|
| + "createTime": {
|
| + "description": "The timestamp when the job was initially created. Immutable and set by the\nCloud Dataflow service.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| - "parameters": {
|
| + "environment": {
|
| + "$ref": "Environment",
|
| + "description": "The environment for the job."
|
| + },
|
| + "labels": {
|
| "additionalProperties": {
|
| "type": "string"
|
| },
|
| - "description": "The runtime parameters to pass to the job.",
|
| + "description": "User-defined labels for this job.\n\nThe labels map can contain no more than 64 entries. Entries of the labels\nmap are UTF8 strings that comply with the following restrictions:\n\n* Keys must conform to regexp: \\p{Ll}\\p{Lo}{0,62}\n* Values must conform to regexp: [\\p{Ll}\\p{Lo}\\p{N}_-]{0,63}\n* Both keys and values are additionally constrained to be <= 128 bytes in\nsize.",
|
| "type": "object"
|
| },
|
| - "environment": {
|
| - "$ref": "RuntimeEnvironment",
|
| - "description": "The runtime environment for the job."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "RuntimeEnvironment": {
|
| - "description": "The environment values to set at runtime.",
|
| - "id": "RuntimeEnvironment",
|
| - "properties": {
|
| - "maxWorkers": {
|
| - "description": "The maximum number of Google Compute Engine instances to be made available to your pipeline during execution, from 1 to 1000.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - },
|
| - "zone": {
|
| - "description": "The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones) for launching worker instances to run your pipeline.",
|
| + "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"
|
| },
|
| - "serviceAccountEmail": {
|
| - "description": "The email address of the service account to run the job as.",
|
| + "projectId": {
|
| + "description": "The ID of the Cloud Platform project that the job belongs to.",
|
| "type": "string"
|
| },
|
| - "tempLocation": {
|
| - "description": "The Cloud Storage path to use for temporary files. Must be a valid Cloud Storage URL, beginning with `gs://`.",
|
| + "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"
|
| - },
|
| - "bypassTempDirValidation": {
|
| - "description": "Whether to bypass the safety checks for the job's temporary directory. Use with caution.",
|
| - "type": "boolean"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ReportWorkItemStatusRequest": {
|
| - "description": "Request to report the status of WorkItems.",
|
| - "id": "ReportWorkItemStatusRequest",
|
| + "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": {
|
| - "workerId": {
|
| - "description": "The ID of the worker reporting the WorkItem status. If this does not match the ID of the worker which the Dataflow service believes currently has the lease on the WorkItem, the report will be dropped (with an error response).",
|
| - "type": "string"
|
| - },
|
| - "workItemStatuses": {
|
| - "description": "The order is unimportant, except that the order of the WorkItemServiceState messages in the ReportWorkItemStatusResponse corresponds to the order of WorkItemStatus messages here.",
|
| - "items": {
|
| - "$ref": "WorkItemStatus"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "currentWorkerTime": {
|
| - "description": "The current timestamp at the worker.",
|
| - "type": "string"
|
| + "residual": {
|
| + "$ref": "DerivedSource",
|
| + "description": "Residual part (returned to the pool of work).\nSpecified relative to the previously-current source."
|
| },
|
| - "location": {
|
| - "description": "The location which contains the WorkItem's job.",
|
| - "type": "string"
|
| + "primary": {
|
| + "$ref": "DerivedSource",
|
| + "description": "Primary part (continued to be processed by worker).\nSpecified relative to the previously-current source.\nBecomes current."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkItemStatus": {
|
| - "description": "Conveys a worker's progress through the work described by a WorkItem.",
|
| - "id": "WorkItemStatus",
|
| + "DerivedSource": {
|
| + "description": "Specification of one of the bundles produced as a result of splitting\na Source (e.g. when executing a SourceSplitRequest, or when\nsplitting an active task using WorkItemStatus.dynamic_source_split),\nrelative to the source being split.",
|
| + "id": "DerivedSource",
|
| "properties": {
|
| - "workItemId": {
|
| - "description": "Identifies the WorkItem.",
|
| - "type": "string"
|
| - },
|
| - "reportIndex": {
|
| - "description": "The report index. When a WorkItem is leased, the lease will contain an initial report index. When a WorkItem's status is reported to the system, the report should be sent with that report index, and the response will contain the index the worker should use for the next report. Reports received with unexpected index values will be rejected by the service. In order to preserve idempotency, the worker should not alter the contents of a report, even if the worker must submit the same report multiple times before getting back a response. The worker should not submit a subsequent report until the response for the previous report had been received from the service.",
|
| - "format": "int64",
|
| - "type": "string"
|
| + "source": {
|
| + "$ref": "Source",
|
| + "description": "Specification of the source."
|
| },
|
| - "requestedLeaseDuration": {
|
| - "description": "Amount of time the worker requests for its lease.",
|
| + "derivationMode": {
|
| + "description": "What source to base the produced source on (if any).",
|
| + "enum": [
|
| + "SOURCE_DERIVATION_MODE_UNKNOWN",
|
| + "SOURCE_DERIVATION_MODE_INDEPENDENT",
|
| + "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
|
| + "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The source derivation is unknown, or unspecified.",
|
| + "Produce a completely independent Source with no base.",
|
| + "Produce a Source based on the Source being split.",
|
| + "Produce a Source based on the base of the Source being split."
|
| + ],
|
| "type": "string"
|
| - },
|
| - "completed": {
|
| - "description": "True if the WorkItem was completed (successfully or unsuccessfully).",
|
| - "type": "boolean"
|
| - },
|
| - "errors": {
|
| - "description": "Specifies errors which occurred during processing. If errors are provided, and completed = true, then the WorkItem is considered to have failed.",
|
| - "items": {
|
| - "$ref": "Status"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "counterUpdates": {
|
| - "description": "Worker output counters for this WorkItem.",
|
| - "items": {
|
| - "$ref": "CounterUpdate"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "metricUpdates": {
|
| - "description": "DEPRECATED in favor of counter_updates.",
|
| - "items": {
|
| - "$ref": "MetricUpdate"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "reportedProgress": {
|
| - "$ref": "ApproximateReportedProgress",
|
| - "description": "The worker's progress through this WorkItem."
|
| - },
|
| - "stopPosition": {
|
| - "$ref": "Position",
|
| - "description": "A worker may split an active map task in two parts, \"primary\" and \"residual\", continuing to process the primary part and returning the residual part into the pool of available work. This event is called a \"dynamic split\" and is critical to the dynamic work rebalancing feature. The two obtained sub-tasks are called \"parts\" of the split. The parts, if concatenated, must represent the same input as would be read by the current task if the split did not happen. The exact way in which the original task is decomposed into the two parts is specified either as a position demarcating them (stop_position), or explicitly as two DerivedSources, if this task consumes a user-defined source type (dynamic_source_split). The \"current\" task is adjusted as a result of the split: after a task with range [A, B) sends a stop_position update at C, its range is considered to be [A, C), e.g.: * Progress should be interpreted relative to the new range, e.g. \"75% completed\" means \"75% of [A, C) completed\" * The worker should interpret proposed_stop_position relative to the new range, e.g. \"split at 68%\" should be interpreted as \"split at 68% of [A, C)\". * If the worker chooses to split again using stop_position, only stop_positions in [A, C) will be accepted. * Etc. dynamic_source_split has similar semantics: e.g., if a task with source S splits using dynamic_source_split into {P, R} (where P and R must be together equivalent to S), then subsequent progress and proposed_stop_position should be interpreted relative to P, and in a potential subsequent dynamic_source_split into {P', R'}, P' and R' must be together equivalent to P, etc."
|
| - },
|
| - "dynamicSourceSplit": {
|
| - "$ref": "DynamicSourceSplit",
|
| - "description": "See documentation of stop_position."
|
| - },
|
| - "sourceOperationResponse": {
|
| - "$ref": "SourceOperationResponse",
|
| - "description": "If the work item represented a SourceOperationRequest, and the work is completed, contains the result of the operation."
|
| - },
|
| - "sourceFork": {
|
| - "$ref": "SourceFork",
|
| - "description": "DEPRECATED in favor of dynamic_source_split."
|
| - },
|
| - "progress": {
|
| - "$ref": "ApproximateProgress",
|
| - "description": "DEPRECATED in favor of reported_progress."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Status": {
|
| - "description": "The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). The error model is designed to be: - Simple to use and understand for most users - Flexible enough to meet unexpected needs # Overview The `Status` message contains three pieces of data: error code, error message, and error details. The error code should be an enum value of google.rpc.Code, but it may accept additional error codes if needed. The error message should be a developer-facing English message that helps developers *understand* and *resolve* the error. If a localized user-facing error message is needed, put the localized message in the error details or localize it in the client. The optional error details may contain arbitrary information about the error. There is a predefined set of error detail types in the package `google.rpc` which can be used for common error conditions. # Language mapping The `Status` message is the logical representation of the error model, but it is not necessarily the actual wire format. When the `Status` message is exposed in different client libraries and different wire protocols, it can be mapped differently. For example, it will likely be mapped to some exceptions in Java, but more likely mapped to some error codes in C. # Other uses The error model and the `Status` message can be used in a variety of environments, either with or without APIs, to provide a consistent developer experience across different environments. Example uses of this error model include: - Partial errors. If a service needs to return partial errors to the client, it may embed the `Status` in the normal response to indicate the partial errors. - Workflow errors. A typical workflow has multiple steps. Each step may have a `Status` message for error reporting purpose. - Batch operations. If a client uses batch request and batch response, the `Status` message should be used directly inside batch response, one for each error sub-response. - Asynchronous operations. If an API call embeds asynchronous operation results in its response, the status of those operations should be represented directly using the `Status` message. - Logging. If some API errors are stored in logs, the message `Status` could be used directly after any stripping needed for security/privacy reasons.",
|
| - "id": "Status",
|
| + "SourceOperationResponse": {
|
| + "description": "The result of a SourceOperationRequest, specified in\nReportWorkItemStatusRequest.source_operation when the work item\nis completed.",
|
| + "id": "SourceOperationResponse",
|
| "properties": {
|
| - "code": {
|
| - "description": "The status code, which should be an enum value of google.rpc.Code.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - },
|
| - "message": {
|
| - "description": "A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.",
|
| - "type": "string"
|
| + "split": {
|
| + "$ref": "SourceSplitResponse",
|
| + "description": "A response to a request to split a source."
|
| },
|
| - "details": {
|
| - "description": "A list of messages that carry the error details. There will be a common set of message types for APIs to use.",
|
| - "items": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object. Contains field @type with type URL.",
|
| - "type": "any"
|
| - },
|
| - "type": "object"
|
| - },
|
| - "type": "array"
|
| + "getMetadata": {
|
| + "$ref": "SourceGetMetadataResponse",
|
| + "description": "A response to a request to get metadata about a source."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "CounterUpdate": {
|
| - "description": "An update to a Counter sent from a worker.",
|
| - "id": "CounterUpdate",
|
| + "SendDebugCaptureResponse": {
|
| + "description": "Response to a send capture request.\nnothing",
|
| + "id": "SendDebugCaptureResponse",
|
| + "properties": {},
|
| + "type": "object"
|
| + },
|
| + "SideInputInfo": {
|
| + "description": "Information about a side input of a DoFn or an input of a SeqDoFn.",
|
| + "id": "SideInputInfo",
|
| "properties": {
|
| - "nameAndKind": {
|
| - "$ref": "NameAndKind",
|
| - "description": "Counter name and aggregation type."
|
| - },
|
| - "shortId": {
|
| - "description": "The service-generated short identifier for this counter. The short_id -> (name, metadata) mapping is constant for the lifetime of a job.",
|
| - "format": "int64",
|
| - "type": "string"
|
| - },
|
| - "structuredNameAndMetadata": {
|
| - "$ref": "CounterStructuredNameAndMetadata",
|
| - "description": "Counter structured name and metadata."
|
| - },
|
| - "cumulative": {
|
| - "description": "True if this counter is reported as the total cumulative aggregate value accumulated since the worker started working on this WorkItem. By default this is false, indicating that this counter is reported as a delta.",
|
| - "type": "boolean"
|
| - },
|
| - "integer": {
|
| - "$ref": "SplitInt64",
|
| - "description": "Integer value for Sum, Max, Min."
|
| - },
|
| - "floatingPoint": {
|
| - "description": "Floating point value for Sum, Max, Min.",
|
| - "format": "double",
|
| - "type": "number"
|
| - },
|
| - "boolean": {
|
| - "description": "Boolean value for And, Or.",
|
| - "type": "boolean"
|
| - },
|
| - "integerMean": {
|
| - "$ref": "IntegerMean",
|
| - "description": "Integer mean aggregation value for Mean."
|
| - },
|
| - "floatingPointMean": {
|
| - "$ref": "FloatingPointMean",
|
| - "description": "Floating point mean aggregation value for Mean."
|
| - },
|
| - "integerList": {
|
| - "$ref": "IntegerList",
|
| - "description": "List of integers, for Set."
|
| - },
|
| - "floatingPointList": {
|
| - "$ref": "FloatingPointList",
|
| - "description": "List of floating point numbers, for Set."
|
| + "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": {
|
| + "$ref": "Source"
|
| + },
|
| + "type": "array"
|
| },
|
| - "stringList": {
|
| - "$ref": "StringList",
|
| - "description": "List of strings, for Set."
|
| + "kind": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "How to interpret the source element(s) as a side input value.",
|
| + "type": "object"
|
| },
|
| - "distribution": {
|
| - "$ref": "DistributionUpdate",
|
| - "description": "Distribution data"
|
| + "tag": {
|
| + "description": "The id of the tag the user code will access this side input by;\nthis should correspond to the tag of some MultiOutputInfo.",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "ConcatPosition": {
|
| + "description": "A position that encapsulates an inner position and an index for the inner\nposition. A ConcatPosition can be used by a reader of a source that\nencapsulates a set of other sources.",
|
| + "id": "ConcatPosition",
|
| + "properties": {
|
| + "position": {
|
| + "$ref": "Position",
|
| + "description": "Position within the inner source."
|
| },
|
| - "internal": {
|
| - "description": "Value for internally-defined counters used by the Dataflow service.",
|
| - "type": "any"
|
| + "index": {
|
| + "description": "Index of the inner source.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "NameAndKind": {
|
| - "description": "Basic metadata about a counter.",
|
| - "id": "NameAndKind",
|
| + "WriteInstruction": {
|
| + "description": "An instruction that writes records.\nTakes one input, produces no outputs.",
|
| + "id": "WriteInstruction",
|
| "properties": {
|
| - "name": {
|
| - "description": "Name of the counter.",
|
| - "type": "string"
|
| + "input": {
|
| + "$ref": "InstructionInput",
|
| + "description": "The input."
|
| },
|
| - "kind": {
|
| - "description": "Counter aggregation kind.",
|
| - "enum": [
|
| - "INVALID",
|
| - "SUM",
|
| - "MAX",
|
| - "MIN",
|
| - "MEAN",
|
| - "OR",
|
| - "AND",
|
| - "SET",
|
| - "DISTRIBUTION"
|
| - ],
|
| - "type": "string"
|
| + "sink": {
|
| + "$ref": "Sink",
|
| + "description": "The sink to write to."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| "CounterStructuredNameAndMetadata": {
|
| - "description": "A single message which encapsulates structured name and metadata for a given counter.",
|
| + "description": "A single message which encapsulates structured name and metadata for a given\ncounter.",
|
| "id": "CounterStructuredNameAndMetadata",
|
| "properties": {
|
| "name": {
|
| @@ -2085,692 +1916,812 @@
|
| },
|
| "type": "object"
|
| },
|
| - "CounterStructuredName": {
|
| - "description": "Identifies a counter within a per-job namespace. Counters whose structured names are the same get merged into a single value for the job.",
|
| - "id": "CounterStructuredName",
|
| + "AutoscalingSettings": {
|
| + "description": "Settings for WorkerPool autoscaling.",
|
| + "id": "AutoscalingSettings",
|
| "properties": {
|
| - "name": {
|
| - "description": "Counter name. Not necessarily globally-unique, but unique within the context of the other fields. Required.",
|
| - "type": "string"
|
| - },
|
| - "standardOrigin": {
|
| - "description": "One of the standard Origins defined above.",
|
| + "algorithm": {
|
| + "description": "The algorithm to use for autoscaling.",
|
| "enum": [
|
| - "DATAFLOW",
|
| - "USER"
|
| + "AUTOSCALING_ALGORITHM_UNKNOWN",
|
| + "AUTOSCALING_ALGORITHM_NONE",
|
| + "AUTOSCALING_ALGORITHM_BASIC"
|
| ],
|
| - "type": "string"
|
| - },
|
| - "otherOrigin": {
|
| - "description": "A string containing the origin of the counter.",
|
| - "type": "string"
|
| - },
|
| - "originalStepName": {
|
| - "description": "System generated name of the original step in the user's graph, before optimization.",
|
| - "type": "string"
|
| - },
|
| - "componentStepName": {
|
| - "description": "Name of the optimized step being executed by the workers.",
|
| - "type": "string"
|
| - },
|
| - "executionStepName": {
|
| - "description": "Name of the stage. An execution step contains multiple component steps.",
|
| - "type": "string"
|
| - },
|
| - "workerId": {
|
| - "description": "ID of a particular worker.",
|
| - "type": "string"
|
| - },
|
| - "portion": {
|
| - "description": "Portion of this counter, either key or value.",
|
| - "enum": [
|
| - "ALL",
|
| - "KEY",
|
| - "VALUE"
|
| + "enumDescriptions": [
|
| + "The algorithm is unknown, or unspecified.",
|
| + "Disable autoscaling.",
|
| + "Increase worker count over time to reduce job execution time."
|
| ],
|
| "type": "string"
|
| + },
|
| + "maxNumWorkers": {
|
| + "description": "The maximum number of workers to cap scaling at.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "CounterMetadata": {
|
| - "description": "CounterMetadata includes all static non-name non-value counter attributes.",
|
| - "id": "CounterMetadata",
|
| + "StreamingComputationRanges": {
|
| + "description": "Describes full or partial data disk assignment information of the computation\nranges.",
|
| + "id": "StreamingComputationRanges",
|
| "properties": {
|
| - "kind": {
|
| - "description": "Counter aggregation kind.",
|
| - "enum": [
|
| - "INVALID",
|
| - "SUM",
|
| - "MAX",
|
| - "MIN",
|
| - "MEAN",
|
| - "OR",
|
| - "AND",
|
| - "SET",
|
| - "DISTRIBUTION"
|
| - ],
|
| - "type": "string"
|
| - },
|
| - "description": {
|
| - "description": "Human-readable description of the counter semantics.",
|
| - "type": "string"
|
| - },
|
| - "standardUnits": {
|
| - "description": "System defined Units, see above enum.",
|
| - "enum": [
|
| - "BYTES",
|
| - "BYTES_PER_SEC",
|
| - "MILLISECONDS",
|
| - "MICROSECONDS",
|
| - "NANOSECONDS",
|
| - "TIMESTAMP_MSEC",
|
| - "TIMESTAMP_USEC",
|
| - "TIMESTAMP_NSEC"
|
| - ],
|
| - "type": "string"
|
| + "rangeAssignments": {
|
| + "description": "Data disk assignments for ranges from this computation.",
|
| + "items": {
|
| + "$ref": "KeyRangeDataDiskAssignment"
|
| + },
|
| + "type": "array"
|
| },
|
| - "otherUnits": {
|
| - "description": "A string referring to the unit type.",
|
| + "computationId": {
|
| + "description": "The ID of the computation.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SplitInt64": {
|
| - "description": "A representation of an int64, n, that is immune to precision loss when encoded in JSON.",
|
| - "id": "SplitInt64",
|
| + "SendWorkerMessagesRequest": {
|
| + "description": "A request for sending worker messages to the service.",
|
| + "id": "SendWorkerMessagesRequest",
|
| "properties": {
|
| - "lowBits": {
|
| - "description": "The low order bits: n & 0xffffffff.",
|
| - "format": "uint32",
|
| - "type": "integer"
|
| - },
|
| - "highBits": {
|
| - "description": "The high order bits, including the sign: n >> 32.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "workerMessages": {
|
| + "description": "The WorkerMessages to send.",
|
| + "items": {
|
| + "$ref": "WorkerMessage"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "IntegerMean": {
|
| - "description": "A representation of an integer mean metric contribution.",
|
| - "id": "IntegerMean",
|
| + "SourceSplitShard": {
|
| + "description": "DEPRECATED in favor of DerivedSource.",
|
| + "id": "SourceSplitShard",
|
| "properties": {
|
| - "sum": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The sum of all values being aggregated."
|
| + "derivationMode": {
|
| + "description": "DEPRECATED",
|
| + "enum": [
|
| + "SOURCE_DERIVATION_MODE_UNKNOWN",
|
| + "SOURCE_DERIVATION_MODE_INDEPENDENT",
|
| + "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
|
| + "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The source derivation is unknown, or unspecified.",
|
| + "Produce a completely independent Source with no base.",
|
| + "Produce a Source based on the Source being split.",
|
| + "Produce a Source based on the base of the Source being split."
|
| + ],
|
| + "type": "string"
|
| },
|
| - "count": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The number of values being aggregated."
|
| + "source": {
|
| + "$ref": "Source",
|
| + "description": "DEPRECATED"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "FloatingPointMean": {
|
| - "description": "A representation of a floating point mean metric contribution.",
|
| - "id": "FloatingPointMean",
|
| + "CPUTime": {
|
| + "description": "Modeled after information exposed by /proc/stat.",
|
| + "id": "CPUTime",
|
| "properties": {
|
| - "sum": {
|
| - "description": "The sum of all values being aggregated.",
|
| + "totalMs": {
|
| + "description": "Total active CPU time across all cores (ie., non-idle) in milliseconds\nsince start-up.",
|
| + "format": "uint64",
|
| + "type": "string"
|
| + },
|
| + "rate": {
|
| + "description": "Average CPU utilization rate (% non-idle cpu / second) since previous\nsample.",
|
| "format": "double",
|
| "type": "number"
|
| },
|
| - "count": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The number of values being aggregated."
|
| + "timestamp": {
|
| + "description": "Timestamp of the measurement.",
|
| + "format": "google-datetime",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "IntegerList": {
|
| - "description": "A metric value representing a list of integers.",
|
| - "id": "IntegerList",
|
| + "Environment": {
|
| + "description": "Describes the environment in which a Dataflow Job runs.",
|
| + "id": "Environment",
|
| "properties": {
|
| - "elements": {
|
| - "description": "Elements of the list.",
|
| + "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}",
|
| + "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": {
|
| - "$ref": "SplitInt64"
|
| + "$ref": "WorkerPool"
|
| + },
|
| + "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}",
|
| + "type": "string"
|
| + },
|
| + "experiments": {
|
| + "description": "The list of experiments to enable.",
|
| + "items": {
|
| + "type": "string"
|
| },
|
| "type": "array"
|
| + },
|
| + "internalExperiments": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object. Contains field @type with type URL.",
|
| + "type": "any"
|
| + },
|
| + "description": "Experimental settings.",
|
| + "type": "object"
|
| + },
|
| + "version": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "A structure describing which components and their versions of the service\nare required in order to run the job.",
|
| + "type": "object"
|
| + },
|
| + "serviceAccountEmail": {
|
| + "description": "Identity to run virtual machines as. Defaults to the default account.",
|
| + "type": "string"
|
| + },
|
| + "userAgent": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "A description of the process that generated the request.",
|
| + "type": "object"
|
| + },
|
| + "sdkPipelineOptions": {
|
| + "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"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "FloatingPointList": {
|
| - "description": "A metric value representing a list of floating point numbers.",
|
| - "id": "FloatingPointList",
|
| + "StreamingComputationTask": {
|
| + "description": "A task which describes what action should be performed for the specified\nstreaming computation ranges.",
|
| + "id": "StreamingComputationTask",
|
| "properties": {
|
| - "elements": {
|
| - "description": "Elements of the list.",
|
| + "dataDisks": {
|
| + "description": "Describes the set of data disks this task should apply to.",
|
| "items": {
|
| - "format": "double",
|
| - "type": "number"
|
| + "$ref": "MountedDataDisk"
|
| },
|
| "type": "array"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "StringList": {
|
| - "description": "A metric value representing a list of strings.",
|
| - "id": "StringList",
|
| - "properties": {
|
| - "elements": {
|
| - "description": "Elements of the list.",
|
| + },
|
| + "taskType": {
|
| + "description": "A type of streaming computation task.",
|
| + "enum": [
|
| + "STREAMING_COMPUTATION_TASK_UNKNOWN",
|
| + "STREAMING_COMPUTATION_TASK_STOP",
|
| + "STREAMING_COMPUTATION_TASK_START"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The streaming computation task is unknown, or unspecified.",
|
| + "Stop processing specified streaming computation range(s).",
|
| + "Start processing specified streaming computation range(s)."
|
| + ],
|
| + "type": "string"
|
| + },
|
| + "computationRanges": {
|
| + "description": "Contains ranges of a streaming computation this task should apply to.",
|
| "items": {
|
| - "type": "string"
|
| + "$ref": "StreamingComputationRanges"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "DistributionUpdate": {
|
| - "description": "A metric value representing a distribution.",
|
| - "id": "DistributionUpdate",
|
| + "SendDebugCaptureRequest": {
|
| + "description": "Request to send encoded debug information.",
|
| + "id": "SendDebugCaptureRequest",
|
| "properties": {
|
| - "min": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The minimum value present in the distribution."
|
| - },
|
| - "max": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The maximum value present in the distribution."
|
| - },
|
| - "count": {
|
| - "$ref": "SplitInt64",
|
| - "description": "The count of the number of elements present in the distribution."
|
| + "componentId": {
|
| + "description": "The internal component id for which debug information is sent.",
|
| + "type": "string"
|
| },
|
| - "sum": {
|
| - "$ref": "SplitInt64",
|
| - "description": "Use an int64 since we'd prefer the added precision. If overflow is a common problem we can detect it and use an additional int64 or a double."
|
| + "workerId": {
|
| + "description": "The worker id, i.e., VM hostname.",
|
| + "type": "string"
|
| },
|
| - "sumOfSquares": {
|
| - "description": "Use a double since the sum of squares is likely to overflow int64.",
|
| - "format": "double",
|
| - "type": "number"
|
| + "data": {
|
| + "description": "The encoded debug information.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ApproximateReportedProgress": {
|
| - "description": "A progress measurement of a WorkItem by a worker.",
|
| - "id": "ApproximateReportedProgress",
|
| + "GetDebugConfigResponse": {
|
| + "description": "Response to a get debug configuration request.",
|
| + "id": "GetDebugConfigResponse",
|
| "properties": {
|
| - "position": {
|
| - "$ref": "Position",
|
| - "description": "A Position within the work to represent a progress."
|
| + "config": {
|
| + "description": "The encoded debug configuration for the requested component.",
|
| + "type": "string"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "StreamingSetupTask": {
|
| + "description": "A task which initializes part of a streaming Dataflow job.",
|
| + "id": "StreamingSetupTask",
|
| + "properties": {
|
| + "workerHarnessPort": {
|
| + "description": "The TCP port used by the worker to communicate with the Dataflow\nworker harness.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| },
|
| - "fractionConsumed": {
|
| - "description": "Completion as fraction of the input consumed, from 0.0 (beginning, nothing consumed), to 1.0 (end of the input, entire input consumed).",
|
| - "format": "double",
|
| - "type": "number"
|
| + "drain": {
|
| + "description": "The user has requested drain.",
|
| + "type": "boolean"
|
| },
|
| - "remainingParallelism": {
|
| - "$ref": "ReportedParallelism",
|
| - "description": "Total amount of parallelism in the input of this task that remains, (i.e. can be delegated to this task and any new tasks via dynamic splitting). Always at least 1 for non-finished work items and 0 for finished. \"Amount of parallelism\" refers to how many non-empty parts of the input can be read in parallel. This does not necessarily equal number of records. An input that can be read in parallel down to the individual records is called \"perfectly splittable\". An example of non-perfectly parallelizable input is a block-compressed file format where a block of records has to be read as a whole, but different blocks can be read in parallel. Examples: * If we are processing record #30 (starting at 1) out of 50 in a perfectly splittable 50-record input, this value should be 21 (20 remaining + 1 current). * If we are reading through block 3 in a block-compressed file consisting of 5 blocks, this value should be 3 (since blocks 4 and 5 can be processed in parallel by new tasks via dynamic splitting and the current task remains processing block 3). * If we are reading through the last block in a block-compressed file, or reading or processing the last record in a perfectly splittable input, this value should be 1, because apart from the current task, no additional remainder can be split off."
|
| + "receiveWorkPort": {
|
| + "description": "The TCP port on which the worker should listen for messages from\nother streaming computation workers.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| },
|
| - "consumedParallelism": {
|
| - "$ref": "ReportedParallelism",
|
| - "description": "Total amount of parallelism in the portion of input of this task that has already been consumed and is no longer active. In the first two examples above (see remaining_parallelism), the value should be 29 or 2 respectively. The sum of remaining_parallelism and consumed_parallelism should equal the total amount of parallelism in this work item. If specified, must be finite."
|
| + "streamingComputationTopology": {
|
| + "$ref": "TopologyConfig",
|
| + "description": "The global topology of the streaming Dataflow job."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Position": {
|
| - "description": "Position defines a position within a collection of data. The value can be either the end position, a key (used with ordered collections), a byte offset, or a record index.",
|
| - "id": "Position",
|
| + "PubsubLocation": {
|
| + "description": "Identifies a pubsub location to use for transferring data into or\nout of a streaming Dataflow job.",
|
| + "id": "PubsubLocation",
|
| "properties": {
|
| - "end": {
|
| - "description": "Position is past all other positions. Also useful for the end position of an unbounded range.",
|
| + "withAttributes": {
|
| + "description": "If true, then the client has requested to get pubsub attributes.",
|
| "type": "boolean"
|
| },
|
| - "key": {
|
| - "description": "Position is a string key, ordered lexicographically.",
|
| + "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"
|
| },
|
| - "byteOffset": {
|
| - "description": "Position is a byte offset.",
|
| - "format": "int64",
|
| + "topic": {
|
| + "description": "A pubsub topic, in the form of\n\"pubsub.googleapis.com/topics/<project-id>/<topic-name>\"",
|
| "type": "string"
|
| },
|
| - "recordIndex": {
|
| - "description": "Position is a record index.",
|
| - "format": "int64",
|
| + "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"
|
| },
|
| - "shufflePosition": {
|
| - "description": "CloudPosition is a base64 encoded BatchShufflePosition (with FIXED sharding).",
|
| + "subscription": {
|
| + "description": "A pubsub subscription, in the form of\n\"pubsub.googleapis.com/subscriptions/<project-id>/<subscription-name>\"",
|
| "type": "string"
|
| },
|
| - "concatPosition": {
|
| - "$ref": "ConcatPosition",
|
| - "description": "CloudPosition is a concat position."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "ConcatPosition": {
|
| - "description": "A position that encapsulates an inner position and an index for the inner position. A ConcatPosition can be used by a reader of a source that encapsulates a set of other sources.",
|
| - "id": "ConcatPosition",
|
| - "properties": {
|
| - "index": {
|
| - "description": "Index of the inner source.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "dropLateData": {
|
| + "description": "Indicates whether the pipeline allows late-arriving data.",
|
| + "type": "boolean"
|
| },
|
| - "position": {
|
| - "$ref": "Position",
|
| - "description": "Position within the inner source."
|
| + "trackingSubscription": {
|
| + "description": "If set, specifies the pubsub subscription that will be used for tracking\ncustom time timestamps for watermark estimation.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ReportedParallelism": {
|
| - "description": "Represents the level of parallelism in a WorkItem's input, reported by the worker.",
|
| - "id": "ReportedParallelism",
|
| + "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": {
|
| - "isInfinite": {
|
| - "description": "Specifies whether the parallelism is infinite. If true, \"value\" is ignored. Infinite parallelism means the service will assume that the work item can always be split into more non-empty work items by dynamic splitting. This is a work-around for lack of support for infinity by the current JSON-based Java RPC stack.",
|
| + "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": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "type": "object"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "vmStartupTime": {
|
| + "description": "The time the VM was booted.",
|
| + "format": "google-datetime",
|
| + "type": "string"
|
| + },
|
| + "vmIsHealthy": {
|
| + "description": "Whether the VM is healthy.",
|
| "type": "boolean"
|
| },
|
| - "value": {
|
| - "description": "Specifies the level of parallelism in case it is finite.",
|
| - "format": "double",
|
| - "type": "number"
|
| + "reportInterval": {
|
| + "description": "The interval at which the worker is sending health reports.\nThe default value of 0 should be interpreted as the field is not being\nexplicitly set by the worker.",
|
| + "format": "google-duration",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "DynamicSourceSplit": {
|
| - "description": "When a task splits using WorkItemStatus.dynamic_source_split, this message describes the two parts of the split relative to the description of the current task's input.",
|
| - "id": "DynamicSourceSplit",
|
| + "JobMessage": {
|
| + "description": "A particular message pertaining to a Dataflow job.",
|
| + "id": "JobMessage",
|
| "properties": {
|
| - "primary": {
|
| - "$ref": "DerivedSource",
|
| - "description": "Primary part (continued to be processed by worker). Specified relative to the previously-current source. Becomes current."
|
| + "id": {
|
| + "description": "Identifies the message. This is automatically generated by the\nservice; the caller should treat it as an opaque string.",
|
| + "type": "string"
|
| },
|
| - "residual": {
|
| - "$ref": "DerivedSource",
|
| - "description": "Residual part (returned to the pool of work). Specified relative to the previously-current source."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "DerivedSource": {
|
| - "description": "Specification of one of the bundles produced as a result of splitting a Source (e.g. when executing a SourceSplitRequest, or when splitting an active task using WorkItemStatus.dynamic_source_split), relative to the source being split.",
|
| - "id": "DerivedSource",
|
| - "properties": {
|
| - "source": {
|
| - "$ref": "Source",
|
| - "description": "Specification of the source."
|
| + "messageText": {
|
| + "description": "The text of the message.",
|
| + "type": "string"
|
| },
|
| - "derivationMode": {
|
| - "description": "What source to base the produced source on (if any).",
|
| + "messageImportance": {
|
| + "description": "Importance level of the message.",
|
| "enum": [
|
| - "SOURCE_DERIVATION_MODE_UNKNOWN",
|
| - "SOURCE_DERIVATION_MODE_INDEPENDENT",
|
| - "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
|
| - "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
|
| + "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"
|
| + },
|
| + "time": {
|
| + "description": "The timestamp of the message.",
|
| + "format": "google-datetime",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Source": {
|
| - "description": "A source that records can be read and decoded from.",
|
| - "id": "Source",
|
| + "MultiOutputInfo": {
|
| + "description": "Information about an output of a multi-output DoFn.",
|
| + "id": "MultiOutputInfo",
|
| "properties": {
|
| - "spec": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The source to read from, plus its parameters.",
|
| - "type": "object"
|
| - },
|
| - "codec": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The codec to use to decode data read from the source.",
|
| - "type": "object"
|
| - },
|
| - "baseSpecs": {
|
| - "description": "While splitting, sources may specify the produced bundles as differences against another source, in order to save backend-side memory and allow bigger jobs. For details, see SourceSplitRequest. To support this use case, the full set of parameters of the source is logically obtained by taking the latest explicitly specified value of each parameter in the order: base_specs (later items win), spec (overrides anything in base_specs).",
|
| - "items": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "type": "object"
|
| - },
|
| - "type": "array"
|
| + "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"
|
| + },
|
| + "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": {
|
| + "source": {
|
| + "$ref": "Source",
|
| + "description": "Specification of the source to be split."
|
| },
|
| + "options": {
|
| + "$ref": "SourceSplitOptions",
|
| + "description": "Hints for tuning the splitting process."
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "SourceGetMetadataResponse": {
|
| + "description": "The result of a SourceGetMetadataOperation.",
|
| + "id": "SourceGetMetadataResponse",
|
| + "properties": {
|
| "metadata": {
|
| "$ref": "SourceMetadata",
|
| - "description": "Optionally, metadata for this source can be supplied right away, avoiding a SourceGetMetadataOperation roundtrip (see SourceOperationRequest). This field is meaningful only in the Source objects populated by the user (e.g. when filling in a DerivedSource). Source objects supplied by the framework to the user don't have this field populated."
|
| - },
|
| - "doesNotNeedSplitting": {
|
| - "description": "Setting this value to true hints to the framework that the source doesn't need splitting, and using SourceSplitRequest on it would yield SOURCE_SPLIT_OUTCOME_USE_CURRENT. E.g. a file splitter may set this to true when splitting a single file into a set of byte ranges of appropriate size, and set this to false when splitting a filepattern into individual files. However, for efficiency, a file splitter may decide to produce file subranges directly from the filepattern to avoid a splitting round-trip. See SourceSplitRequest for an overview of the splitting process. This field is meaningful only in the Source objects populated by the user (e.g. when filling in a DerivedSource). Source objects supplied by the framework to the user don't have this field populated.",
|
| - "type": "boolean"
|
| + "description": "The computed metadata."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceMetadata": {
|
| - "description": "Metadata about a Source useful for automatically optimizing and tuning the pipeline, etc.",
|
| - "id": "SourceMetadata",
|
| + "MetricShortId": {
|
| + "description": "The metric short id is returned to the user alongside an offset into\nReportWorkItemStatusRequest",
|
| + "id": "MetricShortId",
|
| "properties": {
|
| - "producesSortedKeys": {
|
| - "description": "Whether this source is known to produce key/value pairs with the (encoded) keys in lexicographically sorted order.",
|
| - "type": "boolean"
|
| - },
|
| - "infinite": {
|
| - "description": "Specifies that the size of this source is known to be infinite (this is a streaming source).",
|
| - "type": "boolean"
|
| + "metricIndex": {
|
| + "description": "The index of the corresponding metric in\nthe ReportWorkItemStatusRequest. Required.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| },
|
| - "estimatedSizeBytes": {
|
| - "description": "An estimate of the total size (in bytes) of the data that would be read from this source. This estimate is in terms of external storage size, before any decompression or other processing done by the reader.",
|
| + "shortId": {
|
| + "description": "The service-generated short identifier for the metric.",
|
| "format": "int64",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceOperationResponse": {
|
| - "description": "The result of a SourceOperationRequest, specified in ReportWorkItemStatusRequest.source_operation when the work item is completed.",
|
| - "id": "SourceOperationResponse",
|
| + "ShellTask": {
|
| + "description": "A task which consists of a shell command for the worker to execute.",
|
| + "id": "ShellTask",
|
| "properties": {
|
| - "split": {
|
| - "$ref": "SourceSplitResponse",
|
| - "description": "A response to a request to split a source."
|
| + "exitCode": {
|
| + "description": "Exit code for the task.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| },
|
| - "getMetadata": {
|
| - "$ref": "SourceGetMetadataResponse",
|
| - "description": "A response to a request to get metadata about a source."
|
| + "command": {
|
| + "description": "The shell command to run.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceSplitResponse": {
|
| - "description": "The response to a SourceSplitRequest.",
|
| - "id": "SourceSplitResponse",
|
| + "TaskRunnerSettings": {
|
| + "description": "Taskrunner configuration settings.",
|
| + "id": "TaskRunnerSettings",
|
| "properties": {
|
| - "outcome": {
|
| - "description": "Indicates whether splitting happened and produced a list of bundles. If this is USE_CURRENT_SOURCE_AS_IS, the current source should be processed \"as is\" without splitting. \"bundles\" is ignored in this case. If this is SPLITTING_HAPPENED, then \"bundles\" contains a list of bundles into which the source was split.",
|
| - "enum": [
|
| - "SOURCE_SPLIT_OUTCOME_UNKNOWN",
|
| - "SOURCE_SPLIT_OUTCOME_USE_CURRENT",
|
| - "SOURCE_SPLIT_OUTCOME_SPLITTING_HAPPENED"
|
| - ],
|
| + "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"
|
| },
|
| - "bundles": {
|
| - "description": "If outcome is SPLITTING_HAPPENED, then this is a list of bundles into which the source was split. Otherwise this field is ignored. This list can be empty, which means the source represents an empty input.",
|
| - "items": {
|
| - "$ref": "DerivedSource"
|
| - },
|
| - "type": "array"
|
| + "logToSerialconsole": {
|
| + "description": "Whether to send taskrunner log info to Google Compute Engine VM serial\nconsole.",
|
| + "type": "boolean"
|
| },
|
| - "shards": {
|
| - "description": "DEPRECATED in favor of bundles.",
|
| + "continueOnException": {
|
| + "description": "Whether to continue taskrunner if an exception is hit.",
|
| + "type": "boolean"
|
| + },
|
| + "parallelWorkerSettings": {
|
| + "$ref": "WorkerSettings",
|
| + "description": "The settings to pass to the parallel worker harness."
|
| + },
|
| + "vmId": {
|
| + "description": "The ID string of the VM.",
|
| + "type": "string"
|
| + },
|
| + "taskUser": {
|
| + "description": "The UNIX user ID on the worker VM to use for tasks launched by\ntaskrunner; e.g. \"root\".",
|
| + "type": "string"
|
| + },
|
| + "alsologtostderr": {
|
| + "description": "Whether to also send taskrunner log info to stderr.",
|
| + "type": "boolean"
|
| + },
|
| + "taskGroup": {
|
| + "description": "The UNIX group ID on the worker VM to use for tasks launched by\ntaskrunner; e.g. \"wheel\".",
|
| + "type": "string"
|
| + },
|
| + "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": {
|
| - "$ref": "SourceSplitShard"
|
| + "type": "string"
|
| },
|
| "type": "array"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "SourceSplitShard": {
|
| - "description": "DEPRECATED in favor of DerivedSource.",
|
| - "id": "SourceSplitShard",
|
| - "properties": {
|
| - "source": {
|
| - "$ref": "Source",
|
| - "description": "DEPRECATED"
|
| },
|
| - "derivationMode": {
|
| - "description": "DEPRECATED",
|
| - "enum": [
|
| - "SOURCE_DERIVATION_MODE_UNKNOWN",
|
| - "SOURCE_DERIVATION_MODE_INDEPENDENT",
|
| - "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
|
| - "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
|
| - ],
|
| + "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"
|
| + },
|
| + "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"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceGetMetadataResponse": {
|
| - "description": "The result of a SourceGetMetadataOperation.",
|
| - "id": "SourceGetMetadataResponse",
|
| - "properties": {
|
| - "metadata": {
|
| - "$ref": "SourceMetadata",
|
| - "description": "The computed metadata."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "SourceFork": {
|
| - "description": "DEPRECATED in favor of DynamicSourceSplit.",
|
| - "id": "SourceFork",
|
| + "Position": {
|
| + "description": "Position defines a position within a collection of data. The value\ncan be either the end position, a key (used with ordered\ncollections), a byte offset, or a record index.",
|
| + "id": "Position",
|
| "properties": {
|
| - "primary": {
|
| - "$ref": "SourceSplitShard",
|
| - "description": "DEPRECATED"
|
| + "shufflePosition": {
|
| + "description": "CloudPosition is a base64 encoded BatchShufflePosition (with FIXED\nsharding).",
|
| + "type": "string"
|
| },
|
| - "residual": {
|
| - "$ref": "SourceSplitShard",
|
| - "description": "DEPRECATED"
|
| + "concatPosition": {
|
| + "$ref": "ConcatPosition",
|
| + "description": "CloudPosition is a concat position."
|
| },
|
| - "primarySource": {
|
| - "$ref": "DerivedSource",
|
| - "description": "DEPRECATED"
|
| + "byteOffset": {
|
| + "description": "Position is a byte offset.",
|
| + "format": "int64",
|
| + "type": "string"
|
| },
|
| - "residualSource": {
|
| - "$ref": "DerivedSource",
|
| - "description": "DEPRECATED"
|
| + "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"
|
| },
|
| - "ApproximateProgress": {
|
| - "description": "Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest.",
|
| - "id": "ApproximateProgress",
|
| + "SplitInt64": {
|
| + "description": "A representation of an int64, n, that is immune to precision loss when\nencoded in JSON.",
|
| + "id": "SplitInt64",
|
| "properties": {
|
| - "position": {
|
| - "$ref": "Position",
|
| - "description": "Obsolete."
|
| - },
|
| - "percentComplete": {
|
| - "description": "Obsolete.",
|
| - "format": "float",
|
| - "type": "number"
|
| + "lowBits": {
|
| + "description": "The low order bits: n & 0xffffffff.",
|
| + "format": "uint32",
|
| + "type": "integer"
|
| },
|
| - "remainingTime": {
|
| - "description": "Obsolete.",
|
| - "type": "string"
|
| + "highBits": {
|
| + "description": "The high order bits, including the sign: n >> 32.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ReportWorkItemStatusResponse": {
|
| - "description": "Response from a request to report the status of WorkItems.",
|
| - "id": "ReportWorkItemStatusResponse",
|
| + "Source": {
|
| + "description": "A source that records can be read and decoded from.",
|
| + "id": "Source",
|
| "properties": {
|
| - "workItemServiceStates": {
|
| - "description": "A set of messages indicating the service-side state for each WorkItem whose status was reported, in the same order as the WorkItemStatus messages in the ReportWorkItemStatusRequest which resulting in this response.",
|
| + "codec": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "The codec to use to decode data read from the source.",
|
| + "type": "object"
|
| + },
|
| + "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"
|
| + },
|
| + "spec": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "description": "The source to read from, plus its parameters.",
|
| + "type": "object"
|
| + },
|
| + "metadata": {
|
| + "$ref": "SourceMetadata",
|
| + "description": "Optionally, metadata for this source can be supplied right away,\navoiding a SourceGetMetadataOperation roundtrip\n(see SourceOperationRequest).\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated."
|
| + },
|
| + "baseSpecs": {
|
| + "description": "While splitting, sources may specify the produced bundles\nas differences against another source, in order to save backend-side\nmemory and allow bigger jobs. For details, see SourceSplitRequest.\nTo support this use case, the full set of parameters of the source\nis logically obtained by taking the latest explicitly specified value\nof each parameter in the order:\nbase_specs (later items win), spec (overrides anything in base_specs).",
|
| "items": {
|
| - "$ref": "WorkItemServiceState"
|
| + "additionalProperties": {
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| + },
|
| + "type": "object"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkItemServiceState": {
|
| - "description": "The Dataflow service's idea of the current state of a WorkItem being processed by a worker.",
|
| - "id": "WorkItemServiceState",
|
| + "WorkerPool": {
|
| + "description": "Describes one particular pool of Cloud Dataflow workers to be\ninstantiated by the Cloud Dataflow service in order to perform the\ncomputations required by a job. Note that a workflow job may use\nmultiple pools, in order to match the various computational\nrequirements of the various stages of the job.",
|
| + "id": "WorkerPool",
|
| "properties": {
|
| - "splitRequest": {
|
| - "$ref": "ApproximateSplitRequest",
|
| - "description": "The progress point in the WorkItem where the Dataflow service suggests that the worker truncate the task."
|
| - },
|
| - "leaseExpireTime": {
|
| - "description": "Time at which the current lease will expire.",
|
| + "workerHarnessContainerImage": {
|
| + "description": "Required. Docker container image that executes the Cloud Dataflow worker\nharness, residing in Google Container Registry.",
|
| "type": "string"
|
| },
|
| - "reportStatusInterval": {
|
| - "description": "New recommended reporting interval.",
|
| + "diskType": {
|
| + "description": "Type of root disk for VMs. If empty or unspecified, the service will\nattempt to choose a reasonable default.",
|
| "type": "string"
|
| },
|
| - "harnessData": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "Other data returned by the service, specific to the particular worker harness.",
|
| - "type": "object"
|
| + "machineType": {
|
| + "description": "Machine type (e.g. \"n1-standard-1\"). If empty or unspecified, the\nservice will attempt to choose a reasonable default.",
|
| + "type": "string"
|
| },
|
| - "nextReportIndex": {
|
| - "description": "The index value to use for the next report sent by the worker. Note: If the report call fails for whatever reason, the worker should reuse this index for subsequent report attempts.",
|
| - "format": "int64",
|
| + "kind": {
|
| + "description": "The kind of the worker pool; currently only `harness` and `shuffle`\nare supported.",
|
| "type": "string"
|
| },
|
| - "metricShortId": {
|
| - "description": "The short ids that workers should use in subsequent metric updates. Workers should strive to use short ids whenever possible, but it is ok to request the short_id again if a worker lost track of it (e.g. if the worker is recovering from a crash). NOTE: it is possible that the response may have short ids for a subset of the metrics.",
|
| + "dataDisks": {
|
| + "description": "Data disks that are used by a VM in this workflow.",
|
| "items": {
|
| - "$ref": "MetricShortId"
|
| + "$ref": "Disk"
|
| },
|
| "type": "array"
|
| },
|
| - "suggestedStopPosition": {
|
| - "$ref": "Position",
|
| - "description": "Obsolete, always empty."
|
| + "subnetwork": {
|
| + "description": "Subnetwork to which VMs will be assigned, if desired. Expected to be of\nthe form \"regions/REGION/subnetworks/SUBNETWORK\".",
|
| + "type": "string"
|
| },
|
| - "suggestedStopPoint": {
|
| - "$ref": "ApproximateProgress",
|
| - "description": "DEPRECATED in favor of split_request."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "ApproximateSplitRequest": {
|
| - "description": "A suggestion by the service to the worker to dynamically split the WorkItem.",
|
| - "id": "ApproximateSplitRequest",
|
| - "properties": {
|
| - "position": {
|
| - "$ref": "Position",
|
| - "description": "A Position at which to split the work item."
|
| + "ipConfiguration": {
|
| + "description": "Configuration for VM IPs.",
|
| + "enum": [
|
| + "WORKER_IP_UNSPECIFIED",
|
| + "WORKER_IP_PUBLIC",
|
| + "WORKER_IP_PRIVATE"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The configuration is unknown, or unspecified.",
|
| + "Workers should have public IP addresses.",
|
| + "Workers should have private IP addresses."
|
| + ],
|
| + "type": "string"
|
| },
|
| - "fractionConsumed": {
|
| - "description": "A fraction at which to split the work item, from 0.0 (beginning of the input) to 1.0 (end of the input).",
|
| - "format": "double",
|
| - "type": "number"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "MetricShortId": {
|
| - "description": "The metric short id is returned to the user alongside an offset into ReportWorkItemStatusRequest",
|
| - "id": "MetricShortId",
|
| - "properties": {
|
| - "metricIndex": {
|
| - "description": "The index of the corresponding metric in the ReportWorkItemStatusRequest. Required.",
|
| + "autoscalingSettings": {
|
| + "$ref": "AutoscalingSettings",
|
| + "description": "Settings for autoscaling of this WorkerPool."
|
| + },
|
| + "taskrunnerSettings": {
|
| + "$ref": "TaskRunnerSettings",
|
| + "description": "Settings passed through to Google Compute Engine workers when\nusing the standard Dataflow task runner. Users should ignore\nthis field."
|
| + },
|
| + "metadata": {
|
| + "additionalProperties": {
|
| + "type": "string"
|
| + },
|
| + "description": "Metadata to set on the Google Compute Engine VMs.",
|
| + "type": "object"
|
| + },
|
| + "network": {
|
| + "description": "Network to which VMs will be assigned. If empty or unspecified,\nthe service will use the network \"default\".",
|
| + "type": "string"
|
| + },
|
| + "defaultPackageSet": {
|
| + "description": "The default package set to install. This allows the service to\nselect a default set of packages which are useful to worker\nharnesses written in a particular language.",
|
| + "enum": [
|
| + "DEFAULT_PACKAGE_SET_UNKNOWN",
|
| + "DEFAULT_PACKAGE_SET_NONE",
|
| + "DEFAULT_PACKAGE_SET_JAVA",
|
| + "DEFAULT_PACKAGE_SET_PYTHON"
|
| + ],
|
| + "enumDescriptions": [
|
| + "The default set of packages to stage is unknown, or unspecified.",
|
| + "Indicates that no packages should be staged at the worker unless\nexplicitly specified by the job.",
|
| + "Stage packages typically useful to workers written in Java.",
|
| + "Stage pacakges typically useful to workers written in Python."
|
| + ],
|
| + "type": "string"
|
| + },
|
| + "numThreadsPerWorker": {
|
| + "description": "The number of threads per worker harness. If empty or unspecified, the\nservice will choose a number of threads (according to the number of cores\non the selected machine type for batch, or 1 by convention for streaming).",
|
| "format": "int32",
|
| "type": "integer"
|
| },
|
| - "shortId": {
|
| - "description": "The service-generated short identifier for the metric.",
|
| - "format": "int64",
|
| + "numWorkers": {
|
| + "description": "Number of Google Compute Engine workers in this pool needed to\nexecute the job. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| + },
|
| + "zone": {
|
| + "description": "Zone to run the worker pools in. If empty or unspecified, the service\nwill attempt to choose a reasonable default.",
|
| "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "LeaseWorkItemRequest": {
|
| - "description": "Request to lease WorkItems.",
|
| - "id": "LeaseWorkItemRequest",
|
| - "properties": {
|
| - "workItemTypes": {
|
| - "description": "Filter for WorkItem type.",
|
| - "items": {
|
| - "type": "string"
|
| - },
|
| - "type": "array"
|
| },
|
| - "workerCapabilities": {
|
| - "description": "Worker capabilities. WorkItems might be limited to workers with specific capabilities.",
|
| + "diskSourceImage": {
|
| + "description": "Fully qualified source image for disks.",
|
| + "type": "string"
|
| + },
|
| + "packages": {
|
| + "description": "Packages to be installed on workers.",
|
| "items": {
|
| - "type": "string"
|
| + "$ref": "Package"
|
| },
|
| "type": "array"
|
| },
|
| - "requestedLeaseDuration": {
|
| - "description": "The initial lease period.",
|
| + "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"
|
| },
|
| - "currentWorkerTime": {
|
| - "description": "The current timestamp at the worker.",
|
| + "onHostMaintenance": {
|
| + "description": "The action to take on host maintenance, as defined by the Google\nCompute Engine API.",
|
| "type": "string"
|
| },
|
| - "workerId": {
|
| - "description": "Identifies the worker leasing work -- typically the ID of the virtual machine running the worker.",
|
| - "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"
|
| },
|
| - "location": {
|
| - "description": "The location which contains the WorkItem's job.",
|
| - "type": "string"
|
| + "diskSizeGb": {
|
| + "description": "Size of root disk for VMs, in GB. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "LeaseWorkItemResponse": {
|
| - "description": "Response to a request to lease WorkItems.",
|
| - "id": "LeaseWorkItemResponse",
|
| + "SourceOperationRequest": {
|
| + "description": "A work item that represents the different operations that can be\nperformed on a user-defined Source specification.",
|
| + "id": "SourceOperationRequest",
|
| "properties": {
|
| - "workItems": {
|
| - "description": "A list of the leased WorkItems.",
|
| - "items": {
|
| - "$ref": "WorkItem"
|
| - },
|
| - "type": "array"
|
| + "split": {
|
| + "$ref": "SourceSplitRequest",
|
| + "description": "Information about a request to split a source."
|
| + },
|
| + "getMetadata": {
|
| + "$ref": "SourceGetMetadataRequest",
|
| + "description": "Information about a request to get metadata about a source."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| "WorkItem": {
|
| - "description": "WorkItem represents basic information about a WorkItem to be executed in the cloud.",
|
| + "description": "WorkItem represents basic information about a WorkItem to be executed\nin the cloud.",
|
| "id": "WorkItem",
|
| "properties": {
|
| - "id": {
|
| - "description": "Identifies this WorkItem.",
|
| + "initialReportIndex": {
|
| + "description": "The initial index to use when reporting the status of the WorkItem.",
|
| "format": "int64",
|
| "type": "string"
|
| },
|
| - "projectId": {
|
| - "description": "Identifies the cloud project this WorkItem belongs to.",
|
| - "type": "string"
|
| + "streamingComputationTask": {
|
| + "$ref": "StreamingComputationTask",
|
| + "description": "Additional information for StreamingComputationTask WorkItems."
|
| + },
|
| + "shellTask": {
|
| + "$ref": "ShellTask",
|
| + "description": "Additional information for ShellTask WorkItems."
|
| },
|
| "jobId": {
|
| "description": "Identifies the workflow job this WorkItem belongs to.",
|
| "type": "string"
|
| },
|
| - "packages": {
|
| - "description": "Any required packages that need to be fetched in order to execute this WorkItem.",
|
| - "items": {
|
| - "$ref": "Package"
|
| - },
|
| - "type": "array"
|
| + "id": {
|
| + "description": "Identifies this WorkItem.",
|
| + "format": "int64",
|
| + "type": "string"
|
| + },
|
| + "configuration": {
|
| + "description": "Work item-specific configuration as an opaque blob.",
|
| + "type": "string"
|
| },
|
| "mapTask": {
|
| "$ref": "MapTask",
|
| @@ -2780,293 +2731,337 @@
|
| "$ref": "SeqMapTask",
|
| "description": "Additional information for SeqMapTask WorkItems."
|
| },
|
| - "shellTask": {
|
| - "$ref": "ShellTask",
|
| - "description": "Additional information for ShellTask WorkItems."
|
| + "packages": {
|
| + "description": "Any required packages that need to be fetched in order to execute\nthis WorkItem.",
|
| + "items": {
|
| + "$ref": "Package"
|
| + },
|
| + "type": "array"
|
| },
|
| - "streamingSetupTask": {
|
| - "$ref": "StreamingSetupTask",
|
| - "description": "Additional information for StreamingSetupTask WorkItems."
|
| + "projectId": {
|
| + "description": "Identifies the cloud project this WorkItem belongs to.",
|
| + "type": "string"
|
| + },
|
| + "reportStatusInterval": {
|
| + "description": "Recommended reporting interval.",
|
| + "format": "google-duration",
|
| + "type": "string"
|
| },
|
| "sourceOperationTask": {
|
| "$ref": "SourceOperationRequest",
|
| "description": "Additional information for source operation WorkItems."
|
| },
|
| - "streamingComputationTask": {
|
| - "$ref": "StreamingComputationTask",
|
| - "description": "Additional information for StreamingComputationTask WorkItems."
|
| + "streamingSetupTask": {
|
| + "$ref": "StreamingSetupTask",
|
| + "description": "Additional information for StreamingSetupTask WorkItems."
|
| },
|
| "streamingConfigTask": {
|
| "$ref": "StreamingConfigTask",
|
| "description": "Additional information for StreamingConfigTask WorkItems."
|
| },
|
| - "reportStatusInterval": {
|
| - "description": "Recommended reporting interval.",
|
| - "type": "string"
|
| - },
|
| "leaseExpireTime": {
|
| "description": "Time when the lease on this Work will expire.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "ResourceUtilizationReport": {
|
| + "description": "Worker metrics exported from workers. This contains resource utilization\nmetrics accumulated from a variety of sources. For more information, see\ngo/df-resource-signals.",
|
| + "id": "ResourceUtilizationReport",
|
| + "properties": {
|
| + "cpuTime": {
|
| + "description": "CPU utilization samples.",
|
| + "items": {
|
| + "$ref": "CPUTime"
|
| + },
|
| + "type": "array"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "ReportedParallelism": {
|
| + "description": "Represents the level of parallelism in a WorkItem's input,\nreported by the worker.",
|
| + "id": "ReportedParallelism",
|
| + "properties": {
|
| + "isInfinite": {
|
| + "description": "Specifies whether the parallelism is infinite. If true, \"value\" is\nignored.\nInfinite parallelism means the service will assume that the work item\ncan always be split into more non-empty work items by dynamic splitting.\nThis is a work-around for lack of support for infinity by the current\nJSON-based Java RPC stack.",
|
| + "type": "boolean"
|
| },
|
| - "configuration": {
|
| - "description": "Work item-specific configuration as an opaque blob.",
|
| - "type": "string"
|
| - },
|
| - "initialReportIndex": {
|
| - "description": "The initial index to use when reporting the status of the WorkItem.",
|
| - "format": "int64",
|
| - "type": "string"
|
| + "value": {
|
| + "description": "Specifies the level of parallelism in case it is finite.",
|
| + "format": "double",
|
| + "type": "number"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "MapTask": {
|
| - "description": "MapTask consists of an ordered set of instructions, each of which describes one particular low-level operation for the worker to perform in order to accomplish the MapTask's WorkItem. Each instruction must appear in the list before any instructions which depends on its output.",
|
| - "id": "MapTask",
|
| + "TopologyConfig": {
|
| + "description": "Global topology of the streaming Dataflow job, including all\ncomputations and their sharded locations.",
|
| + "id": "TopologyConfig",
|
| "properties": {
|
| - "instructions": {
|
| - "description": "The instructions in the MapTask.",
|
| + "forwardingKeyBits": {
|
| + "description": "The size (in bits) of keys that will be assigned to source messages.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| + },
|
| + "userStageToComputationNameMap": {
|
| + "additionalProperties": {
|
| + "type": "string"
|
| + },
|
| + "description": "Maps user stage names to stable computation names.",
|
| + "type": "object"
|
| + },
|
| + "computations": {
|
| + "description": "The computations associated with a streaming Dataflow job.",
|
| "items": {
|
| - "$ref": "ParallelInstruction"
|
| + "$ref": "ComputationTopology"
|
| },
|
| "type": "array"
|
| },
|
| - "systemName": {
|
| - "description": "System-defined name of this MapTask. Unique across the workflow.",
|
| + "dataDiskAssignments": {
|
| + "description": "The disks assigned to a streaming Dataflow job.",
|
| + "items": {
|
| + "$ref": "DataDiskAssignment"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "persistentStateVersion": {
|
| + "description": "Version number for persistent state.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "SourceSplitOptions": {
|
| + "description": "Hints for splitting a Source into bundles (parts for parallel\nprocessing) using SourceSplitRequest.",
|
| + "id": "SourceSplitOptions",
|
| + "properties": {
|
| + "desiredBundleSizeBytes": {
|
| + "description": "The source should be split into a set of bundles where the estimated size\nof each is approximately this many bytes.",
|
| + "format": "int64",
|
| "type": "string"
|
| },
|
| - "stageName": {
|
| - "description": "System-defined name of the stage containing this MapTask. Unique across the workflow.",
|
| + "desiredShardSizeBytes": {
|
| + "description": "DEPRECATED in favor of desired_bundle_size_bytes.",
|
| + "format": "int64",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ParallelInstruction": {
|
| - "description": "Describes a particular operation comprising a MapTask.",
|
| - "id": "ParallelInstruction",
|
| + "ReadInstruction": {
|
| + "description": "An instruction that reads records.\nTakes no inputs, produces one output.",
|
| + "id": "ReadInstruction",
|
| "properties": {
|
| - "systemName": {
|
| - "description": "System-defined name of this operation. Unique across the workflow.",
|
| + "source": {
|
| + "$ref": "Source",
|
| + "description": "The source to read from."
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "WorkerSettings": {
|
| + "description": "Provides data to pass through to the worker harness.",
|
| + "id": "WorkerSettings",
|
| + "properties": {
|
| + "servicePath": {
|
| + "description": "The Cloud Dataflow service path relative to the root URL, for example,\n\"dataflow/v1b3/projects\".",
|
| "type": "string"
|
| },
|
| - "name": {
|
| - "description": "User-provided name of this operation.",
|
| + "shuffleServicePath": {
|
| + "description": "The Shuffle service path relative to the root URL, for example,\n\"shuffle/v1beta1\".",
|
| "type": "string"
|
| },
|
| - "originalName": {
|
| - "description": "System-defined name for the operation in the original workflow graph.",
|
| + "workerId": {
|
| + "description": "The ID of the worker running this pipeline.",
|
| "type": "string"
|
| },
|
| - "read": {
|
| - "$ref": "ReadInstruction",
|
| - "description": "Additional information for Read instructions."
|
| - },
|
| - "write": {
|
| - "$ref": "WriteInstruction",
|
| - "description": "Additional information for Write instructions."
|
| - },
|
| - "parDo": {
|
| - "$ref": "ParDoInstruction",
|
| - "description": "Additional information for ParDo instructions."
|
| + "tempStoragePrefix": {
|
| + "description": "The prefix of the resources the system should use for temporary\nstorage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
|
| + "type": "string"
|
| },
|
| - "partialGroupByKey": {
|
| - "$ref": "PartialGroupByKeyInstruction",
|
| - "description": "Additional information for PartialGroupByKey instructions."
|
| + "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"
|
| },
|
| - "flatten": {
|
| - "$ref": "FlattenInstruction",
|
| - "description": "Additional information for Flatten instructions."
|
| + "reportingEnabled": {
|
| + "description": "Whether to send work progress updates to the service.",
|
| + "type": "boolean"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "DataDiskAssignment": {
|
| + "description": "Data disk assignment for a given VM instance.",
|
| + "id": "DataDiskAssignment",
|
| + "properties": {
|
| + "vmInstance": {
|
| + "description": "VM instance name the data disks mounted to, for example\n\"myproject-1014-104817-4c2-harness-0\".",
|
| + "type": "string"
|
| },
|
| - "outputs": {
|
| - "description": "Describes the outputs of the instruction.",
|
| + "dataDisks": {
|
| + "description": "Mounted data disks. The order is important a data disk's 0-based index in\nthis list defines which persistent directory the disk is mounted to, for\nexample the list of { \"myproject-1014-104817-4c2-harness-0-disk-0\" },\n{ \"myproject-1014-104817-4c2-harness-0-disk-1\" }.",
|
| "items": {
|
| - "$ref": "InstructionOutput"
|
| + "type": "string"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ReadInstruction": {
|
| - "description": "An instruction that reads records. Takes no inputs, produces one output.",
|
| - "id": "ReadInstruction",
|
| + "StreamingStageLocation": {
|
| + "description": "Identifies the location of a streaming computation stage, for\nstage-to-stage communication.",
|
| + "id": "StreamingStageLocation",
|
| "properties": {
|
| - "source": {
|
| - "$ref": "Source",
|
| - "description": "The source to read from."
|
| + "streamId": {
|
| + "description": "Identifies the particular stream within the streaming Dataflow\njob.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WriteInstruction": {
|
| - "description": "An instruction that writes records. Takes one input, produces no outputs.",
|
| - "id": "WriteInstruction",
|
| + "ApproximateSplitRequest": {
|
| + "description": "A suggestion by the service to the worker to dynamically split the WorkItem.",
|
| + "id": "ApproximateSplitRequest",
|
| "properties": {
|
| - "input": {
|
| - "$ref": "InstructionInput",
|
| - "description": "The input."
|
| + "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"
|
| },
|
| - "sink": {
|
| - "$ref": "Sink",
|
| - "description": "The sink to write to."
|
| + "position": {
|
| + "$ref": "Position",
|
| + "description": "A Position at which to split the work item."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "InstructionInput": {
|
| - "description": "An input of an instruction, as a reference to an output of a producer instruction.",
|
| - "id": "InstructionInput",
|
| + "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` which 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 purpose.\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": {
|
| - "producerInstructionIndex": {
|
| - "description": "The index (origin zero) of the parallel instruction that produces the output to be consumed by this input. This index is relative to the list of instructions in this input's instruction's containing MapTask.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| + "details": {
|
| + "description": "A list of messages that carry the error details. There will be a\ncommon set of message types for APIs to use.",
|
| + "items": {
|
| + "additionalProperties": {
|
| + "description": "Properties of the object. Contains field @type with type URL.",
|
| + "type": "any"
|
| + },
|
| + "type": "object"
|
| + },
|
| + "type": "array"
|
| },
|
| - "outputNum": {
|
| - "description": "The output index (origin zero) within the producer.",
|
| + "code": {
|
| + "description": "The status code, which should be an enum value of google.rpc.Code.",
|
| "format": "int32",
|
| "type": "integer"
|
| + },
|
| + "message": {
|
| + "description": "A developer-facing error message, which should be in English. Any\nuser-facing error message should be localized and sent in the\ngoogle.rpc.Status.details field, or localized by the client.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "Sink": {
|
| - "description": "A sink that records can be encoded and written to.",
|
| - "id": "Sink",
|
| + "StreamLocation": {
|
| + "description": "Describes a stream of data, either as input to be processed or as\noutput of a streaming Dataflow job.",
|
| + "id": "StreamLocation",
|
| "properties": {
|
| - "spec": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The sink to write to, plus its parameters.",
|
| - "type": "object"
|
| + "customSourceLocation": {
|
| + "$ref": "CustomSourceLocation",
|
| + "description": "The stream is a custom source."
|
| },
|
| - "codec": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The codec to use to encode data written to the sink.",
|
| - "type": "object"
|
| + "streamingStageLocation": {
|
| + "$ref": "StreamingStageLocation",
|
| + "description": "The stream is part of another computation within the current\nstreaming Dataflow job."
|
| + },
|
| + "pubsubLocation": {
|
| + "$ref": "PubsubLocation",
|
| + "description": "The stream is a pubsub stream."
|
| + },
|
| + "sideInputLocation": {
|
| + "$ref": "StreamingSideInputLocation",
|
| + "description": "The stream is a streaming side input."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ParDoInstruction": {
|
| - "description": "An instruction that does a ParDo operation. Takes one main input and zero or more side inputs, and produces zero or more outputs. Runs user code.",
|
| - "id": "ParDoInstruction",
|
| + "SendWorkerMessagesResponse": {
|
| + "description": "The response to the worker messages.",
|
| + "id": "SendWorkerMessagesResponse",
|
| "properties": {
|
| - "input": {
|
| - "$ref": "InstructionInput",
|
| - "description": "The input."
|
| - },
|
| - "sideInputs": {
|
| - "description": "Zero or more side inputs.",
|
| - "items": {
|
| - "$ref": "SideInputInfo"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "userFn": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "The user function to invoke.",
|
| - "type": "object"
|
| - },
|
| - "numOutputs": {
|
| - "description": "The number of outputs.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - },
|
| - "multiOutputInfos": {
|
| - "description": "Information about each of the outputs, if user_fn is a MultiDoFn.",
|
| + "workerMessageResponses": {
|
| + "description": "The servers response to the worker messages.",
|
| "items": {
|
| - "$ref": "MultiOutputInfo"
|
| + "$ref": "WorkerMessageResponse"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SideInputInfo": {
|
| - "description": "Information about a side input of a DoFn or an input of a SeqDoFn.",
|
| - "id": "SideInputInfo",
|
| + "LeaseWorkItemResponse": {
|
| + "description": "Response to a request to lease WorkItems.",
|
| + "id": "LeaseWorkItemResponse",
|
| "properties": {
|
| - "sources": {
|
| - "description": "The source(s) to read element(s) from to get the value of this side input. If more than one source, then the elements are taken from the sources, in the specified order if order matters. At least one source is required.",
|
| - "items": {
|
| - "$ref": "Source"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "kind": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| + "workItems": {
|
| + "description": "A list of the leased WorkItems.",
|
| + "items": {
|
| + "$ref": "WorkItem"
|
| },
|
| - "description": "How to interpret the source element(s) as a side input value.",
|
| - "type": "object"
|
| - },
|
| - "tag": {
|
| - "description": "The id of the tag the user code will access this side input by; this should correspond to the tag of some MultiOutputInfo.",
|
| - "type": "string"
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "MultiOutputInfo": {
|
| - "description": "Information about an output of a multi-output DoFn.",
|
| - "id": "MultiOutputInfo",
|
| + "StreamingComputationConfig": {
|
| + "description": "Configuration information for a single streaming computation.",
|
| + "id": "StreamingComputationConfig",
|
| "properties": {
|
| - "tag": {
|
| - "description": "The id of the tag the user code will emit to this output by; this should correspond to the tag of some SideInputInfo.",
|
| + "computationId": {
|
| + "description": "Unique identifier for this computation.",
|
| + "type": "string"
|
| + },
|
| + "systemName": {
|
| + "description": "System defined name for this computation.",
|
| + "type": "string"
|
| + },
|
| + "stageName": {
|
| + "description": "Stage name of this computation.",
|
| "type": "string"
|
| + },
|
| + "instructions": {
|
| + "description": "Instructions that comprise the computation.",
|
| + "items": {
|
| + "$ref": "ParallelInstruction"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "PartialGroupByKeyInstruction": {
|
| - "description": "An instruction that does a partial group-by-key. One input and one output.",
|
| - "id": "PartialGroupByKeyInstruction",
|
| + "Sink": {
|
| + "description": "A sink that records can be encoded and written to.",
|
| + "id": "Sink",
|
| "properties": {
|
| - "input": {
|
| - "$ref": "InstructionInput",
|
| - "description": "Describes the input to the partial group-by-key instruction."
|
| - },
|
| - "inputElementCodec": {
|
| + "codec": {
|
| "additionalProperties": {
|
| "description": "Properties of the object.",
|
| "type": "any"
|
| },
|
| - "description": "The codec to use for interpreting an element in the input PTable.",
|
| + "description": "The codec to use to encode data written to the sink.",
|
| "type": "object"
|
| },
|
| - "valueCombiningFn": {
|
| + "spec": {
|
| "additionalProperties": {
|
| "description": "Properties of the object.",
|
| "type": "any"
|
| },
|
| - "description": "The value combining function to invoke.",
|
| + "description": "The sink to write to, plus its parameters.",
|
| "type": "object"
|
| - },
|
| - "sideInputs": {
|
| - "description": "Zero or more side inputs.",
|
| - "items": {
|
| - "$ref": "SideInputInfo"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "originalCombineValuesStepName": {
|
| - "description": "If this instruction includes a combining function, this is the name of the CombineValues instruction lifted into this instruction.",
|
| - "type": "string"
|
| - },
|
| - "originalCombineValuesInputStoreName": {
|
| - "description": "If this instruction includes a combining function this is the name of the intermediate store between the GBK and the CombineValues.",
|
| - "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| @@ -3085,489 +3080,466 @@
|
| },
|
| "type": "object"
|
| },
|
| - "InstructionOutput": {
|
| - "description": "An output of an instruction.",
|
| - "id": "InstructionOutput",
|
| + "PartialGroupByKeyInstruction": {
|
| + "description": "An instruction that does a partial group-by-key.\nOne input and one output.",
|
| + "id": "PartialGroupByKeyInstruction",
|
| "properties": {
|
| - "name": {
|
| - "description": "The user-provided name of this output.",
|
| - "type": "string"
|
| - },
|
| - "systemName": {
|
| - "description": "System-defined name of this output. Unique across the workflow.",
|
| - "type": "string"
|
| - },
|
| - "originalName": {
|
| - "description": "System-defined name for this output in the original workflow graph. Outputs that do not contribute to an original instruction do not set this.",
|
| - "type": "string"
|
| - },
|
| - "codec": {
|
| + "valueCombiningFn": {
|
| "additionalProperties": {
|
| "description": "Properties of the object.",
|
| "type": "any"
|
| },
|
| - "description": "The codec to use to encode data being written via this output.",
|
| + "description": "The value combining function to invoke.",
|
| "type": "object"
|
| },
|
| - "onlyCountKeyBytes": {
|
| - "description": "For system-generated byte and mean byte metrics, certain instructions should only report the key size.",
|
| - "type": "boolean"
|
| - },
|
| - "onlyCountValueBytes": {
|
| - "description": "For system-generated byte and mean byte metrics, certain instructions should only report the value size.",
|
| - "type": "boolean"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "SeqMapTask": {
|
| - "description": "Describes a particular function to invoke.",
|
| - "id": "SeqMapTask",
|
| - "properties": {
|
| - "inputs": {
|
| - "description": "Information about each of the inputs.",
|
| - "items": {
|
| - "$ref": "SideInputInfo"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "userFn": {
|
| + "inputElementCodec": {
|
| "additionalProperties": {
|
| "description": "Properties of the object.",
|
| "type": "any"
|
| },
|
| - "description": "The user function to invoke.",
|
| + "description": "The codec to use for interpreting an element in the input PTable.",
|
| "type": "object"
|
| },
|
| - "outputInfos": {
|
| - "description": "Information about each of the outputs.",
|
| - "items": {
|
| - "$ref": "SeqMapTaskOutputInfo"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "name": {
|
| - "description": "The user-provided name of the SeqDo operation.",
|
| - "type": "string"
|
| - },
|
| - "systemName": {
|
| - "description": "System-defined name of the SeqDo operation. Unique across the workflow.",
|
| - "type": "string"
|
| - },
|
| - "stageName": {
|
| - "description": "System-defined name of the stage containing the SeqDo operation. Unique across the workflow.",
|
| - "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "SeqMapTaskOutputInfo": {
|
| - "description": "Information about an output of a SeqMapTask.",
|
| - "id": "SeqMapTaskOutputInfo",
|
| - "properties": {
|
| - "tag": {
|
| - "description": "The id of the TupleTag the user code will tag the output value by.",
|
| + "originalCombineValuesInputStoreName": {
|
| + "description": "If this instruction includes a combining function this is the name of the\nintermediate store between the GBK and the CombineValues.",
|
| "type": "string"
|
| },
|
| - "sink": {
|
| - "$ref": "Sink",
|
| - "description": "The sink to write the output value to."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "ShellTask": {
|
| - "description": "A task which consists of a shell command for the worker to execute.",
|
| - "id": "ShellTask",
|
| - "properties": {
|
| - "command": {
|
| - "description": "The shell command to run.",
|
| + "originalCombineValuesStepName": {
|
| + "description": "If this instruction includes a combining function, this is the name of the\nCombineValues instruction lifted into this instruction.",
|
| "type": "string"
|
| },
|
| - "exitCode": {
|
| - "description": "Exit code for the task.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "StreamingSetupTask": {
|
| - "description": "A task which initializes part of a streaming Dataflow job.",
|
| - "id": "StreamingSetupTask",
|
| - "properties": {
|
| - "receiveWorkPort": {
|
| - "description": "The TCP port on which the worker should listen for messages from other streaming computation workers.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - },
|
| - "workerHarnessPort": {
|
| - "description": "The TCP port used by the worker to communicate with the Dataflow worker harness.",
|
| - "format": "int32",
|
| - "type": "integer"
|
| - },
|
| - "streamingComputationTopology": {
|
| - "$ref": "TopologyConfig",
|
| - "description": "The global topology of the streaming Dataflow job."
|
| + "sideInputs": {
|
| + "description": "Zero or more side inputs.",
|
| + "items": {
|
| + "$ref": "SideInputInfo"
|
| + },
|
| + "type": "array"
|
| },
|
| - "drain": {
|
| - "description": "The user has requested drain.",
|
| - "type": "boolean"
|
| + "input": {
|
| + "$ref": "InstructionInput",
|
| + "description": "Describes the input to the partial group-by-key instruction."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "TopologyConfig": {
|
| - "description": "Global topology of the streaming Dataflow job, including all computations and their sharded locations.",
|
| - "id": "TopologyConfig",
|
| + "InstructionInput": {
|
| + "description": "An input of an instruction, as a reference to an output of a\nproducer instruction.",
|
| + "id": "InstructionInput",
|
| "properties": {
|
| - "computations": {
|
| - "description": "The computations associated with a streaming Dataflow job.",
|
| - "items": {
|
| - "$ref": "ComputationTopology"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "dataDiskAssignments": {
|
| - "description": "The disks assigned to a streaming Dataflow job.",
|
| - "items": {
|
| - "$ref": "DataDiskAssignment"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "userStageToComputationNameMap": {
|
| - "additionalProperties": {
|
| - "type": "string"
|
| - },
|
| - "description": "Maps user stage names to stable computation names.",
|
| - "type": "object"
|
| - },
|
| - "forwardingKeyBits": {
|
| - "description": "The size (in bits) of keys that will be assigned to source messages.",
|
| + "producerInstructionIndex": {
|
| + "description": "The index (origin zero) of the parallel instruction that produces\nthe output to be consumed by this input. This index is relative\nto the list of instructions in this input's instruction's\ncontaining MapTask.",
|
| "format": "int32",
|
| "type": "integer"
|
| },
|
| - "persistentStateVersion": {
|
| - "description": "Version number for persistent state.",
|
| + "outputNum": {
|
| + "description": "The output index (origin zero) within the producer.",
|
| "format": "int32",
|
| "type": "integer"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "ComputationTopology": {
|
| - "description": "All configuration data for a particular Computation.",
|
| - "id": "ComputationTopology",
|
| - "properties": {
|
| - "systemStageName": {
|
| - "description": "The system stage name.",
|
| - "type": "string"
|
| - },
|
| - "computationId": {
|
| - "description": "The ID of the computation.",
|
| - "type": "string"
|
| - },
|
| - "userStageName": {
|
| - "description": "The user stage name.",
|
| - "type": "string"
|
| - },
|
| - "keyRanges": {
|
| - "description": "The key ranges processed by the computation.",
|
| - "items": {
|
| - "$ref": "KeyRangeLocation"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "inputs": {
|
| - "description": "The inputs to the computation.",
|
| - "items": {
|
| - "$ref": "StreamLocation"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "outputs": {
|
| - "description": "The outputs from the computation.",
|
| - "items": {
|
| - "$ref": "StreamLocation"
|
| - },
|
| - "type": "array"
|
| - },
|
| - "stateFamilies": {
|
| - "description": "The state family values.",
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "StringList": {
|
| + "description": "A metric value representing a list of strings.",
|
| + "id": "StringList",
|
| + "properties": {
|
| + "elements": {
|
| + "description": "Elements of the list.",
|
| "items": {
|
| - "$ref": "StateFamilyConfig"
|
| + "type": "string"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "KeyRangeLocation": {
|
| - "description": "Location information for a specific key-range of a sharded computation. Currently we only support UTF-8 character splits to simplify encoding into JSON.",
|
| - "id": "KeyRangeLocation",
|
| + "LeaseWorkItemRequest": {
|
| + "description": "Request to lease WorkItems.",
|
| + "id": "LeaseWorkItemRequest",
|
| "properties": {
|
| - "start": {
|
| - "description": "The start (inclusive) of the key range.",
|
| - "type": "string"
|
| + "workerCapabilities": {
|
| + "description": "Worker capabilities. WorkItems might be limited to workers with specific\ncapabilities.",
|
| + "items": {
|
| + "type": "string"
|
| + },
|
| + "type": "array"
|
| },
|
| - "end": {
|
| - "description": "The end (exclusive) of the key range.",
|
| + "workerId": {
|
| + "description": "Identifies the worker leasing work -- typically the ID of the\nvirtual machine running the worker.",
|
| "type": "string"
|
| },
|
| - "deliveryEndpoint": {
|
| - "description": "The physical location of this range assignment to be used for streaming computation cross-worker message delivery.",
|
| + "requestedLeaseDuration": {
|
| + "description": "The initial lease period.",
|
| + "format": "google-duration",
|
| "type": "string"
|
| },
|
| - "persistentDirectory": {
|
| - "description": "The location of the persistent state for this range, as a persistent directory in the worker local filesystem.",
|
| + "currentWorkerTime": {
|
| + "description": "The current timestamp at the worker.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| - "dataDisk": {
|
| - "description": "The name of the data disk where data for this range is stored. This name is local to the Google Cloud Platform project and uniquely identifies the disk within that project, for example \"myproject-1014-104817-4c2-harness-0-disk-1\".",
|
| + "workItemTypes": {
|
| + "description": "Filter for WorkItem type.",
|
| + "items": {
|
| + "type": "string"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "location": {
|
| + "description": "The location which contains the WorkItem's job.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamLocation": {
|
| - "description": "Describes a stream of data, either as input to be processed or as output of a streaming Dataflow job.",
|
| - "id": "StreamLocation",
|
| + "GetDebugConfigRequest": {
|
| + "description": "Request to get updated debug configuration for component.",
|
| + "id": "GetDebugConfigRequest",
|
| "properties": {
|
| - "streamingStageLocation": {
|
| - "$ref": "StreamingStageLocation",
|
| - "description": "The stream is part of another computation within the current streaming Dataflow job."
|
| - },
|
| - "pubsubLocation": {
|
| - "$ref": "PubsubLocation",
|
| - "description": "The stream is a pubsub stream."
|
| - },
|
| - "sideInputLocation": {
|
| - "$ref": "StreamingSideInputLocation",
|
| - "description": "The stream is a streaming side input."
|
| + "componentId": {
|
| + "description": "The internal component id for which debug configuration is\nrequested.",
|
| + "type": "string"
|
| },
|
| - "customSourceLocation": {
|
| - "$ref": "CustomSourceLocation",
|
| - "description": "The stream is a custom source."
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "StreamingStageLocation": {
|
| - "description": "Identifies the location of a streaming computation stage, for stage-to-stage communication.",
|
| - "id": "StreamingStageLocation",
|
| - "properties": {
|
| - "streamId": {
|
| - "description": "Identifies the particular stream within the streaming Dataflow job.",
|
| + "workerId": {
|
| + "description": "The worker id, i.e., VM hostname.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "PubsubLocation": {
|
| - "description": "Identifies a pubsub location to use for transferring data into or out of a streaming Dataflow job.",
|
| - "id": "PubsubLocation",
|
| + "ReportWorkItemStatusRequest": {
|
| + "description": "Request to report the status of WorkItems.",
|
| + "id": "ReportWorkItemStatusRequest",
|
| "properties": {
|
| - "topic": {
|
| - "description": "A pubsub topic, in the form of \"pubsub.googleapis.com/topics/\n/\"",
|
| - "type": "string"
|
| - },
|
| - "subscription": {
|
| - "description": "A pubsub subscription, in the form of \"pubsub.googleapis.com/subscriptions/\n/\"",
|
| + "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"
|
| },
|
| - "timestampLabel": {
|
| - "description": "If set, contains a pubsub label from which to extract record timestamps. If left empty, record timestamps will be generated upon arrival.",
|
| + "currentWorkerTime": {
|
| + "description": "The current timestamp at the worker.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| - "idLabel": {
|
| - "description": "If set, contains a pubsub label from which to extract record ids. If left empty, record deduplication will be strictly best effort.",
|
| + "location": {
|
| + "description": "The location which contains the WorkItem's job.",
|
| "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 custom time timestamps for watermark estimation.",
|
| - "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"
|
| + },
|
| + "StreamingConfigTask": {
|
| + "description": "A task that carries configuration information for streaming computations.",
|
| + "id": "StreamingConfigTask",
|
| + "properties": {
|
| + "userStepToStateFamilyNameMap": {
|
| + "additionalProperties": {
|
| + "type": "string"
|
| + },
|
| + "description": "Map from user step names to state families.",
|
| + "type": "object"
|
| },
|
| - "withAttributes": {
|
| - "description": "If true, then the client has requested to get pubsub attributes.",
|
| - "type": "boolean"
|
| + "streamingComputationConfigs": {
|
| + "description": "Set of computation configuration information.",
|
| + "items": {
|
| + "$ref": "StreamingComputationConfig"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamingSideInputLocation": {
|
| - "description": "Identifies the location of a streaming side input.",
|
| - "id": "StreamingSideInputLocation",
|
| + "JobExecutionInfo": {
|
| + "description": "Additional information about how a Cloud Dataflow job will be executed that\nisn't contained in the submitted job.",
|
| + "id": "JobExecutionInfo",
|
| "properties": {
|
| - "tag": {
|
| - "description": "Identifies the particular side input within the streaming Dataflow job.",
|
| + "stages": {
|
| + "additionalProperties": {
|
| + "$ref": "JobExecutionStageInfo"
|
| + },
|
| + "description": "A mapping from each stage to the information about that stage.",
|
| + "type": "object"
|
| + }
|
| + },
|
| + "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",
|
| + "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"
|
| },
|
| - "stateFamily": {
|
| - "description": "Identifies the state family where this side input is stored.",
|
| + "kind": {
|
| + "description": "The kind of step in the Cloud Dataflow job.",
|
| "type": "string"
|
| + },
|
| + "properties": {
|
| + "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.",
|
| + "type": "object"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "CustomSourceLocation": {
|
| - "description": "Identifies the location of a custom souce.",
|
| - "id": "CustomSourceLocation",
|
| + "FailedLocation": {
|
| + "description": "Indicates which location failed to respond to a request for data.",
|
| + "id": "FailedLocation",
|
| "properties": {
|
| - "stateful": {
|
| - "description": "Whether this source is stateful.",
|
| - "type": "boolean"
|
| + "name": {
|
| + "description": "The name of the failed location.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StateFamilyConfig": {
|
| - "description": "State family configuration.",
|
| - "id": "StateFamilyConfig",
|
| + "Disk": {
|
| + "description": "Describes the data disk used by a workflow job.",
|
| + "id": "Disk",
|
| "properties": {
|
| - "stateFamily": {
|
| - "description": "The state family value.",
|
| + "sizeGb": {
|
| + "description": "Size of disk in GB. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| + },
|
| + "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"
|
| },
|
| - "isRead": {
|
| - "description": "If true, this family corresponds to a read operation.",
|
| - "type": "boolean"
|
| + "mountPoint": {
|
| + "description": "Directory in a VM where disk is mounted.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "DataDiskAssignment": {
|
| - "description": "Data disk assignment for a given VM instance.",
|
| - "id": "DataDiskAssignment",
|
| + "ListJobMessagesResponse": {
|
| + "description": "Response to a request to list job messages.",
|
| + "id": "ListJobMessagesResponse",
|
| "properties": {
|
| - "vmInstance": {
|
| - "description": "VM instance name the data disks mounted to, for example \"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 this list defines which persistent directory the disk is mounted to, for example the list of { \"myproject-1014-104817-4c2-harness-0-disk-0\" }, { \"myproject-1014-104817-4c2-harness-0-disk-1\" }.",
|
| + "jobMessages": {
|
| + "description": "Messages in ascending timestamp order.",
|
| "items": {
|
| - "type": "string"
|
| + "$ref": "JobMessage"
|
| },
|
| "type": "array"
|
| + },
|
| + "nextPageToken": {
|
| + "description": "The token to obtain the next page of results if there are more.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceOperationRequest": {
|
| - "description": "A work item that represents the different operations that can be performed on a user-defined Source specification.",
|
| - "id": "SourceOperationRequest",
|
| + "CounterMetadata": {
|
| + "description": "CounterMetadata includes all static non-name non-value counter attributes.",
|
| + "id": "CounterMetadata",
|
| "properties": {
|
| - "split": {
|
| - "$ref": "SourceSplitRequest",
|
| - "description": "Information about a request to split a source."
|
| + "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"
|
| },
|
| - "getMetadata": {
|
| - "$ref": "SourceGetMetadataRequest",
|
| - "description": "Information about a request to get metadata about a source."
|
| + "otherUnits": {
|
| + "description": "A string referring to the unit type.",
|
| + "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"
|
| + },
|
| + "description": {
|
| + "description": "Human-readable description of the counter semantics.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| - },
|
| - "SourceSplitRequest": {
|
| - "description": "Represents the operation to split a high-level Source specification into bundles (parts for parallel processing). At a high level, splitting of a source into bundles happens as follows: SourceSplitRequest is applied to the source. If it returns SOURCE_SPLIT_OUTCOME_USE_CURRENT, no further splitting happens and the source is used \"as is\". Otherwise, splitting is applied recursively to each produced DerivedSource. As an optimization, for any Source, if its does_not_need_splitting is true, the framework assumes that splitting this source would return SOURCE_SPLIT_OUTCOME_USE_CURRENT, and doesn't initiate a SourceSplitRequest. This applies both to the initial source being split and to bundles produced from it.",
|
| - "id": "SourceSplitRequest",
|
| + },
|
| + "ApproximateReportedProgress": {
|
| + "description": "A progress measurement of a WorkItem by a worker.",
|
| + "id": "ApproximateReportedProgress",
|
| "properties": {
|
| - "source": {
|
| - "$ref": "Source",
|
| - "description": "Specification of the source to be split."
|
| + "remainingParallelism": {
|
| + "$ref": "ReportedParallelism",
|
| + "description": "Total amount of parallelism in the input of this task that remains,\n(i.e. can be delegated to this task and any new tasks via dynamic\nsplitting). Always at least 1 for non-finished work items and 0 for\nfinished.\n\n\"Amount of parallelism\" refers to how many non-empty parts of the input\ncan be read in parallel. This does not necessarily equal number\nof records. An input that can be read in parallel down to the\nindividual records is called \"perfectly splittable\".\nAn example of non-perfectly parallelizable input is a block-compressed\nfile format where a block of records has to be read as a whole,\nbut different blocks can be read in parallel.\n\nExamples:\n* If we are processing record #30 (starting at 1) out of 50 in a perfectly\n splittable 50-record input, this value should be 21 (20 remaining + 1\n current).\n* If we are reading through block 3 in a block-compressed file consisting\n of 5 blocks, this value should be 3 (since blocks 4 and 5 can be\n processed in parallel by new tasks via dynamic splitting and the current\n task remains processing block 3).\n* If we are reading through the last block in a block-compressed file,\n or reading or processing the last record in a perfectly splittable\n input, this value should be 1, because apart from the current task, no\n additional remainder can be split off."
|
| },
|
| - "options": {
|
| - "$ref": "SourceSplitOptions",
|
| - "description": "Hints for tuning the splitting process."
|
| + "position": {
|
| + "$ref": "Position",
|
| + "description": "A Position within the work to represent a progress."
|
| + },
|
| + "fractionConsumed": {
|
| + "description": "Completion as fraction of the input consumed, from 0.0 (beginning, nothing\nconsumed), to 1.0 (end of the input, entire input consumed).",
|
| + "format": "double",
|
| + "type": "number"
|
| + },
|
| + "consumedParallelism": {
|
| + "$ref": "ReportedParallelism",
|
| + "description": "Total amount of parallelism in the portion of input of this task that has\nalready been consumed and is no longer active. In the first two examples\nabove (see remaining_parallelism), the value should be 29 or 2\nrespectively. The sum of remaining_parallelism and consumed_parallelism\nshould equal the total amount of parallelism in this work item. If\nspecified, must be finite."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceSplitOptions": {
|
| - "description": "Hints for splitting a Source into bundles (parts for parallel processing) using SourceSplitRequest.",
|
| - "id": "SourceSplitOptions",
|
| + "StateFamilyConfig": {
|
| + "description": "State family configuration.",
|
| + "id": "StateFamilyConfig",
|
| "properties": {
|
| - "desiredBundleSizeBytes": {
|
| - "description": "The source should be split into a set of bundles where the estimated size of each is approximately this many bytes.",
|
| - "format": "int64",
|
| + "stateFamily": {
|
| + "description": "The state family value.",
|
| "type": "string"
|
| },
|
| - "desiredShardSizeBytes": {
|
| - "description": "DEPRECATED in favor of desired_bundle_size_bytes.",
|
| - "format": "int64",
|
| - "type": "string"
|
| + "isRead": {
|
| + "description": "If true, this family corresponds to a read operation.",
|
| + "type": "boolean"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SourceGetMetadataRequest": {
|
| - "description": "A request to compute the SourceMetadata of a Source.",
|
| - "id": "SourceGetMetadataRequest",
|
| + "IntegerList": {
|
| + "description": "A metric value representing a list of integers.",
|
| + "id": "IntegerList",
|
| "properties": {
|
| - "source": {
|
| - "$ref": "Source",
|
| - "description": "Specification of the source whose metadata should be computed."
|
| + "elements": {
|
| + "description": "Elements of the list.",
|
| + "items": {
|
| + "$ref": "SplitInt64"
|
| + },
|
| + "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamingComputationTask": {
|
| - "description": "A task which describes what action should be performed for the specified streaming computation ranges.",
|
| - "id": "StreamingComputationTask",
|
| + "ResourceUtilizationReportResponse": {
|
| + "description": "Service-side response to WorkerMessage reporting resource utilization.",
|
| + "id": "ResourceUtilizationReportResponse",
|
| + "properties": {},
|
| + "type": "object"
|
| + },
|
| + "SourceSplitResponse": {
|
| + "description": "The response to a SourceSplitRequest.",
|
| + "id": "SourceSplitResponse",
|
| "properties": {
|
| - "taskType": {
|
| - "description": "A type of streaming computation task.",
|
| + "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": [
|
| - "STREAMING_COMPUTATION_TASK_UNKNOWN",
|
| - "STREAMING_COMPUTATION_TASK_STOP",
|
| - "STREAMING_COMPUTATION_TASK_START"
|
| + "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"
|
| },
|
| - "dataDisks": {
|
| - "description": "Describes the set of data disks this task should apply to.",
|
| + "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": {
|
| - "$ref": "MountedDataDisk"
|
| + "$ref": "DerivedSource"
|
| },
|
| "type": "array"
|
| },
|
| - "computationRanges": {
|
| - "description": "Contains ranges of a streaming computation this task should apply to.",
|
| + "shards": {
|
| + "description": "DEPRECATED in favor of bundles.",
|
| "items": {
|
| - "$ref": "StreamingComputationRanges"
|
| + "$ref": "SourceSplitShard"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "MountedDataDisk": {
|
| - "description": "Describes mounted data disk.",
|
| - "id": "MountedDataDisk",
|
| + "ParallelInstruction": {
|
| + "description": "Describes a particular operation comprising a MapTask.",
|
| + "id": "ParallelInstruction",
|
| "properties": {
|
| - "dataDisk": {
|
| - "description": "The name of the data disk. This name is local to the Google Cloud Platform project and uniquely identifies the disk within that project, for example \"myproject-1014-104817-4c2-harness-0-disk-1\".",
|
| + "name": {
|
| + "description": "User-provided name of this operation.",
|
| "type": "string"
|
| - }
|
| - },
|
| - "type": "object"
|
| - },
|
| - "StreamingComputationRanges": {
|
| - "description": "Describes full or partial data disk assignment information of the computation ranges.",
|
| - "id": "StreamingComputationRanges",
|
| - "properties": {
|
| - "computationId": {
|
| - "description": "The ID of the computation.",
|
| + },
|
| + "parDo": {
|
| + "$ref": "ParDoInstruction",
|
| + "description": "Additional information for ParDo instructions."
|
| + },
|
| + "read": {
|
| + "$ref": "ReadInstruction",
|
| + "description": "Additional information for Read instructions."
|
| + },
|
| + "flatten": {
|
| + "$ref": "FlattenInstruction",
|
| + "description": "Additional information for Flatten instructions."
|
| + },
|
| + "originalName": {
|
| + "description": "System-defined name for the operation in the original workflow graph.",
|
| "type": "string"
|
| },
|
| - "rangeAssignments": {
|
| - "description": "Data disk assignments for ranges from this computation.",
|
| + "write": {
|
| + "$ref": "WriteInstruction",
|
| + "description": "Additional information for Write instructions."
|
| + },
|
| + "systemName": {
|
| + "description": "System-defined name of this operation.\nUnique across the workflow.",
|
| + "type": "string"
|
| + },
|
| + "partialGroupByKey": {
|
| + "$ref": "PartialGroupByKeyInstruction",
|
| + "description": "Additional information for PartialGroupByKey instructions."
|
| + },
|
| + "outputs": {
|
| + "description": "Describes the outputs of the instruction.",
|
| "items": {
|
| - "$ref": "KeyRangeDataDiskAssignment"
|
| + "$ref": "InstructionOutput"
|
| },
|
| "type": "array"
|
| }
|
| @@ -3575,81 +3547,210 @@
|
| "type": "object"
|
| },
|
| "KeyRangeDataDiskAssignment": {
|
| - "description": "Data disk assignment information for a specific key-range of a sharded computation. Currently we only support UTF-8 character splits to simplify encoding into JSON.",
|
| + "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": {
|
| "start": {
|
| "description": "The start (inclusive) 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"
|
| + },
|
| "end": {
|
| "description": "The end (exclusive) 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": {
|
| + "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"
|
| },
|
| - "dataDisk": {
|
| - "description": "The name of the data disk where data for this range is stored. This name is local to the Google Cloud Platform project and uniquely identifies the disk within that project, for example \"myproject-1014-104817-4c2-harness-0-disk-1\".",
|
| + "name": {
|
| + "description": "The name of the package.",
|
| "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamingConfigTask": {
|
| - "description": "A task that carries configuration information for streaming computations.",
|
| - "id": "StreamingConfigTask",
|
| + "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": {
|
| - "streamingComputationConfigs": {
|
| - "description": "Set of computation configuration information.",
|
| + "numOutputs": {
|
| + "description": "The number of outputs.",
|
| + "format": "int32",
|
| + "type": "integer"
|
| + },
|
| + "sideInputs": {
|
| + "description": "Zero or more side inputs.",
|
| "items": {
|
| - "$ref": "StreamingComputationConfig"
|
| + "$ref": "SideInputInfo"
|
| },
|
| "type": "array"
|
| },
|
| - "userStepToStateFamilyNameMap": {
|
| + "multiOutputInfos": {
|
| + "description": "Information about each of the outputs, if user_fn is a MultiDoFn.",
|
| + "items": {
|
| + "$ref": "MultiOutputInfo"
|
| + },
|
| + "type": "array"
|
| + },
|
| + "userFn": {
|
| "additionalProperties": {
|
| - "type": "string"
|
| + "description": "Properties of the object.",
|
| + "type": "any"
|
| },
|
| - "description": "Map from user step names to state families.",
|
| + "description": "The user function to invoke.",
|
| "type": "object"
|
| + },
|
| + "input": {
|
| + "$ref": "InstructionInput",
|
| + "description": "The input."
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "MetricUpdate": {
|
| + "description": "Describes the state of a metric.",
|
| + "id": "MetricUpdate",
|
| + "properties": {
|
| + "meanSum": {
|
| + "description": "Worker-computed aggregate value for the \"Mean\" aggregation kind.\nThis holds the sum of the aggregated values and is used in combination\nwith mean_count below to obtain the actual mean aggregate value.\nThe only possible value types are Long and Double.",
|
| + "type": "any"
|
| + },
|
| + "updateTime": {
|
| + "description": "Timestamp associated with the metric value. Optional when workers are\nreporting work progress; it will be filled in responses from the\nmetrics API.",
|
| + "format": "google-datetime",
|
| + "type": "string"
|
| + },
|
| + "name": {
|
| + "$ref": "MetricStructuredName",
|
| + "description": "Name of the metric."
|
| + },
|
| + "set": {
|
| + "description": "Worker-computed aggregate value for the \"Set\" aggregation kind. The only\npossible value type is a list of Values whose type can be Long, Double,\nor String, according to the metric's type. All Values in the list must\nbe of the same type.",
|
| + "type": "any"
|
| + },
|
| + "internal": {
|
| + "description": "Worker-computed aggregate value for internal use by the Dataflow\nservice.",
|
| + "type": "any"
|
| + },
|
| + "cumulative": {
|
| + "description": "True if this metric is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this metric is reported\nas a delta that is not associated with any WorkItem.",
|
| + "type": "boolean"
|
| + },
|
| + "kind": {
|
| + "description": "Metric aggregation kind. The possible metric aggregation kinds are\n\"Sum\", \"Max\", \"Min\", \"Mean\", \"Set\", \"And\", and \"Or\".\nThe specified aggregation kind is case-insensitive.\n\nIf omitted, this is not an aggregated value but instead\na single metric sample value.",
|
| + "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"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "CounterStructuredName": {
|
| + "description": "Identifies a counter within a per-job namespace. Counters whose structured\nnames are the same get merged into a single value for the job.",
|
| + "id": "CounterStructuredName",
|
| + "properties": {
|
| + "workerId": {
|
| + "description": "ID of a particular worker.",
|
| + "type": "string"
|
| + },
|
| + "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"
|
| + },
|
| + "componentStepName": {
|
| + "description": "Name of the optimized step being executed by the workers.",
|
| + "type": "string"
|
| + },
|
| + "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"
|
| + },
|
| + "originalStepName": {
|
| + "description": "System generated name of the original step in the user's graph, before\noptimization.",
|
| + "type": "string"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "StreamingComputationConfig": {
|
| - "description": "Configuration information for a single streaming computation.",
|
| - "id": "StreamingComputationConfig",
|
| + "ApproximateProgress": {
|
| + "description": "Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest.",
|
| + "id": "ApproximateProgress",
|
| "properties": {
|
| - "computationId": {
|
| - "description": "Unique identifier for this computation.",
|
| - "type": "string"
|
| - },
|
| - "systemName": {
|
| - "description": "System defined name for this computation.",
|
| - "type": "string"
|
| + "percentComplete": {
|
| + "description": "Obsolete.",
|
| + "format": "float",
|
| + "type": "number"
|
| },
|
| - "stageName": {
|
| - "description": "Stage name of this computation.",
|
| + "remainingTime": {
|
| + "description": "Obsolete.",
|
| + "format": "google-duration",
|
| "type": "string"
|
| },
|
| - "instructions": {
|
| - "description": "Instructions that comprise the computation.",
|
| - "items": {
|
| - "$ref": "ParallelInstruction"
|
| - },
|
| - "type": "array"
|
| + "position": {
|
| + "$ref": "Position",
|
| + "description": "Obsolete."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SendWorkerMessagesRequest": {
|
| - "description": "A request for sending worker messages to the service.",
|
| - "id": "SendWorkerMessagesRequest",
|
| + "WorkerMessageResponse": {
|
| + "description": "A worker_message response allows the server to pass information to the\nsender.",
|
| + "id": "WorkerMessageResponse",
|
| "properties": {
|
| - "workerMessages": {
|
| - "description": "The WorkerMessages to send.",
|
| - "items": {
|
| - "$ref": "WorkerMessage"
|
| - },
|
| - "type": "array"
|
| + "workerMetricsResponse": {
|
| + "$ref": "ResourceUtilizationReportResponse",
|
| + "description": "Service's response to reporting worker metrics (currently empty)."
|
| + },
|
| + "workerHealthReportResponse": {
|
| + "$ref": "WorkerHealthReportResponse",
|
| + "description": "The service's response to a worker's health report."
|
| }
|
| },
|
| "type": "object"
|
| @@ -3658,143 +3759,214 @@
|
| "description": "WorkerMessage provides information to the backend about a worker.",
|
| "id": "WorkerMessage",
|
| "properties": {
|
| + "workerMessageCode": {
|
| + "$ref": "WorkerMessageCode",
|
| + "description": "A worker message code."
|
| + },
|
| + "workerMetrics": {
|
| + "$ref": "ResourceUtilizationReport",
|
| + "description": "Resource metrics reported by workers."
|
| + },
|
| "labels": {
|
| "additionalProperties": {
|
| "type": "string"
|
| },
|
| - "description": "Labels are used to group WorkerMessages. For example, a worker_message about a particular container might have the labels: { \"JOB_ID\": \"2015-04-22\", \"WORKER_ID\": \"wordcount-vm-2015…\" \"CONTAINER_TYPE\": \"worker\", \"CONTAINER_ID\": \"ac1234def\"} Label tags typically correspond to Label enum values. However, for ease of development other strings can be used as tags. LABEL_UNSPECIFIED should not be used here.",
|
| + "description": "Labels are used to group WorkerMessages.\nFor example, a worker_message about a particular container\nmight have the labels:\n{ \"JOB_ID\": \"2015-04-22\",\n \"WORKER_ID\": \"wordcount-vm-2015…\"\n \"CONTAINER_TYPE\": \"worker\",\n \"CONTAINER_ID\": \"ac1234def\"}\nLabel tags typically correspond to Label enum values. However, for ease\nof development other strings can be used as tags. LABEL_UNSPECIFIED should\nnot be used here.",
|
| "type": "object"
|
| },
|
| "time": {
|
| "description": "The timestamp of the worker_message.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| "workerHealthReport": {
|
| "$ref": "WorkerHealthReport",
|
| "description": "The health of a worker."
|
| - },
|
| - "workerMessageCode": {
|
| - "$ref": "WorkerMessageCode",
|
| - "description": "A worker message code."
|
| - },
|
| - "workerMetrics": {
|
| - "$ref": "ResourceUtilizationReport",
|
| - "description": "Resource metrics reported by workers."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerHealthReport": {
|
| - "description": "WorkerHealthReport contains information about the health of a worker. The VM should be identified by the labels attached to the WorkerMessage that this health ping belongs to.",
|
| - "id": "WorkerHealthReport",
|
| + "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": {
|
| - "vmIsHealthy": {
|
| - "description": "Whether the VM is healthy.",
|
| - "type": "boolean"
|
| - },
|
| - "vmStartupTime": {
|
| - "description": "The time the VM was booted.",
|
| - "type": "string"
|
| - },
|
| - "reportInterval": {
|
| - "description": "The interval at which the worker is sending health reports. The default value of 0 should be interpreted as the field is not being explicitly set by the worker.",
|
| + "metricTime": {
|
| + "description": "Timestamp as of which metric values are current.",
|
| + "format": "google-datetime",
|
| "type": "string"
|
| },
|
| - "pods": {
|
| - "description": "The pods running on the worker. See: http://kubernetes.io/v1.1/docs/api-reference/v1/definitions.html#_v1_pod This field is used by the worker to send the status of the indvidual containers running on each worker.",
|
| + "metrics": {
|
| + "description": "All metrics for this job.",
|
| "items": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "type": "object"
|
| + "$ref": "MetricUpdate"
|
| },
|
| "type": "array"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerMessageCode": {
|
| - "description": "A message code is used to report status and error messages to the service. The message codes are intended to be machine readable. The service will take care of translating these into user understandable messages if necessary. Example use cases: 1. Worker processes reporting successful startup. 2. Worker processes reporting specific errors (e.g. package staging 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 the type of message being sent. Examples: 1. \"HARNESS_STARTED\" might be used to indicate the worker harness has started. 2. \"GCS_DOWNLOAD_ERROR\" might be used to indicate an error downloading a GCS file as part of the boot process of one of the worker containers. This is a string and not an enum to make it easy to add new codes without waiting for an API change.",
|
| + "elements": {
|
| + "description": "Elements of the list.",
|
| + "items": {
|
| + "format": "double",
|
| + "type": "number"
|
| + },
|
| + "type": "array"
|
| + }
|
| + },
|
| + "type": "object"
|
| + },
|
| + "CounterUpdate": {
|
| + "description": "An update to a Counter sent from a worker.",
|
| + "id": "CounterUpdate",
|
| + "properties": {
|
| + "shortId": {
|
| + "description": "The service-generated short identifier for this counter.\nThe short_id -> (name, metadata) mapping is constant for the lifetime of\na job.",
|
| + "format": "int64",
|
| "type": "string"
|
| },
|
| - "parameters": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "description": "Parameters contains specific information about the code. This is a struct to allow parameters of different types. Examples: 1. For a \"HARNESS_STARTED\" message parameters might provide the name of the worker and additional data like timing information. 2. For a \"GCS_DOWNLOAD_ERROR\" parameters might contain fields listing the GCS objects being downloaded and fields containing errors. In general complex data structures should be avoided. If a worker needs to send a specific and complicated data structure then please consider defining a new proto and adding it to the data oneof in WorkerMessageResponse. Conventions: Parameters should only be used for information that isn't typically passed as a label. hostname and other worker identifiers should almost always be passed as labels since they will be included on most messages.",
|
| - "type": "object"
|
| + "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."
|
| + },
|
| + "cumulative": {
|
| + "description": "True if this counter is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this counter is reported\nas a delta.",
|
| + "type": "boolean"
|
| + },
|
| + "internal": {
|
| + "description": "Value for internally-defined counters used by the Dataflow service.",
|
| + "type": "any"
|
| + },
|
| + "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"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "ResourceUtilizationReport": {
|
| - "description": "Worker metrics exported from workers. This contains resource utilization metrics accumulated from a variety of sources. For more information, see go/df-resource-signals. Note that this proto closely follows the structure of its DFE siblings in its contents.",
|
| - "id": "ResourceUtilizationReport",
|
| + "SourceMetadata": {
|
| + "description": "Metadata about a Source useful for automatically optimizing\nand tuning the pipeline, etc.",
|
| + "id": "SourceMetadata",
|
| "properties": {
|
| - "metrics": {
|
| - "description": "Each Struct must parallel DFE worker metrics protos (eg., cpu_time metric will have nested values “timestamp_ms, total_ms, rate”).",
|
| - "items": {
|
| - "additionalProperties": {
|
| - "description": "Properties of the object.",
|
| - "type": "any"
|
| - },
|
| - "type": "object"
|
| - },
|
| - "type": "array"
|
| + "producesSortedKeys": {
|
| + "description": "Whether this source is known to produce key/value pairs with\nthe (encoded) keys in lexicographically sorted order.",
|
| + "type": "boolean"
|
| + },
|
| + "infinite": {
|
| + "description": "Specifies that the size of this source is known to be infinite\n(this is a streaming source).",
|
| + "type": "boolean"
|
| + },
|
| + "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"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "SendWorkerMessagesResponse": {
|
| - "description": "The response to the worker messages.",
|
| - "id": "SendWorkerMessagesResponse",
|
| + "DistributionUpdate": {
|
| + "description": "A metric value representing a distribution.",
|
| + "id": "DistributionUpdate",
|
| "properties": {
|
| - "workerMessageResponses": {
|
| - "description": "The servers response to the worker messages.",
|
| - "items": {
|
| - "$ref": "WorkerMessageResponse"
|
| - },
|
| - "type": "array"
|
| + "count": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The count of the number of elements present in the distribution."
|
| + },
|
| + "min": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The minimum value present in the distribution."
|
| + },
|
| + "sumOfSquares": {
|
| + "description": "Use a double since the sum of squares is likely to overflow int64.",
|
| + "format": "double",
|
| + "type": "number"
|
| + },
|
| + "max": {
|
| + "$ref": "SplitInt64",
|
| + "description": "The maximum value present in the distribution."
|
| + },
|
| + "sum": {
|
| + "$ref": "SplitInt64",
|
| + "description": "Use an int64 since we'd prefer the added precision. If overflow is a common\nproblem we can detect it and use an additional int64 or a double."
|
| }
|
| },
|
| "type": "object"
|
| },
|
| - "WorkerMessageResponse": {
|
| - "description": "A worker_message response allows the server to pass information to the sender.",
|
| - "id": "WorkerMessageResponse",
|
| + "SourceFork": {
|
| + "description": "DEPRECATED in favor of DynamicSourceSplit.",
|
| + "id": "SourceFork",
|
| "properties": {
|
| - "workerHealthReportResponse": {
|
| - "$ref": "WorkerHealthReportResponse",
|
| - "description": "The service's response to a worker's health report."
|
| + "residualSource": {
|
| + "$ref": "DerivedSource",
|
| + "description": "DEPRECATED"
|
| },
|
| - "workerMetricsResponse": {
|
| - "$ref": "ResourceUtilizationReportResponse",
|
| - "description": "Service's response to reporting worker metrics (currently empty)."
|
| + "primary": {
|
| + "$ref": "SourceSplitShard",
|
| + "description": "DEPRECATED"
|
| + },
|
| + "primarySource": {
|
| + "$ref": "DerivedSource",
|
| + "description": "DEPRECATED"
|
| + },
|
| + "residual": {
|
| + "$ref": "SourceSplitShard",
|
| + "description": "DEPRECATED"
|
| }
|
| },
|
| "type": "object"
|
| },
|
| "WorkerHealthReportResponse": {
|
| - "description": "WorkerHealthReportResponse contains information returned to the worker in response to a health ping.",
|
| + "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 to the specified value. The default value of zero means no change in report rate is requested by the server.",
|
| + "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"
|
| - },
|
| - "ResourceUtilizationReportResponse": {
|
| - "description": "Service-side response to WorkerMessage reporting resource utilization.",
|
| - "id": "ResourceUtilizationReportResponse",
|
| - "type": "object"
|
| }
|
| },
|
| "servicePath": "",
|
|
|
Chromium Code Reviews
Issue 2695743002:
Api-roll 45: 2017-02-13 (Closed)
