"description":"Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
"description":"Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
"type":"string"
},
"location":{
"location":"path",
"description":"The location to which to direct the request.",
"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.",
"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.",
"description":"If specified, return only messages with timestamps \u003e= start_time.\nThe default is the job creation time (i.e. beginning of messages).",
"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.",
"description":"Required. The ID of the Cloud Platform project that the job belongs to.",
"type":"string",
"required":true
},
"gcsPath":{
"location":"query",
"description":"Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
"type":"string"
},
"location":{
"location":"query",
"description":"The location to which to direct the request.",
"type":"string"
},
"validateOnly":{
"location":"query",
"description":"If true, the request is validated but not actually executed.\nDefaults to false.",
"description":"Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
"description":"Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
"type":"string",
"location":"query"
},
"pageSize":{
"location":"query",
"format":"int32",
"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.",
"description":"Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
"type":"string"
},
"projectId":{
"location":"path",
"description":"The project which owns the jobs.",
"type":"string",
"required":true
},
"filter":{
"location":"query",
"enum":[
"UNKNOWN",
"ALL",
"TERMINATED",
"ACTIVE"
],
"description":"The kind of filter to use.",
"type":"string"
},
"location":{
"location":"query",
"description":"The location that contains this job.",
"type":"string"
},
"pageToken":{
"location":"query",
"description":"Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
"type":"string"
},
"pageSize":{
"format":"int32",
"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.",
"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.",
"description":"If specified, return only messages with timestamps \u003e= start_time.\nThe default is the job creation time (i.e. beginning of messages).",
"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.",
"type":"integer"
},
"minimumImportance":{
"location":"query",
"enum":[
"JOB_MESSAGE_IMPORTANCE_UNKNOWN",
"JOB_MESSAGE_DEBUG",
"JOB_MESSAGE_DETAILED",
"JOB_MESSAGE_BASIC",
"JOB_MESSAGE_WARNING",
"JOB_MESSAGE_ERROR"
],
"description":"Filter to only get messages with importance \u003e= level",
"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.",
"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.",
"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.",
"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/",
"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.",
"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\".",
"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.",
"description":"Shutdown notification from workers. This is to be sent by the shutdown\nscript of the worker VM so that the backend knows that the VM is being\nshut down.",
"type":"object",
"properties":{
"reason":{
"description":"Optional reason to be attached for the shutdown notice.\nFor example: \"PREEMPTION\" would indicate the VM is being shut down because\nof preemption. Other possible reasons may be added in the future.",
"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.",
"description":"ID of a side input being read from/written to. Side inputs are identified\nby a pair of (reader, input_index). The reader is usually equal to the\noriginal name, but it may be different, if a ParDo emits it's Iterator /\nMap side input object.",
"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.",
"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\", \"Or\", and \"Distribution\".\nThe specified aggregation kind is case-insensitive.\n\nIf omitted, this is not an aggregated value but instead\na single metric sample value.",
"description":"Worker-computed aggregate value for aggregation kinds \"Sum\", \"Max\", \"Min\",\n\"And\", and \"Or\". The possible value types are Long, Double, and Boolean."
"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.",
"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":{
"format":"google-datetime",
"description":"Timestamp associated with the metric value. Optional when workers are\nreporting work progress; it will be filled in responses from the\nmetrics API.",
"description":"Labels are used to group WorkerMessages.\nFor example, a worker_message about a particular container\nmight have the labels:\n{ \"JOB_ID\": \"2015-04-22\",\n \"WORKER_ID\": \"wordcount-vm-2015…\"\n \"CONTAINER_TYPE\": \"worker\",\n \"CONTAINER_ID\": \"ac1234def\"}\nLabel tags typically correspond to Label enum values. However, for ease\nof development other strings can be used as tags. LABEL_UNSPECIFIED should\nnot be used here.",
"description":"Service-side response to WorkerMessage issuing shutdown notice."
},
"JobMetrics":{
"id":"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.",
"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."
"description":"The service-generated short identifier for this counter.\nThe short_id -\u003e (name, metadata) mapping is constant for the lifetime of\na job.",
"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.",
"description":"The minimum value present in the distribution."
},
"sumOfSquares":{
"format":"double",
"description":"Use a double since the sum of squares is likely to overflow int64.",
"type":"number"
},
"sum":{
"$ref":"SplitInt64",
"description":"Use an int64 since we'd prefer the added precision. If overflow is a common\nproblem we can detect it and use an additional int64 or a double."
"description":"A positive value indicates the worker should change its reporting interval\nto the specified value.\n\nThe default value of zero means no change in report rate is requested by\nthe server.",
"description":"Specifies errors which occurred during processing. If errors are\nprovided, and completed = true, then the WorkItem is considered\nto have failed.",
"description":"See documentation of stop_position."
},
"sourceOperationResponse":{
"description":"If the work item represented a SourceOperationRequest, and the work\nis completed, contains the result of the operation.",
"$ref":"SourceOperationResponse"
},
"progress":{
"$ref":"ApproximateProgress",
"description":"DEPRECATED in favor of reported_progress."
},
"requestedLeaseDuration":{
"format":"google-duration",
"description":"Amount of time the worker requests for its lease.",
"type":"string"
},
"reportIndex":{
"type":"string",
"format":"int64",
"description":"The report index. When a WorkItem is leased, the lease will\ncontain an initial report index. When a WorkItem's status is\nreported to the system, the report should be sent with\nthat report index, and the response will contain the index the\nworker should use for the next report. Reports received with\nunexpected index values will be rejected by the service.\n\nIn order to preserve idempotency, the worker should not alter the\ncontents of a report, even if the worker must submit the same\nreport multiple times before getting back a response. The worker\nshould not submit a subsequent report until the response for the\nprevious report had been received from the service."
},
"stopPosition":{
"$ref":"Position",
"description":"A worker may split an active map task in two parts, \"primary\" and\n\"residual\", continuing to process the primary part and returning the\nresidual part into the pool of available work.\nThis event is called a \"dynamic split\" and is critical to the dynamic\nwork rebalancing feature. The two obtained sub-tasks are called\n\"parts\" of the split.\nThe parts, if concatenated, must represent the same input as would\nbe read by the current task if the split did not happen.\nThe exact way in which the original task is decomposed into the two\nparts is specified either as a position demarcating them\n(stop_position), or explicitly as two DerivedSources, if this\ntask consumes a user-defined source type (dynamic_source_split).\n\nThe \"current\" task is adjusted as a result of the split: after a task\nwith range [A, B) sends a stop_position update at C, its range is\nconsidered to be [A, C), e.g.:\n* Progress should be interpreted relative to the new range, e.g.\n \"75% completed\" means \"75% of [A, C) completed\"\n* The worker should interpret proposed_stop_position relative to the\n new range, e.g. \"split at 68%\" should be interpreted as\n \"split at 68% of [A, C)\".\n* If the worker chooses to split again using stop_position, only\n stop_positions in [A, C) will be accepted.\n* Etc.\ndynamic_source_split has similar semantics: e.g., if a task with\nsource S splits using dynamic_source_split into {P, R}\n(where P and R must be together equivalent to S), then subsequent\nprogress and proposed_stop_position should be interpreted relative\nto P, and in a potential subsequent dynamic_source_split into {P', R'},\nP' and R' must be together equivalent to P, etc."
},
"completed":{
"description":"True if the WorkItem was completed (successfully or unsuccessfully).",
"type":"boolean"
},
"reportedProgress":{
"description":"The worker's progress through this WorkItem.",
"$ref":"ApproximateReportedProgress"
},
"sourceFork":{
"$ref":"SourceFork",
"description":"DEPRECATED in favor of dynamic_source_split."
"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.",
"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.",
"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."
},
"context":{
"additionalProperties":{
"type":"string"
},
"description":"Zero or more labeled fields which identify the part of the job this\nmetric is associated with, such as the name of a step or collection.\n\nFor example, built-in counters associated with steps will have\ncontext['step'] = \u003cstep-name\u003e. Counters associated with PCollections\nin the SDK will have context['pcollection'] = \u003cpcollection-name\u003e.",
"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."
"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.",
"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\".",
"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).",
"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.",
"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.",
"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.",
"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.",
"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.",
"description":"Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
"description":"The sum of all values being aggregated."
}
},
"id":"IntegerMean",
"description":"A representation of an integer mean metric contribution.",
"type":"object"
},
"ListJobsResponse":{
"description":"Response to a request to list Cloud Dataflow jobs. This may be a partial\nresponse, depending on the page size in the ListJobsRequest.",
"type":"object",
"properties":{
"jobs":{
"description":"A subset of the requested job information.",
"description":"The key ranges processed by the computation.",
"items":{
"$ref":"KeyRangeLocation"
},
"type":"array"
}
},
"id":"ComputationTopology",
"description":"All configuration data for a particular Computation."
},
"RuntimeEnvironment":{
"properties":{
"zone":{
"description":"The Compute Engine [availability\nzone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)\nfor launching worker instances to run your pipeline.",
"description":"The machine type to use for the job. Defaults to the value from the\ntemplate if not specified.",
"type":"string"
}
},
"id":"RuntimeEnvironment",
"description":"The environment values to set at runtime.",
"type":"object"
},
"MountedDataDisk":{
"description":"Describes mounted data disk.",
"type":"object",
"properties":{
"dataDisk":{
"description":"The name of the data disk.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
"type":"string"
}
},
"id":"MountedDataDisk"
},
"StreamingSideInputLocation":{
"properties":{
"stateFamily":{
"description":"Identifies the state family where this side input is stored.",
"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.",
"`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
"`JOB_STATE_RUNNING` indicates that the job is currently running.",
"`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
"`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
"`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
"`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
"`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
"`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
"'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
"'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
],
"enum":[
"JOB_STATE_UNKNOWN",
"JOB_STATE_STOPPED",
"JOB_STATE_RUNNING",
"JOB_STATE_DONE",
"JOB_STATE_FAILED",
"JOB_STATE_CANCELLED",
"JOB_STATE_UPDATED",
"JOB_STATE_DRAINING",
"JOB_STATE_DRAINED",
"JOB_STATE_PENDING",
"JOB_STATE_CANCELLING"
],
"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.",
"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 \u003c= 128 bytes in\nsize.",
"description":"Preliminary field: The format of this data may change at any time.\nA description of the user pipeline and stages through which it is executed.\nCreated by Cloud Dataflow service. Only retrieved with\nJOB_VIEW_DESCRIPTION or JOB_VIEW_ALL."
"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.",
"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.",
"`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
"`JOB_STATE_RUNNING` indicates that the job is currently running.",
"`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
"`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
"`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
"`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
"`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
"`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
"'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
"'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
"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}",
"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.",
"description":"The user-specified Cloud Dataflow job name.\n\nOnly one Job with a given name may exist in a project at any\ngiven time. If a caller attempts to create a Job with the same\nname as an already-existing Job, the attempt returns the\nexisting Job.\n\nThe name must match the regular expression\n`[a-z]([-a-z0-9]{0,38}[a-z0-9])?`",
"description":"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.",
"type":"object",
"properties":{
"primary":{
"$ref":"DerivedSource",
"description":"Primary part (continued to be processed by worker).\nSpecified relative to the previously-current source.\nBecomes current."
"description":"Residual part (returned to the pool of work).\nSpecified relative to the previously-current source."
}
}
},
"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.",
"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.",
"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.",
"description":"The maximum number of workers to cap scaling at.",
"type":"integer"
}
}
},
"ExecutionStageSummary":{
"id":"ExecutionStageSummary",
"description":"Description of the composing transforms, names/ids, and input/outputs of a\nstage of execution. Some composing transforms and sources may have been\ngenerated by the Dataflow service during execution planning.",
"type":"object",
"properties":{
"componentSource":{
"description":"Collections produced and consumed by component transforms of this stage.",
"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\".",
"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}",
"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}",
"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"
},
"userAgent":{
"additionalProperties":{
"description":"Properties of the object.",
"type":"any"
},
"description":"A description of the process that generated the request.",
"description":"If true, then the client has requested to get pubsub attributes.",
"type":"boolean"
},
"idLabel":{
"description":"If set, contains a pubsub label from which to extract record ids.\nIf left empty, record deduplication will be strictly best effort.",
"type":"string"
},
"topic":{
"description":"A pubsub topic, in the form of\n\"pubsub.googleapis.com/topics/\u003cproject-id\u003e/\u003ctopic-name\u003e\"",
"type":"string"
},
"timestampLabel":{
"description":"If set, contains a pubsub label from which to extract record timestamps.\nIf left empty, record timestamps will be generated upon arrival.",
"type":"string"
},
"subscription":{
"description":"A pubsub subscription, in the form of\n\"pubsub.googleapis.com/subscriptions/\u003cproject-id\u003e/\u003csubscription-name\u003e\"",
"type":"string"
},
"dropLateData":{
"description":"Indicates whether the pipeline allows late-arriving data.",
"type":"boolean"
},
"trackingSubscription":{
"description":"If set, specifies the pubsub subscription that will be used for tracking\ncustom time timestamps for watermark estimation.",
"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.",
"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."
"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.",
"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."
"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.",
"description":"The type of autoscaling event to report.",
"type":"string",
"enumDescriptions":[
"Default type for the enum. Value should never be returned.",
"The TARGET_NUM_WORKERS_CHANGED type should be used when the target\nworker pool size has changed at the start of an actuation. An event\nshould always be specified as TARGET_NUM_WORKERS_CHANGED if it reflects\na change in the target_num_workers.",
"The CURRENT_NUM_WORKERS_CHANGED type should be used when actual worker\npool size has been changed, but the target_num_workers has not changed.",
"The ACTUATION_FAILURE type should be used when we want to report\nan error to the user indicating why the current number of workers\nin the pool could not be changed.\nDisplayed in the current status and history widgets.",
"Used when we want to report to the user a reason why we are\nnot currently adjusting the number of workers.\nShould specify both target_num_workers, current_num_workers and a\ndecision_message."
]
},
"targetNumWorkers":{
"format":"int64",
"description":"The target number of workers the worker pool wants to resize to use.",
"description":"The time this event was emitted to indicate a new target or current\nnum_workers value.",
"type":"string"
},
"description":{
"$ref":"StructuredMessage",
"description":"A message describing why the system decided to adjust the current\nnumber of workers, why it failed, or why the system decided to\nnot make any changes to the number of workers."
"description":"The API version of endpoint, e.g. \"v1b3\""
},
"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}",
"description":"The file to store preprocessing commands in.",
"type":"string"
},
"baseTaskDir":{
"description":"The location on the worker for task-specific subdirectories.",
"type":"string"
},
"tempStoragePrefix":{
"description":"The prefix of the resources the taskrunner should use for\ntemporary storage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
"type":"string"
},
"baseUrl":{
"description":"The base URL for the taskrunner to use when accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
"type":"string"
},
"logToSerialconsole":{
"type":"boolean",
"description":"Whether to send taskrunner log info to Google Compute Engine VM serial\nconsole."
},
"continueOnException":{
"description":"Whether to continue taskrunner if an exception is hit.",
"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.",
"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).",
"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."
},
"codec":{
"description":"The codec to use to decode data read from the source.",
"type":"object",
"additionalProperties":{
"description":"Properties of the object.",
"type":"any"
}
},
"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."
"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.",
"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.",
"type":"string",
"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."
"description":"Settings passed through to Google Compute Engine workers when\nusing the standard Dataflow task runner. Users should ignore\nthis field.",
"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."
],
"enum":[
"DEFAULT_PACKAGE_SET_UNKNOWN",
"DEFAULT_PACKAGE_SET_NONE",
"DEFAULT_PACKAGE_SET_JAVA",
"DEFAULT_PACKAGE_SET_PYTHON"
],
"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.",
"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).",
"type":"integer"
},
"numWorkers":{
"format":"int32",
"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.",
"description":"A rich message format, including a human readable string, a key for\nidentifying the message, and structured data associated with the message for\nprogrammatic consumption.",
"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.",
"description":"Specifies whether the parallelism is infinite. If true, \"value\" is\nignored.\nInfinite parallelism means the service will assume that the work item\ncan always be split into more non-empty work items by dynamic splitting.\nThis is a work-around for lack of support for infinity by the current\nJSON-based Java RPC stack.",
"type":"boolean"
},
"value":{
"format":"double",
"description":"Specifies the level of parallelism in case it is finite.",
"description":"The ID of the worker running this pipeline.",
"type":"string"
},
"tempStoragePrefix":{
"description":"The prefix of the resources the system should use for temporary\nstorage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
"type":"string"
},
"reportingEnabled":{
"type":"boolean",
"description":"Whether to send work progress updates to the service."
},
"baseUrl":{
"description":"The base URL for accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
"type":"string"
},
"servicePath":{
"description":"The Cloud Dataflow service path relative to the root URL, for example,\n\"dataflow/v1b3/projects\".",
"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\" }.",
"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."
"description":"The `Status` type defines a logical error model that is suitable for different\nprogramming environments, including REST APIs and RPC APIs. It is used by\n[gRPC](https://github.com/grpc). The error model is designed to be:\n\n- Simple to use and understand for most users\n- Flexible enough to meet unexpected needs\n\n# Overview\n\nThe `Status` message contains three pieces of data: error code, error message,\nand error details. The error code should be an enum value of\ngoogle.rpc.Code, but it may accept additional error codes if needed. The\nerror message should be a developer-facing English message that helps\ndevelopers *understand* and *resolve* the error. If a localized user-facing\nerror message is needed, put the localized message in the error details or\nlocalize it in the client. The optional error details may contain arbitrary\ninformation about the error. There is a predefined set of error detail types\nin the package `google.rpc` that can be used for common error conditions.\n\n# Language mapping\n\nThe `Status` message is the logical representation of the error model, but it\nis not necessarily the actual wire format. When the `Status` message is\nexposed in different client libraries and different wire protocols, it can be\nmapped differently. For example, it will likely be mapped to some exceptions\nin Java, but more likely mapped to some error codes in C.\n\n# Other uses\n\nThe error model and the `Status` message can be used in a variety of\nenvironments, either with or without APIs, to provide a\nconsistent developer experience across different environments.\n\nExample uses of this error model include:\n\n- Partial errors. If a service needs to return partial errors to the client,\n it may embed the `Status` in the normal response to indicate the partial\n errors.\n\n- Workflow errors. A typical workflow has multiple steps. Each step may\n have a `Status` message for error reporting.\n\n- Batch operations. If a client uses batch request and batch response, the\n `Status` message should be used directly inside batch response, one for\n each error sub-response.\n\n- Asynchronous operations. If an API call embeds asynchronous operation\n results in its response, the status of those operations should be\n represented directly using the `Status` message.\n\n- Logging. If some API errors are stored in logs, the message `Status` could\n be used directly after any stripping needed for security/privacy reasons."
"`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
"`JOB_STATE_RUNNING` indicates that the job is currently running.",
"`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
"`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
"`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
"`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
"`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
"`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
"'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
"'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
],
"enum":[
"JOB_STATE_UNKNOWN",
"JOB_STATE_STOPPED",
"JOB_STATE_RUNNING",
"JOB_STATE_DONE",
"JOB_STATE_FAILED",
"JOB_STATE_CANCELLED",
"JOB_STATE_UPDATED",
"JOB_STATE_DRAINING",
"JOB_STATE_DRAINED",
"JOB_STATE_PENDING",
"JOB_STATE_CANCELLING"
],
"description":"Executions stage states allow the same set of values as JobState.",
"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.",
"type":"integer"
},
"outputNum":{
"format":"int32",
"description":"The output index (origin zero) within the producer.",
"type":"integer"
}
},
"id":"InstructionInput"
},
"StageSource":{
"description":"Description of an input or output of an execution stage.",
"description":"Contains value if the data is of string type.",
"type":"string"
},
"durationValue":{
"format":"google-duration",
"description":"Contains value if the data is of duration type.",
"type":"string"
},
"int64Value":{
"format":"int64",
"description":"Contains value if the data is of int64 type.",
"type":"string"
},
"namespace":{
"description":"The namespace for the key. This is usually a class name or programming\nlanguage namespace (i.e. python module) which defines the display data.\nThis allows a dax monitoring system to specially handle the data\nand perform custom rendering.",
"type":"string"
},
"floatValue":{
"format":"float",
"description":"Contains value if the data is of float type.",
"description":"The key identifying the display data.\nThis is intended to be used as a label for the display data\nwhen viewed in a dax monitoring system."
},
"shortStrValue":{
"description":"A possible additional shorter value to display.\nFor example a java_class_name_value of com.mypackage.MyDoFn\nwill be stored with MyDoFn as the short_str_value and\ncom.mypackage.MyDoFn as the java_class_name value.\nshort_str_value can be displayed and java_class_name_value\nwill be displayed as a tooltip.",
"type":"string"
},
"url":{
"description":"An optional full URL.",
"type":"string"
},
"label":{
"description":"An optional label to display in a dax UI for the element.",
"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"
},
"currentWorkerTime":{
"format":"google-datetime",
"description":"The current timestamp at the worker.",
"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).",
"description":"If present, the worker must use this endpoint to communicate with Windmill\nService dispatchers, otherwise the worker must continue to use whatever\nendpoint it had been using.",
"description":"If present, the worker must use this port to communicate with Windmill\nService dispatchers. Only applicable when windmill_service_endpoint is\nspecified.",
"description":"A task that carries configuration information for streaming computations.",
"type":"object"
},
"PipelineDescription":{
"description":"A descriptive representation of submitted pipeline as well as the executed\nform. This data is provided by the Dataflow service for ease of visualizing\nthe pipeline and interpretting Dataflow provided metrics.",
"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.",
"description":"Named properties associated with the step. Each kind of\npredefined step has its own required set of properties.\nMust be provided on Create. Only retrieved with JOB_VIEW_ALL.",
"description":"Disk storage type, as defined by Google Compute Engine. This\nmust be a disk type appropriate to the project and zone in which\nthe workers will run. If unknown or unspecified, the service\nwill attempt to choose a reasonable default.\n\nFor example, the standard persistent disk type is a resource name\ntypically ending in \"pd-standard\". If SSD persistent disks are\navailable, the resource name typically ends with \"pd-ssd\". The\nactual valid values are defined the Google Compute Engine API,\nnot by the Cloud Dataflow API; consult the Google Compute Engine\ndocumentation for more information about determining the set of\navailable disk types for a particular project and zone.\n\nGoogle Compute Engine Disk types are local to a particular\nproject in a particular zone, and so the resource name will\ntypically look something like this:\n\ncompute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard",
"type":"string"
},
"sizeGb":{
"format":"int32",
"description":"Size of disk in GB. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
"type":"integer"
},
"mountPoint":{
"description":"Directory in a VM where disk is mounted.",
"description":"A progress measurement of a WorkItem by a worker.",
"type":"object",
"properties":{
"fractionConsumed":{
"format":"double",
"description":"Completion as fraction of the input consumed, from 0.0 (beginning, nothing\nconsumed), to 1.0 (end of the input, entire input consumed).",
"type":"number"
},
"consumedParallelism":{
"$ref":"ReportedParallelism",
"description":"Total amount of parallelism in the portion of input of this task that has\nalready been consumed and is no longer active. In the first two examples\nabove (see remaining_parallelism), the value should be 29 or 2\nrespectively. The sum of remaining_parallelism and consumed_parallelism\nshould equal the total amount of parallelism in this work item. If\nspecified, must be finite."
},
"remainingParallelism":{
"$ref":"ReportedParallelism",
"description":"Total amount of parallelism in the input of this task that remains,\n(i.e. can be delegated to this task and any new tasks via dynamic\nsplitting). Always at least 1 for non-finished work items and 0 for\nfinished.\n\n\"Amount of parallelism\" refers to how many non-empty parts of the input\ncan be read in parallel. This does not necessarily equal number\nof records. An input that can be read in parallel down to the\nindividual records is called \"perfectly splittable\".\nAn example of non-perfectly parallelizable input is a block-compressed\nfile format where a block of records has to be read as a whole,\nbut different blocks can be read in parallel.\n\nExamples:\n* If we are processing record #30 (starting at 1) out of 50 in a perfectly\n splittable 50-record input, this value should be 21 (20 remaining + 1\n current).\n* If we are reading through block 3 in a block-compressed file consisting\n of 5 blocks, this value should be 3 (since blocks 4 and 5 can be\n processed in parallel by new tasks via dynamic splitting and the current\n task remains processing block 3).\n* If we are reading through the last block in a block-compressed file,\n or reading or processing the last record in a perfectly splittable\n input, this value should be 1, because apart from the current task, no\n additional remainder can be split off."
},
"position":{
"$ref":"Position",
"description":"A Position within the work to represent a progress."
}
}
},
"StateFamilyConfig":{
"properties":{
"isRead":{
"description":"If true, this family corresponds to a read operation.",
"type":"boolean"
},
"stateFamily":{
"description":"The state family value.",
"type":"string"
}
},
"id":"StateFamilyConfig",
"description":"State family configuration.",
"type":"object"
},
"IntegerList":{
"description":"A metric value representing a list of integers.",
"type":"object",
"properties":{
"elements":{
"items":{
"$ref":"SplitInt64"
},
"type":"array",
"description":"Elements of the list."
}
},
"id":"IntegerList"
},
"ResourceUtilizationReportResponse":{
"description":"Service-side response to WorkerMessage reporting resource utilization.",
"type":"object",
"properties":{},
"id":"ResourceUtilizationReportResponse"
},
"SourceSplitResponse":{
"description":"The response to a SourceSplitRequest.",
"type":"object",
"properties":{
"outcome":{
"description":"Indicates whether splitting happened and produced a list of bundles.\nIf this is USE_CURRENT_SOURCE_AS_IS, the current source should\nbe processed \"as is\" without splitting. \"bundles\" is ignored in this case.\nIf this is SPLITTING_HAPPENED, then \"bundles\" contains a list of\nbundles into which the source was split.",
"type":"string",
"enumDescriptions":[
"The source split outcome is unknown, or unspecified.",
"The current source should be processed \"as is\" without splitting.",
"Splitting produced a list of bundles."
],
"enum":[
"SOURCE_SPLIT_OUTCOME_UNKNOWN",
"SOURCE_SPLIT_OUTCOME_USE_CURRENT",
"SOURCE_SPLIT_OUTCOME_SPLITTING_HAPPENED"
]
},
"bundles":{
"items":{
"$ref":"DerivedSource"
},
"type":"array",
"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."
