Apache Doris · Schema

RoutineLoadJob

Configuration and state of a Routine Load job that continuously ingests data from Apache Kafka into Doris.

AnalyticsApacheDatabaseLakehouseMPPOLAPOpen SourceReal-TimeSQL

Properties

Name	Type	Description
id	integer	Routine Load job ID.
name	string	Name of the Routine Load job.
dbName	string	Target database name.
tableName	string	Target table name.
state	string	Current state of the load job.
dataSourceType	string	Data source type.
kafkaBrokerList	string	Kafka broker list.
kafkaTopic	string	Kafka topic to consume from.
format	string	Data format.
totalRows	integer	Total number of rows loaded since job start.
loadedRows	integer	Number of rows successfully loaded.
filteredRows	integer	Number of rows filtered.
createTime	string	Job creation time.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/apache-doris/refs/heads/main/json-schema/apache-doris-routine-load-job-schema.json",
  "title": "RoutineLoadJob",
  "description": "Configuration and state of a Routine Load job that continuously ingests data from Apache Kafka into Doris.",
  "type": "object",
  "properties": {
    "id": {
      "type": "integer",
      "description": "Routine Load job ID.",
      "example": 601
    },
    "name": {
      "type": "string",
      "description": "Name of the Routine Load job.",
      "example": "kafka-sales-load"
    },
    "dbName": {
      "type": "string",
      "description": "Target database name.",
      "example": "analytics"
    },
    "tableName": {
      "type": "string",
      "description": "Target table name.",
      "example": "sales_events"
    },
    "state": {
      "type": "string",
      "description": "Current state of the load job.",
      "enum": [
        "NEED_SCHEDULE",
        "RUNNING",
        "PAUSED",
        "STOPPED",
        "CANCELLED"
      ],
      "example": "RUNNING"
    },
    "dataSourceType": {
      "type": "string",
      "description": "Data source type.",
      "enum": [
        "KAFKA"
      ],
      "example": "KAFKA"
    },
    "kafkaBrokerList": {
      "type": "string",
      "description": "Kafka broker list.",
      "example": "broker1:9092,broker2:9092"
    },
    "kafkaTopic": {
      "type": "string",
      "description": "Kafka topic to consume from.",
      "example": "sales-events"
    },
    "format": {
      "type": "string",
      "description": "Data format.",
      "enum": [
        "CSV",
        "JSON",
        "AVRO"
      ],
      "example": "JSON"
    },
    "totalRows": {
      "type": "integer",
      "description": "Total number of rows loaded since job start.",
      "example": 5000000
    },
    "loadedRows": {
      "type": "integer",
      "description": "Number of rows successfully loaded.",
      "example": 4999800
    },
    "filteredRows": {
      "type": "integer",
      "description": "Number of rows filtered.",
      "example": 200
    },
    "createTime": {
      "type": "string",
      "format": "date-time",
      "description": "Job creation time.",
      "example": "2025-03-15T14:30:00Z"
    }
  },
  "required": [
    "name",
    "dbName",
    "tableName",
    "kafkaBrokerList",
    "kafkaTopic"
  ]
}