mirror of
https://github.com/apache/druid.git
synced 2025-02-06 10:08:26 +00:00
85a3d416b0
* Tutorials use new ingestion spec where possible There are 2 main changes * Use task type index_parallel instead of index * Remove the use of parser + firehose in favor of inputFormat + inputSource index_parallel is the preferred method starting in 0.17. Setting the job to index_parallel with the default maxNumConcurrentSubTasks(1) is the equivalent of an index task Instead of using a parserSpec, dimensionSpec and timestampSpec have been promoted to the dataSchema. The format is described in the ioConfig as the inputFormat. There are a few cases where the new format is not supported * Hadoop must use firehoses instead of the inputSource and inputFormat * There is no equivalent of a combining firehose as an inputSource * A Combining firehose does not support index_parallel * fix typo
46 lines
1.1 KiB
JSON
46 lines
1.1 KiB
JSON
{
|
|
"type" : "index_parallel",
|
|
"spec" : {
|
|
"dataSchema" : {
|
|
"dataSource" : "updates-tutorial",
|
|
"timestampSpec": {
|
|
"column": "timestamp",
|
|
"format": "iso"
|
|
},
|
|
"dimensionsSpec" : {
|
|
"dimensions" : [
|
|
"animal"
|
|
]
|
|
},
|
|
"metricsSpec" : [
|
|
{ "type" : "count", "name" : "count" },
|
|
{ "type" : "longSum", "name" : "number", "fieldName" : "number" }
|
|
],
|
|
"granularitySpec" : {
|
|
"type" : "uniform",
|
|
"segmentGranularity" : "week",
|
|
"queryGranularity" : "minute",
|
|
"intervals" : ["2018-01-01/2018-01-03"],
|
|
"rollup" : true
|
|
}
|
|
},
|
|
"ioConfig" : {
|
|
"type" : "index_parallel",
|
|
"inputSource" : {
|
|
"type" : "local",
|
|
"baseDir" : "quickstart/tutorial",
|
|
"filter" : "updates-data2.json"
|
|
},
|
|
"inputFormat" : {
|
|
"type" : "json"
|
|
},
|
|
"appendToExisting" : false
|
|
},
|
|
"tuningConfig" : {
|
|
"type" : "index_parallel",
|
|
"maxRowsPerSegment" : 5000000,
|
|
"maxRowsInMemory" : 25000
|
|
}
|
|
}
|
|
}
|