Я пытаюсь использовать druid для получения событий от kafka, однако, когда я использую свертку для получения данных, количество событий кажется неправильным. без сворачивания числа точны. Я использую Друид 0.17.1. я наблюдал, что, хотя сведение происходит вместо того, чтобы агрегировать события в n, оно агрегирует в 1.
, вот мое употребление spe c
{
"dataSchema": {
"dataSource": "notificationstatus",
"timestampSpec": {
"column": "date",
"format": "yyyy-MM-dd-HH:mm:ss Z",
"missingValue": null
},
"dimensionsSpec": {
"dimensions": [{
"type": "string",
"name": "Process",
"multiValueHandling": "SORTED_ARRAY",
"createBitmapIndex": true
},
{
"type": "string",
"name": "Channel",
"multiValueHandling": "SORTED_ARRAY",
"createBitmapIndex": true
},
{
"type": "string",
"name": "Status",
"multiValueHandling": "SORTED_ARRAY",
"createBitmapIndex": true
},
{
"type": "string",
"name": "Message",
"multiValueHandling": "SORTED_ARRAY",
"createBitmapIndex": true
},
{
"type": "string",
"name": "CampaignID",
"multiValueHandling": "SORTED_ARRAY",
"createBitmapIndex": true
},
{
"type": "string",
"name": "BannerID",
"multiValueHandling": "SORTED_ARRAY",
"createBitmapIndex": true
}
],
"dimensionExclusions": [
"date",
"count"
]
},
"metricsSpec": [{
"type": "count",
"name": "count"
}],
"granularitySpec": {
"type": "uniform",
"segmentGranularity": "HOUR",
"queryGranularity": "MINUTE",
"rollup": true,
"intervals": null
},
"transformSpec": {
"filter": {
"type": "not",
"field": {
"type": "like",
"dimension": "Status",
"pattern": "INFO",
"escape": null,
"extractionFn": null
}
},
"transforms": []
}
},
"ioConfig": {
"topic": "notificationstatus",
"inputFormat": {
"type": "tsv",
"columns": [
"source",
"ymd",
"date",
"Process",
"deviceID",
"Channel",
"CampaignID",
"BannerID",
"Status",
"Message",
"11",
"12"
],
"listDelimiter": null,
"delimiter": "\t",
"findColumnsFromHeader": false,
"skipHeaderRows": 0
},
"replicas": 1,
"taskCount": 1,
"taskDuration": "PT3600S",
"consumerProperties": {},
"pollTimeout": 100,
"startDelay": "PT5S",
"period": "PT30S",
"useEarliestOffset": false,
"completionTimeout": "PT1800S",
"lateMessageRejectionPeriod": null,
"earlyMessageRejectionPeriod": null,
"lateMessageRejectionStartDateTime": null,
"stream": "notificationstatus",
"useEarliestSequenceNumber": false,
"type": "kafka"
},
"tuningConfig": {
"type": "kafka",
"maxRowsInMemory": 1000000,
"maxBytesInMemory": 0,
"maxRowsPerSegment": 5000000,
"maxTotalRows": null,
"intermediatePersistPeriod": "PT10M",
"basePersistDirectory": "/home/akash/Downloads/druidVer/apache-druid-0.17.1/var/tmp/druid-realtime-persist622909873559398926",
"maxPendingPersists": 0,
"indexSpec": {
"bitmap": {
"type": "concise"
},
"dimensionCompression": "lz4",
"metricCompression": "lz4",
"longEncoding": "longs"
},
"indexSpecForIntermediatePersists": {
"bitmap": {
"type": "concise"
},
"dimensionCompression": "lz4",
"metricCompression": "lz4",
"longEncoding": "longs"
},
"buildV9Directly": true,
"reportParseExceptions": false,
"handoffConditionTimeout": 0,
"resetOffsetAutomatically": false,
"segmentWriteOutMediumFactory": null,
"workerThreads": null,
"chatThreads": null,
"chatRetries": 8,
"httpTimeout": "PT10S",
"shutdownTimeout": "PT80S",
"offsetFetchPeriod": "PT30S",
"intermediateHandoffPeriod": "P2147483647D",
"logParseExceptions": false,
"maxParseExceptions": 2147483647,
"maxSavedParseExceptions": 0,
"skipSequenceNumberAvailabilityCheck": false,
"repartitionTransitionDuration": "PT120S"
},
"type": "kafka"
}