pdeva commented on issue #8276: KIS tasks in 0.15.1 RC2 sometimes duplicate rows with the same dimension values URL: https://github.com/apache/incubator-druid/issues/8276#issuecomment-519988927 it gets worse. [query-a65b3b59-3a39-4168-9261-912020fd591c.zip](https://github.com/apache/incubator-druid/files/3487289/query-a65b3b59-3a39-4168-9261-912020fd591c.zip) here the aggregation is PT30M, and you can see `2019-08-09T15:00:00.000Z` row is repeated four times!! ```sql SELECT * FROM "kube-metrics-30m" WHERE accountid='52c7e28eebb26a86fb1505b5' AND "__time" >= TIMESTAMP '2019-08-09 14:00:00' AND "__time" < TIMESTAMP '2019-08-09 16:30:00' AND cluster='ds' AND etype='container' AND namespace='default' AND name='app-alertproc' AND pod='alertproc-deployment-65f59b6b8-gc57m' ``` KIS spec ``` { "type": "kafka", "dataSchema": { "dataSource": "kube-metrics-30m", "parser": { "type": "string", "parseSpec": { "format": "json", "timestampSpec": { "column": "timestamp", "format": "auto" }, "dimensionsSpec": { "dimensions": [ "accountid", "cluster", "name", "namespace", "etype", "labels", "owner", "owner_kind", "node", "image", "pod", "node_pool" ] } } }, "metricsSpec": [ { "name": "count", "type": "count" }, { "name": "req_cpu", "fieldName": "req_cpu", "type": "floatMax" }, { "name": "req_mem", "fieldName": "req_mem", "type": "longMax" }, { "name": "lim_cpu", "fieldName": "lim_cpu", "type": "floatMax" }, { "name": "lim_mem", "fieldName": "lim_mem", "type": "longMax" }, { "name": "cap_cpu", "fieldName": "cap_cpu", "type": "floatMax" }, { "name": "cap_mem", "fieldName": "cap_mem", "type": "longMax" }, { "name": "cap_pods", "fieldName": "cap_pods", "type": "floatMax" }, { "name": "alloc_cpu", "fieldName": "alloc_cpu", "type": "floatMax" }, { "name": "alloc_mem", "fieldName": "alloc_mem", "type": "longMax" }, { "name": "alloc_pods", "fieldName": "alloc_pods", "type": "floatMax" }, { "name": "cpu", "fieldName": "cpu", "type": "doubleMax" }, { "name": "rxBytes", "fieldName": "rxBytes", "type": "longMax" }, { "name": "txBytes", "fieldName": "txBytes", "type": "longMax" }, { "name": "mem_used", "fieldName": "mem_used", "type": "longMax" }, { "name": "mem_limit", "fieldName": "mem_limit", "type": "longMax" } ], "granularitySpec": { "type": "uniform", "segmentGranularity": {"type": "period", "period": "PT12H"}, "queryGranularity": {"type": "period", "period": "PT30M"} } }, "tuningConfig": { "type": "kafka", "maxRowsPerSegment": 5000000 }, "ioConfig": { "topic": "kube-metrics", "consumerProperties": { "bootstrap.servers": "xx" }, "taskCount": 1, "replicas": 2, "taskDuration": "PT12H" } } ```
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
