pdeva edited a comment 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-519775305 nope. in fact, we have another datasource reading from the same topic with second level granularity, and it shows no duplication at all. (10s is the interval at which data is generated). Results from different data source with higher resolution (base resolution at which data is generated) [query-3014d0a9-3a96-4b2f-9180-b90a8c73a1f1.zip](https://github.com/apache/incubator-druid/files/3484776/query-3014d0a9-3a96-4b2f-9180-b90a8c73a1f1.zip) Note that data here is perfect for the same time range and same kafka topic ```SQL SELECT * FROM "kube-metrics-second" WHERE accountid='52c7e28eebb26a86fb1505b5' AND "__time" >= TIMESTAMP '2019-08-09 02:37:00' AND "__time" < TIMESTAMP '2019-08-09 02:40:00' AND cluster='ds' AND etype='container' AND namespace='default' AND name='app-alertproc' AND pod='alertproc-deployment-65f59b6b8-gc57m' ``` KIS spec ```js { "type": "kafka", "dataSchema": { "dataSource": "kube-metrics-second", "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": "HOUR", "queryGranularity": "SECOND" } }, "tuningConfig": { "type": "kafka", "maxRowsPerSegment": 5000000 }, "ioConfig": { "topic": "kube-metrics", "consumerProperties": { "bootstrap.servers": "xxx" }, "taskCount": 1, "replicas": 2, "taskDuration": "PT1H" } } ```
---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@druid.apache.org For additional commands, e-mail: commits-h...@druid.apache.org
