Hi, Dennis. As Ron said, we could judge this situation by the metrics. We are usually reporting the metrics to the external system like Prometheus by the metric reporter[1]. And these metrics could be shown by some other tools like grafana[2].
Best, Hang [1] https://nightlies.apache.org/flink/flink-docs-release-1.17/docs/deployment/metric_reporters/#prometheus [2] https://grafana.com/oss/ liu ron <ron9....@gmail.com> 于2023年8月16日周三 14:39写道: > Hi, Dennis, > > Although all operators are chained together, each operator metrics is > there, you can view the metrcis related to the corresponding operator's > input and output records through the UI, as following: > [image: image.png] > > > Best, > Ron > > Dennis Jung <inylov...@gmail.com> 于2023年8月16日周三 14:13写道: > >> Hello people, >> I'm trying to monitor data skewness with 'web-ui', between TaskManagers. >> >> Currently all operators has been chained, so I cannot find how data has >> been skewed to TaskManagers (or subtasks). But if I disable chaining, >> AFAIK, it can degrade performance. >> >> >> https://nightlies.apache.org/flink/flink-docs-master/docs/dev/datastream/operators/overview/#task-chaining-and-resource-groups >> >> Could someone give a good suggestion on how to monitor whether data skew >> happens or not, in Flink app? >> >> Thank you. >> >> >>