[
https://issues.apache.org/jira/browse/FLINK-3160?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15709120#comment-15709120
]
Greg Hogan commented on FLINK-3160:
-----------------------------------
For large parallelism (> 1000, depending on device and browser) the number of
subtasks is unwieldy. The TaskManager tab aggregates subtasks per TaskManager
so the table is generally much smaller. Also, the aggregated statistics can be
quite useful.
How useful would it be to sort by subtask ID when that value is not included in
the table? A user would need to count down the list to locate a specific index.
> Aggregate operator statistics by TaskManager
> --------------------------------------------
>
> Key: FLINK-3160
> URL: https://issues.apache.org/jira/browse/FLINK-3160
> Project: Flink
> Issue Type: Improvement
> Components: Webfrontend
> Affects Versions: 1.0.0
> Reporter: Greg Hogan
> Assignee: Greg Hogan
> Fix For: 1.0.0
>
>
> The web client job info page presents a table of the following per task
> statistics: start time, end time, duration, bytes received, records received,
> bytes sent, records sent, attempt, host, status.
> Flink supports clusters with thousands of slots and a job setting a high
> parallelism renders this job info page unwieldy and difficult to analyze in
> real-time.
> It would be helpful to optionally or automatically aggregate statistics by
> TaskManager. These rows could then be expanded to reveal the current per task
> statistics.
> Start time, end time, duration, and attempt are not applicable to a
> TaskManager since new tasks for repeated attempts may be started. Bytes
> received, records received, bytes sent, and records sent are summed. Any
> throughput metrics can be averaged over the total task time or time window.
> Status could reference the number of running tasks on the TaskManager or an
> idle state.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
