You are viewing a plain text version of this content. The canonical link for it is here.

Posted to mapreduce-issues@hadoop.apache.org by "Lantao Jin (JIRA)" <ji...@apache.org> on 2017/12/18 08:39:00 UTC

[jira] [Created] (MAPREDUCE-7025) Avg and Max of memory could be record in TaskCount

Lantao Jin created MAPREDUCE-7025:
-------------------------------------

             Summary: Avg and Max of memory could be record in TaskCount
                 Key: MAPREDUCE-7025
                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-7025
             Project: Hadoop Map/Reduce
          Issue Type: Improvement
            Reporter: Lantao Jin
            Assignee: Lantao Jin


MapReduce Counter is very helpful tool to do statistics, analysis and tuning in industry. One popular way is analysing job historical status of running to optimise continuously. But when the job completed, the memory usage in counter is a snapshot value {{PHYSICAL_MEMORY_BYTES}}. So if we can record the average value and the max value instead of the last snapshot value, it could be much helpful.

If you think it' ok. I will contribute the code.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

---------------------------------------------------------------------
To unsubscribe, e-mail: mapreduce-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: mapreduce-issues-help@hadoop.apache.org