[
https://issues.apache.org/jira/browse/TEZ-2888?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14957991#comment-14957991
]
Rajesh Balamohan commented on TEZ-2888:
---------------------------------------
Comment on getLastDataEvents() was an observation. Please ignore. Nothing needs
to be fixed there.
>> maxConcurrency is determined at the DAG level.
concurrencyByTime can be used to get better accuracy instead of maxConcurrency.
But still not guaranteed (quite possible that at the beginning of the attempt
the concurrency was different and the at the end of the task the concurrency
was different). For time being, average concurrency (based on start & end time
of attempt) can be considered. In tool tip, it would be good to add both
maxConcurrency and the computed one, so that it would also be possible to
correlate whether maxConcurrency happened before or after this time period.
{noformat}
if (numWaves > 1) {
if (numWaves%1 < 0.5) {
// more than 1 wave needed and last wave is small
step.notes.add("Last partial wave did not use full concurrency.
");
}
}
{noformat}
The % condition needs to be fixed?.
> Make critical path calculation resilient to AM crash
> ----------------------------------------------------
>
> Key: TEZ-2888
> URL: https://issues.apache.org/jira/browse/TEZ-2888
> Project: Apache Tez
> Issue Type: Sub-task
> Reporter: Bikas Saha
> Assignee: Bikas Saha
> Attachments: TEZ-2888.1.patch
>
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
