hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Varun Saxena (JIRA)" <j...@apache.org>
Subject [jira] [Comment Edited] (YARN-4835) [YARN-3368] REST API related changes for new Web UI
Date Tue, 24 May 2016 20:52:12 GMT

    [ https://issues.apache.org/jira/browse/YARN-4835?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15298846#comment-15298846
] 

Varun Saxena edited comment on YARN-4835 at 5/24/16 8:51 PM:
-------------------------------------------------------------

I have added a few REST endpoints which are required for WebUI. Primarily for MapReduce AM.
Not updated documentation for this because we need to reach a consensus on naming and also
whether we make it public or not. Because its primarily for UI. These URLs' are not necessarily
following the scheme followed for other REST endpoints.
Because we are fetching things like counters for all tasks belonging to a job(if we do this
the normal way, will have to fetch all the tasks and then fetch counters for each one of them).
The use case for UI is primarily to fetch a particular counter for all tasks belonging to
a job. For this I have provided a query param for counter group and counter name. Did not
put it as part of path. We can choose either of the 2 approaches.
If we go with query param, we can probably extend counter group and name as query param to
other counter related REST endpoints as well.


was (Author: varun_saxena):
I have added a few APIs' which are required for WebUI. Primarily for MapReduce AM.
Not updated documentation for this because we need to reach a consensus on naming and also
whether we make it public or not. Because its primarily for UI. These URLs' are not necessarily
following the scheme followed for other REST endpoints.
Because we are fetching things like counters for all tasks belonging to a job(if we do this
the normal way, will have to fetch all the tasks and then fetch counters for each one of them).
The use case for UI is primarily to fetch a particular counter for all tasks belonging to
a job. For this I have provided a query param for counter group and counter name. Did not
put it as part of path. We can choose either of the 2 approaches.
If we go with query param, we can probably extend counter group and name as query param to
other counter related REST endpoints as well.

> [YARN-3368] REST API related changes for new Web UI
> ---------------------------------------------------
>
>                 Key: YARN-4835
>                 URL: https://issues.apache.org/jira/browse/YARN-4835
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: webapp
>            Reporter: Varun Saxena
>            Assignee: Varun Saxena
>         Attachments: YARN-4835-YARN-3368.01.patch
>
>
> Following things need to be added for AM related web pages.
> 1. Support task state query param in REST URL for fetching tasks.
> 2. Support task attempt state query param in REST URL for fetching task attempts.
> 3. A new REST endpoint to fetch counters for each task belonging to a job. Also have
a query param for counter name.
>    i.e. something like :
>   {{/jobs/\{jobid\}/taskCounters}}
> 4. A REST endpoint in NM for fetching all log files associated with a container. Useful
if logs served by NM.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

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


Mime
View raw message