hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Ranjit Mathew (JIRA)" <j...@apache.org>
Subject [jira] Commented: (MAPREDUCE-2139) Gridmix test for submitting jobs with different traces and runtime options.
Date Tue, 07 Dec 2010 10:42:09 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-2139?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12968671#action_12968671
] 

Ranjit Mathew commented on MAPREDUCE-2139:
------------------------------------------

This looks OK to me in conjunction with the patch for MAPREDUCE-2138.

The only minor comment I have is that we probably should be using the constants in {{GridmixConfig.java}}
in the patch for MAPREDUCE-2138 as well. It's slightly inconsistent otherwise.

> Gridmix test for submitting jobs with different traces and runtime options.
> ---------------------------------------------------------------------------
>
>                 Key: MAPREDUCE-2139
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-2139
>             Project: Hadoop Map/Reduce
>          Issue Type: Task
>          Components: test
>            Reporter: Vinay Kumar Thota
>            Assignee: Vinay Kumar Thota
>         Attachments: MAPREDUCE-2139.patch, MAPREDUCE-2139.patch
>
>
> 1.Generate input data based on cluster size and create the synthetic jobs by using the
7 min folded MR trace and submit
> the jobs with below arguments.
> GRIDMIX_JOB_TYPE = SleepJob
> GRIDMIX_USER_RESOLVER = SubmitterUserResolver
> GRIDMIX_MIN_FILE = 200 MB
> GRIDMIX_SUBMISSION_POLICY = STRESS
> GRIDMIX_JOB_SUBMISSION_QUEUE_IN_TRACE = false
> Input Size = 400 MB * No. of nodes in cluster.
> TRACE_FILE = 7 min folded trace.
> Verify each job status, summary(QueueName, UserName, StatTime, FinishTime, maps, reducers
and counters etc) after
> completion of execution. Make sure the queue should be default queue name.
> 2. Generate input data based on cluster size and create the synthetic jobs by using the
10 min folded MR trace and
> submit the jobs with below arguments.
> GRIDMIX_JOB_TYPE = SleepJob
> GRIDMIX_USER_RESOLVER = RoundRobinUserResolver
> GRIDMIX_MIN_FILE = 200 MB
> GRIDMIX_SUBMISSION_POLICY = SERIAL
> GRIDMIX_JOB_SUBMISSION_QUEUE_IN_TRACE = false
> SLEEPJOB_MAPTASK_ONLY = true
> GRIDMIX_SLEEP_MAX_MAP_TIME = 10 sec
> Input Size = 250 MB * No. of nodes in cluster.
> TRACE_FILE = 10 min folded trace.
> Verify each job status, summary(QueueName, UserName, StatTime, FinishTime, maps and counters
etc) after completion of
> execution. Make sure the reducers should be zero.
> 3. Generate input data based on cluster size and create the synthetic jobs by using the
12 min folded MR trace and submit the jobs with below arguments.
> GRIDMIX_JOB_TYPE = SleepJob
> GRIDMIX_USER_RESOLVER = SubmitterUserResolver
> GRIDMIX_MIN_FILE = 200 MB
> GRIDMIX_SUBMISSION_POLICY = STRESS
> GRIDMIX_SLEEP_MAX_MAP_TIME = 10 sec
> GRIDMIX_SLEEP_MAX_REDUCE_TIME = 5 sec
> Input Size = 150 MB * No. of nodes in cluster.
> TRACE_FILE = 12 min folded trace.
> Verify each job status, summary(QueueName, UserName, StatTime, FinishTime, maps,reducers
and counters etc) after completion of execution.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message