hadoop-mapreduce-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Zhizhen Hou (JIRA)" <j...@apache.org>
Subject [jira] [Created] (MAPREDUCE-7081) Default speculator won't sepculate the last several submitted reduced task if the total task num is large
Date Tue, 17 Apr 2018 06:10:00 GMT
Zhizhen Hou created MAPREDUCE-7081:
--------------------------------------

             Summary: Default speculator won't sepculate the last several submitted reduced
task if the total task num is large
                 Key: MAPREDUCE-7081
                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-7081
             Project: Hadoop Map/Reduce
          Issue Type: Improvement
          Components: mrv2
    Affects Versions: 2.7.5, 2.9.0
            Reporter: Zhizhen Hou


DefaultSpeculator speculates a task one time.  By default, the number of speculators is max(max(10,
0.01 * tasks.size), 0.1 * running tasks).

I  set mapreduce.job.reduce.slowstart.completedmaps = 1 to start reduce after all the map
tasks are finished. The cluster has 1000 vcores, and the Job has 5000 reduce jobs. At first,
1000 reduces tasks can run simultaneously, number of speculators can speculator at most is
0.1 * 1000 = 100 tasks. Reduce tasks with less data can over shortly, and speculator will
speculator a task per second by default. The task be speculated execution may be because the
more data to be processed. It will speculator  100 tasks within 100 seconds. When 4900 reduces
is over, If a reduce is executed with a lot of  data be processed and is put on a slow machine.
The speculate opportunity is running out, it will not be speculated. It can increase the execution
time of job significantly.

In short, it may waste the speculate opportunity at first only because the execution time
of  reduce with less data to be processed as average time. At  end of job, there is no speculate
opportunity available, especially last several running tasks, judged the number of the running
tasks .  

In my opinion, the number of running tasks should not determine the number of speculate opportunity
.The number of tasks be speculated can be judged by square of finished task percent. Take
an example, if ninety percent of  the task is finished, only 0.9*0.9 = 0.81 speculate opportunity
can be used. It will leave enough opportunity for latter tasks.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

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


Mime
View raw message