[jira] [Updated] (YARN-6289) Fail to achieve data locality when runing MapReduce and Spark on HDFS

["Huangkaixuan (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/YARN-6289?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Huangkaixuan updated YARN-6289:
-------------------------------
    Summary: Fail to achieve data locality when runing MapReduce and Spark on HDFS  (was: yarn got little data locality)

> Fail to achieve data locality when runing MapReduce and Spark on HDFS
> ---------------------------------------------------------------------
>
>                 Key: YARN-6289
>                 URL: https://issues.apache.org/jira/browse/YARN-6289
>             Project: Hadoop YARN
>          Issue Type: Improvement
>          Components: capacity scheduler
>         Environment: Hardware configuration
> CPU: 2 x Intel(R) Xeon(R) E5-2620 v2 @ 2.10GHz /15M Cache 6-Core 12-Thread 
> Memory: 128GB Memory (16x8GB) 1600MHz
> Disk: 600GBx2 3.5-inch with RAID-1
> Network bandwidth: 968Mb/s
> Software configuration
> Spark-1.6.2	Hadoop-2.7.1 
>            Reporter: Huangkaixuan
>            Priority: Minor
>         Attachments: YARN-6289.01.docx
>
>
>      When I ran experiments with both Spark and MapReduce wordcount with yarn on the file, I noticed that the job did not get data locality every time. It was seemingly random in the placement of the tasks, even though there is no other job running on the cluster. I expected the task placement to always be on the single machine which is holding the data block, but that did not happen.
>      I run the experiments with a 7 node cluster with 2x replication(1 master, 6 data nodes/node managers) , the experiment details are in the patch so you can recreate the result.
>      In the experiments, I run Spark/MapReduce wordcount with yarn for 10 times in a single block and the results show that only 30% of tasks can satisfy data locality, it seems like random in the placement of tasks.  
>      Next,I will run two more experiments(7 node cluster with 2x replication with 2 blocks and 4 blocks) to verify the results and plan to do some optimization work (optimize the schedule policy) to improve data locality



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

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