hadoop-common-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jason Lowe (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HADOOP-9639) truly shared cache for jars (jobjar/libjar)
Date Wed, 12 Jun 2013 15:02:20 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-9639?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13681313#comment-13681313
] 

Jason Lowe commented on HADOOP-9639:
------------------------------------

This feature is already supported in the MapReduce framework.  See ClientDistributedCacheManager.determineCacheVisibilities
and MRApps.setupDistributedCache.  In a nutshell: if the file/archive is publicly accessible
then the resource will be marked PUBLIC in the ApplicationSubmissionContext and will be shared
in the distributed cache.  So as long as the permissions of the parent directories and the
file/archive itself are appropriate, the resource should be automatically marked PUBLIC and
shared across jobs.  The key is to make sure these files are already in HDFS and referenced
directly by the job when it is submitted.  If the jar is sitting in a local filesystem when
the job is submitted then it will be uploaded to the staging area which is always private.
                
> truly shared cache for jars (jobjar/libjar)
> -------------------------------------------
>
>                 Key: HADOOP-9639
>                 URL: https://issues.apache.org/jira/browse/HADOOP-9639
>             Project: Hadoop Common
>          Issue Type: New Feature
>          Components: filecache
>    Affects Versions: 2.0.4-alpha
>            Reporter: Sangjin Lee
>
> Currently there is the distributed cache that enables you to cache jars and files so
that attempts from the same job can reuse them. However, sharing is limited with the distributed
cache because it is normally on a per-job basis. On a large cluster, sometimes copying of
jobjars and libjars becomes so prevalent that it consumes a large portion of the network bandwidth,
not to speak of defeating the purpose of "bringing compute to where data is". This is wasteful
because in most cases code doesn't change much across many jobs.
> I'd like to propose and discuss feasibility of introducing a truly shared cache so that
multiple jobs from multiple users can share and cache jars. This JIRA is to open the discussion.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message