hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Karthik Kambatla (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-1492) truly shared cache for jars (jobjar/libjar)
Date Wed, 10 Sep 2014 23:47:38 GMT

    [ https://issues.apache.org/jira/browse/YARN-1492?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14129378#comment-14129378
] 

Karthik Kambatla commented on YARN-1492:
----------------------------------------

I am good with fixing the in-memory store so store-specific details don't creep into the code
elsewhere. 

Personally, I am okay with working on leveldb and zk stores post merge. My main concern is
with providing a way to initialize the store, as we don't have a good answer for long-running
apps and it will not be required when using leveldb and zk implementations for non-HA and
HA cases. I would rather avoid that piece completely. I am okay with having an in-memory store
that the tests exercise and has a trivial recovery. Having a "real" store though would definitely
boost people's confidence at merge time :)

> truly shared cache for jars (jobjar/libjar)
> -------------------------------------------
>
>                 Key: YARN-1492
>                 URL: https://issues.apache.org/jira/browse/YARN-1492
>             Project: Hadoop YARN
>          Issue Type: New Feature
>    Affects Versions: 2.0.4-alpha
>            Reporter: Sangjin Lee
>            Assignee: Chris Trezzo
>         Attachments: YARN-1492-all-trunk-v1.patch, YARN-1492-all-trunk-v2.patch, YARN-1492-all-trunk-v3.patch,
YARN-1492-all-trunk-v4.patch, YARN-1492-all-trunk-v5.patch, shared_cache_design.pdf, shared_cache_design_v2.pdf,
shared_cache_design_v3.pdf, shared_cache_design_v4.pdf, shared_cache_design_v5.pdf, shared_cache_design_v6.pdf
>
>
> 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 was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message