[
https://issues.apache.org/jira/browse/YARN-1492?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14128984#comment-14128984
]
Karthik Kambatla commented on YARN-1492:
----------------------------------------
Thanks for updating the design, Chris.
Chris and I discussed the design and current implementation offline. A couple
of comments in that discussion:
# I like the idea of having a separate daemon for SCM, but if it is not very
resource (memory) intensive, it might make sense to embed it in the RM by
default. This takes care of HA etc. for free. We can do this at the end.
# The choice of SCM store should be transparent to the rest of SCM code. It
would be better to define an interface for the SCMStore similar to the
RMStateStore today.
# Defaulting to the in-memory store requires providing a way to initialize the
store with currently running applications and cached jars, which is quite
involved and not so elegant either. I propose implementing leveldb and zk
stores. We could default to leveldb on non-HA clusters, and ZK store for HA
clusters if we choose to embed the SCM in the RM.
> 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)
