[
https://issues.apache.org/jira/browse/HADOOP-8468?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13503100#comment-13503100
]
Junping Du commented on HADOOP-8468:
------------------------------------
Hi Konstantin, Thanks for your question and carefully reading on the result.
Yes. TestDFSIO has no locality awareness in task scheduling as you said.
However, after tasks are scheduled, the work in this umbrella (let's call it
HVE for short) can enhance the possibility for client to choose local physical
host's data block for two reasons:
1. HVE make sure all replica cross 3 physical hosts (total 6 hosts), so for any
HDFS read, there is 50% chance to have a replica living on the same physical
host (previously, it is between 1/3 - 1/2)
2. With HVE, HDFS client can correctly sort the replicas to have
nodegroup-local replica have priority to be chosen rather than rack-local
replica.
The first reason is just special for this case, but second reason affects more
general.
Is that make sense?
> Umbrella of enhancements to support different failure and locality topologies
> -----------------------------------------------------------------------------
>
> Key: HADOOP-8468
> URL: https://issues.apache.org/jira/browse/HADOOP-8468
> Project: Hadoop Common
> Issue Type: Improvement
> Components: ha, io
> Affects Versions: 1.0.0, 2.0.0-alpha
> Reporter: Junping Du
> Assignee: Junping Du
> Attachments: HADOOP-8468-total.patch, HADOOP-8468-total-v3.patch,
> HVE_Hadoop World Meetup 2012.pptx, HVE User Guide on branch-1(draft ).pdf,
> Proposal for enchanced failure and locality topologies.pdf, Proposal for
> enchanced failure and locality topologies (revised-1.0).pdf
>
>
> The current hadoop network topology (described in some previous issues like:
> Hadoop-692) works well in classic three-tiers network when it comes out.
> However, it does not take into account other failure models or changes in the
> infrastructure that can affect network bandwidth efficiency like:
> virtualization.
> Virtualized platform has following genes that shouldn't been ignored by
> hadoop topology in scheduling tasks, placing replica, do balancing or
> fetching block for reading:
> 1. VMs on the same physical host are affected by the same hardware failure.
> In order to match the reliability of a physical deployment, replication of
> data across two virtual machines on the same host should be avoided.
> 2. The network between VMs on the same physical host has higher throughput
> and lower latency and does not consume any physical switch bandwidth.
> Thus, we propose to make hadoop network topology extend-able and introduce a
> new level in the hierarchical topology, a node group level, which maps well
> onto an infrastructure that is based on a virtualized environment.
--
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
