[
https://issues.apache.org/jira/browse/HADOOP-1985?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12564428#action_12564428
]
Hairong Kuang commented on HADOOP-1985:
---------------------------------------
A few dfs-related comments:
1. A datanode should not be added the cluster map before its network location
is resolved;
2. A datanode's block report should not be processed before its network
location is resolved.
Violating (1) cause the datanode be a candiate target of block allocation;
Violating (2) may cause block rereplication or excessive block deletion to
wrongly think replicas on the same rack to be on different racks. Both may
result all replicas of a block to end up on the same rack.
I also think that doing network resolution per datanode is inefficient. It
would be nice if NN could have a list or a range of nodes that are alllowed to
join the cluster and then resolve their network locations by running a script
that takes a list or a range of nodes and returns all racks and the nodes
belonged to each rack. Datanode network locations resolutions are performed
before accepting any datanode registration. This would eliminate all the
problems that are caused by lazy network resolution.
> Abstract node to switch mapping into a topology service class used by
> namenode and jobtracker
> ---------------------------------------------------------------------------------------------
>
> Key: HADOOP-1985
> URL: https://issues.apache.org/jira/browse/HADOOP-1985
> Project: Hadoop Core
> Issue Type: New Feature
> Components: dfs, mapred
> Reporter: eric baldeschwieler
> Assignee: Devaraj Das
> Fix For: 0.17.0
>
> Attachments: 1985.new.patch, 1985.v1.patch, 1985.v10.patch,
> 1985.v11.patch, 1985.v2.patch, 1985.v3.patch, 1985.v4.patch, 1985.v5.patch,
> 1985.v6.patch, 1985.v9.patch, jobinprogress.patch
>
>
> In order to implement switch locality in MapReduce, we need to have switch
> location in both the namenode and job tracker. Currently the namenode asks
> the data nodes for this info and they run a local script to answer this
> question. In our environment and others that I know of there is no reason to
> push this to each node. It is easier to maintain a centralized script that
> maps node DNS names to switch strings.
> I propose that we build a new class that caches known DNS name to switch
> mappings and invokes a loadable class or a configurable system call to
> resolve unknown DNS to switch mappings. We can then add this to the namenode
> to support the current block to switch mapping needs and simplify the data
> nodes. We can also add this same callout to the job tracker and then
> implement rack locality logic there without needing to chane the filesystem
> API or the split planning API.
> Not only is this the least intrusive path to building racklocal MR I can ID,
> it is also future compatible to future infrastructures that may derive
> topology on the fly, etc, etc...
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
