[
https://issues.apache.org/jira/browse/HDFS-5168?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13760872#comment-13760872
]
Junping Du commented on HDFS-5168:
----------------------------------
That's a good idea. Nichola! I think you are mentioning case for VMs running on
shared storages, i.e. SAN. Isn't it?
Previously, DAS (HDD) is considered as default and the only one backed storage
type for Hadoop even in virtualization case. Now, we are addressing different
storage tiers (including SSD, remote storage, etc.) under HDFS-2832. I had
similar comments there that storage failure group should be addressed when we
are enabling remote storage. I would prefer the first approach especially it
could be easier after enabling storage type awareness. The second approach will
break some basic assumptions of Hadoop - hierarchical network topology, which
seems unnecessary for me. Thoughts?
> BlockPlacementPolicy does not work for cross rack/node group dependencies
> -------------------------------------------------------------------------
>
> Key: HDFS-5168
> URL: https://issues.apache.org/jira/browse/HDFS-5168
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Nikola Vujic
> Priority: Critical
>
> Block placement policies do not work for cross rack/node group dependencies.
> In reality this is needed when compute servers and storage fall in two
> independent fault domains, then both BlockPlacementPolicyDefault and
> BlockPlacementPolicyWithNodeGroup are not able to provide proper block
> placement.
> Let's suppose that we have Hadoop cluster with one rack with two servers, and
> we run 2 VMs per server. Node group topology for this cluster would be:
> server1-vm1 -> /d1/r1/n1
> server1-vm2 -> /d1/r1/n1
> server2-vm1 -> /d1/r1/n2
> server2-vm2 -> /d1/r1/n2
> This is working fine as long as server and storage fall into the same fault
> domain but if storage is in a different fault domain from the server, we will
> not be able to handle that. For example, if storage of server1-vm1 is in the
> same fault domain as storage of server2-vm1, then we must not place two
> replicas on these two nodes although they are in different node groups.
> Two possible approaches:
> - One approach would be to define cross rack/node group dependencies and to
> use them when excluding nodes from the search space. This looks as the
> cleanest way to fix this as it requires minor changes in the
> BlockPlacementPolicy classes.
> - Other approach would be to allow nodes to fall in more than one node group.
> When we chose a node to hold a replica we have to exclude from the search
> space all nodes from the node groups where the chosen node belongs. This
> approach may require major changes in the NetworkTopology.
--
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
