[
https://issues.apache.org/jira/browse/HDFS-12946?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16678547#comment-16678547
]
Xiao Chen commented on HDFS-12946:
----------------------------------
Thanks Kitti for revving. Latest patch didn't apply to trunk due to DFSTestUtil
conflicts, but I reviewed based on an older trunk, looks great!
+1 pending:
- missing the new method in
{{hadoop-hdfs-project/hadoop-hdfs-rbf/src/main/java/org/apache/hadoop/hdfs/server/federation/metrics/NamenodeBeanMetrics.java}},
which failed compilation for me
- do we really need {{ECTopologyVerifierResultMBean}}?
- we can add the topology check to {{FSN#enableErasureCodingPolicy}} as
discussed earlier, can do this in a separate jira if you'd like.
> Add a tool to check rack configuration against EC policies
> ----------------------------------------------------------
>
> Key: HDFS-12946
> URL: https://issues.apache.org/jira/browse/HDFS-12946
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: erasure-coding
> Reporter: Xiao Chen
> Assignee: Kitti Nanasi
> Priority: Major
> Attachments: HDFS-12946.01.patch, HDFS-12946.02.patch,
> HDFS-12946.03.patch, HDFS-12946.04.fsck.patch, HDFS-12946.05.patch,
> HDFS-12946.06.patch, HDFS-12946.07.patch, HDFS-12946.08.patch
>
>
> From testing we have seen setups with problematic racks / datanodes that
> would not suffice basic EC usages. These are usually found out only after the
> tests failed.
> We should provide a way to check this beforehand.
> Some scenarios:
> - not enough datanodes compared to EC policy's highest data+parity number
> - not enough racks to satisfy BPPRackFaultTolerant
> - highly uneven racks to satisfy BPPRackFaultTolerant
> - highly uneven racks (so that BPP's considerLoad logic may exclude some busy
> nodes on the rack, resulting in #2)
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
