[
https://issues.apache.org/jira/browse/HDFS-15759?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Toshihiko Uchida reassigned HDFS-15759:
---------------------------------------
Assignee: Toshihiko Uchida
> EC: Verify EC reconstruction correctness on DataNode
> ----------------------------------------------------
>
> Key: HDFS-15759
> URL: https://issues.apache.org/jira/browse/HDFS-15759
> Project: Hadoop HDFS
> Issue Type: New Feature
> Components: datanode, ec, erasure-coding
> Affects Versions: 3.4.0
> Reporter: Toshihiko Uchida
> Assignee: Toshihiko Uchida
> Priority: Major
>
> EC reconstruction on DataNode has caused data corruption: HDFS-14768,
> HDFS-15186 and HDFS-15240. Those issues occur under specific conditions and
> the corruption is neither detected nor auto-healed by HDFS. It is obviously
> hard for users to monitor data integrity by themselves, and even if they find
> corrupted data, it is difficult or sometimes impossible to recover them.
> To prevent further data corruption issues, this feature proposes a simple and
> effective way to verify EC reconstruction correctness on DataNode at each
> reconstruction process.
> It verifies correctness of outputs decoded from inputs as follows:
> 1. Decoding an input with the outputs;
> 2. Compare the decoded input with the original input.
> For instance, in RS-6-3, assume that outputs [d1, p1] are decoded from inputs
> [d0, d2, d3, d4, d5, p0]. Then the verification is done by decoding d0 from
> [d1, d2, d3, d4, d5, p1], and comparing the original and decoded data of d0.
> When an EC reconstruction task goes wrong, the comparison will fail with high
> probability.
> Then the task will also fail and be retried by NameNode.
> The next reconstruction will succeed if the condition triggered the failure
> is gone.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
