[
https://issues.apache.org/jira/browse/HDFS-8486?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14563196#comment-14563196
]
Daryn Sharp commented on HDFS-8486:
-----------------------------------
What you'll notice is a spike in corrupt blocks that tapers down. What's going
on is the DN's block report included all the blocks it deleted. Over the next
6 hours, the slice scanner slowly detects missing blocks and reports them as
corrupt. After 6 hours, the directory scanner detects and mass removes all the
missing blocks.
In the 6 hour window, the NN does not know the block is under-replicated and it
continues to send clients to the DN. Will file a separate bug for the DN not
informing the NN when it's missing a block it thought it had.
> DN startup may cause severe data loss
> -------------------------------------
>
> Key: HDFS-8486
> URL: https://issues.apache.org/jira/browse/HDFS-8486
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: datanode
> Affects Versions: 0.23.1, 2.0.0-alpha
> Reporter: Daryn Sharp
> Assignee: Daryn Sharp
> Priority: Blocker
>
> A race condition between block pool initialization and the directory scanner
> may cause a mass deletion of blocks in multiple storages.
> If block pool initialization finds a block on disk that is already in the
> replica map, it deletes one of the blocks based on size, GS, etc.
> Unfortunately it _always_ deletes one of the blocks even if identical, thus
> the replica map _must_ be empty when the pool is initialized.
> The directory scanner starts at a random time within its periodic interval
> (default 6h). If the scanner starts very early it races to populate the
> replica map, causing the block pool init to erroneously delete blocks.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
