[
https://issues.apache.org/jira/browse/HDFS-17550?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17894853#comment-17894853
]
ASF GitHub Bot commented on HDFS-17550:
---------------------------------------
zhengchenyu opened a new pull request, #7142:
URL: https://github.com/apache/hadoop/pull/7142
### Description of PR
By enabling reconstruction to decommissioning datanode, the speed increased
by 12 times on a small-scale cluster with only 100 machines dedicated to
storing EC data. I think in prodcution cluster with thousands of clusters,
there will be hundreds of times growth.
### How was this patch tested?
unit test and test in cluster
### For code changes:
- [x] Support decommissioning DataNode by EC block reconstruction.
- [x] `liveBusyBlockIndices` rename to `liveAndDecommissioningBusyIndices`.
- [x] remove `excludeReconstructedIndices` which is duplicate with
`liveAndDecommissioningBusyIndices`
- [x] add new `liveAndDecommissioningBusyIndices` which is used when
reconstruct the busy decommissioning block.
> EC: Support decommissioning DataNode by EC block reconstruction
> ---------------------------------------------------------------
>
> Key: HDFS-17550
> URL: https://issues.apache.org/jira/browse/HDFS-17550
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Chenyu Zheng
> Priority: Major
>
> By enabling reconstruction to decommissioning datanode, the speed increased
> by 12 times on a small-scale cluster with only 100 machines dedicated to
> storing EC data. I think in prodcution cluster with thousands of clusters,
> there will be hundreds of times growth.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
