[
https://issues.apache.org/jira/browse/HADOOP-3933?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ning Li updated HADOOP-3933:
----------------------------
Attachment: hadoop-3933.patch
The patch is attached.
> The existing code reads 0 to 511 bytes more depending on startOffset.
It could be more depending on the value of "io.bytes.per.checksum".
> DataNode's BlockSender sends more data than necessary
> -----------------------------------------------------
>
> Key: HADOOP-3933
> URL: https://issues.apache.org/jira/browse/HADOOP-3933
> Project: Hadoop Core
> Issue Type: Bug
> Components: dfs
> Reporter: Ning Li
> Priority: Minor
> Attachments: hadoop-3933.patch
>
>
> DataNode's BlockSender sends more data than necessary because of how it
> computes endOffset.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
