[
https://issues.apache.org/jira/browse/HDFS-7661?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15082062#comment-15082062
]
Zhe Zhang commented on HDFS-7661:
---------------------------------
Agreed that "versioning" the parity {{blk_}} files is the most challenging
part. Should we store the length (based on which the parity block was
calculated) info in the {{.meta}} file instead of the blk file itself?
I don't think it's likely that we need additional locks on the DN side -- there
must already be appropriate locking to guarantee a {{blk_}} file and its
{{.meta}} file are accessed consistently.
> Erasure coding: support hflush and hsync
> ----------------------------------------
>
> Key: HDFS-7661
> URL: https://issues.apache.org/jira/browse/HDFS-7661
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Reporter: Tsz Wo Nicholas Sze
> Assignee: GAO Rui
> Attachments: EC-file-flush-and-sync-steps-plan-2015-12-01.png,
> HDFS-7661-unitTest-wip-trunk.patch,
> HDFS-EC-file-flush-sync-design-version1.1.pdf
>
>
> We also need to support hflush/hsync and visible length.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
