[
https://issues.apache.org/jira/browse/HDFS-5281?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14804703#comment-14804703
]
Constantine Peresypkin commented on HDFS-5281:
----------------------------------------------
Ehm, this change violates NFSv3 protocol, by sending `commited = UNSTABLE`
after `stable = FILE_SYNC` was sent.
It's also unclear to me why the write was demoted to UNSTABLE suddenly, NFS
gateway either should send all its responses as UNSTABLE or rely on internal
cache to be durable.
> COMMIT request should not block
> -------------------------------
>
> Key: HDFS-5281
> URL: https://issues.apache.org/jira/browse/HDFS-5281
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: nfs
> Reporter: Brandon Li
> Assignee: Brandon Li
> Fix For: 2.3.0
>
> Attachments: HDFS-5281.001.patch, HDFS-5281.002.patch,
> HDFS-5281.003.patch, HDFS-5281.004.patch
>
>
> Currently Commit request is handled synchronously, blocked at most 30 seconds
> before timeout. This JIRA is to make is asynchronous and thus it won't block
> other requests coming from the same channel.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
