[
https://issues.apache.org/jira/browse/HDFS-744?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Lars Hofhansl updated HDFS-744:
-------------------------------
Attachment: HDFS-744-trunk-v3.patch
Most tests fail due to an NPE in flush.
currentPacket can be null in DFSOutputStream.{hflush|hsync} even when
bytesCurBlock > lastFlushOffset, which I found a bit surprising.
I think in that case it is OK not to send a sync packet (if FORCE is enabled,
because there is nothing outstanding to sync).
Also fixed TestFilterFileSystem.
Not sure what's wrong with testTrash.
Also I could use guidance for:
* what types of tests should I add
* If I wanted to add a feature where optionally only the first DN in the
replication chain does the fsync, how should a client convey that to the
FS.create method (it does not make sense that add another CreateFlag).
> Support hsync in HDFS
> ---------------------
>
> Key: HDFS-744
> URL: https://issues.apache.org/jira/browse/HDFS-744
> Project: Hadoop HDFS
> Issue Type: New Feature
> Components: data-node, hdfs client
> Reporter: Hairong Kuang
> Assignee: Lars Hofhansl
> Attachments: HDFS-744-trunk-v2.patch, HDFS-744-trunk-v3.patch,
> HDFS-744-trunk.patch, hdfs-744-v2.txt, hdfs-744-v3.txt, hdfs-744.txt
>
>
> HDFS-731 implements hsync by default as hflush. As descriibed in HADOOP-6313,
> the real expected semantics should be "flushes out to all replicas and all
> replicas have done posix fsync equivalent - ie the OS has flushed it to the
> disk device (but the disk may have it in its cache)." This jira aims to
> implement the expected behaviour.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
