You are viewing a plain text version of this content. The canonical link for it is here.
Posted to hdfs-dev@hadoop.apache.org by "Samer Al-Kiswany (JIRA)" <ji...@apache.org> on 2014/08/05 19:44:12 UTC

[jira] [Created] (HDFS-6821) Atomicity of multi file operations

Samer Al-Kiswany created HDFS-6821:
--------------------------------------

             Summary: Atomicity of multi file operations
                 Key: HDFS-6821
                 URL: https://issues.apache.org/jira/browse/HDFS-6821
             Project: Hadoop HDFS
          Issue Type: Bug
            Reporter: Samer Al-Kiswany
            Priority: Minor


Looking how HDFS updates the log files in case of chmod –r or chown –r operations. In these operations, HDFS name node seems to update each file separately; consequently the strace of the operation looks as follows.

append(edits)
fsync(edits)

append(edits)
fsync(edits)
-----------------------
append(edits)
fsync(edits)

append(edits)
fsync(edits)

If a crash happens in the middle of this operation (e.g. at the dashed line in the trace), the system will end up with part of the files updates with the new owner or permissions and part still with the old owner.

Isn’t it better to log the whole operations (chown -r) as one entry in the edit file?




--
This message was sent by Atlassian JIRA
(v6.2#6252)