You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@kudu.apache.org by "Dan Burkert (JIRA)" <ji...@apache.org> on 2017/07/27 19:27:00 UTC

[jira] [Created] (KUDU-2081) LBM - possible data directory sync race

Dan Burkert created KUDU-2081:
---------------------------------

             Summary: LBM - possible data directory sync race
                 Key: KUDU-2081
                 URL: https://issues.apache.org/jira/browse/KUDU-2081
             Project: Kudu
          Issue Type: Bug
          Components: tablet
    Affects Versions: 1.4.0
            Reporter: Dan Burkert


Inspecting the LBM code, it became apparent that there is a potential race when multiple threads are sync-ing the same dirty data directory in [LogBlockManager::SyncContainer|https://github.com/apache/kudu/blob/1.4.0/src/kudu/fs/log_block_manager.cc#L1715].  The issue is that when two threads race to sync the same dirty directory, one of them will 'win', and start syncing the directory.  The other will 'lose', and immediately return early, and assume the directory sync is complete (which may or may not be the case).  After discussing with [~haohao] and [~adar] we think it's mostly benign do to the way the LBM is used, but still probably worth fixing.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)