[ https://issues.apache.org/jira/browse/HDFS-1595?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12985939#action_12985939 ]
Todd Lipcon commented on HDFS-1595: ----------------------------------- {quote} How about we change DFSClient so that if the replication factor is greater than one, it stops writing when there is only one datanode remained in the pipeline because that datanode may be faulty? {quote} Come to think of it, isn't that what dfs.replication.min does -- at least makes close() block until there are two replicas, so in this case you wouldn't have gotten a successful close. Though, I guess this setting is cluster-wide rather than per-stream. > DFSClient may incorrectly detect datanode failure > ------------------------------------------------- > > Key: HDFS-1595 > URL: https://issues.apache.org/jira/browse/HDFS-1595 > Project: Hadoop HDFS > Issue Type: Bug > Components: data-node, hdfs client > Affects Versions: 0.20.4 > Reporter: Tsz Wo (Nicholas), SZE > > Suppose a source datanode S is writing to a destination datanode D in a write > pipeline. We have an implicit assumption that _if S catches an exception > when it is writing to D, then D is faulty and S is fine._ As a result, > DFSClient will take out D from the pipeline, reconstruct the write pipeline > with the remaining datanodes and then continue writing . > However, we find a case that the faulty machine F is indeed S but not D. In > the case we found, F has a faulty network interface (or a faulty switch port) > in such a way that the faulty network interface works fine when sending out a > small amount of data, say 1MB, but it fails when sending out a large amount > of data, say 100MB. > It is even worst if F is the first datanode in the pipeline. Consider the > following: > # DFSClient creates a pipeline with three datanodes. The first of the > datanode is F. > # F catches an IOException when writing to the second datanode. Then, F > reports the second datanode has error. > # DFSClient removes the second datanode from the pipeline and continue > writing with the remaining datanode(s). > # The pipeline now has two datanodes but (2) and (3) repeat. > # Now, only F remains in the pipeline. DFSClient continues writing with one > replica in F. > # The write succeeds and DFSClient is able to close the file successfully. > # The block is under replicated. The NameNode schedules replication from F > to some other datanode D. > # The replication fails from the same reason. D reports to the NameNode that > the replica in F is corrupted. > # The NameNode marks the replica in F is corrupted. > # The block is corrupted since no replica is available. -- This message is automatically generated by JIRA. - You can reply to this email to add a comment to the issue online.