[ https://issues.apache.org/jira/browse/HDFS-13248?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16415925#comment-16415925 ]
Íñigo Goiri commented on HDFS-13248: ------------------------------------ {quote} One comment for this: I would suggest to move following codes into rbf and be called in NameNodeRpcServer. {quote} Currently, hadoop-hdfs-rbf depends on hadoop-hdfs, not the other way around. If we do this, we would have a cyclic dependency. {quote} Does this mean we have tested in real cluster and it will return client ip address rather than router ip? {quote} Correct. I haven't tested at scale but in our dev deployment. > RBF: Namenode need to choose block location for the client > ---------------------------------------------------------- > > Key: HDFS-13248 > URL: https://issues.apache.org/jira/browse/HDFS-13248 > Project: Hadoop HDFS > Issue Type: Sub-task > Reporter: Weiwei Wu > Assignee: Íñigo Goiri > Priority: Major > Attachments: HDFS-13248.000.patch, HDFS-13248.001.patch, > clientMachine-call-path.jpeg, debug-info-1.jpeg, debug-info-2.jpeg > > > When execute a put operation via router, the NameNode will choose block > location for the router, not for the real client. This will affect the file's > locality. > I think on both NameNode and Router, we should add a new addBlock method, or > add a parameter for the current addBlock method, to pass the real client > information. -- This message was sent by Atlassian JIRA (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org