[ https://issues.apache.org/jira/browse/HDFS-13767?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16568851#comment-16568851 ]
Plamen Jeliazkov commented on HDFS-13767: ----------------------------------------- Thanks for the responses, [~vagarychen]! Thank you I think I understand (2) and (3) now. Regarding (4) -- Thanks for pointing out it could be worse. I understand where you are coming from. Do you think we could end up hitting that scenario anyway in the case of a slow / dying / dead ObserverNode? The client would just end up calling _msync()_ on another node, no? I agree that we would just end up going to a heuristic (configuration of some timeout interval). I also suppose if we had enough healthy ObserverNodes then its may not really be a concern to have a bunch of calls queue'd if we could actually support holding them all across hosts vs spontaneous client network traffic trying to find a "good" host. > Add msync server implementation. > -------------------------------- > > Key: HDFS-13767 > URL: https://issues.apache.org/jira/browse/HDFS-13767 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: namenode > Reporter: Chen Liang > Assignee: Chen Liang > Priority: Major > Attachments: HDFS-13767-HDFS-12943.001.patch, > HDFS-13767-HDFS-12943.002.patch, HDFS-13767.WIP.001.patch, > HDFS-13767.WIP.002.patch, HDFS-13767.WIP.003.patch, HDFS-13767.WIP.004.patch > > > This is a followup on HDFS-13688, where msync API is introduced to > {{ClientProtocol}} but the server side implementation is missing. This is > Jira is to implement the server side logic. -- 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