[ https://issues.apache.org/jira/browse/HDFS-12011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16061785#comment-16061785 ]
chencan commented on HDFS-12011: -------------------------------- Thank you for your reply. I found fsvolume's reference count may increase/decrease during every read and write process. So i think this can represent the load on the disk. It seems thoughtless. I have tested it in my environment using hibench dfsioe,the performance of this policy is not better than other ones. I think part of the reason is dfsioe's test filesize is equal. May be this policy is a choice in a complex situation where the disk load is uneven. > Add a new load balancing volume choosing policy > ------------------------------------------------ > > Key: HDFS-12011 > URL: https://issues.apache.org/jira/browse/HDFS-12011 > Project: Hadoop HDFS > Issue Type: Improvement > Components: datanode > Reporter: chencan > Assignee: chencan > Attachments: HADOOP-12011.002.path, HADOOP-12011.patch > > > There are two types of volume choosing policies when choose a volume > inner a datanode to write in a datablock : RoundRobinVolumeChoosingPolicy and > AvailableSpaceVolumeChoosingPolicy.This two policies do not take into account > the fsvolume's load. We can add a new load balancing volume choosing policy, > using existing reference in FsVolumeImpl. -- This message was sent by Atlassian JIRA (v6.4.14#64029) --------------------------------------------------------------------- To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org