[ https://issues.apache.org/jira/browse/HDFS-9720?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Anu Engineer updated HDFS-9720: ------------------------------- Attachment: HDFS-9720-HDFS-1312.003.patch fix findbugs warnings > DiskBalancer : Add configuration parameters > ------------------------------------------- > > Key: HDFS-9720 > URL: https://issues.apache.org/jira/browse/HDFS-9720 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: balancer & mover > Affects Versions: HDFS-1312 > Reporter: Anu Engineer > Assignee: Anu Engineer > Fix For: HDFS-1312 > > Attachments: HDFS-9720-HDFS-1312.001.patch, > HDFS-9720-HDFS-1312.002.patch, HDFS-9720-HDFS-1312.003.patch > > > Add the following config params: > # Max Disk Throughput - This allows users to control how much disk I/O is > generated while disk balancer is running > # Max Disk Errors - For each move operation, this allows user to specify how > many I/O failures are tolerated before we declare the operation as failed. > #Block Tolerance - Specifies how much movement of data is good enough. since > the datanodes are active while the copy is going on, tolerance lets the user > specify that if we reached something like 5% of projected Ideal storage on > the destination disk, we can consider that move to be successful. > Each of these parameter can be specified for each MoveStep. if not specified > then the config parameters are used. -- This message was sent by Atlassian JIRA (v6.3.4#6332)