[ https://issues.apache.org/jira/browse/HDFS-9733?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15156529#comment-15156529 ]
Uma Maheswara Rao G commented on HDFS-9733: ------------------------------------------- Thanks for the refactor Kai. Overall it looks good to me. Following are my questions/comments # Why do you think we need 2 abstract classes here? AbstractBlockChecksumComputer BlockChecksumComputer One is enough? # Could you please add doc for this class? what it is doing? ReplicatedBlockChecksumComputer # Small doc for this method as well? compute # How does this class related? CorruptedBlocks I think overall you can take advantage to improve javadoc around this newly created classes. This classes added in DFSUtilClient.java > Refactor DFSClient#getFileChecksum and DataXceiver#blockChecksum > ---------------------------------------------------------------- > > Key: HDFS-9733 > URL: https://issues.apache.org/jira/browse/HDFS-9733 > Project: Hadoop HDFS > Issue Type: Improvement > Reporter: Kai Zheng > Assignee: Kai Zheng > Attachments: HDFS-9733-v1.patch, HDFS-9733-v2.patch, > HDFS-9733-v3.patch > > > To prepare for file checksum computing for striped files, this refactors the > existing codes in Refactor {{DFSClient#getFileChecksum}} and > {{DataXceiver#blockChecksum}} to make HDFS-8430 and HDFS-9694 easier. -- This message was sent by Atlassian JIRA (v6.3.4#6332)