[ https://issues.apache.org/jira/browse/HDFS-16549?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17525376#comment-17525376 ]
Mingxiang Li commented on HDFS-16549: ------------------------------------- in FsDatasetImpl.invalidate the scope protected by block pool write lock is just do some lightweight operate , it won't take long time when hold lock.If change to volume lock when user delete batch of blocks, you have to search volume information in volume map for every block, so I don't think this method is necessary to change to volume lock > Consider using volume level lock for deleting blocks > ---------------------------------------------------- > > Key: HDFS-16549 > URL: https://issues.apache.org/jira/browse/HDFS-16549 > Project: Hadoop HDFS > Issue Type: Improvement > Reporter: Yuanbo Liu > Priority: Major > > It's great to see the implement of fine-grain lock for DN has been committed > into trunk. > FsDatasetImpl.invalidate is a frequent method to response the delete command > from NN. How about using volume-level write lock instead of pool-level write > lock to reduce the cost of write lock. > cc: [~hexiaoqiao] [~Aiphag0] . > Thanks for your great work! -- This message was sent by Atlassian Jira (v8.20.7#820007) --------------------------------------------------------------------- To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org