[ https://issues.apache.org/jira/browse/HDFS-16931?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17692196#comment-17692196 ]
ASF GitHub Bot commented on HDFS-16931: --------------------------------------- liuaer opened a new pull request, #5424: URL: https://github.com/apache/hadoop/pull/5424 In our HDFS cluster that holds hundreds of millions of metadata, all of which is EC data. When Observer NN replays the OP_DELETE operation which deletes a large directory, involving tens of millions of metadata. Because the operation is synchronous, the Observer NN is stuck for nearly 50 minutes. [HDFS-16043](https://issues.apache.org/jira/browse/HDFS-16043) has solved the asynchronous deletion on the active NN. This is to solve the asynchronous deletion on the Observer NN. > Observer nn delete blocks asynchronously when tail OP_DELETE editlog > -------------------------------------------------------------------- > > Key: HDFS-16931 > URL: https://issues.apache.org/jira/browse/HDFS-16931 > Project: Hadoop HDFS > Issue Type: Improvement > Components: namenode > Reporter: kinit > Priority: Minor > -- This message was sent by Atlassian Jira (v8.20.10#820010) --------------------------------------------------------------------- To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org