[ https://issues.apache.org/jira/browse/HDFS-15650?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17371155#comment-17371155 ]
Hongbing Wang commented on HDFS-15650: -------------------------------------- [~yhaya] [~weichiu] Hi! In our practice, when there are a large number of ec checksum scenarios (such as distcp with checksum), there will be many socket timeout, and generally retrying is normal. (Note: -HDFS-15709- has been merged). I think it makes sense to fix the hard-code. New config `dfs.checksum.ec.socket-timeout` looks good. Do you have any plan to fix this issue? Thanks! > Make the socket timeout for computing checksum of striped blocks configurable > ----------------------------------------------------------------------------- > > Key: HDFS-15650 > URL: https://issues.apache.org/jira/browse/HDFS-15650 > Project: Hadoop HDFS > Issue Type: Improvement > Components: datanode, ec, erasure-coding > Reporter: Yushi Hayasaka > Priority: Minor > Labels: pull-request-available > Time Spent: 0.5h > Remaining Estimate: 0h > > Regarding the DataNode tries to get the checksum of EC internal blocks from > another DataNode for computing the checksum of striped blocks, the timeout is > hard-coded now, but it should be configurable. -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org