[
https://issues.apache.org/jira/browse/HADOOP-5713?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12707883#action_12707883
]
Alban Chevignard commented on HADOOP-5713:
------------------------------------------
You are right that the client does not know why the data node is unavailable,
but it does not necessarily need to. In the proposed solution, the node is
excluded for the lifetime of the output stream only, which does not affect
other clients or any of the data structures on the name node.
This issue first came up while testing a cluster with 200 nodes, so it's
actually more a matter of network topology rather than just cluster size. For
example, if a rack in the cluster contains only two nodes and one of them goes
down while a worker on the other node is trying to write to a file, the name
node will keep assigning that dead node to the writer until it realizes that
the node is down. Increasing the number of write retries in that case won't
help. This happens even if there are hundreds of other live nodes in the
cluster. Since we have seen this issue occur on a production cluster, we feel
it's definitely worth the additional complexity on the client to address it.
> File write fails after data node goes down
> ------------------------------------------
>
> Key: HADOOP-5713
> URL: https://issues.apache.org/jira/browse/HADOOP-5713
> Project: Hadoop Core
> Issue Type: Bug
> Components: dfs
> Reporter: Alban Chevignard
> Attachments: failed_write.patch
>
>
> If a data node goes down while a file is being written do HDFS, the write
> fails with the following errors:
> {noformat}
> 09/04/20 17:15:39 INFO dfs.DFSClient: Exception in createBlockOutputStream
> java.io.IOException:
> Bad connect ack with firstBadLink 192.168.0.66:50010
> 09/04/20 17:15:39 INFO dfs.DFSClient: Abandoning block
> blk_-6792221430152215651_1003
> 09/04/20 17:15:45 INFO dfs.DFSClient: Exception in createBlockOutputStream
> java.io.IOException:
> Bad connect ack with firstBadLink 192.168.0.66:50010
> 09/04/20 17:15:45 INFO dfs.DFSClient: Abandoning block
> blk_-1056044503329698571_1003
> 09/04/20 17:15:51 INFO dfs.DFSClient: Exception in createBlockOutputStream
> java.io.IOException:
> Bad connect ack with firstBadLink 192.168.0.66:50010
> 09/04/20 17:15:51 INFO dfs.DFSClient: Abandoning block
> blk_-1144491637577072681_1003
> 09/04/20 17:15:57 INFO dfs.DFSClient: Exception in createBlockOutputStream
> java.io.IOException:
> Bad connect ack with firstBadLink 192.168.0.66:50010
> 09/04/20 17:15:57 INFO dfs.DFSClient: Abandoning block
> blk_6574618270268421892_1003
> 09/04/20 17:16:03 WARN dfs.DFSClient: DataStreamer Exception:
> java.io.IOException:
> Unable to create new block.
> at
> org.apache.hadoop.dfs.DFSClient$DFSOutputStream.nextBlockOutputStream(DFSClient.java:2387)
> at
> org.apache.hadoop.dfs.DFSClient$DFSOutputStream.access$1800(DFSClient.java:1746)
> at
> org.apache.hadoop.dfs.DFSClient$DFSOutputStream$DataStreamer.run(DFSClient.java:1924)
> 09/04/20 17:16:03 WARN dfs.DFSClient: Error Recovery for block
> blk_6574618270268421892_1003 bad datanode[1]
> {noformat}
> The tests were done with the following configuration:
> * Hadoop version 0.18.3
> * 3 data nodes with replication count of 2
> * 1 GB file write
> * 1 data node taken down during write
> This issue seems to be caused by the fact that there is a delay between the
> time a data node goes down and the time it is marked as dead by the name
> node. This delay is unavoidable, but the name node should not keep allocating
> new blocks to data nodes that are known to be down by the client. Even by
> adjusting {{heartbeat.recheck.interval}}, there is still a window during
> which this issue can occur.
> One possible fix would be to allow clients to exclude known bad data nodes
> when allocating new blocks. See {{failed_write.patch}} for an example.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
