[
https://issues.apache.org/jira/browse/HDFS-9752?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Walter Su updated HDFS-9752:
----------------------------
Attachment: HDFS-9752.03.patch
bq. The test can just verify that pipelineRecoveryCount is not incremented
after DN restart and pipeline recovery...
Good idea. Thanks. Uploaded 03 patch.
It's still difficult to remove the sleep used for waiting DN shutdown.
bq. To avoid sleeping for arbitrary amount of time to wait for a datanode to
shutdown, we can have DataNode#shutdown() to set a variable at the end to
indicate shutdown is complete.
I use thread name and GenericTestUtils.waitForThreadTermination(..) to do that.
Hope it's ok to you.
> Permanent write failures may happen to slow writers during datanode rolling
> upgrades
> ------------------------------------------------------------------------------------
>
> Key: HDFS-9752
> URL: https://issues.apache.org/jira/browse/HDFS-9752
> Project: Hadoop HDFS
> Issue Type: Bug
> Reporter: Kihwal Lee
> Assignee: Walter Su
> Priority: Critical
> Attachments: HDFS-9752.01.patch, HDFS-9752.02.patch,
> HDFS-9752.03.patch, HdfsWriter.java
>
>
> When datanodes are being upgraded, an out-of-band ack is sent upstream and
> the client does a pipeline recovery. The client may hit this multiple times
> as more nodes get upgraded. This normally does not cause any issue, but if
> the client is holding the stream open without writing any data during this
> time, a permanent write failure can occur.
> This is because there is a limit of 5 recovery trials for the same packet,
> which is tracked by "last acked sequence number". Since the empty heartbeat
> packets for an idle output stream does not increment the sequence number, the
> write will fail after it seeing 5 pipeline breakages by datanode upgrades.
> This check/limit was added to avoid spinning until running out of nodes in
> the cluster due to a corruption or any other irrecoverable conditions. The
> datanode upgrade-restart should be excluded from the count.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
