[
https://issues.apache.org/jira/browse/HADOOP-4584?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12677280#action_12677280
]
Konstantin Shvachko commented on HADOOP-4584:
---------------------------------------------
> May be (3) still has some advantage : could you give a specific example that
> shows the advantage?
The example is as I mentioned before: In (2) when blockReport is scanning
directories, which may take minutes according to Suresh, blockRecieved can not
be processed, and the commands returned from the name-node
in reply to heartbeats like replicate and delete blocks will just accumulate on
the command queue and wait until block report is done. True, the data-node will
not die, but it will still be frozen in offerService thread.
I am just proposing to do with block reports the same we did with received
blocks: when they arrive we place them into {{receivedBlockList}}, and
offerService sends blockRecieved when the list is not empty. Block reports are
prepared by a separate thread and placed into {{readyBlockReport}} member.
offerService sends it whenever the member is not null.
> Slow generation of blockReport at DataNode causes delay of sending heartbeat
> to NameNode
> ----------------------------------------------------------------------------------------
>
> Key: HADOOP-4584
> URL: https://issues.apache.org/jira/browse/HADOOP-4584
> Project: Hadoop Core
> Issue Type: Bug
> Components: dfs
> Reporter: Hairong Kuang
> Assignee: Suresh Srinivas
> Fix For: 0.20.0
>
> Attachments: 4584.patch, 4584.patch, 4584.patch, 4584.patch,
> 4584.patch, 4584.patch
>
>
> sometimes due to disk or some other problems, datanode takes minutes or tens
> of minutes to generate a block report. It causes the datanode not able to
> send heartbeat to NameNode every 3 seconds. In the worst case, it makes
> NameNode to detect a lost heartbeat and wrongly decide that the datanode is
> dead.
> It would be nice to have two threads instead. One thread is for scanning data
> directories and generating block report, and executes the requests sent by
> NameNode; Another thread is for sending heartbeats, block reports, and
> picking up the requests from NameNode. By having these two threads, the
> sending of heartbeats will not get delayed by any slow block report or slow
> execution of NameNode requests.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
