[
https://issues.apache.org/jira/browse/HDFS-7964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15061297#comment-15061297
]
Jing Zhao commented on HDFS-7964:
---------------------------------
The patch looks good to me. One nit is that two places in FSEditLogAsync have
some commented code:
{code}
//if (LOG.isDebugEnabled()) {
LOG.info("logSync "+edit);
//}
{code}
+1 after addressing this.
Besides, the current postponeResponse/sendResponse code uses a counter to delay
the response. This looks a little hacky to me. But I understand this may be the
only way to add the new functionality without changing the original code. Maybe
we can do some extra refactoring in the future.
> Add support for async edit logging
> ----------------------------------
>
> Key: HDFS-7964
> URL: https://issues.apache.org/jira/browse/HDFS-7964
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: namenode
> Affects Versions: 2.0.2-alpha
> Reporter: Daryn Sharp
> Assignee: Daryn Sharp
> Attachments: HDFS-7964.patch, HDFS-7964.patch, HDFS-7964.patch
>
>
> Edit logging is a major source of contention within the NN. LogEdit is
> called within the namespace write log, while logSync is called outside of the
> lock to allow greater concurrency. The handler thread remains busy until
> logSync returns to provide the client with a durability guarantee for the
> response.
> Write heavy RPC load and/or slow IO causes handlers to stall in logSync.
> Although the write lock is not held, readers are limited/starved and the call
> queue fills. Combining an edit log thread with postponed RPC responses from
> HADOOP-10300 will provide the same durability guarantee but immediately free
> up the handlers.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
