[
https://issues.apache.org/jira/browse/HDFS-9608?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15082288#comment-15082288
]
Kai Zheng commented on HDFS-9608:
---------------------------------
Thanks Wei for the work. The patch makes sense to me.
* In addition to the work as described, it also uses fine-grained locks for the
supported storage types when choosing volumes. It's good, you may update the
issue description to reflect this as well.
* The change won't impact and is compatible with clusters of no more than one
storage types, but will impact clusters that deploy HSM. However, the behavior
would be desired and can provide better performance.
In the test codes:
1. Better to provide both positive and negative tests as existing codes do;
2. {{+ // with volume and block sizes in exception message}}, what did it mean?
3. Block size of 0 is used to choose a volume. Would you add test case that
uses a practical one?
> Disk IO imbalance in HDFS with heterogeneous storages
> -----------------------------------------------------
>
> Key: HDFS-9608
> URL: https://issues.apache.org/jira/browse/HDFS-9608
> Project: Hadoop HDFS
> Issue Type: Bug
> Reporter: Wei Zhou
> Assignee: Wei Zhou
> Attachments: HDFS-9608.01.patch
>
>
> Currently RoundRobinVolumeChoosingPolicy use a shared index to choose volumes
> in HDFS with heterogeneous storages, this leads to non-RR choosing mode for
> certain type of storage.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
