[
https://issues.apache.org/jira/browse/HDFS-9436?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15027931#comment-15027931
]
Konstantin Shvachko commented on HDFS-9436:
-------------------------------------------
In {{BlockReportStats}}
- {{numOpsRequired}} means the total number of block reports processed by NN
from all DNs
- {{numThreads}} is the number of DNs, sending the reports, each as a separate
thread
- {{addBlock()}} appends a new block to the list of {{blocks}}, which
represents replicas to be reported. The list is formed from "real" blocks first
and then padded by fake ones.
- {{blockReportList}} is a sequence of longs, representing the actual report of
all the replicas in {{blocks}}, which is sent to the NN
Hope this clarifies. A better JavaDoc is always welcome.
I think everything works as expected, except the EMPTY array introduced as you
mentioned by HDFS-7435. We should fix it in a different jira.
> Make NNThroughputBenchmark$BlockReportStats run with 10 datanodes by default
> ----------------------------------------------------------------------------
>
> Key: HDFS-9436
> URL: https://issues.apache.org/jira/browse/HDFS-9436
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: test
> Reporter: Mingliang Liu
> Assignee: Mingliang Liu
> Priority: Minor
> Fix For: 2.8.0
>
> Attachments: HDFS-9436.000.patch, HDFS-9436.001.patch
>
>
> This is a follow-up of [HDFS-9379].
> Though for actual benchmarking the defaults are rarely used, it would be good
> to change the default for {{numThreads}} as a >=10 value and may be
> {{numOpsRequired}} in {{BlockReportStats}} just to make sure the condition in
> [HDFS-9379] is tested in the future.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
