[
https://issues.apache.org/jira/browse/HDFS-11898?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16032544#comment-16032544
]
John Zhuge commented on HDFS-11898:
-----------------------------------
Should we cap the total number of hedgedRead threads globally with a semaphore?
It'd be safer even when the number of DFSClients gets out of hand and all the
clients perform tons of hedged reads. This scenario may be possible when there
is a network glitch.
Is the following Colin's comment in HDFS-5776 is still true?
bq. Unfortunately, the FileContext API creates a new DFSClient instance for
each operation that it does.
> DFSClient#isHedgedReadsEnabled() should be per client flag
> -----------------------------------------------------------
>
> Key: HDFS-11898
> URL: https://issues.apache.org/jira/browse/HDFS-11898
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: hdfs-client
> Reporter: Vinayakumar B
> Assignee: Vinayakumar B
> Attachments: HDFS-11898-01.patch
>
>
> DFSClient#isHedgedReadsEnabled() returns value based on static
> {{HEDGED_READ_THREAD_POOL}}.
> Hence if any of the client initialized this in JVM, all remaining client
> reads will be going through hedged read itself.
> This flag should be per client value.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
