[
https://issues.apache.org/jira/browse/HDFS-5776?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13884351#comment-13884351
]
Arpit Agarwal commented on HDFS-5776:
-------------------------------------
[~stack] I am basically +1 on the v9 patch at this point but v10 is a step
back. We need a throttle on unbounded thread growth and threadpool size is the
most trivial to add. We can file a separate Jira to replace the thread pool
limit with something more sophisticated e.g. the client can keep a dynamic
estimate of the 95th percentile latency and use that instead of a fixed value
from configuration.
Jing mentioned some issues that look fairly easy to address.
{quote}
In the old impl, the refetchToken/refetchEncryptionKey are shared by all nodes
from chooseDataNode once key/token exception happened. that means if the first
node consumed this retry quota, then if the second or third node hit the
key/token exception, clearDataEncryptionKey/fetchBlockAt opeerations will not
be called, it's a little unfair
{quote}
[~xieliang007] That makes sense, thanks for the clarification.
> Support 'hedged' reads in DFSClient
> -----------------------------------
>
> Key: HDFS-5776
> URL: https://issues.apache.org/jira/browse/HDFS-5776
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: hdfs-client
> Affects Versions: 3.0.0
> Reporter: Liang Xie
> Assignee: Liang Xie
> Attachments: HDFS-5776-v10.txt, HDFS-5776-v2.txt, HDFS-5776-v3.txt,
> HDFS-5776-v4.txt, HDFS-5776-v5.txt, HDFS-5776-v6.txt, HDFS-5776-v7.txt,
> HDFS-5776-v8.txt, HDFS-5776-v9.txt, HDFS-5776.txt
>
>
> This is a placeholder of hdfs related stuff backport from
> https://issues.apache.org/jira/browse/HBASE-7509
> The quorum read ability should be helpful especially to optimize read outliers
> we can utilize "dfs.dfsclient.quorum.read.threshold.millis" &
> "dfs.dfsclient.quorum.read.threadpool.size" to enable/disable the hedged read
> ability from client side(e.g. HBase), and by using DFSQuorumReadMetrics, we
> could export the interested metric valus into client system(e.g. HBase's
> regionserver metric).
> The core logic is in pread code path, we decide to goto the original
> fetchBlockByteRange or the new introduced fetchBlockByteRangeSpeculative per
> the above config items.
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)
