[
https://issues.apache.org/jira/browse/HBASE-11564?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14073758#comment-14073758
]
Enis Soztutar commented on HBASE-11564:
---------------------------------------
This should be good for branch-1. But I am concerned about the change in
ResultBoundedCompletionService that we changed from returning the first
successful response from replicas to returning the first response (even though
an exception). In testing, I think we ended up changing it to wait for all
retries from all replicas to be consumed, because in some cases, the replica
retries will just throw RetriesExhausted and we do not wait for success from
other replicas. I might be mis-reading the patch though.
> Improve cancellation management in the rpc layer
> ------------------------------------------------
>
> Key: HBASE-11564
> URL: https://issues.apache.org/jira/browse/HBASE-11564
> Project: HBase
> Issue Type: Bug
> Components: Client
> Affects Versions: 1.0.0, 2.0.0
> Reporter: Nicolas Liochon
> Assignee: Nicolas Liochon
> Fix For: 1.0.0, 2.0.0
>
> Attachments: 11564.v1.patch, 11564.v2.patch
>
>
> The current client code depends on interrupting the thread for canceling a
> request. It's actually possible to rely on a callback in protobuf.
> The patch includes as well various performance improvements in replica
> management.
> On a version before HBASE-11492 the perf was ~35% better. I will redo the
> test with the last version.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
