[
https://issues.apache.org/jira/browse/ARTEMIS-2205?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16739527#comment-16739527
]
ASF subversion and git services commented on ARTEMIS-2205:
----------------------------------------------------------
Commit d79762fa0489954d91e417f6110c213bc3d6db06 in activemq-artemis's branch
refs/heads/master from Clebert Suconic
[ https://gitbox.apache.org/repos/asf?p=activemq-artemis.git;h=d79762f ]
ARTEMIS-2205 Refactor AMQP Processing into Netty Thread
These improvements were also part of this task:
- Routing is now cached as much as possible.
- A new Runnable is avoided for each individual message,
since we use the Netty executor to perform delivery
https://issues.apache.org/jira/browse/ARTEMIS-2205
> Make AMQP Processing Single Threaded and other AMQP perf improvements
> ---------------------------------------------------------------------
>
> Key: ARTEMIS-2205
> URL: https://issues.apache.org/jira/browse/ARTEMIS-2205
> Project: ActiveMQ Artemis
> Issue Type: Improvement
> Components: AMQP
> Affects Versions: 2.6.3
> Reporter: clebert suconic
> Assignee: clebert suconic
> Priority: Major
> Fix For: 2.7.0
>
>
> This is using Netty Executor (NIOLoop) to process AMQP.
> Instead of using a lock to enter the AMQP processing, what has issues on
> scaling up multiple connections per queue, it's using a single threaded
> executor.
>
>
> This represents a major improvement in AMQP. I will take my time to write a
> blog post about this with multiple scenarios comparing 2.6.3, master (before
> this change) and after. (I will post a link here to this JIRA).
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
