GitHub user clebertsuconic opened a pull request: https://github.com/apache/activemq-artemis/pull/2467
ARTEMIS-2205 Performance improvements on AMQP and other parts You can merge this pull request into a Git repository by running: $ git pull https://github.com/clebertsuconic/activemq-artemis amqp-PR Alternatively you can review and apply these changes as the patch at: https://github.com/apache/activemq-artemis/pull/2467.patch To close this pull request, make a commit to your master/trunk branch with (at least) the following in the commit message: This closes #2467 ---- commit 3199e32d2c98e7cdfd9ef157b9ea0cb19ca85e75 Author: Clebert Suconic <clebertsuconic@...> Date: 2018-12-17T14:11:54Z ARTEMIS-2205 Refactor AMQP Processing into Single Threaded (per connection) https://issues.apache.org/jira/browse/ARTEMIS-2205 commit a72c73fad3b8b4ca03737c6733d018dbd385bfbd Author: Clebert Suconic <clebertsuconic@...> Date: 2018-12-17T14:12:07Z ARTEMIS-2205 Broker Improvement by caching Routing for most common cases During AMQP Perf tests this became more relevant on profiling. It is a general improvement done as part of this AMQP performance task. commit 6d93d0aff908c23e68a135041d663c3c39701c72 Author: Clebert Suconic <clebertsuconic@...> Date: 2018-12-17T14:12:14Z ARTEMIS-2205 Avoid new Runnable for every message sent As we now use the netty executor, creating a new Runnable for every message received became a relevant CPU, memory and putting extra GC pressure. By doing this change alone I was able to improve performance by 5% more or less. https://issues.apache.org/jira/browse/ARTEMIS-2205 commit c11605e00737f570ee4eddc62d9f2bacebcdfb2b Author: Francesco Nigro <nigro.fra@...> Date: 2018-12-17T14:12:19Z ARTEMIS-2205 Optimizing some Lambda usages https://issues.apache.org/jira/browse/ARTEMIS-2205 ---- ---