[
https://issues.apache.org/jira/browse/DISPATCH-1352?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16856395#comment-16856395
]
Francesco Nigro commented on DISPATCH-1352:
-------------------------------------------
[~kgiusti] [~ganeshmurthy] I've improved the POC and I'm getting the expected
performance now:
https://github.com/franz1981/qpid-dispatch/tree/ref_counted_buf_list.
On my tests I'm getting:
with 9 pairs on master: 50K msg/s x 9 = 450 K msg/s
with 9 pairs on the POC: 62K msg/s x 9 = 558 K msg/s
I think that's a significant increase in performance and that this optimization
worths to be implemented.
CPU flamegraph shows a significan reduction of cost for both qd_message_copy
and qd_message_free (their cost is nearly halved), now the point is how to
deliver it in a way that is always applied (y)
> qd_buffer_list_clone cost is dominated by cache misses
> ------------------------------------------------------
>
> Key: DISPATCH-1352
> URL: https://issues.apache.org/jira/browse/DISPATCH-1352
> Project: Qpid Dispatch
> Issue Type: Improvement
> Components: Routing Engine
> Affects Versions: 1.7.0
> Reporter: Francesco Nigro
> Priority: Major
> Attachments: screenshot-1.png, screenshot-2.png
>
>
> qd_buffer_list_clone on qd_message_copy for
> qd_message_pvt_t.ma_to_override/ma_trace/ma_ingress is dominated by cache
> misses costs:
> * to "allocate" new qd_buffer_t
> * to reference any qd_buffer_t from the source qd_buffer_list_t
> Such cost is the main reason why the core thread is having a very low IPC (<
> 1 istr/cycle) and given the single threaded nature of the router while
> dealing with it, by solving it will bring a huge performance improvement to
> make the router able to scale better.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
