[
https://issues.apache.org/jira/browse/DISPATCH-1352?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16854410#comment-16854410
]
Francesco Nigro commented on DISPATCH-1352:
-------------------------------------------
[~ganeshmurthy] [~tedross] [~kgiusti]
I see different solutions to this issue:
* embedd some node of qd_buffer_list_t until a specified depth directly into
qd_message to save allocation/freeing them and pointer chasing
* make qd_buffer_t able to create reference counted slices sharing the original
content (but exclusive fanout, next, prev, size fileds) so the cloned
qd_buffer_list_t could contain qd_buffer_t nodes whose content is owned by the
original list and won't be freeing until the last reference of them will be
alive
wdyt?
> 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]
