You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@qpid.apache.org by "Justin Ross (JIRA)" <ji...@apache.org> on 2017/09/08 17:43:01 UTC

[jira] [Updated] (PROTON-1550) Epoll proactor performance improvement

     [ https://issues.apache.org/jira/browse/PROTON-1550?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Justin Ross updated PROTON-1550:
--------------------------------
    Affects Version/s:     (was: proton-c-0.18.0)

> Epoll proactor performance improvement
> --------------------------------------
>
>                 Key: PROTON-1550
>                 URL: https://issues.apache.org/jira/browse/PROTON-1550
>             Project: Qpid Proton
>          Issue Type: Improvement
>          Components: proton-c
>         Environment: Linux
>            Reporter: Cliff Jansen
>             Fix For: proton-c-0.19.0
>
>
> While stress testing and evaluating performance of the epoll proactor there have been indications that as the number of connections increase, the throughput increases more slowly than overall cpu use.
> Instrumenting and profiling suggest that, at least for applications like qpid-dispatch, there can be a large number of simultaneous pending pn_connection_wake() requests for thread-safe handoff of messages from one connection context to another.
> As the number of connections rise, the use of adaptive spin locks for this purpose is suspected to be an inefficient strategy, perhaps resulting in a lock convoy.  A trial use of one or more lockless queues could yield substantial performance gain or at least better understanding of current hot spots.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@qpid.apache.org
For additional commands, e-mail: dev-help@qpid.apache.org