qpid-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ASF GitHub Bot (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (QPIDJMS-430) Lock-Free FifoMessageQueue
Date Fri, 11 Jan 2019 17:54:00 GMT

    [ https://issues.apache.org/jira/browse/QPIDJMS-430?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16740593#comment-16740593
] 

ASF GitHub Bot commented on QPIDJMS-430:
----------------------------------------

franz1981 commented on issue #26: QPIDJMS-430 Lock-Free FifoMessageQueue
URL: https://github.com/apache/qpid-jms/pull/26#issuecomment-453601630
 
 
   @tabish121 I haven't had the chance to measure the gains now that https://github.com/apache/activemq-artemis/pull/2467
has been merged and sadly I don't have such a fast box ATM, but I would try it and see if
it can make any difference. 
   I can surely avoid the padding even if it will lower the performance, given that it would
be anyway better then the orignal version, that was locked.
   @gemmellr @tabish121 My only worry is that the original version were having a resizable
backlog of messages while this version is quite strict and never grows exceeding a configured
capacity ie `prefetchSize`, I hope it is not a limitation, given that it would (yield)wait
on offer side until one slot became available.
 
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


> Lock-Free FifoMessageQueue
> --------------------------
>
>                 Key: QPIDJMS-430
>                 URL: https://issues.apache.org/jira/browse/QPIDJMS-430
>             Project: Qpid JMS
>          Issue Type: Improvement
>            Reporter: Francesco Nigro
>            Priority: Minor
>
> A lock-free single producer multi consumer double ended queue would allow for the common
cases (enqueue/dequeue) to benefit from a better throughput and lower latencies while allowing
busy spin waits to benefits from some additional boost



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

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


Mime
View raw message