[
https://issues.apache.org/jira/browse/DISPATCH-1389?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16902963#comment-16902963
]
ASF subversion and git services commented on DISPATCH-1389:
-----------------------------------------------------------
Commit 717be609925646d0856e129c6760098e976a12f2 in qpid-dispatch's branch
refs/heads/master from Ken Giusti
[ https://gitbox.apache.org/repos/asf?p=qpid-dispatch.git;h=717be60 ]
DISPATCH-1389: optimize qd_iterator_advance, qd_iterator_ncopy and
qd_iterator_equal to use multi-byte operations when the iterator view
is in the raw data.
This closes #546
> Optimize the parsing of message annotations
> -------------------------------------------
>
> Key: DISPATCH-1389
> URL: https://issues.apache.org/jira/browse/DISPATCH-1389
> Project: Qpid Dispatch
> Issue Type: Improvement
> Reporter: Ken Giusti
> Assignee: Ken Giusti
> Priority: Major
>
> Parsing message annotations, especially on the inter router incoming link,
> are quite expensive.
> For example, in a simple standalone router test the time it takes on average
> (on my puny laptop) to receive a message and hand it off to the core is ~1
> usec:
> TestRouterA: link MyReceiver count=500000 rx=1.094
> Compare that time to the same operation performed on the inbound router link
> on a two-hop router configuration:
> TestRouterB: link MyReceiver count=500000 rx=7.035
> On average it's 7x slower. Most of this time appears to be spent
> manipulating inbound message annotations.
>
> This Jira tracks work towards improving the performance of message annotation
> processing.
--
This message was sent by Atlassian JIRA
(v7.6.14#76016)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
