[
https://issues.apache.org/jira/browse/AMQ-5578?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15176566#comment-15176566
]
Christian Posta commented on AMQ-5578:
--------------------------------------
IIRC, the buffer.limit(size) did *not* properly pre-allocate the structures on
backing storage which was the root of the speed up in
http://blog.christianposta.com/activemq/speeding-up-activemq-persistent-messaging-performance-by-25x/
iirc it resolved to using ftruncate vs fallocate in the system calls on
linux... we want fallocate for this kind of allocation.
If you're verified this is still the behavior after this change, should be good
to go.
> preallocate journal files
> -------------------------
>
> Key: AMQ-5578
> URL: https://issues.apache.org/jira/browse/AMQ-5578
> Project: ActiveMQ
> Issue Type: Improvement
> Components: Message Store
> Affects Versions: 5.11.0
> Reporter: Gary Tully
> Assignee: Gary Tully
> Labels: journal, kahaDB, perfomance
> Fix For: 5.14.0
>
>
> Our journals are append only, however we use the size to track journal
> rollover on recovery and replay. We can improve performance if we never
> update the size on disk and preallocate on creation.
> Rework journal logic to ensure size is never updated. This will allow the
> configuration option from https://issues.apache.org/jira/browse/AMQ-4947 to
> be the default.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
