[infinispan-dev] Misleading cache store, and average write time, stats
Manik Surtani
manik at jboss.org
Wed Jun 20 07:16:03 EDT 2012
On 20 Jun 2012, at 12:05, Galder Zamarreño wrote:
> Hi all,
>
> Running some tests for Infinispan stats for next week's conference and I'm seeing something funny:
>
> 1. In a sync replicated cache, average write time is 1ms and average repl time is 3ms (wtf?)
>
> 2. Linked to 1, replication count is 260.249 and store count 520.307!! We're counting the number of stores twice, when someone calls put(), and we get a put call replicated to the node. The latter should not be count. That explains 1.
>
> Thoughts?
Well, it's a bug and should be fixed. :)
--
Manik Surtani
manik at jboss.org
twitter.com/maniksurtani
Project Lead, Infinispan
http://www.infinispan.org
Platform Architect, JBoss Data Grid
http://www.redhat.com/promo/dg6beta
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.jboss.org/pipermail/infinispan-dev/attachments/20120620/5292a233/attachment.html
More information about the infinispan-dev
mailing list