Hi Radim
If you run the test with only 2 nodes and FC disabled, it's going to
perform even better. But then as you increase the number of nodes, the
speed with no FC will drop dramatically (when we didn't have RSVP enabled,
with only 3 nodes, it didn't manage to send 1 x 10MB message in 10 minutes
Besides a bunch of critical fixes, this release adds support for concurrent
updates for non-transactional caches (high impact on server mode).
More about it here:
http://infinispan.blogspot.co.uk/2012/12/infinispan-520beta6-is-out.html
Cheers,
--
Mircea Markus
Infinispan lead (www.infinispan.
Hi Galder,
thanks a lot for your response. I've already created JIRA -
https://issues.jboss.org/browse/ISPN-2648 .
Best regards,
Anna.
- Original Message -
From: "Galder Zamarreño"
To: "infinispan -Dev List"
Sent: Monday, December 17, 2012 5:02:20 PM
Subject: Re: [infinispan-dev] Fail
That looks like an env issue of some sort…
I suggest you repeat the test with TRACE on org.infinispan and org.jgroups
categories and see why the nodes are being suspected.
Default values should be to use localhost and TCP for internode communication,
so it's kinda odd to see suspicious in those
On Dec 14, 2012, at 2:56 PM, Tristan Tarrant wrote:
> I would really like ISPN-2281 to be solved by the proper solution, i.e.
> attach any additional metadata required by the servers (or any other data
> "enricher") to the InternalCacheEntry and not as part of the value itself.
> Metadata wou
Sorry I haven't specified the amount, I am a stupido... my tests are working
with 500k credits.
UUPerf (JGroups 3.2.4.Final-redhat-1) from one computer in perflab to another,
2 threads (default), 1000x sends 10MB message (default chunkSize = 1 * our
entry size is usually 1kB) executed 3x
Not sure what could be going on here.
It runs fine locally. One other option would be that you're running with group
filters with out adding the 'arquillian' group as well (which the parent
Arquillian class needs). But then it shouldn't really run the beforeClass
configuration methods either..
On Mon, Dec 17, 2012 at 1:28 PM, Bela Ban wrote:
> Dan reduced those values to 200K, IIRC it was for UUPerfwhich behaved
> best with 200K. Idon't know if this is still needed. Dan ?
>
>
I haven't run UUPerf in a while...
>
> On 12/17/12 12:19 PM, Radim Vansa wrote:
> > Hi,
> >
> > recently I ha
Dan reduced those values to 200K, IIRC it was for UUPerfwhich behaved
best with 200K. Idon't know if this is still needed. Dan ?
On 12/17/12 12:19 PM, Radim Vansa wrote:
> Hi,
>
> recently I have synchronized our jgroups configuration with the default one
> shipped with Infinispan (core/src/mai
Hi,
recently I have synchronized our jgroups configuration with the default one
shipped with Infinispan (core/src/main/resources/jgroups-(tcp|udp).xml) and it
has shown that 200k credits in UFC/MFC (I keep the two values in sync) is not
enough even for our smallest resilience test (killing one
|
| 3# Since get operations are always local (site), they are as you say
| not meaningful for the benchmark; now since put operations are also
| not meaningful as it's async .. what is the benchmark measuring?
|
That's an assumption and the test is there also to confirm it. For example in
my XS
11 matches
Mail list logo