On Wed, Mar 14, 2012 at 7:53 AM, Bela Ban <[email protected]> wrote:
>
>
> On 3/14/12 1:14 AM, Manik Surtani wrote:
>>
>> On 13 Mar 2012, at 03:28, Bela Ban wrote:
>>
>>>
>>>
>>> On 3/13/12 6:35 AM, Manik Surtani wrote:
>>>>
>>>> On 12 Mar 2012, at 08:03, Dan Berindei wrote:
>>>>
>>>>>>
>>>>>> Well, probably not, because we only want to send keys to nodes that
>>>>>> actually need to store them...
>>>>>>
>>>>>
>>>>> Sending the whole tx as a multicast would certainly be more efficient
>>>>> than what we do now with lots of targets.
>>>>> With unicasts we could send only the minimum required data to each
>>>>> target, but that computation would be complex and error-prone.
>>>>
>>>> Well, this is what ANYCAST was all about initially, where JGroups would 
>>>> decide, based on the recipient list versus the total cluster size, on 
>>>> whether to send multiple unicasts or a multicast.  But we didn't end up 
>>>> doing this in the end, perhaps we need to revisit.
>>>>
>>>> Bela, I'm guessing this thread was prompted by the poor performance in 
>>>> DIST that was reported, right?  I'd like to profile the test provided to 
>>>> understand where we should be looking in the first place.  E.g., is it the 
>>>> fact that we have too many RPCs?  Or maybe a locking/concurrency issue 
>>>> elsewhere, etc.  If you have done any of this analysis already, we should 
>>>> talk about that.
>>>
>>>
>>> Yes. My current findings are that we're doing unneeded sync RPCs even if
>>> <async.../>  is defined. I'll run this with the latest Infinispan and see
>>> if it's still the case (Galder mentioned this was gone in 5.2 master).
>>> Also, there should be performance improvements by locking only the
>>> primary owners (changes by Mircea and/or Dan), so I'll need to re-run
>>> with the latest and greatest of Infinispan (and JGroups).
>>
>> Any such changes should also be in 5.1.x.  If you do see any sync RPCs 
>> (except perhaps remote GETs) when running in async mode, then that is almost 
>> certainly a bug.
>
>
> Yes, this is a bug, I confirmed that with Dan yesterday. He's aware of
> it and the fix is simple, so I expect this will be fixed shortly. The
> workaround is to define <stateTransfer .../>.
>

Indeed, somehow I missed this thread yesterday, but based on my chat
with Bela I've created https://issues.jboss.org/browse/ISPN-1910 and
https://github.com/infinispan/infinispan/pull/998.

Cheers
Dan

_______________________________________________
infinispan-dev mailing list
[email protected]
https://lists.jboss.org/mailman/listinfo/infinispan-dev

Reply via email to