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 .../>.


-- 
Bela Ban, JGroups lead (http://www.jgroups.org)
_______________________________________________
infinispan-dev mailing list
[email protected]
https://lists.jboss.org/mailman/listinfo/infinispan-dev

Reply via email to