hama-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Thomas Jungblut <thomas.jungb...@googlemail.com>
Subject Re: [Share] "Infrastructures and Bounds for Distributed Entity Resolution"
Date Tue, 18 Oct 2011 05:16:20 GMT
>
> I've heard the barrier synchronization was the greatest "barrier" to
> scaling their solution with HAMA.


Oh really? I can swear someone told me yesterday that ZooKeeper is fine?;))

If you're interested, you could ask for the HAMA patch that did the tricks
> ;-)


Sure, I think it is quite sad that they did not share their researched
problems with us.

2011/10/17 Miklós Erdélyi <erdelyim@gmail.com>

> The paper was prepared by the group that I also worked with before. As
> I've heard the barrier synchronization was the greatest "barrier" to
> scaling their solution with HAMA. They had to also overcome memory
> problems with message buffering.
> If you're interested, you could ask for the HAMA patch that did the tricks
> ;-)
>
> On Mon, Oct 17, 2011 at 9:58 AM, Edward J. Yoon <edwardyoon@apache.org>
> wrote:
> >> looks like my university (Roma Tre) was deeply involved there, will try
> to
> >> have some other feedback personally :)
> >
> > Haha, don't abandon us what they say, tommaso. Just kidding. It would
> > be really nice if we could get feedback from them. :)
> >
> > P.S., The paper is published at QDB workshop at VLDB'11.
> >
> > On Mon, Oct 17, 2011 at 4:35 PM, Tommaso Teofili
> > <tommaso.teofili@gmail.com> wrote:
> >> looks like my university (Roma Tre) was deeply involved there, will try
> to
> >> have some other feedback personally :)
> >> Tommaso
> >>
> >> 2011/10/17 Edward J. Yoon <edwardyoon@apache.org>
> >>
> >>> http://qdb2011.dia.uniroma3.it/participants/program/p11-SIDLO.pdf
> >>>
> >>> --
> >>> Best Regards, Edward J. Yoon
> >>> @eddieyoon
> >>>
> >>
> >
> >
> >
> > --
> > Best Regards, Edward J. Yoon
> > @eddieyoon
> >
>



-- 
Thomas Jungblut
Berlin <thomas.jungblut@gmail.com>

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message