Looks like the discussion if winding down and I don't see any negative
reaction to the proposal. Which is great as it seems to make sense to have an
ability to offer a different approach to in-memory processing as well as
performance acceleration for the tools that rely on traditional MR model.
Dmitriy, as the next set of steps I'd recommend you guys to follow Apache
process where everything is done on JIRAs and via patches. As you might know
the integration into the bigtop includes the following parts:
- packaging
- tests: both integration and package
- deployment code (Puppet and perhaps Vagrant if embed VM is important)
We have a wiki page
https://cwiki.apache.org/confluence/display/BIGTOP/How+to+Contribute
that should help you to get started on this. Looking forward for your
contributions! Once the ball is rolling there might be more people joining and
helping you guys to feel welcome ;)!
Please don't hesistate to send your questions, discussion topics to the dev@
list. Good luck.
Cos
On Mon, Mar 24, 2014 at 10:43PM, Konstantin Boudnik wrote:
> Re-shaping the thread into a [DISCUSSION].
>
> I encourage community members to chime in with your stand on the proposal so
> we can have a discussion around it!
>
> Thanks,
> Cos
>
> On Mon, Mar 24, 2014 at 06:07PM, Dmitriy Setrakyan wrote:
> > Hi,
> >
> > I am writing on behalf of GridGain open source project (www.gridgain.org),
> > licensed under Apache 2.0. At GridGain we are working on In-Memory
> > Computing Platform which is becoming one-stop place for many distributed
> > compute, data, and streaming needs.
> >
> > One of the main pieces of our platform is our In-Memory Apache Hadoop
> > Accelerator which aims to accelerate HDFS and Map/Reduce by bringing both,
> > data and computations into memory. We do it with our GGFS - Hadoop
> > compliant in-memory file system. For I/O intensive jobs GridGain GGFS
> > offers performance close to 100x faster than standard HDFS. More
> > information can be found here:
> > http://www.gridgain.org/features/hadoop-acceleration/
> >
> > We would like to have an opportunity to integrate our Apache Hadoop
> > Accelerator with Apache Bigtop. Please let us know if this is possible and
> > what steps are required of us.
> >
> > Thanks in advance.
> > -
> > Dmitriy Setrakyan, EVP Engineering
> > *GridGain Systems*
> > www.gridgain.com
