For now, I’d recommend opening a PR against spark-perf. It would be great to
try to integrate this into the spark-perf harness so that I can run it
automatically as part of Spark 1.2.0 release testing. If you open a rough WIP
PR over there, I’ll be able to provide some feedback to help you get
Shall I move the code to spark-perf then and submit a PR? Or shall I
submit a PR to spark where it can remain an idiomatic example and we can
clone it in spark-perf where it can potentially evolve non-idiomatic
optimizations?
Yours,
Ewan
On 11/11/2014 07:58 PM, Reynold Xin wrote:
This is grea
This is great. I think the consensus from last time was that we would put
performance stuff into spark-perf, so it is easy to test different Spark
versions.
On Tue, Nov 11, 2014 at 5:03 AM, Ewan Higgs wrote:
> Hi all,
> I saw that Reynold Xin had a Terasort example PR on Github[1]. It didn't
>
