Just to clarify. The pull request 410 does not optimize the degree of parallelism of operators with respect to performance / gain. It just sets the maximum possible parallelization for the current execution environment.
Cheers, Fabian 2015-03-02 17:20 GMT+01:00 Max Michels <m...@apache.org>: > Hi! > > There is a pending pull request for this feature. If that is what you > had in mind: > > https://github.com/apache/flink/pull/410 > > Best regards, > Max > > On Mon, Mar 2, 2015 at 5:11 PM, Alexander Alexandrov > <alexander.s.alexand...@gmail.com> wrote: > > AFAIK at the moment this is not supported but at the TU Berlin we have a > > master student working on this feature, so it might be possible within > the > > next 3-6 months. > > > > Regards, > > Alexander > > > > 2015-03-02 17:01 GMT+01:00 Malte Schwarzer <m...@mieo.de>: > >> > >> Hi everyone, > >> > >> I read that Flink is supposed to automatically optimize the degree of > >> parallelism. But I never saw any change of parallelism in the web > interface > >> without defining dop manually (-p parameter). > >> > >> Is there any of this optimization actually happening? Or how can I > switch > >> it on? > >> > >> > >> Cheers > >> Malte > > > > >
