Re: Apache Flink on Hadoop YARN using a YARN Session

Hi, most users don't have that choice, they have to use Flink on YARN. Both modes have their advantages and disadvantages, but the decision is up to you. You can use a little bit more of your memory using the standalone mode, but you'll have to install Flink manually on all machines. Regarding th

Re: Apache Flink on Hadoop YARN using a YARN Session

Hi Robert, In this case, if both the standalone and yarn modes will run jobs if they have resources, is it better to rely on which one? I would be interested in a feature like the dynamic resource allocation with a fair scheduler that Spark has implemented. If you guys will consider this feature

Re: Apache Flink on Hadoop YARN using a YARN Session

Hi Ovidiu, good choice on your research topic ;) I think doing some hands on experiments will help you to understand much better how Flink works and what you can do with it. If I got it right: > -with standalone (cluster) you can run multiple workloads if you have > enough resources, else the jo

Re: Apache Flink on Hadoop YARN using a YARN Session

Thank you, Robert! My research interest includes Flink (I am a PhD student, BigStorage EU project, Inria Rennes) so I am currently preparing some experiments in order to understand better how it works. If I got it right: -with standalone (cluster) you can run multiple workloads if you have enou

Re: Apache Flink on Hadoop YARN using a YARN Session

Hi, I'll fix the link in the YARN documentation. Thank you for reporting the issue. I'm not aware of any discussions or implementations related to the scheduling. From my experience working with users and also from the mailing list, I don't think that such features are very important. Since stream

Re: Apache Flink on Hadoop YARN using a YARN Session

Hi, The link to FAQ (https://ci.apache.org/projects/flink/flink-docs-release-0.10/faq.html ) is on the yarn setup 0.10 documentation page (https://ci.apache.org/projects/flink/flink-docs-release-0.10/setup/yarn_setup.html

Re: Apache Flink on Hadoop YARN using a YARN Session

Hi Ovidiu, you can submit multiple programs to a running Flink cluster (or a YARN session). Flink does currently not have any queuing mechanism. The JobManager will reject a program if there are not enough free resources for it. If there are enough resources for multiple programs, they'll run conc

Apache Flink on Hadoop YARN using a YARN Session

Hi, I am currently interested in experimenting on Flink over Hadoop YARN. I am documenting from the documentation we have here: https://ci.apache.org/projects/flink/flink-docs-release-0.10/setup/yarn_setup.html