The scheduler code lives in the hadoop-yarn-project here <https://github.com/apache/hadoop/tree/trunk/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler>. You'll find a few implementations in that directory - "fair" for the FairScheduler and "capacity" for the CapacityScheduler for example. You can look at these to get some ideas on how the existing schedulers work. If you're writing a new one, start by extending the AbstractYarnScheduler and take it forward from there.
Thanks, Hariharan On Thu, Jul 1, 2021 at 8:07 PM Abhishek 2 <[email protected]> wrote: > Hi > > I am a Ph.D. research scholar in IIITM Gwalior and a newbie in hadoop. My > research topic is to develop an algorithm for efficient yarn scheduling. I > am trying with a heuristic optimization algorithm but not sure how to start > writing code. I am not able to understand which module or repsitory should > be edited. > > It will be a great help if I get any guidance or simialr code to study on > it. > -- > Abhishek Gupta > PhD Scholar > IIITM Gwalior >
