Hello @junmin park
It seems like you are using HPC Pack to distribute jobs across your compute nodes. When you add new compute nodes to your cluster, HPC Pack will automatically start using them to distribute jobs.
Regarding the order in which the jobs are assigned to the compute nodes, HPC Pack uses a load balancing algorithm to distribute the jobs across the available compute nodes. This algorithm considers the current load on each node, as well as the resources required by the job.
If you want to check the criteria used by HPC Pack to distribute jobs, you can look at the job scheduler logs. These logs contain detailed information about how HPC Pack schedules jobs, including the criteria used to select compute nodes. You can find the logs in the HPC Pack Management Console under the "Monitoring" tab.
I hope this helps! Let me know if you have any further questions.
Please accept answer and upvote if the above information is helpful for the benefit of the community.