[Core] Reducing scheduling fragmentation

[jjyao]

Description

Fragmentation can happen when the cluster has enough total resources to schedule a task but no single node has enough resources.

Ways to reduce the change of fragmentation are like avoiding GPUs node for scheduling CPU tasks.

PG can also have fragmentation just like other resources: #35409

Use case

No response

[cszhu]

This P2 issue has seen no activity in the past 2 years. It will be closed in 2 weeks as part of ongoing cleanup efforts.

Please comment and remove the pending-cleanup label if you believe this issue should remain open.

Thanks for contributing to Ray!