Support k8s for job submission and management

[IKACE]

Why are these changes needed?

Support using k8s to manage job lifecycles, including job submission, initialization, termination and clean-up.

TODO:

• [x] add README for k8s job management tutorial

1. change in docker/driver.py is added to use k8s client apis for job management, now the driver will support "default", "docker" and "k8s" modes.
2. add a yaml generator for automating generation of k8s container configs.
3. add new example k8s configs in benchmark

Related issue number

Checks

• [x] I've included any doc changes needed for https://fedscale.readthedocs.io/en/latest/
• [x] I've made sure the following tests are passing.
• Testing Configurations
  • k8s
    • [x] Dry Run (20 training rounds & 1 evaluation round)
    • [x] Cifar 10 (20 training rounds & 1 evaluation round)
    • [x] Femnist (20 training rounds & 1 evaluation round)
  • Regression 1: docker
    • [x] Cifar 10 (20 training rounds & 1 evaluation round)
    • [x] Femnist (20 training rounds & 1 evaluation round)
  • Regression 2: default
    • [x] Cifar 10 (20 training rounds & 1 evaluation round)
    • [x] Femnist (20 training rounds & 1 evaluation round)